Upload folder using huggingface_hub

checkpoint-12208/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/mnt/parscratch/users/acp23ay/private/models/Qwen2.5-7B-Instruct-bn-madlad-mean/",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.0.dev0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 161672
+}

checkpoint-12208/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.44.0.dev0"
+}

checkpoint-12208/model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f326a082f4f407f7c7c0b09d83d9ca190122fbb5713fd3fc5c3a3b1ffc1fc68a
+size 4842817304

checkpoint-12208/model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:becf3c41c7359877372d1f9bdba9efe52cb2b8dab7330b346e831a36665b8f0e
+size 4998852224

checkpoint-12208/model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad9da13aef49ef9aa84ff7ac6ae375fc2f8c339648214e7663e44e16a6763847
+size 4984124304

checkpoint-12208/model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfc2c86e34819a46908bfe3ad42f3986e7efdfc34f67e43f40f690f77c7b0672
+size 4932743992

checkpoint-12208/model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:891f86a74d6b1791b98b581ff94cbedb16bfdb78595b9697dc3fd2ecc5974ba2
+size 4998852296

checkpoint-12208/model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f226e286b1b9c78b185944365fcbcb5d78c833a5f102ee955637c1224efeca6a
+size 3662865184

checkpoint-12208/model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c761133f5d5ae6d36ad8b429b54d5f5e7d3174bf1f6423f9490332c4eb714f3c
+size 2317729920

checkpoint-12208/model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 30737946624
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.norm.weight": "model-00006-of-00007.safetensors"
+  }
+}

checkpoint-12208/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54f99722a1fd3240877e3bd8e5d77d7b1144d1187297fc66d2580e6776260743
+size 16728842070

checkpoint-12208/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d9cd6a0487226e5bd30d1846894c82af483733ab4381b75bae9c0745e05d405
+size 14244

checkpoint-12208/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abe644ed33a3c4139223f0857a985127f3e6fbaa8c89fa14b57671b49ca52c21
+size 1064

checkpoint-12208/trainer_state.json

@@ -0,0 +1,2784 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.42957176536823954,
+  "eval_steps": 500,
+  "global_step": 12208,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0010908195221506739,
+      "grad_norm": 27.24474334716797,
+      "learning_rate": 1.0157273918741808e-06,
+      "loss": 9.0396,
+      "step": 31
+    },
+    {
+      "epoch": 0.0021816390443013477,
+      "grad_norm": 16.773351669311523,
+      "learning_rate": 2.0314547837483616e-06,
+      "loss": 7.9471,
+      "step": 62
+    },
+    {
+      "epoch": 0.0032724585664520214,
+      "grad_norm": 15.084428787231445,
+      "learning_rate": 3.0471821756225426e-06,
+      "loss": 6.5868,
+      "step": 93
+    },
+    {
+      "epoch": 0.0043632780886026954,
+      "grad_norm": 6.7851786613464355,
+      "learning_rate": 4.062909567496723e-06,
+      "loss": 5.3744,
+      "step": 124
+    },
+    {
+      "epoch": 0.0054540976107533695,
+      "grad_norm": 7.081949234008789,
+      "learning_rate": 5.078636959370905e-06,
+      "loss": 4.6378,
+      "step": 155
+    },
+    {
+      "epoch": 0.006544917132904043,
+      "grad_norm": 8.945405960083008,
+      "learning_rate": 6.094364351245085e-06,
+      "loss": 4.2292,
+      "step": 186
+    },
+    {
+      "epoch": 0.007635736655054717,
+      "grad_norm": 15.078816413879395,
+      "learning_rate": 7.110091743119267e-06,
+      "loss": 3.9767,
+      "step": 217
+    },
+    {
+      "epoch": 0.008726556177205391,
+      "grad_norm": 8.799291610717773,
+      "learning_rate": 8.125819134993446e-06,
+      "loss": 3.765,
+      "step": 248
+    },
+    {
+      "epoch": 0.009817375699356064,
+      "grad_norm": 9.741459846496582,
+      "learning_rate": 9.141546526867629e-06,
+      "loss": 3.6496,
+      "step": 279
+    },
+    {
+      "epoch": 0.010908195221506739,
+      "grad_norm": 9.403132438659668,
+      "learning_rate": 1.015727391874181e-05,
+      "loss": 3.4936,
+      "step": 310
+    },
+    {
+      "epoch": 0.011999014743657412,
+      "grad_norm": 8.479109764099121,
+      "learning_rate": 1.117300131061599e-05,
+      "loss": 3.3879,
+      "step": 341
+    },
+    {
+      "epoch": 0.013089834265808085,
+      "grad_norm": 4.988598823547363,
+      "learning_rate": 1.218872870249017e-05,
+      "loss": 3.3147,
+      "step": 372
+    },
+    {
+      "epoch": 0.01418065378795876,
+      "grad_norm": 5.518200874328613,
+      "learning_rate": 1.3204456094364351e-05,
+      "loss": 3.2022,
+      "step": 403
+    },
+    {
+      "epoch": 0.015271473310109434,
+      "grad_norm": 5.685606002807617,
+      "learning_rate": 1.4220183486238533e-05,
+      "loss": 3.1393,
+      "step": 434
+    },
+    {
+      "epoch": 0.01636229283226011,
+      "grad_norm": 5.6373491287231445,
+      "learning_rate": 1.5235910878112714e-05,
+      "loss": 3.05,
+      "step": 465
+    },
+    {
+      "epoch": 0.017453112354410782,
+      "grad_norm": 5.174935340881348,
+      "learning_rate": 1.6251638269986893e-05,
+      "loss": 2.992,
+      "step": 496
+    },
+    {
+      "epoch": 0.018543931876561455,
+      "grad_norm": 5.266006946563721,
+      "learning_rate": 1.7267365661861077e-05,
+      "loss": 2.9558,
+      "step": 527
+    },
+    {
+      "epoch": 0.019634751398712128,
+      "grad_norm": 4.111412048339844,
+      "learning_rate": 1.8283093053735257e-05,
+      "loss": 2.9089,
+      "step": 558
+    },
+    {
+      "epoch": 0.0207255709208628,
+      "grad_norm": 4.149659156799316,
+      "learning_rate": 1.9298820445609438e-05,
+      "loss": 2.879,
+      "step": 589
+    },
+    {
+      "epoch": 0.021816390443013478,
+      "grad_norm": 4.711772441864014,
+      "learning_rate": 2.031454783748362e-05,
+      "loss": 2.8057,
+      "step": 620
+    },
+    {
+      "epoch": 0.02290720996516415,
+      "grad_norm": 4.372698783874512,
+      "learning_rate": 2.13302752293578e-05,
+      "loss": 2.7954,
+      "step": 651
+    },
+    {
+      "epoch": 0.023998029487314824,
+      "grad_norm": 3.9052813053131104,
+      "learning_rate": 2.234600262123198e-05,
+      "loss": 2.7286,
+      "step": 682
+    },
+    {
+      "epoch": 0.025088849009465498,
+      "grad_norm": 3.544926404953003,
+      "learning_rate": 2.336173001310616e-05,
+      "loss": 2.6875,
+      "step": 713
+    },
+    {
+      "epoch": 0.02617966853161617,
+      "grad_norm": 4.380484104156494,
+      "learning_rate": 2.437745740498034e-05,
+      "loss": 2.6703,
+      "step": 744
+    },
+    {
+      "epoch": 0.027270488053766848,
+      "grad_norm": 4.843706130981445,
+      "learning_rate": 2.5393184796854525e-05,
+      "loss": 2.6387,
+      "step": 775
+    },
+    {
+      "epoch": 0.02836130757591752,
+      "grad_norm": 3.555110454559326,
+      "learning_rate": 2.6408912188728702e-05,
+      "loss": 2.5996,
+      "step": 806
+    },
+    {
+      "epoch": 0.029452127098068194,
+      "grad_norm": 3.3113982677459717,
+      "learning_rate": 2.7424639580602886e-05,
+      "loss": 2.5823,
+      "step": 837
+    },
+    {
+      "epoch": 0.030542946620218867,
+      "grad_norm": 3.4552953243255615,
+      "learning_rate": 2.8440366972477066e-05,
+      "loss": 2.5643,
+      "step": 868
+    },
+    {
+      "epoch": 0.03163376614236954,
+      "grad_norm": 2.9786770343780518,
+      "learning_rate": 2.9456094364351244e-05,
+      "loss": 2.5426,
+      "step": 899
+    },
+    {
+      "epoch": 0.03272458566452022,
+      "grad_norm": 3.227999210357666,
+      "learning_rate": 3.0471821756225428e-05,
+      "loss": 2.4834,
+      "step": 930
+    },
+    {
+      "epoch": 0.03381540518667089,
+      "grad_norm": 3.0225250720977783,
+      "learning_rate": 3.148754914809961e-05,
+      "loss": 2.4755,
+      "step": 961
+    },
+    {
+      "epoch": 0.034906224708821564,
+      "grad_norm": 2.6292648315429688,
+      "learning_rate": 3.2503276539973785e-05,
+      "loss": 2.4393,
+      "step": 992
+    },
+    {
+      "epoch": 0.03599704423097224,
+      "grad_norm": 2.767667055130005,
+      "learning_rate": 3.351900393184797e-05,
+      "loss": 2.4124,
+      "step": 1023
+    },
+    {
+      "epoch": 0.03708786375312291,
+      "grad_norm": 2.6588900089263916,
+      "learning_rate": 3.453473132372215e-05,
+      "loss": 2.3551,
+      "step": 1054
+    },
+    {
+      "epoch": 0.03817868327527359,
+      "grad_norm": 2.7497403621673584,
+      "learning_rate": 3.555045871559633e-05,
+      "loss": 2.3576,
+      "step": 1085
+    },
+    {
+      "epoch": 0.039269502797424256,
+      "grad_norm": 2.5148332118988037,
+      "learning_rate": 3.6566186107470514e-05,
+      "loss": 2.3078,
+      "step": 1116
+    },
+    {
+      "epoch": 0.04036032231957493,
+      "grad_norm": 3.0025594234466553,
+      "learning_rate": 3.7581913499344695e-05,
+      "loss": 2.303,
+      "step": 1147
+    },
+    {
+      "epoch": 0.0414511418417256,
+      "grad_norm": 2.6871118545532227,
+      "learning_rate": 3.8597640891218876e-05,
+      "loss": 2.3062,
+      "step": 1178
+    },
+    {
+      "epoch": 0.04254196136387628,
+      "grad_norm": 10.630929946899414,
+      "learning_rate": 3.9613368283093056e-05,
+      "loss": 2.307,
+      "step": 1209
+    },
+    {
+      "epoch": 0.043632780886026956,
+      "grad_norm": 2.571220874786377,
+      "learning_rate": 4.062909567496724e-05,
+      "loss": 2.2837,
+      "step": 1240
+    },
+    {
+      "epoch": 0.044723600408177626,
+      "grad_norm": 3.5510289669036865,
+      "learning_rate": 4.164482306684142e-05,
+      "loss": 2.2797,
+      "step": 1271
+    },
+    {
+      "epoch": 0.0458144199303283,
+      "grad_norm": 2.794853925704956,
+      "learning_rate": 4.26605504587156e-05,
+      "loss": 2.2797,
+      "step": 1302
+    },
+    {
+      "epoch": 0.04690523945247897,
+      "grad_norm": 6.132640838623047,
+      "learning_rate": 4.367627785058978e-05,
+      "loss": 2.2504,
+      "step": 1333
+    },
+    {
+      "epoch": 0.04799605897462965,
+      "grad_norm": 6.17495584487915,
+      "learning_rate": 4.469200524246396e-05,
+      "loss": 2.2414,
+      "step": 1364
+    },
+    {
+      "epoch": 0.049086878496780326,
+      "grad_norm": 2.3518564701080322,
+      "learning_rate": 4.570773263433814e-05,
+      "loss": 2.2198,
+      "step": 1395
+    },
+    {
+      "epoch": 0.050177698018930995,
+      "grad_norm": 2.2073466777801514,
+      "learning_rate": 4.672346002621232e-05,
+      "loss": 2.2057,
+      "step": 1426
+    },
+    {
+      "epoch": 0.05126851754108167,
+      "grad_norm": 2.018749237060547,
+      "learning_rate": 4.77391874180865e-05,
+      "loss": 2.1965,
+      "step": 1457
+    },
+    {
+      "epoch": 0.05235933706323234,
+      "grad_norm": 2.7125244140625,
+      "learning_rate": 4.875491480996068e-05,
+      "loss": 2.19,
+      "step": 1488
+    },
+    {
+      "epoch": 0.05345015658538302,
+      "grad_norm": 1.9725641012191772,
+      "learning_rate": 4.977064220183487e-05,
+      "loss": 2.1669,
+      "step": 1519
+    },
+    {
+      "epoch": 0.054540976107533695,
+      "grad_norm": 2.0198206901550293,
+      "learning_rate": 4.9999915451558777e-05,
+      "loss": 2.1486,
+      "step": 1550
+    },
+    {
+      "epoch": 0.055631795629684365,
+      "grad_norm": 2.068424940109253,
+      "learning_rate": 4.999955597496219e-05,
+      "loss": 2.1476,
+      "step": 1581
+    },
+    {
+      "epoch": 0.05672261515183504,
+      "grad_norm": 1.8509161472320557,
+      "learning_rate": 4.9998914381774255e-05,
+      "loss": 2.1129,
+      "step": 1612
+    },
+    {
+      "epoch": 0.05781343467398571,
+      "grad_norm": 1.805915355682373,
+      "learning_rate": 4.999799067923527e-05,
+      "loss": 2.1014,
+      "step": 1643
+    },
+    {
+      "epoch": 0.05890425419613639,
+      "grad_norm": 1.9447969198226929,
+      "learning_rate": 4.999678487776908e-05,
+      "loss": 2.1067,
+      "step": 1674
+    },
+    {
+      "epoch": 0.059995073718287065,
+      "grad_norm": 2.131700277328491,
+      "learning_rate": 4.9995296990983006e-05,
+      "loss": 2.0817,
+      "step": 1705
+    },
+    {
+      "epoch": 0.061085893240437734,
+      "grad_norm": 1.9113484621047974,
+      "learning_rate": 4.999352703566763e-05,
+      "loss": 2.067,
+      "step": 1736
+    },
+    {
+      "epoch": 0.06217671276258841,
+      "grad_norm": 1.8802495002746582,
+      "learning_rate": 4.999147503179668e-05,
+      "loss": 2.0617,
+      "step": 1767
+    },
+    {
+      "epoch": 0.06326753228473908,
+      "grad_norm": 1.6704238653182983,
+      "learning_rate": 4.998914100252672e-05,
+      "loss": 2.0671,
+      "step": 1798
+    },
+    {
+      "epoch": 0.06435835180688976,
+      "grad_norm": 4.303380966186523,
+      "learning_rate": 4.998652497419696e-05,
+      "loss": 2.0436,
+      "step": 1829
+    },
+    {
+      "epoch": 0.06544917132904043,
+      "grad_norm": 1.8054529428482056,
+      "learning_rate": 4.9983626976328927e-05,
+      "loss": 2.0499,
+      "step": 1860
+    },
+    {
+      "epoch": 0.06653999085119111,
+      "grad_norm": 1.663872241973877,
+      "learning_rate": 4.998044704162613e-05,
+      "loss": 2.0227,
+      "step": 1891
+    },
+    {
+      "epoch": 0.06763081037334177,
+      "grad_norm": 10.130581855773926,
+      "learning_rate": 4.9976985205973705e-05,
+      "loss": 2.0022,
+      "step": 1922
+    },
+    {
+      "epoch": 0.06872162989549245,
+      "grad_norm": 3.7727627754211426,
+      "learning_rate": 4.997324150843799e-05,
+      "loss": 2.0172,
+      "step": 1953
+    },
+    {
+      "epoch": 0.06981244941764313,
+      "grad_norm": 1.8669508695602417,
+      "learning_rate": 4.99692159912661e-05,
+      "loss": 2.0214,
+      "step": 1984
+    },
+    {
+      "epoch": 0.0709032689397938,
+      "grad_norm": 17.45224952697754,
+      "learning_rate": 4.996490869988546e-05,
+      "loss": 1.9959,
+      "step": 2015
+    },
+    {
+      "epoch": 0.07199408846194448,
+      "grad_norm": 1.7007793188095093,
+      "learning_rate": 4.996031968290326e-05,
+      "loss": 2.0139,
+      "step": 2046
+    },
+    {
+      "epoch": 0.07308490798409514,
+      "grad_norm": 1.6912076473236084,
+      "learning_rate": 4.995544899210594e-05,
+      "loss": 1.9963,
+      "step": 2077
+    },
+    {
+      "epoch": 0.07417572750624582,
+      "grad_norm": 1.6827666759490967,
+      "learning_rate": 4.9950296682458583e-05,
+      "loss": 1.973,
+      "step": 2108
+    },
+    {
+      "epoch": 0.0752665470283965,
+      "grad_norm": 1.767269253730774,
+      "learning_rate": 4.994486281210429e-05,
+      "loss": 1.9949,
+      "step": 2139
+    },
+    {
+      "epoch": 0.07635736655054717,
+      "grad_norm": 7.507472038269043,
+      "learning_rate": 4.9939147442363566e-05,
+      "loss": 1.9837,
+      "step": 2170
+    },
+    {
+      "epoch": 0.07744818607269784,
+      "grad_norm": 1.6840234994888306,
+      "learning_rate": 4.9933150637733574e-05,
+      "loss": 1.9789,
+      "step": 2201
+    },
+    {
+      "epoch": 0.07853900559484851,
+      "grad_norm": 1.6442159414291382,
+      "learning_rate": 4.992687246588743e-05,
+      "loss": 1.9436,
+      "step": 2232
+    },
+    {
+      "epoch": 0.07962982511699919,
+      "grad_norm": 1.546859622001648,
+      "learning_rate": 4.992031299767347e-05,
+      "loss": 1.9341,
+      "step": 2263
+    },
+    {
+      "epoch": 0.08072064463914987,
+      "grad_norm": 1.4932371377944946,
+      "learning_rate": 4.9913472307114386e-05,
+      "loss": 1.9583,
+      "step": 2294
+    },
+    {
+      "epoch": 0.08181146416130054,
+      "grad_norm": 1.4531840085983276,
+      "learning_rate": 4.9906350471406446e-05,
+      "loss": 1.9414,
+      "step": 2325
+    },
+    {
+      "epoch": 0.0829022836834512,
+      "grad_norm": 1.5285487174987793,
+      "learning_rate": 4.989894757091861e-05,
+      "loss": 1.9502,
+      "step": 2356
+    },
+    {
+      "epoch": 0.08399310320560188,
+      "grad_norm": 1.4159945249557495,
+      "learning_rate": 4.989126368919158e-05,
+      "loss": 1.9299,
+      "step": 2387
+    },
+    {
+      "epoch": 0.08508392272775256,
+      "grad_norm": 1.4361426830291748,
+      "learning_rate": 4.988329891293693e-05,
+      "loss": 1.9266,
+      "step": 2418
+    },
+    {
+      "epoch": 0.08617474224990324,
+      "grad_norm": 1.4310742616653442,
+      "learning_rate": 4.987505333203608e-05,
+      "loss": 1.9116,
+      "step": 2449
+    },
+    {
+      "epoch": 0.08726556177205391,
+      "grad_norm": 1.3780311346054077,
+      "learning_rate": 4.9866527039539276e-05,
+      "loss": 1.9189,
+      "step": 2480
+    },
+    {
+      "epoch": 0.08835638129420458,
+      "grad_norm": 1.3917787075042725,
+      "learning_rate": 4.9857720131664594e-05,
+      "loss": 1.9107,
+      "step": 2511
+    },
+    {
+      "epoch": 0.08944720081635525,
+      "grad_norm": 1.3963998556137085,
+      "learning_rate": 4.9848632707796773e-05,
+      "loss": 1.899,
+      "step": 2542
+    },
+    {
+      "epoch": 0.09053802033850593,
+      "grad_norm": 1.3573299646377563,
+      "learning_rate": 4.9839264870486155e-05,
+      "loss": 1.9084,
+      "step": 2573
+    },
+    {
+      "epoch": 0.0916288398606566,
+      "grad_norm": 1.362552523612976,
+      "learning_rate": 4.9829616725447526e-05,
+      "loss": 1.8954,
+      "step": 2604
+    },
+    {
+      "epoch": 0.09271965938280728,
+      "grad_norm": 1.3538340330123901,
+      "learning_rate": 4.981968838155888e-05,
+      "loss": 1.9035,
+      "step": 2635
+    },
+    {
+      "epoch": 0.09381047890495794,
+      "grad_norm": 1.407291054725647,
+      "learning_rate": 4.980947995086024e-05,
+      "loss": 1.8778,
+      "step": 2666
+    },
+    {
+      "epoch": 0.09490129842710862,
+      "grad_norm": 1.3554202318191528,
+      "learning_rate": 4.979899154855234e-05,
+      "loss": 1.8783,
+      "step": 2697
+    },
+    {
+      "epoch": 0.0959921179492593,
+      "grad_norm": 1.3513182401657104,
+      "learning_rate": 4.9788223292995386e-05,
+      "loss": 1.8857,
+      "step": 2728
+    },
+    {
+      "epoch": 0.09708293747140997,
+      "grad_norm": 1.345706582069397,
+      "learning_rate": 4.977717530570768e-05,
+      "loss": 1.8882,
+      "step": 2759
+    },
+    {
+      "epoch": 0.09817375699356065,
+      "grad_norm": 1.3450254201889038,
+      "learning_rate": 4.976584771136425e-05,
+      "loss": 1.8746,
+      "step": 2790
+    },
+    {
+      "epoch": 0.09926457651571131,
+      "grad_norm": 1.7820961475372314,
+      "learning_rate": 4.975424063779547e-05,
+      "loss": 1.8557,
+      "step": 2821
+    },
+    {
+      "epoch": 0.10035539603786199,
+      "grad_norm": 1.3493785858154297,
+      "learning_rate": 4.974235421598557e-05,
+      "loss": 1.8683,
+      "step": 2852
+    },
+    {
+      "epoch": 0.10144621556001267,
+      "grad_norm": 1.3066306114196777,
+      "learning_rate": 4.973018858007122e-05,
+      "loss": 1.8777,
+      "step": 2883
+    },
+    {
+      "epoch": 0.10253703508216334,
+      "grad_norm": 1.2991000413894653,
+      "learning_rate": 4.9717743867339963e-05,
+      "loss": 1.8605,
+      "step": 2914
+    },
+    {
+      "epoch": 0.10362785460431402,
+      "grad_norm": 1.3748496770858765,
+      "learning_rate": 4.9705020218228695e-05,
+      "loss": 1.8683,
+      "step": 2945
+    },
+    {
+      "epoch": 0.10471867412646468,
+      "grad_norm": 1.3229252099990845,
+      "learning_rate": 4.969201777632205e-05,
+      "loss": 1.858,
+      "step": 2976
+    },
+    {
+      "epoch": 0.10580949364861536,
+      "grad_norm": 1.2874318361282349,
+      "learning_rate": 4.9678736688350846e-05,
+      "loss": 1.8435,
+      "step": 3007
+    },
+    {
+      "epoch": 0.10690031317076604,
+      "grad_norm": 1.3341971635818481,
+      "learning_rate": 4.966517710419033e-05,
+      "loss": 1.8663,
+      "step": 3038
+    },
+    {
+      "epoch": 0.10799113269291671,
+      "grad_norm": 1.276282548904419,
+      "learning_rate": 4.965133917685858e-05,
+      "loss": 1.854,
+      "step": 3069
+    },
+    {
+      "epoch": 0.10908195221506739,
+      "grad_norm": 1.2999404668807983,
+      "learning_rate": 4.9637223062514714e-05,
+      "loss": 1.8498,
+      "step": 3100
+    },
+    {
+      "epoch": 0.11017277173721805,
+      "grad_norm": 1.2905164957046509,
+      "learning_rate": 4.962282892045718e-05,
+      "loss": 1.8436,
+      "step": 3131
+    },
+    {
+      "epoch": 0.11126359125936873,
+      "grad_norm": 1.9952430725097656,
+      "learning_rate": 4.9608156913121904e-05,
+      "loss": 1.8316,
+      "step": 3162
+    },
+    {
+      "epoch": 0.1123544107815194,
+      "grad_norm": 1.2637739181518555,
+      "learning_rate": 4.959320720608049e-05,
+      "loss": 1.8391,
+      "step": 3193
+    },
+    {
+      "epoch": 0.11344523030367008,
+      "grad_norm": 1.3711034059524536,
+      "learning_rate": 4.9577979968038354e-05,
+      "loss": 1.814,
+      "step": 3224
+    },
+    {
+      "epoch": 0.11453604982582076,
+      "grad_norm": 1.3050326108932495,
+      "learning_rate": 4.956247537083282e-05,
+      "loss": 1.8635,
+      "step": 3255
+    },
+    {
+      "epoch": 0.11562686934797142,
+      "grad_norm": 1.230220079421997,
+      "learning_rate": 4.9546693589431145e-05,
+      "loss": 1.8203,
+      "step": 3286
+    },
+    {
+      "epoch": 0.1167176888701221,
+      "grad_norm": 1.2535375356674194,
+      "learning_rate": 4.9530634801928595e-05,
+      "loss": 1.8319,
+      "step": 3317
+    },
+    {
+      "epoch": 0.11780850839227278,
+      "grad_norm": 1.227552890777588,
+      "learning_rate": 4.9514299189546395e-05,
+      "loss": 1.8157,
+      "step": 3348
+    },
+    {
+      "epoch": 0.11889932791442345,
+      "grad_norm": 1.2049622535705566,
+      "learning_rate": 4.949768693662973e-05,
+      "loss": 1.8135,
+      "step": 3379
+    },
+    {
+      "epoch": 0.11999014743657413,
+      "grad_norm": 1.1608529090881348,
+      "learning_rate": 4.948079823064559e-05,
+      "loss": 1.8191,
+      "step": 3410
+    },
+    {
+      "epoch": 0.12108096695872479,
+      "grad_norm": 1.2294845581054688,
+      "learning_rate": 4.946363326218074e-05,
+      "loss": 1.7977,
+      "step": 3441
+    },
+    {
+      "epoch": 0.12217178648087547,
+      "grad_norm": 1.1883920431137085,
+      "learning_rate": 4.9446192224939525e-05,
+      "loss": 1.8153,
+      "step": 3472
+    },
+    {
+      "epoch": 0.12326260600302615,
+      "grad_norm": 1.2770321369171143,
+      "learning_rate": 4.942847531574167e-05,
+      "loss": 1.8064,
+      "step": 3503
+    },
+    {
+      "epoch": 0.12435342552517682,
+      "grad_norm": 1.5442144870758057,
+      "learning_rate": 4.941048273452008e-05,
+      "loss": 1.8134,
+      "step": 3534
+    },
+    {
+      "epoch": 0.12544424504732749,
+      "grad_norm": 1.1753895282745361,
+      "learning_rate": 4.9392214684318605e-05,
+      "loss": 1.7909,
+      "step": 3565
+    },
+    {
+      "epoch": 0.12653506456947816,
+      "grad_norm": 1.2292894124984741,
+      "learning_rate": 4.93736713712897e-05,
+      "loss": 1.7894,
+      "step": 3596
+    },
+    {
+      "epoch": 0.12762588409162884,
+      "grad_norm": 1.1696261167526245,
+      "learning_rate": 4.9354853004692124e-05,
+      "loss": 1.7913,
+      "step": 3627
+    },
+    {
+      "epoch": 0.12871670361377952,
+      "grad_norm": 1.1935744285583496,
+      "learning_rate": 4.93357597968886e-05,
+      "loss": 1.8103,
+      "step": 3658
+    },
+    {
+      "epoch": 0.1298075231359302,
+      "grad_norm": 1.1842865943908691,
+      "learning_rate": 4.931639196334338e-05,
+      "loss": 1.7778,
+      "step": 3689
+    },
+    {
+      "epoch": 0.13089834265808087,
+      "grad_norm": 1.187715768814087,
+      "learning_rate": 4.9296749722619826e-05,
+      "loss": 1.7955,
+      "step": 3720
+    },
+    {
+      "epoch": 0.13198916218023155,
+      "grad_norm": 1.1973644495010376,
+      "learning_rate": 4.9276833296377966e-05,
+      "loss": 1.7786,
+      "step": 3751
+    },
+    {
+      "epoch": 0.13307998170238222,
+      "grad_norm": 1.129618525505066,
+      "learning_rate": 4.925664290937196e-05,
+      "loss": 1.7819,
+      "step": 3782
+    },
+    {
+      "epoch": 0.13417080122453287,
+      "grad_norm": 1.1466953754425049,
+      "learning_rate": 4.9236178789447576e-05,
+      "loss": 1.7732,
+      "step": 3813
+    },
+    {
+      "epoch": 0.13526162074668355,
+      "grad_norm": 1.1432143449783325,
+      "learning_rate": 4.921544116753962e-05,
+      "loss": 1.7872,
+      "step": 3844
+    },
+    {
+      "epoch": 0.13635244026883422,
+      "grad_norm": 1.1669626235961914,
+      "learning_rate": 4.919443027766935e-05,
+      "loss": 1.7708,
+      "step": 3875
+    },
+    {
+      "epoch": 0.1374432597909849,
+      "grad_norm": 1.1273548603057861,
+      "learning_rate": 4.91731463569418e-05,
+      "loss": 1.7767,
+      "step": 3906
+    },
+    {
+      "epoch": 0.13853407931313558,
+      "grad_norm": 1.146063208580017,
+      "learning_rate": 4.915158964554312e-05,
+      "loss": 1.7695,
+      "step": 3937
+    },
+    {
+      "epoch": 0.13962489883528625,
+      "grad_norm": 1.1724731922149658,
+      "learning_rate": 4.912976038673786e-05,
+      "loss": 1.7709,
+      "step": 3968
+    },
+    {
+      "epoch": 0.14071571835743693,
+      "grad_norm": 1.122382402420044,
+      "learning_rate": 4.9107658826866254e-05,
+      "loss": 1.7871,
+      "step": 3999
+    },
+    {
+      "epoch": 0.1418065378795876,
+      "grad_norm": 1.2005928754806519,
+      "learning_rate": 4.908528521534139e-05,
+      "loss": 1.7896,
+      "step": 4030
+    },
+    {
+      "epoch": 0.14289735740173828,
+      "grad_norm": 1.1000254154205322,
+      "learning_rate": 4.906263980464644e-05,
+      "loss": 1.7645,
+      "step": 4061
+    },
+    {
+      "epoch": 0.14398817692388896,
+      "grad_norm": 1.1797596216201782,
+      "learning_rate": 4.903972285033178e-05,
+      "loss": 1.7702,
+      "step": 4092
+    },
+    {
+      "epoch": 0.1450789964460396,
+      "grad_norm": 1.145271897315979,
+      "learning_rate": 4.901653461101213e-05,
+      "loss": 1.7541,
+      "step": 4123
+    },
+    {
+      "epoch": 0.1461698159681903,
+      "grad_norm": 1.1336746215820312,
+      "learning_rate": 4.8993075348363626e-05,
+      "loss": 1.7604,
+      "step": 4154
+    },
+    {
+      "epoch": 0.14726063549034096,
+      "grad_norm": 1.1435718536376953,
+      "learning_rate": 4.896934532712084e-05,
+      "loss": 1.7461,
+      "step": 4185
+    },
+    {
+      "epoch": 0.14835145501249164,
+      "grad_norm": 1.1105029582977295,
+      "learning_rate": 4.8945344815073846e-05,
+      "loss": 1.7691,
+      "step": 4216
+    },
+    {
+      "epoch": 0.14944227453464232,
+      "grad_norm": 1.1397055387496948,
+      "learning_rate": 4.892107408306516e-05,
+      "loss": 1.7599,
+      "step": 4247
+    },
+    {
+      "epoch": 0.150533094056793,
+      "grad_norm": 1.1158910989761353,
+      "learning_rate": 4.889653340498669e-05,
+      "loss": 1.7537,
+      "step": 4278
+    },
+    {
+      "epoch": 0.15162391357894367,
+      "grad_norm": 1.1238468885421753,
+      "learning_rate": 4.8871723057776664e-05,
+      "loss": 1.7672,
+      "step": 4309
+    },
+    {
+      "epoch": 0.15271473310109435,
+      "grad_norm": 1.1303473711013794,
+      "learning_rate": 4.8846643321416476e-05,
+      "loss": 1.7542,
+      "step": 4340
+    },
+    {
+      "epoch": 0.15380555262324502,
+      "grad_norm": 1.117262840270996,
+      "learning_rate": 4.882129447892753e-05,
+      "loss": 1.7378,
+      "step": 4371
+    },
+    {
+      "epoch": 0.15489637214539567,
+      "grad_norm": 1.1086496114730835,
+      "learning_rate": 4.8795676816368076e-05,
+      "loss": 1.7439,
+      "step": 4402
+    },
+    {
+      "epoch": 0.15598719166754635,
+      "grad_norm": 1.276014804840088,
+      "learning_rate": 4.876979062282995e-05,
+      "loss": 1.7699,
+      "step": 4433
+    },
+    {
+      "epoch": 0.15707801118969703,
+      "grad_norm": 1.1294457912445068,
+      "learning_rate": 4.8743636190435325e-05,
+      "loss": 1.7292,
+      "step": 4464
+    },
+    {
+      "epoch": 0.1581688307118477,
+      "grad_norm": 1.1111900806427002,
+      "learning_rate": 4.871721381433344e-05,
+      "loss": 1.7487,
+      "step": 4495
+    },
+    {
+      "epoch": 0.15925965023399838,
+      "grad_norm": 1.0868422985076904,
+      "learning_rate": 4.869052379269719e-05,
+      "loss": 1.7397,
+      "step": 4526
+    },
+    {
+      "epoch": 0.16035046975614906,
+      "grad_norm": 1.0772205591201782,
+      "learning_rate": 4.866356642671985e-05,
+      "loss": 1.7377,
+      "step": 4557
+    },
+    {
+      "epoch": 0.16144128927829973,
+      "grad_norm": 1.0649960041046143,
+      "learning_rate": 4.8636342020611634e-05,
+      "loss": 1.7253,
+      "step": 4588
+    },
+    {
+      "epoch": 0.1625321088004504,
+      "grad_norm": 1.0653575658798218,
+      "learning_rate": 4.860885088159626e-05,
+      "loss": 1.7319,
+      "step": 4619
+    },
+    {
+      "epoch": 0.16362292832260109,
+      "grad_norm": 1.0669118165969849,
+      "learning_rate": 4.858109331990751e-05,
+      "loss": 1.7425,
+      "step": 4650
+    },
+    {
+      "epoch": 0.16471374784475176,
+      "grad_norm": 1.0559724569320679,
+      "learning_rate": 4.855306964878567e-05,
+      "loss": 1.7364,
+      "step": 4681
+    },
+    {
+      "epoch": 0.1658045673669024,
+      "grad_norm": 1.038191318511963,
+      "learning_rate": 4.8524780184474084e-05,
+      "loss": 1.7299,
+      "step": 4712
+    },
+    {
+      "epoch": 0.1668953868890531,
+      "grad_norm": 1.0602952241897583,
+      "learning_rate": 4.8496225246215496e-05,
+      "loss": 1.7256,
+      "step": 4743
+    },
+    {
+      "epoch": 0.16798620641120376,
+      "grad_norm": 1.0466082096099854,
+      "learning_rate": 4.8467405156248505e-05,
+      "loss": 1.7148,
+      "step": 4774
+    },
+    {
+      "epoch": 0.16907702593335444,
+      "grad_norm": 1.051708698272705,
+      "learning_rate": 4.843832023980392e-05,
+      "loss": 1.722,
+      "step": 4805
+    },
+    {
+      "epoch": 0.17016784545550512,
+      "grad_norm": 1.065427541732788,
+      "learning_rate": 4.840897082510106e-05,
+      "loss": 1.7088,
+      "step": 4836
+    },
+    {
+      "epoch": 0.1712586649776558,
+      "grad_norm": 1.0983659029006958,
+      "learning_rate": 4.8379357243344084e-05,
+      "loss": 1.7422,
+      "step": 4867
+    },
+    {
+      "epoch": 0.17234948449980647,
+      "grad_norm": 1.0919371843338013,
+      "learning_rate": 4.8349479828718236e-05,
+      "loss": 1.7253,
+      "step": 4898
+    },
+    {
+      "epoch": 0.17344030402195715,
+      "grad_norm": 1.0881919860839844,
+      "learning_rate": 4.8319338918386075e-05,
+      "loss": 1.7185,
+      "step": 4929
+    },
+    {
+      "epoch": 0.17453112354410782,
+      "grad_norm": 1.0374606847763062,
+      "learning_rate": 4.828893485248369e-05,
+      "loss": 1.7255,
+      "step": 4960
+    },
+    {
+      "epoch": 0.1756219430662585,
+      "grad_norm": 1.0947892665863037,
+      "learning_rate": 4.825826797411682e-05,
+      "loss": 1.7095,
+      "step": 4991
+    },
+    {
+      "epoch": 0.17671276258840915,
+      "grad_norm": 1.1086746454238892,
+      "learning_rate": 4.822733862935702e-05,
+      "loss": 1.7233,
+      "step": 5022
+    },
+    {
+      "epoch": 0.17780358211055983,
+      "grad_norm": 1.0662850141525269,
+      "learning_rate": 4.819614716723775e-05,
+      "loss": 1.7426,
+      "step": 5053
+    },
+    {
+      "epoch": 0.1788944016327105,
+      "grad_norm": 1.0137659311294556,
+      "learning_rate": 4.8164693939750425e-05,
+      "loss": 1.7358,
+      "step": 5084
+    },
+    {
+      "epoch": 0.17998522115486118,
+      "grad_norm": 1.049338698387146,
+      "learning_rate": 4.813297930184042e-05,
+      "loss": 1.6981,
+      "step": 5115
+    },
+    {
+      "epoch": 0.18107604067701186,
+      "grad_norm": 1.08591628074646,
+      "learning_rate": 4.810100361140314e-05,
+      "loss": 1.7178,
+      "step": 5146
+    },
+    {
+      "epoch": 0.18216686019916253,
+      "grad_norm": 1.0983690023422241,
+      "learning_rate": 4.8068767229279885e-05,
+      "loss": 1.7179,
+      "step": 5177
+    },
+    {
+      "epoch": 0.1832576797213132,
+      "grad_norm": 1.0783159732818604,
+      "learning_rate": 4.8036270519253854e-05,
+      "loss": 1.7198,
+      "step": 5208
+    },
+    {
+      "epoch": 0.1843484992434639,
+      "grad_norm": 1.0519956350326538,
+      "learning_rate": 4.8003513848046e-05,
+      "loss": 1.7154,
+      "step": 5239
+    },
+    {
+      "epoch": 0.18543931876561456,
+      "grad_norm": 1.0484226942062378,
+      "learning_rate": 4.79704975853109e-05,
+      "loss": 1.7081,
+      "step": 5270
+    },
+    {
+      "epoch": 0.18653013828776524,
+      "grad_norm": 1.0263608694076538,
+      "learning_rate": 4.793722210363262e-05,
+      "loss": 1.6961,
+      "step": 5301
+    },
+    {
+      "epoch": 0.1876209578099159,
+      "grad_norm": 0.9863409399986267,
+      "learning_rate": 4.7903687778520414e-05,
+      "loss": 1.7198,
+      "step": 5332
+    },
+    {
+      "epoch": 0.18871177733206657,
+      "grad_norm": 1.0293922424316406,
+      "learning_rate": 4.7869894988404593e-05,
+      "loss": 1.6958,
+      "step": 5363
+    },
+    {
+      "epoch": 0.18980259685421724,
+      "grad_norm": 0.9902015924453735,
+      "learning_rate": 4.783584411463221e-05,
+      "loss": 1.7162,
+      "step": 5394
+    },
+    {
+      "epoch": 0.19089341637636792,
+      "grad_norm": 1.0472259521484375,
+      "learning_rate": 4.780153554146274e-05,
+      "loss": 1.7189,
+      "step": 5425
+    },
+    {
+      "epoch": 0.1919842358985186,
+      "grad_norm": 1.0958000421524048,
+      "learning_rate": 4.7766969656063766e-05,
+      "loss": 1.7288,
+      "step": 5456
+    },
+    {
+      "epoch": 0.19307505542066927,
+      "grad_norm": 1.0132781267166138,
+      "learning_rate": 4.773214684850662e-05,
+      "loss": 1.6915,
+      "step": 5487
+    },
+    {
+      "epoch": 0.19416587494281995,
+      "grad_norm": 1.0274685621261597,
+      "learning_rate": 4.769706751176193e-05,
+      "loss": 1.7063,
+      "step": 5518
+    },
+    {
+      "epoch": 0.19525669446497063,
+      "grad_norm": 1.0145214796066284,
+      "learning_rate": 4.7661732041695264e-05,
+      "loss": 1.7072,
+      "step": 5549
+    },
+    {
+      "epoch": 0.1963475139871213,
+      "grad_norm": 1.053489327430725,
+      "learning_rate": 4.762614083706258e-05,
+      "loss": 1.6897,
+      "step": 5580
+    },
+    {
+      "epoch": 0.19743833350927198,
+      "grad_norm": 1.0426928997039795,
+      "learning_rate": 4.759029429950581e-05,
+      "loss": 1.6868,
+      "step": 5611
+    },
+    {
+      "epoch": 0.19852915303142263,
+      "grad_norm": 1.0594595670700073,
+      "learning_rate": 4.7554192833548235e-05,
+      "loss": 1.6978,
+      "step": 5642
+    },
+    {
+      "epoch": 0.1996199725535733,
+      "grad_norm": 1.0251655578613281,
+      "learning_rate": 4.751783684659e-05,
+      "loss": 1.6834,
+      "step": 5673
+    },
+    {
+      "epoch": 0.20071079207572398,
+      "grad_norm": 1.0762938261032104,
+      "learning_rate": 4.748122674890348e-05,
+      "loss": 1.6825,
+      "step": 5704
+    },
+    {
+      "epoch": 0.20180161159787466,
+      "grad_norm": 1.0672742128372192,
+      "learning_rate": 4.7444362953628654e-05,
+      "loss": 1.6811,
+      "step": 5735
+    },
+    {
+      "epoch": 0.20289243112002533,
+      "grad_norm": 1.0267951488494873,
+      "learning_rate": 4.7407245876768424e-05,
+      "loss": 1.7024,
+      "step": 5766
+    },
+    {
+      "epoch": 0.203983250642176,
+      "grad_norm": 1.0520440340042114,
+      "learning_rate": 4.736987593718397e-05,
+      "loss": 1.7008,
+      "step": 5797
+    },
+    {
+      "epoch": 0.2050740701643267,
+      "grad_norm": 1.0106167793273926,
+      "learning_rate": 4.733225355658999e-05,
+      "loss": 1.6721,
+      "step": 5828
+    },
+    {
+      "epoch": 0.20616488968647737,
+      "grad_norm": 0.9883444905281067,
+      "learning_rate": 4.7294379159549926e-05,
+      "loss": 1.6884,
+      "step": 5859
+    },
+    {
+      "epoch": 0.20725570920862804,
+      "grad_norm": 0.9873078465461731,
+      "learning_rate": 4.725625317347119e-05,
+      "loss": 1.7011,
+      "step": 5890
+    },
+    {
+      "epoch": 0.2083465287307787,
+      "grad_norm": 0.9925514459609985,
+      "learning_rate": 4.7217876028600374e-05,
+      "loss": 1.6965,
+      "step": 5921
+    },
+    {
+      "epoch": 0.20943734825292937,
+      "grad_norm": 1.0054575204849243,
+      "learning_rate": 4.717924815801832e-05,
+      "loss": 1.6923,
+      "step": 5952
+    },
+    {
+      "epoch": 0.21052816777508004,
+      "grad_norm": 1.0051021575927734,
+      "learning_rate": 4.714036999763532e-05,
+      "loss": 1.6864,
+      "step": 5983
+    },
+    {
+      "epoch": 0.21161898729723072,
+      "grad_norm": 1.0312145948410034,
+      "learning_rate": 4.7101241986186116e-05,
+      "loss": 1.6776,
+      "step": 6014
+    },
+    {
+      "epoch": 0.2127098068193814,
+      "grad_norm": 0.9964466094970703,
+      "learning_rate": 4.7061864565225e-05,
+      "loss": 1.6811,
+      "step": 6045
+    },
+    {
+      "epoch": 0.21380062634153207,
+      "grad_norm": 0.9997463226318359,
+      "learning_rate": 4.702223817912081e-05,
+      "loss": 1.6805,
+      "step": 6076
+    },
+    {
+      "epoch": 0.21489144586368275,
+      "grad_norm": 0.9945687055587769,
+      "learning_rate": 4.698236327505195e-05,
+      "loss": 1.6746,
+      "step": 6107
+    },
+    {
+      "epoch": 0.21598226538583343,
+      "grad_norm": 1.0496478080749512,
+      "learning_rate": 4.694224030300127e-05,
+      "loss": 1.6791,
+      "step": 6138
+    },
+    {
+      "epoch": 0.2170730849079841,
+      "grad_norm": 1.0148327350616455,
+      "learning_rate": 4.690186971575107e-05,
+      "loss": 1.6848,
+      "step": 6169
+    },
+    {
+      "epoch": 0.21816390443013478,
+      "grad_norm": 0.9963369965553284,
+      "learning_rate": 4.6861251968877916e-05,
+      "loss": 1.7055,
+      "step": 6200
+    },
+    {
+      "epoch": 0.21925472395228543,
+      "grad_norm": 0.9630306959152222,
+      "learning_rate": 4.68203875207476e-05,
+      "loss": 1.6716,
+      "step": 6231
+    },
+    {
+      "epoch": 0.2203455434744361,
+      "grad_norm": 0.9671465158462524,
+      "learning_rate": 4.677927683250983e-05,
+      "loss": 1.6754,
+      "step": 6262
+    },
+    {
+      "epoch": 0.22143636299658678,
+      "grad_norm": 0.9531513452529907,
+      "learning_rate": 4.6737920368093156e-05,
+      "loss": 1.6792,
+      "step": 6293
+    },
+    {
+      "epoch": 0.22252718251873746,
+      "grad_norm": 0.9835436344146729,
+      "learning_rate": 4.669631859419965e-05,
+      "loss": 1.6651,
+      "step": 6324
+    },
+    {
+      "epoch": 0.22361800204088814,
+      "grad_norm": 0.9870143532752991,
+      "learning_rate": 4.6654471980299676e-05,
+      "loss": 1.6903,
+      "step": 6355
+    },
+    {
+      "epoch": 0.2247088215630388,
+      "grad_norm": 1.0126017332077026,
+      "learning_rate": 4.661238099862658e-05,
+      "loss": 1.6883,
+      "step": 6386
+    },
+    {
+      "epoch": 0.2257996410851895,
+      "grad_norm": 1.0292701721191406,
+      "learning_rate": 4.657004612417138e-05,
+      "loss": 1.6841,
+      "step": 6417
+    },
+    {
+      "epoch": 0.22689046060734017,
+      "grad_norm": 0.9697965979576111,
+      "learning_rate": 4.6527467834677374e-05,
+      "loss": 1.684,
+      "step": 6448
+    },
+    {
+      "epoch": 0.22798128012949084,
+      "grad_norm": 0.9756552577018738,
+      "learning_rate": 4.648464661063478e-05,
+      "loss": 1.6756,
+      "step": 6479
+    },
+    {
+      "epoch": 0.22907209965164152,
+      "grad_norm": 1.1156080961227417,
+      "learning_rate": 4.6441582935275264e-05,
+      "loss": 1.6707,
+      "step": 6510
+    },
+    {
+      "epoch": 0.23016291917379217,
+      "grad_norm": 0.975688636302948,
+      "learning_rate": 4.6398277294566586e-05,
+      "loss": 1.6738,
+      "step": 6541
+    },
+    {
+      "epoch": 0.23125373869594285,
+      "grad_norm": 0.9863653779029846,
+      "learning_rate": 4.6354730177207e-05,
+      "loss": 1.6748,
+      "step": 6572
+    },
+    {
+      "epoch": 0.23234455821809352,
+      "grad_norm": 0.9869725108146667,
+      "learning_rate": 4.6310942074619787e-05,
+      "loss": 1.6715,
+      "step": 6603
+    },
+    {
+      "epoch": 0.2334353777402442,
+      "grad_norm": 0.9991948008537292,
+      "learning_rate": 4.626691348094777e-05,
+      "loss": 1.6692,
+      "step": 6634
+    },
+    {
+      "epoch": 0.23452619726239488,
+      "grad_norm": 0.9353803992271423,
+      "learning_rate": 4.622264489304762e-05,
+      "loss": 1.6571,
+      "step": 6665
+    },
+    {
+      "epoch": 0.23561701678454555,
+      "grad_norm": 0.9929242134094238,
+      "learning_rate": 4.617813681048434e-05,
+      "loss": 1.6614,
+      "step": 6696
+    },
+    {
+      "epoch": 0.23670783630669623,
+      "grad_norm": 1.003203272819519,
+      "learning_rate": 4.61333897355256e-05,
+      "loss": 1.6577,
+      "step": 6727
+    },
+    {
+      "epoch": 0.2377986558288469,
+      "grad_norm": 0.9584728479385376,
+      "learning_rate": 4.608840417313604e-05,
+      "loss": 1.6862,
+      "step": 6758
+    },
+    {
+      "epoch": 0.23888947535099758,
+      "grad_norm": 0.9825113415718079,
+      "learning_rate": 4.6043180630971646e-05,
+      "loss": 1.6651,
+      "step": 6789
+    },
+    {
+      "epoch": 0.23998029487314826,
+      "grad_norm": 0.9904153347015381,
+      "learning_rate": 4.599771961937391e-05,
+      "loss": 1.6665,
+      "step": 6820
+    },
+    {
+      "epoch": 0.2410711143952989,
+      "grad_norm": 0.9444073438644409,
+      "learning_rate": 4.5952021651364204e-05,
+      "loss": 1.6591,
+      "step": 6851
+    },
+    {
+      "epoch": 0.24216193391744958,
+      "grad_norm": 0.9723752737045288,
+      "learning_rate": 4.590608724263786e-05,
+      "loss": 1.6711,
+      "step": 6882
+    },
+    {
+      "epoch": 0.24325275343960026,
+      "grad_norm": 1.0078589916229248,
+      "learning_rate": 4.585991691155845e-05,
+      "loss": 1.6764,
+      "step": 6913
+    },
+    {
+      "epoch": 0.24434357296175094,
+      "grad_norm": 0.9442929625511169,
+      "learning_rate": 4.581351117915188e-05,
+      "loss": 1.6484,
+      "step": 6944
+    },
+    {
+      "epoch": 0.24543439248390161,
+      "grad_norm": 0.9573075771331787,
+      "learning_rate": 4.5766870569100534e-05,
+      "loss": 1.6638,
+      "step": 6975
+    },
+    {
+      "epoch": 0.2465252120060523,
+      "grad_norm": 0.9371550679206848,
+      "learning_rate": 4.571999560773736e-05,
+      "loss": 1.6565,
+      "step": 7006
+    },
+    {
+      "epoch": 0.24761603152820297,
+      "grad_norm": 0.9628654718399048,
+      "learning_rate": 4.5672886824039915e-05,
+      "loss": 1.653,
+      "step": 7037
+    },
+    {
+      "epoch": 0.24870685105035364,
+      "grad_norm": 1.265812635421753,
+      "learning_rate": 4.5625544749624435e-05,
+      "loss": 1.6661,
+      "step": 7068
+    },
+    {
+      "epoch": 0.24979767057250432,
+      "grad_norm": 0.9990148544311523,
+      "learning_rate": 4.5577969918739794e-05,
+      "loss": 1.6536,
+      "step": 7099
+    },
+    {
+      "epoch": 0.25088849009465497,
+      "grad_norm": 0.9349009394645691,
+      "learning_rate": 4.5530162868261486e-05,
+      "loss": 1.6578,
+      "step": 7130
+    },
+    {
+      "epoch": 0.25197930961680565,
+      "grad_norm": 0.9215208292007446,
+      "learning_rate": 4.548212413768558e-05,
+      "loss": 1.6454,
+      "step": 7161
+    },
+    {
+      "epoch": 0.2530701291389563,
+      "grad_norm": 0.9580157995223999,
+      "learning_rate": 4.543385426912261e-05,
+      "loss": 1.6643,
+      "step": 7192
+    },
+    {
+      "epoch": 0.254160948661107,
+      "grad_norm": 0.9289986491203308,
+      "learning_rate": 4.53853538072915e-05,
+      "loss": 1.6659,
+      "step": 7223
+    },
+    {
+      "epoch": 0.2552517681832577,
+      "grad_norm": 0.9344154000282288,
+      "learning_rate": 4.533662329951336e-05,
+      "loss": 1.6772,
+      "step": 7254
+    },
+    {
+      "epoch": 0.25634258770540835,
+      "grad_norm": 0.9400781393051147,
+      "learning_rate": 4.528766329570536e-05,
+      "loss": 1.6493,
+      "step": 7285
+    },
+    {
+      "epoch": 0.25743340722755903,
+      "grad_norm": 0.963218092918396,
+      "learning_rate": 4.523847434837447e-05,
+      "loss": 1.6394,
+      "step": 7316
+    },
+    {
+      "epoch": 0.2585242267497097,
+      "grad_norm": 0.9619491696357727,
+      "learning_rate": 4.518905701261128e-05,
+      "loss": 1.6574,
+      "step": 7347
+    },
+    {
+      "epoch": 0.2596150462718604,
+      "grad_norm": 0.9310999512672424,
+      "learning_rate": 4.5139411846083715e-05,
+      "loss": 1.673,
+      "step": 7378
+    },
+    {
+      "epoch": 0.26070586579401106,
+      "grad_norm": 1.1424349546432495,
+      "learning_rate": 4.508953940903073e-05,
+      "loss": 1.6626,
+      "step": 7409
+    },
+    {
+      "epoch": 0.26179668531616174,
+      "grad_norm": 0.9687772393226624,
+      "learning_rate": 4.5039440264255994e-05,
+      "loss": 1.6548,
+      "step": 7440
+    },
+    {
+      "epoch": 0.2628875048383124,
+      "grad_norm": 0.9415249824523926,
+      "learning_rate": 4.498911497712155e-05,
+      "loss": 1.6452,
+      "step": 7471
+    },
+    {
+      "epoch": 0.2639783243604631,
+      "grad_norm": 0.9598653316497803,
+      "learning_rate": 4.493856411554142e-05,
+      "loss": 1.6527,
+      "step": 7502
+    },
+    {
+      "epoch": 0.26506914388261377,
+      "grad_norm": 0.9518615007400513,
+      "learning_rate": 4.4887788249975206e-05,
+      "loss": 1.6445,
+      "step": 7533
+    },
+    {
+      "epoch": 0.26615996340476444,
+      "grad_norm": 0.9153622388839722,
+      "learning_rate": 4.4836787953421656e-05,
+      "loss": 1.6255,
+      "step": 7564
+    },
+    {
+      "epoch": 0.26725078292691506,
+      "grad_norm": 0.9497701525688171,
+      "learning_rate": 4.478556380141218e-05,
+      "loss": 1.6499,
+      "step": 7595
+    },
+    {
+      "epoch": 0.26834160244906574,
+      "grad_norm": 0.9468094706535339,
+      "learning_rate": 4.4734116372004375e-05,
+      "loss": 1.6269,
+      "step": 7626
+    },
+    {
+      "epoch": 0.2694324219712164,
+      "grad_norm": 0.9106606245040894,
+      "learning_rate": 4.4682446245775477e-05,
+      "loss": 1.6396,
+      "step": 7657
+    },
+    {
+      "epoch": 0.2705232414933671,
+      "grad_norm": 0.946415901184082,
+      "learning_rate": 4.463055400581586e-05,
+      "loss": 1.6443,
+      "step": 7688
+    },
+    {
+      "epoch": 0.27161406101551777,
+      "grad_norm": 0.9249156713485718,
+      "learning_rate": 4.4578440237722374e-05,
+      "loss": 1.649,
+      "step": 7719
+    },
+    {
+      "epoch": 0.27270488053766845,
+      "grad_norm": 0.9326067566871643,
+      "learning_rate": 4.452610552959183e-05,
+      "loss": 1.6399,
+      "step": 7750
+    },
+    {
+      "epoch": 0.2737957000598191,
+      "grad_norm": 0.9351608157157898,
+      "learning_rate": 4.447355047201428e-05,
+      "loss": 1.6286,
+      "step": 7781
+    },
+    {
+      "epoch": 0.2748865195819698,
+      "grad_norm": 0.9721508622169495,
+      "learning_rate": 4.4420775658066414e-05,
+      "loss": 1.6503,
+      "step": 7812
+    },
+    {
+      "epoch": 0.2759773391041205,
+      "grad_norm": 0.9394717812538147,
+      "learning_rate": 4.436778168330484e-05,
+      "loss": 1.6514,
+      "step": 7843
+    },
+    {
+      "epoch": 0.27706815862627115,
+      "grad_norm": 0.9202150702476501,
+      "learning_rate": 4.4314569145759353e-05,
+      "loss": 1.6252,
+      "step": 7874
+    },
+    {
+      "epoch": 0.27815897814842183,
+      "grad_norm": 0.9670141339302063,
+      "learning_rate": 4.42611386459262e-05,
+      "loss": 1.6349,
+      "step": 7905
+    },
+    {
+      "epoch": 0.2792497976705725,
+      "grad_norm": 0.9340211749076843,
+      "learning_rate": 4.420749078676133e-05,
+      "loss": 1.642,
+      "step": 7936
+    },
+    {
+      "epoch": 0.2803406171927232,
+      "grad_norm": 0.9478600025177002,
+      "learning_rate": 4.4153626173673516e-05,
+      "loss": 1.6552,
+      "step": 7967
+    },
+    {
+      "epoch": 0.28143143671487386,
+      "grad_norm": 0.9464743733406067,
+      "learning_rate": 4.409954541451762e-05,
+      "loss": 1.6378,
+      "step": 7998
+    },
+    {
+      "epoch": 0.28252225623702454,
+      "grad_norm": 0.9389581084251404,
+      "learning_rate": 4.404524911958764e-05,
+      "loss": 1.6325,
+      "step": 8029
+    },
+    {
+      "epoch": 0.2836130757591752,
+      "grad_norm": 0.9357293248176575,
+      "learning_rate": 4.399073790160989e-05,
+      "loss": 1.6422,
+      "step": 8060
+    },
+    {
+      "epoch": 0.2847038952813259,
+      "grad_norm": 0.9474714398384094,
+      "learning_rate": 4.393601237573607e-05,
+      "loss": 1.6595,
+      "step": 8091
+    },
+    {
+      "epoch": 0.28579471480347657,
+      "grad_norm": 0.9302358031272888,
+      "learning_rate": 4.388107315953628e-05,
+      "loss": 1.6439,
+      "step": 8122
+    },
+    {
+      "epoch": 0.28688553432562724,
+      "grad_norm": 0.948805570602417,
+      "learning_rate": 4.382592087299212e-05,
+      "loss": 1.6459,
+      "step": 8153
+    },
+    {
+      "epoch": 0.2879763538477779,
+      "grad_norm": 0.9055014252662659,
+      "learning_rate": 4.377055613848964e-05,
+      "loss": 1.6427,
+      "step": 8184
+    },
+    {
+      "epoch": 0.28906717336992854,
+      "grad_norm": 0.9128564596176147,
+      "learning_rate": 4.3714979580812355e-05,
+      "loss": 1.6254,
+      "step": 8215
+    },
+    {
+      "epoch": 0.2901579928920792,
+      "grad_norm": 0.8954737782478333,
+      "learning_rate": 4.365919182713416e-05,
+      "loss": 1.6265,
+      "step": 8246
+    },
+    {
+      "epoch": 0.2912488124142299,
+      "grad_norm": 0.9502245783805847,
+      "learning_rate": 4.360319350701226e-05,
+      "loss": 1.6366,
+      "step": 8277
+    },
+    {
+      "epoch": 0.2923396319363806,
+      "grad_norm": 0.907567024230957,
+      "learning_rate": 4.3546985252380115e-05,
+      "loss": 1.6222,
+      "step": 8308
+    },
+    {
+      "epoch": 0.29343045145853125,
+      "grad_norm": 0.9578949809074402,
+      "learning_rate": 4.349056769754021e-05,
+      "loss": 1.6411,
+      "step": 8339
+    },
+    {
+      "epoch": 0.2945212709806819,
+      "grad_norm": 0.9497959613800049,
+      "learning_rate": 4.3433941479156994e-05,
+      "loss": 1.632,
+      "step": 8370
+    },
+    {
+      "epoch": 0.2956120905028326,
+      "grad_norm": 1.1019785404205322,
+      "learning_rate": 4.3377107236249647e-05,
+      "loss": 1.6495,
+      "step": 8401
+    },
+    {
+      "epoch": 0.2967029100249833,
+      "grad_norm": 0.9178378582000732,
+      "learning_rate": 4.332006561018488e-05,
+      "loss": 1.6298,
+      "step": 8432
+    },
+    {
+      "epoch": 0.29779372954713396,
+      "grad_norm": 0.9462074041366577,
+      "learning_rate": 4.3262817244669683e-05,
+      "loss": 1.6327,
+      "step": 8463
+    },
+    {
+      "epoch": 0.29888454906928463,
+      "grad_norm": 0.9369425177574158,
+      "learning_rate": 4.3205362785744083e-05,
+      "loss": 1.6372,
+      "step": 8494
+    },
+    {
+      "epoch": 0.2999753685914353,
+      "grad_norm": 0.918860912322998,
+      "learning_rate": 4.314770288177384e-05,
+      "loss": 1.6205,
+      "step": 8525
+    },
+    {
+      "epoch": 0.301066188113586,
+      "grad_norm": 0.9392362236976624,
+      "learning_rate": 4.308983818344313e-05,
+      "loss": 1.6184,
+      "step": 8556
+    },
+    {
+      "epoch": 0.30215700763573666,
+      "grad_norm": 0.9137156009674072,
+      "learning_rate": 4.3031769343747206e-05,
+      "loss": 1.6253,
+      "step": 8587
+    },
+    {
+      "epoch": 0.30324782715788734,
+      "grad_norm": 0.9086781144142151,
+      "learning_rate": 4.297349701798505e-05,
+      "loss": 1.6264,
+      "step": 8618
+    },
+    {
+      "epoch": 0.304338646680038,
+      "grad_norm": 0.9457340240478516,
+      "learning_rate": 4.2915021863751916e-05,
+      "loss": 1.6098,
+      "step": 8649
+    },
+    {
+      "epoch": 0.3054294662021887,
+      "grad_norm": 0.9216846823692322,
+      "learning_rate": 4.285634454093198e-05,
+      "loss": 1.6325,
+      "step": 8680
+    },
+    {
+      "epoch": 0.30652028572433937,
+      "grad_norm": 0.9189222455024719,
+      "learning_rate": 4.279746571169086e-05,
+      "loss": 1.6164,
+      "step": 8711
+    },
+    {
+      "epoch": 0.30761110524649005,
+      "grad_norm": 0.9216083288192749,
+      "learning_rate": 4.2738386040468136e-05,
+      "loss": 1.6084,
+      "step": 8742
+    },
+    {
+      "epoch": 0.3087019247686407,
+      "grad_norm": 0.9195507764816284,
+      "learning_rate": 4.2679106193969866e-05,
+      "loss": 1.6249,
+      "step": 8773
+    },
+    {
+      "epoch": 0.30979274429079134,
+      "grad_norm": 0.9332253932952881,
+      "learning_rate": 4.261962684116106e-05,
+      "loss": 1.633,
+      "step": 8804
+    },
+    {
+      "epoch": 0.310883563812942,
+      "grad_norm": 0.9223430752754211,
+      "learning_rate": 4.2559948653258145e-05,
+      "loss": 1.6117,
+      "step": 8835
+    },
+    {
+      "epoch": 0.3119743833350927,
+      "grad_norm": 0.8972631692886353,
+      "learning_rate": 4.250007230372134e-05,
+      "loss": 1.5931,
+      "step": 8866
+    },
+    {
+      "epoch": 0.3130652028572434,
+      "grad_norm": 0.8789275288581848,
+      "learning_rate": 4.2439998468247126e-05,
+      "loss": 1.6384,
+      "step": 8897
+    },
+    {
+      "epoch": 0.31415602237939405,
+      "grad_norm": 0.8869777321815491,
+      "learning_rate": 4.2379727824760566e-05,
+      "loss": 1.6043,
+      "step": 8928
+    },
+    {
+      "epoch": 0.3152468419015447,
+      "grad_norm": 0.9047911167144775,
+      "learning_rate": 4.231926105340768e-05,
+      "loss": 1.6301,
+      "step": 8959
+    },
+    {
+      "epoch": 0.3163376614236954,
+      "grad_norm": 0.8834474086761475,
+      "learning_rate": 4.225859883654776e-05,
+      "loss": 1.624,
+      "step": 8990
+    },
+    {
+      "epoch": 0.3174284809458461,
+      "grad_norm": 0.9142968058586121,
+      "learning_rate": 4.219774185874569e-05,
+      "loss": 1.6232,
+      "step": 9021
+    },
+    {
+      "epoch": 0.31851930046799676,
+      "grad_norm": 0.9930256009101868,
+      "learning_rate": 4.213669080676418e-05,
+      "loss": 1.6091,
+      "step": 9052
+    },
+    {
+      "epoch": 0.31961011999014743,
+      "grad_norm": 0.9061794877052307,
+      "learning_rate": 4.2075446369556056e-05,
+      "loss": 1.6468,
+      "step": 9083
+    },
+    {
+      "epoch": 0.3207009395122981,
+      "grad_norm": 0.8935773372650146,
+      "learning_rate": 4.201400923825648e-05,
+      "loss": 1.598,
+      "step": 9114
+    },
+    {
+      "epoch": 0.3217917590344488,
+      "grad_norm": 0.9085298180580139,
+      "learning_rate": 4.195238010617511e-05,
+      "loss": 1.6136,
+      "step": 9145
+    },
+    {
+      "epoch": 0.32288257855659946,
+      "grad_norm": 0.9264605045318604,
+      "learning_rate": 4.1890559668788344e-05,
+      "loss": 1.6174,
+      "step": 9176
+    },
+    {
+      "epoch": 0.32397339807875014,
+      "grad_norm": 0.9291498064994812,
+      "learning_rate": 4.1828548623731405e-05,
+      "loss": 1.6179,
+      "step": 9207
+    },
+    {
+      "epoch": 0.3250642176009008,
+      "grad_norm": 0.8831276893615723,
+      "learning_rate": 4.1766347670790506e-05,
+      "loss": 1.6119,
+      "step": 9238
+    },
+    {
+      "epoch": 0.3261550371230515,
+      "grad_norm": 0.9102134108543396,
+      "learning_rate": 4.170395751189495e-05,
+      "loss": 1.6266,
+      "step": 9269
+    },
+    {
+      "epoch": 0.32724585664520217,
+      "grad_norm": 0.8952730298042297,
+      "learning_rate": 4.164137885110921e-05,
+      "loss": 1.622,
+      "step": 9300
+    },
+    {
+      "epoch": 0.32833667616735285,
+      "grad_norm": 0.9174513220787048,
+      "learning_rate": 4.157861239462495e-05,
+      "loss": 1.6163,
+      "step": 9331
+    },
+    {
+      "epoch": 0.3294274956895035,
+      "grad_norm": 0.880759060382843,
+      "learning_rate": 4.1515658850753114e-05,
+      "loss": 1.5997,
+      "step": 9362
+    },
+    {
+      "epoch": 0.3305183152116542,
+      "grad_norm": 0.8925946950912476,
+      "learning_rate": 4.145251892991588e-05,
+      "loss": 1.5974,
+      "step": 9393
+    },
+    {
+      "epoch": 0.3316091347338048,
+      "grad_norm": 0.9017757773399353,
+      "learning_rate": 4.138919334463868e-05,
+      "loss": 1.6019,
+      "step": 9424
+    },
+    {
+      "epoch": 0.3326999542559555,
+      "grad_norm": 0.9045889377593994,
+      "learning_rate": 4.1325682809542124e-05,
+      "loss": 1.6318,
+      "step": 9455
+    },
+    {
+      "epoch": 0.3337907737781062,
+      "grad_norm": 0.870001494884491,
+      "learning_rate": 4.126198804133398e-05,
+      "loss": 1.6092,
+      "step": 9486
+    },
+    {
+      "epoch": 0.33488159330025685,
+      "grad_norm": 0.8898991942405701,
+      "learning_rate": 4.1198109758801055e-05,
+      "loss": 1.6015,
+      "step": 9517
+    },
+    {
+      "epoch": 0.33597241282240753,
+      "grad_norm": 0.8767693638801575,
+      "learning_rate": 4.113404868280107e-05,
+      "loss": 1.5911,
+      "step": 9548
+    },
+    {
+      "epoch": 0.3370632323445582,
+      "grad_norm": 0.8673516511917114,
+      "learning_rate": 4.106980553625457e-05,
+      "loss": 1.6137,
+      "step": 9579
+    },
+    {
+      "epoch": 0.3381540518667089,
+      "grad_norm": 0.9067351818084717,
+      "learning_rate": 4.100538104413674e-05,
+      "loss": 1.5993,
+      "step": 9610
+    },
+    {
+      "epoch": 0.33924487138885956,
+      "grad_norm": 0.9343692660331726,
+      "learning_rate": 4.09407759334692e-05,
+      "loss": 1.6074,
+      "step": 9641
+    },
+    {
+      "epoch": 0.34033569091101024,
+      "grad_norm": 0.9002503752708435,
+      "learning_rate": 4.087599093331186e-05,
+      "loss": 1.6267,
+      "step": 9672
+    },
+    {
+      "epoch": 0.3414265104331609,
+      "grad_norm": 0.9147412776947021,
+      "learning_rate": 4.081102677475462e-05,
+      "loss": 1.6106,
+      "step": 9703
+    },
+    {
+      "epoch": 0.3425173299553116,
+      "grad_norm": 0.9228988885879517,
+      "learning_rate": 4.0745884190909194e-05,
+      "loss": 1.6258,
+      "step": 9734
+    },
+    {
+      "epoch": 0.34360814947746227,
+      "grad_norm": 0.8599364757537842,
+      "learning_rate": 4.0680563916900796e-05,
+      "loss": 1.6039,
+      "step": 9765
+    },
+    {
+      "epoch": 0.34469896899961294,
+      "grad_norm": 0.844178318977356,
+      "learning_rate": 4.0615066689859815e-05,
+      "loss": 1.5899,
+      "step": 9796
+    },
+    {
+      "epoch": 0.3457897885217636,
+      "grad_norm": 0.9241573810577393,
+      "learning_rate": 4.0549393248913584e-05,
+      "loss": 1.5916,
+      "step": 9827
+    },
+    {
+      "epoch": 0.3468806080439143,
+      "grad_norm": 0.9131301641464233,
+      "learning_rate": 4.048354433517794e-05,
+      "loss": 1.6045,
+      "step": 9858
+    },
+    {
+      "epoch": 0.347971427566065,
+      "grad_norm": 0.8763211965560913,
+      "learning_rate": 4.0417520691748916e-05,
+      "loss": 1.6088,
+      "step": 9889
+    },
+    {
+      "epoch": 0.34906224708821565,
+      "grad_norm": 0.9151899218559265,
+      "learning_rate": 4.035132306369438e-05,
+      "loss": 1.5976,
+      "step": 9920
+    },
+    {
+      "epoch": 0.3501530666103663,
+      "grad_norm": 0.8976767063140869,
+      "learning_rate": 4.028495219804555e-05,
+      "loss": 1.6129,
+      "step": 9951
+    },
+    {
+      "epoch": 0.351243886132517,
+      "grad_norm": 0.8878459930419922,
+      "learning_rate": 4.021840884378864e-05,
+      "loss": 1.5994,
+      "step": 9982
+    },
+    {
+      "epoch": 0.3523347056546677,
+      "grad_norm": 0.8572807312011719,
+      "learning_rate": 4.015169375185633e-05,
+      "loss": 1.6002,
+      "step": 10013
+    },
+    {
+      "epoch": 0.3534255251768183,
+      "grad_norm": 0.8996985554695129,
+      "learning_rate": 4.0084807675119396e-05,
+      "loss": 1.6136,
+      "step": 10044
+    },
+    {
+      "epoch": 0.354516344698969,
+      "grad_norm": 0.8947619795799255,
+      "learning_rate": 4.0017751368378106e-05,
+      "loss": 1.598,
+      "step": 10075
+    },
+    {
+      "epoch": 0.35560716422111965,
+      "grad_norm": 0.9073825478553772,
+      "learning_rate": 3.995052558835377e-05,
+      "loss": 1.6164,
+      "step": 10106
+    },
+    {
+      "epoch": 0.35669798374327033,
+      "grad_norm": 0.8670364022254944,
+      "learning_rate": 3.988313109368017e-05,
+      "loss": 1.6012,
+      "step": 10137
+    },
+    {
+      "epoch": 0.357788803265421,
+      "grad_norm": 0.8530169725418091,
+      "learning_rate": 3.981556864489504e-05,
+      "loss": 1.5947,
+      "step": 10168
+    },
+    {
+      "epoch": 0.3588796227875717,
+      "grad_norm": 0.8809841275215149,
+      "learning_rate": 3.974783900443142e-05,
+      "loss": 1.6033,
+      "step": 10199
+    },
+    {
+      "epoch": 0.35997044230972236,
+      "grad_norm": 0.8582516312599182,
+      "learning_rate": 3.9679942936609095e-05,
+      "loss": 1.6029,
+      "step": 10230
+    },
+    {
+      "epoch": 0.36106126183187304,
+      "grad_norm": 0.8762260675430298,
+      "learning_rate": 3.961188120762596e-05,
+      "loss": 1.5921,
+      "step": 10261
+    },
+    {
+      "epoch": 0.3621520813540237,
+      "grad_norm": 0.8775869011878967,
+      "learning_rate": 3.954365458554938e-05,
+      "loss": 1.6101,
+      "step": 10292
+    },
+    {
+      "epoch": 0.3632429008761744,
+      "grad_norm": 0.9066540002822876,
+      "learning_rate": 3.947526384030751e-05,
+      "loss": 1.5928,
+      "step": 10323
+    },
+    {
+      "epoch": 0.36433372039832507,
+      "grad_norm": 0.9105854630470276,
+      "learning_rate": 3.9406709743680624e-05,
+      "loss": 1.5973,
+      "step": 10354
+    },
+    {
+      "epoch": 0.36542453992047574,
+      "grad_norm": 0.8927069902420044,
+      "learning_rate": 3.9337993069292366e-05,
+      "loss": 1.6159,
+      "step": 10385
+    },
+    {
+      "epoch": 0.3665153594426264,
+      "grad_norm": 0.9006061553955078,
+      "learning_rate": 3.926911459260109e-05,
+      "loss": 1.6111,
+      "step": 10416
+    },
+    {
+      "epoch": 0.3676061789647771,
+      "grad_norm": 0.8990784883499146,
+      "learning_rate": 3.920007509089102e-05,
+      "loss": 1.5975,
+      "step": 10447
+    },
+    {
+      "epoch": 0.3686969984869278,
+      "grad_norm": 0.9229722619056702,
+      "learning_rate": 3.913087534326357e-05,
+      "loss": 1.5962,
+      "step": 10478
+    },
+    {
+      "epoch": 0.36978781800907845,
+      "grad_norm": 0.9110054969787598,
+      "learning_rate": 3.9061516130628475e-05,
+      "loss": 1.6129,
+      "step": 10509
+    },
+    {
+      "epoch": 0.3708786375312291,
+      "grad_norm": 0.917635440826416,
+      "learning_rate": 3.8991998235695025e-05,
+      "loss": 1.5975,
+      "step": 10540
+    },
+    {
+      "epoch": 0.3719694570533798,
+      "grad_norm": 0.8891541957855225,
+      "learning_rate": 3.8922322442963224e-05,
+      "loss": 1.5711,
+      "step": 10571
+    },
+    {
+      "epoch": 0.3730602765755305,
+      "grad_norm": 0.8646354675292969,
+      "learning_rate": 3.885248953871491e-05,
+      "loss": 1.6038,
+      "step": 10602
+    },
+    {
+      "epoch": 0.3741510960976811,
+      "grad_norm": 0.8377805948257446,
+      "learning_rate": 3.8782500311004915e-05,
+      "loss": 1.6113,
+      "step": 10633
+    },
+    {
+      "epoch": 0.3752419156198318,
+      "grad_norm": 0.8636441826820374,
+      "learning_rate": 3.871235554965218e-05,
+      "loss": 1.5802,
+      "step": 10664
+    },
+    {
+      "epoch": 0.37633273514198246,
+      "grad_norm": 0.8898093700408936,
+      "learning_rate": 3.864205604623078e-05,
+      "loss": 1.6054,
+      "step": 10695
+    },
+    {
+      "epoch": 0.37742355466413313,
+      "grad_norm": 0.887256383895874,
+      "learning_rate": 3.857160259406107e-05,
+      "loss": 1.5933,
+      "step": 10726
+    },
+    {
+      "epoch": 0.3785143741862838,
+      "grad_norm": 0.8577413558959961,
+      "learning_rate": 3.8500995988200674e-05,
+      "loss": 1.5875,
+      "step": 10757
+    },
+    {
+      "epoch": 0.3796051937084345,
+      "grad_norm": 0.8893071413040161,
+      "learning_rate": 3.843023702543556e-05,
+      "loss": 1.5857,
+      "step": 10788
+    },
+    {
+      "epoch": 0.38069601323058516,
+      "grad_norm": 0.847111165523529,
+      "learning_rate": 3.8359326504270984e-05,
+      "loss": 1.5837,
+      "step": 10819
+    },
+    {
+      "epoch": 0.38178683275273584,
+      "grad_norm": 0.8827951550483704,
+      "learning_rate": 3.828826522492255e-05,
+      "loss": 1.5748,
+      "step": 10850
+    },
+    {
+      "epoch": 0.3828776522748865,
+      "grad_norm": 0.8470546007156372,
+      "learning_rate": 3.821705398930713e-05,
+      "loss": 1.5995,
+      "step": 10881
+    },
+    {
+      "epoch": 0.3839684717970372,
+      "grad_norm": 0.987573504447937,
+      "learning_rate": 3.814569360103385e-05,
+      "loss": 1.5926,
+      "step": 10912
+    },
+    {
+      "epoch": 0.38505929131918787,
+      "grad_norm": 0.8766013383865356,
+      "learning_rate": 3.807418486539499e-05,
+      "loss": 1.581,
+      "step": 10943
+    },
+    {
+      "epoch": 0.38615011084133855,
+      "grad_norm": 0.9069483876228333,
+      "learning_rate": 3.80025285893569e-05,
+      "loss": 1.5912,
+      "step": 10974
+    },
+    {
+      "epoch": 0.3872409303634892,
+      "grad_norm": 0.9085988998413086,
+      "learning_rate": 3.793072558155093e-05,
+      "loss": 1.5871,
+      "step": 11005
+    },
+    {
+      "epoch": 0.3883317498856399,
+      "grad_norm": 0.9167149066925049,
+      "learning_rate": 3.785877665226426e-05,
+      "loss": 1.5902,
+      "step": 11036
+    },
+    {
+      "epoch": 0.3894225694077906,
+      "grad_norm": 0.8932046294212341,
+      "learning_rate": 3.778668261343079e-05,
+      "loss": 1.6048,
+      "step": 11067
+    },
+    {
+      "epoch": 0.39051338892994125,
+      "grad_norm": 0.8533083200454712,
+      "learning_rate": 3.771444427862192e-05,
+      "loss": 1.5803,
+      "step": 11098
+    },
+    {
+      "epoch": 0.39160420845209193,
+      "grad_norm": 0.8877330422401428,
+      "learning_rate": 3.7642062463037465e-05,
+      "loss": 1.5855,
+      "step": 11129
+    },
+    {
+      "epoch": 0.3926950279742426,
+      "grad_norm": 0.8700180649757385,
+      "learning_rate": 3.7569537983496373e-05,
+      "loss": 1.5843,
+      "step": 11160
+    },
+    {
+      "epoch": 0.3937858474963933,
+      "grad_norm": 0.8378989100456238,
+      "learning_rate": 3.749687165842753e-05,
+      "loss": 1.5664,
+      "step": 11191
+    },
+    {
+      "epoch": 0.39487666701854396,
+      "grad_norm": 0.8885537981987,
+      "learning_rate": 3.7424064307860536e-05,
+      "loss": 1.5822,
+      "step": 11222
+    },
+    {
+      "epoch": 0.3959674865406946,
+      "grad_norm": 0.8644111752510071,
+      "learning_rate": 3.735111675341645e-05,
+      "loss": 1.5893,
+      "step": 11253
+    },
+    {
+      "epoch": 0.39705830606284526,
+      "grad_norm": 0.8942341804504395,
+      "learning_rate": 3.7278029818298524e-05,
+      "loss": 1.5909,
+      "step": 11284
+    },
+    {
+      "epoch": 0.39814912558499593,
+      "grad_norm": 0.858748733997345,
+      "learning_rate": 3.720480432728287e-05,
+      "loss": 1.5832,
+      "step": 11315
+    },
+    {
+      "epoch": 0.3992399451071466,
+      "grad_norm": 0.8919023275375366,
+      "learning_rate": 3.71314411067092e-05,
+      "loss": 1.5804,
+      "step": 11346
+    },
+    {
+      "epoch": 0.4003307646292973,
+      "grad_norm": 0.8735581636428833,
+      "learning_rate": 3.70579409844715e-05,
+      "loss": 1.5856,
+      "step": 11377
+    },
+    {
+      "epoch": 0.40142158415144796,
+      "grad_norm": 0.843586266040802,
+      "learning_rate": 3.698430479000865e-05,
+      "loss": 1.5814,
+      "step": 11408
+    },
+    {
+      "epoch": 0.40251240367359864,
+      "grad_norm": 0.8684964776039124,
+      "learning_rate": 3.691053335429509e-05,
+      "loss": 1.5823,
+      "step": 11439
+    },
+    {
+      "epoch": 0.4036032231957493,
+      "grad_norm": 0.8695327639579773,
+      "learning_rate": 3.683662750983147e-05,
+      "loss": 1.5817,
+      "step": 11470
+    },
+    {
+      "epoch": 0.4046940427179,
+      "grad_norm": 0.9438059329986572,
+      "learning_rate": 3.676258809063518e-05,
+      "loss": 1.6003,
+      "step": 11501
+    },
+    {
+      "epoch": 0.40578486224005067,
+      "grad_norm": 0.8711549043655396,
+      "learning_rate": 3.6688415932231004e-05,
+      "loss": 1.5843,
+      "step": 11532
+    },
+    {
+      "epoch": 0.40687568176220135,
+      "grad_norm": 0.9110082387924194,
+      "learning_rate": 3.661411187164166e-05,
+      "loss": 1.5942,
+      "step": 11563
+    },
+    {
+      "epoch": 0.407966501284352,
+      "grad_norm": 0.8768247961997986,
+      "learning_rate": 3.65396767473784e-05,
+      "loss": 1.6002,
+      "step": 11594
+    },
+    {
+      "epoch": 0.4090573208065027,
+      "grad_norm": 0.8380584120750427,
+      "learning_rate": 3.6465111399431465e-05,
+      "loss": 1.5755,
+      "step": 11625
+    },
+    {
+      "epoch": 0.4101481403286534,
+      "grad_norm": 0.8617690801620483,
+      "learning_rate": 3.6390416669260674e-05,
+      "loss": 1.5817,
+      "step": 11656
+    },
+    {
+      "epoch": 0.41123895985080405,
+      "grad_norm": 0.8809701800346375,
+      "learning_rate": 3.63155933997859e-05,
+      "loss": 1.5779,
+      "step": 11687
+    },
+    {
+      "epoch": 0.41232977937295473,
+      "grad_norm": 0.8623855113983154,
+      "learning_rate": 3.624064243537758e-05,
+      "loss": 1.5749,
+      "step": 11718
+    },
+    {
+      "epoch": 0.4134205988951054,
+      "grad_norm": 0.9026786684989929,
+      "learning_rate": 3.616556462184716e-05,
+      "loss": 1.5676,
+      "step": 11749
+    },
+    {
+      "epoch": 0.4145114184172561,
+      "grad_norm": 0.8784968852996826,
+      "learning_rate": 3.609036080643755e-05,
+      "loss": 1.6103,
+      "step": 11780
+    },
+    {
+      "epoch": 0.41560223793940676,
+      "grad_norm": 0.8578303456306458,
+      "learning_rate": 3.60150318378136e-05,
+      "loss": 1.6004,
+      "step": 11811
+    },
+    {
+      "epoch": 0.4166930574615574,
+      "grad_norm": 0.8620411157608032,
+      "learning_rate": 3.5939578566052465e-05,
+      "loss": 1.5821,
+      "step": 11842
+    },
+    {
+      "epoch": 0.41778387698370806,
+      "grad_norm": 0.8622260093688965,
+      "learning_rate": 3.586400184263408e-05,
+      "loss": 1.5735,
+      "step": 11873
+    },
+    {
+      "epoch": 0.41887469650585873,
+      "grad_norm": 0.871585488319397,
+      "learning_rate": 3.578830252043148e-05,
+      "loss": 1.5705,
+      "step": 11904
+    },
+    {
+      "epoch": 0.4199655160280094,
+      "grad_norm": 0.8741966485977173,
+      "learning_rate": 3.571248145370125e-05,
+      "loss": 1.5898,
+      "step": 11935
+    },
+    {
+      "epoch": 0.4210563355501601,
+      "grad_norm": 0.8671961426734924,
+      "learning_rate": 3.5636539498073794e-05,
+      "loss": 1.5662,
+      "step": 11966
+    },
+    {
+      "epoch": 0.42214715507231076,
+      "grad_norm": 0.8873665928840637,
+      "learning_rate": 3.556047751054378e-05,
+      "loss": 1.5856,
+      "step": 11997
+    },
+    {
+      "epoch": 0.42323797459446144,
+      "grad_norm": 0.8614113926887512,
+      "learning_rate": 3.548429634946039e-05,
+      "loss": 1.5609,
+      "step": 12028
+    },
+    {
+      "epoch": 0.4243287941166121,
+      "grad_norm": 0.8387187719345093,
+      "learning_rate": 3.540799687451768e-05,
+      "loss": 1.5728,
+      "step": 12059
+    },
+    {
+      "epoch": 0.4254196136387628,
+      "grad_norm": 0.8875289559364319,
+      "learning_rate": 3.533157994674485e-05,
+      "loss": 1.5749,
+      "step": 12090
+    },
+    {
+      "epoch": 0.42651043316091347,
+      "grad_norm": 0.8648973107337952,
+      "learning_rate": 3.5255046428496546e-05,
+      "loss": 1.5695,
+      "step": 12121
+    },
+    {
+      "epoch": 0.42760125268306415,
+      "grad_norm": 0.8634358048439026,
+      "learning_rate": 3.517839718344311e-05,
+      "loss": 1.5685,
+      "step": 12152
+    },
+    {
+      "epoch": 0.4286920722052148,
+      "grad_norm": 0.8736028075218201,
+      "learning_rate": 3.510163307656086e-05,
+      "loss": 1.5721,
+      "step": 12183
+    }
+  ],
+  "logging_steps": 31,
+  "max_steps": 30517,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 3052,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.526741678122336e+18,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-12208/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0ca846c3dadf09d6ea20e996f3b024f89f025d88b771ce5d9eb5e978edeb732
+size 5304

checkpoint-15260/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/mnt/parscratch/users/acp23ay/private/models/Qwen2.5-7B-Instruct-bn-madlad-mean/",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.0.dev0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 161672
+}

checkpoint-15260/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.44.0.dev0"
+}

checkpoint-15260/model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d45d270b8f0a07193b431cc6831c60580db71b427e8ccbddb217311a2df7f71a
+size 4842817304

checkpoint-15260/model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:becf3c41c7359877372d1f9bdba9efe52cb2b8dab7330b346e831a36665b8f0e
+size 4998852224

checkpoint-15260/model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad9da13aef49ef9aa84ff7ac6ae375fc2f8c339648214e7663e44e16a6763847
+size 4984124304

checkpoint-15260/model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfc2c86e34819a46908bfe3ad42f3986e7efdfc34f67e43f40f690f77c7b0672
+size 4932743992

checkpoint-15260/model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:891f86a74d6b1791b98b581ff94cbedb16bfdb78595b9697dc3fd2ecc5974ba2
+size 4998852296

checkpoint-15260/model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:784c1e7b05372183e2a12d214b6588387655892bc19906cd33f52318c98facaf
+size 3662865184

checkpoint-15260/model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1323b77e030a15be5b1a543c2d382ecf1a58bd5909aff8e21d7a4675c24a960e
+size 2317729920

checkpoint-15260/model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 30737946624
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.norm.weight": "model-00006-of-00007.safetensors"
+  }
+}

checkpoint-15260/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd280aa5f0fe0d48567f04b2f84e11467dedffd0254e801a963609de96dcf1ee
+size 16728842070

checkpoint-15260/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d9cd6a0487226e5bd30d1846894c82af483733ab4381b75bae9c0745e05d405
+size 14244

checkpoint-15260/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ce335347efaebf038b8915bc0a8d2d587a4a1aa08ad0e015b4bc7cc4fba634e
+size 1064

checkpoint-15260/trainer_state.json

@@ -0,0 +1,3477 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.5369647067102995,
+  "eval_steps": 500,
+  "global_step": 15260,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0010908195221506739,
+      "grad_norm": 27.24474334716797,
+      "learning_rate": 1.0157273918741808e-06,
+      "loss": 9.0396,
+      "step": 31
+    },
+    {
+      "epoch": 0.0021816390443013477,
+      "grad_norm": 16.773351669311523,
+      "learning_rate": 2.0314547837483616e-06,
+      "loss": 7.9471,
+      "step": 62
+    },
+    {
+      "epoch": 0.0032724585664520214,
+      "grad_norm": 15.084428787231445,
+      "learning_rate": 3.0471821756225426e-06,
+      "loss": 6.5868,
+      "step": 93
+    },
+    {
+      "epoch": 0.0043632780886026954,
+      "grad_norm": 6.7851786613464355,
+      "learning_rate": 4.062909567496723e-06,
+      "loss": 5.3744,
+      "step": 124
+    },
+    {
+      "epoch": 0.0054540976107533695,
+      "grad_norm": 7.081949234008789,
+      "learning_rate": 5.078636959370905e-06,
+      "loss": 4.6378,
+      "step": 155
+    },
+    {
+      "epoch": 0.006544917132904043,
+      "grad_norm": 8.945405960083008,
+      "learning_rate": 6.094364351245085e-06,
+      "loss": 4.2292,
+      "step": 186
+    },
+    {
+      "epoch": 0.007635736655054717,
+      "grad_norm": 15.078816413879395,
+      "learning_rate": 7.110091743119267e-06,
+      "loss": 3.9767,
+      "step": 217
+    },
+    {
+      "epoch": 0.008726556177205391,
+      "grad_norm": 8.799291610717773,
+      "learning_rate": 8.125819134993446e-06,
+      "loss": 3.765,
+      "step": 248
+    },
+    {
+      "epoch": 0.009817375699356064,
+      "grad_norm": 9.741459846496582,
+      "learning_rate": 9.141546526867629e-06,
+      "loss": 3.6496,
+      "step": 279
+    },
+    {
+      "epoch": 0.010908195221506739,
+      "grad_norm": 9.403132438659668,
+      "learning_rate": 1.015727391874181e-05,
+      "loss": 3.4936,
+      "step": 310
+    },
+    {
+      "epoch": 0.011999014743657412,
+      "grad_norm": 8.479109764099121,
+      "learning_rate": 1.117300131061599e-05,
+      "loss": 3.3879,
+      "step": 341
+    },
+    {
+      "epoch": 0.013089834265808085,
+      "grad_norm": 4.988598823547363,
+      "learning_rate": 1.218872870249017e-05,
+      "loss": 3.3147,
+      "step": 372
+    },
+    {
+      "epoch": 0.01418065378795876,
+      "grad_norm": 5.518200874328613,
+      "learning_rate": 1.3204456094364351e-05,
+      "loss": 3.2022,
+      "step": 403
+    },
+    {
+      "epoch": 0.015271473310109434,
+      "grad_norm": 5.685606002807617,
+      "learning_rate": 1.4220183486238533e-05,
+      "loss": 3.1393,
+      "step": 434
+    },
+    {
+      "epoch": 0.01636229283226011,
+      "grad_norm": 5.6373491287231445,
+      "learning_rate": 1.5235910878112714e-05,
+      "loss": 3.05,
+      "step": 465
+    },
+    {
+      "epoch": 0.017453112354410782,
+      "grad_norm": 5.174935340881348,
+      "learning_rate": 1.6251638269986893e-05,
+      "loss": 2.992,
+      "step": 496
+    },
+    {
+      "epoch": 0.018543931876561455,
+      "grad_norm": 5.266006946563721,
+      "learning_rate": 1.7267365661861077e-05,
+      "loss": 2.9558,
+      "step": 527
+    },
+    {
+      "epoch": 0.019634751398712128,
+      "grad_norm": 4.111412048339844,
+      "learning_rate": 1.8283093053735257e-05,
+      "loss": 2.9089,
+      "step": 558
+    },
+    {
+      "epoch": 0.0207255709208628,
+      "grad_norm": 4.149659156799316,
+      "learning_rate": 1.9298820445609438e-05,
+      "loss": 2.879,
+      "step": 589
+    },
+    {
+      "epoch": 0.021816390443013478,
+      "grad_norm": 4.711772441864014,
+      "learning_rate": 2.031454783748362e-05,
+      "loss": 2.8057,
+      "step": 620
+    },
+    {
+      "epoch": 0.02290720996516415,
+      "grad_norm": 4.372698783874512,
+      "learning_rate": 2.13302752293578e-05,
+      "loss": 2.7954,
+      "step": 651
+    },
+    {
+      "epoch": 0.023998029487314824,
+      "grad_norm": 3.9052813053131104,
+      "learning_rate": 2.234600262123198e-05,
+      "loss": 2.7286,
+      "step": 682
+    },
+    {
+      "epoch": 0.025088849009465498,
+      "grad_norm": 3.544926404953003,
+      "learning_rate": 2.336173001310616e-05,
+      "loss": 2.6875,
+      "step": 713
+    },
+    {
+      "epoch": 0.02617966853161617,
+      "grad_norm": 4.380484104156494,
+      "learning_rate": 2.437745740498034e-05,
+      "loss": 2.6703,
+      "step": 744
+    },
+    {
+      "epoch": 0.027270488053766848,
+      "grad_norm": 4.843706130981445,
+      "learning_rate": 2.5393184796854525e-05,
+      "loss": 2.6387,
+      "step": 775
+    },
+    {
+      "epoch": 0.02836130757591752,
+      "grad_norm": 3.555110454559326,
+      "learning_rate": 2.6408912188728702e-05,
+      "loss": 2.5996,
+      "step": 806
+    },
+    {
+      "epoch": 0.029452127098068194,
+      "grad_norm": 3.3113982677459717,
+      "learning_rate": 2.7424639580602886e-05,
+      "loss": 2.5823,
+      "step": 837
+    },
+    {
+      "epoch": 0.030542946620218867,
+      "grad_norm": 3.4552953243255615,
+      "learning_rate": 2.8440366972477066e-05,
+      "loss": 2.5643,
+      "step": 868
+    },
+    {
+      "epoch": 0.03163376614236954,
+      "grad_norm": 2.9786770343780518,
+      "learning_rate": 2.9456094364351244e-05,
+      "loss": 2.5426,
+      "step": 899
+    },
+    {
+      "epoch": 0.03272458566452022,
+      "grad_norm": 3.227999210357666,
+      "learning_rate": 3.0471821756225428e-05,
+      "loss": 2.4834,
+      "step": 930
+    },
+    {
+      "epoch": 0.03381540518667089,
+      "grad_norm": 3.0225250720977783,
+      "learning_rate": 3.148754914809961e-05,
+      "loss": 2.4755,
+      "step": 961
+    },
+    {
+      "epoch": 0.034906224708821564,
+      "grad_norm": 2.6292648315429688,
+      "learning_rate": 3.2503276539973785e-05,
+      "loss": 2.4393,
+      "step": 992
+    },
+    {
+      "epoch": 0.03599704423097224,
+      "grad_norm": 2.767667055130005,
+      "learning_rate": 3.351900393184797e-05,
+      "loss": 2.4124,
+      "step": 1023
+    },
+    {
+      "epoch": 0.03708786375312291,
+      "grad_norm": 2.6588900089263916,
+      "learning_rate": 3.453473132372215e-05,
+      "loss": 2.3551,
+      "step": 1054
+    },
+    {
+      "epoch": 0.03817868327527359,
+      "grad_norm": 2.7497403621673584,
+      "learning_rate": 3.555045871559633e-05,
+      "loss": 2.3576,
+      "step": 1085
+    },
+    {
+      "epoch": 0.039269502797424256,
+      "grad_norm": 2.5148332118988037,
+      "learning_rate": 3.6566186107470514e-05,
+      "loss": 2.3078,
+      "step": 1116
+    },
+    {
+      "epoch": 0.04036032231957493,
+      "grad_norm": 3.0025594234466553,
+      "learning_rate": 3.7581913499344695e-05,
+      "loss": 2.303,
+      "step": 1147
+    },
+    {
+      "epoch": 0.0414511418417256,
+      "grad_norm": 2.6871118545532227,
+      "learning_rate": 3.8597640891218876e-05,
+      "loss": 2.3062,
+      "step": 1178
+    },
+    {
+      "epoch": 0.04254196136387628,
+      "grad_norm": 10.630929946899414,
+      "learning_rate": 3.9613368283093056e-05,
+      "loss": 2.307,
+      "step": 1209
+    },
+    {
+      "epoch": 0.043632780886026956,
+      "grad_norm": 2.571220874786377,
+      "learning_rate": 4.062909567496724e-05,
+      "loss": 2.2837,
+      "step": 1240
+    },
+    {
+      "epoch": 0.044723600408177626,
+      "grad_norm": 3.5510289669036865,
+      "learning_rate": 4.164482306684142e-05,
+      "loss": 2.2797,
+      "step": 1271
+    },
+    {
+      "epoch": 0.0458144199303283,
+      "grad_norm": 2.794853925704956,
+      "learning_rate": 4.26605504587156e-05,
+      "loss": 2.2797,
+      "step": 1302
+    },
+    {
+      "epoch": 0.04690523945247897,
+      "grad_norm": 6.132640838623047,
+      "learning_rate": 4.367627785058978e-05,
+      "loss": 2.2504,
+      "step": 1333
+    },
+    {
+      "epoch": 0.04799605897462965,
+      "grad_norm": 6.17495584487915,
+      "learning_rate": 4.469200524246396e-05,
+      "loss": 2.2414,
+      "step": 1364
+    },
+    {
+      "epoch": 0.049086878496780326,
+      "grad_norm": 2.3518564701080322,
+      "learning_rate": 4.570773263433814e-05,
+      "loss": 2.2198,
+      "step": 1395
+    },
+    {
+      "epoch": 0.050177698018930995,
+      "grad_norm": 2.2073466777801514,
+      "learning_rate": 4.672346002621232e-05,
+      "loss": 2.2057,
+      "step": 1426
+    },
+    {
+      "epoch": 0.05126851754108167,
+      "grad_norm": 2.018749237060547,
+      "learning_rate": 4.77391874180865e-05,
+      "loss": 2.1965,
+      "step": 1457
+    },
+    {
+      "epoch": 0.05235933706323234,
+      "grad_norm": 2.7125244140625,
+      "learning_rate": 4.875491480996068e-05,
+      "loss": 2.19,
+      "step": 1488
+    },
+    {
+      "epoch": 0.05345015658538302,
+      "grad_norm": 1.9725641012191772,
+      "learning_rate": 4.977064220183487e-05,
+      "loss": 2.1669,
+      "step": 1519
+    },
+    {
+      "epoch": 0.054540976107533695,
+      "grad_norm": 2.0198206901550293,
+      "learning_rate": 4.9999915451558777e-05,
+      "loss": 2.1486,
+      "step": 1550
+    },
+    {
+      "epoch": 0.055631795629684365,
+      "grad_norm": 2.068424940109253,
+      "learning_rate": 4.999955597496219e-05,
+      "loss": 2.1476,
+      "step": 1581
+    },
+    {
+      "epoch": 0.05672261515183504,
+      "grad_norm": 1.8509161472320557,
+      "learning_rate": 4.9998914381774255e-05,
+      "loss": 2.1129,
+      "step": 1612
+    },
+    {
+      "epoch": 0.05781343467398571,
+      "grad_norm": 1.805915355682373,
+      "learning_rate": 4.999799067923527e-05,
+      "loss": 2.1014,
+      "step": 1643
+    },
+    {
+      "epoch": 0.05890425419613639,
+      "grad_norm": 1.9447969198226929,
+      "learning_rate": 4.999678487776908e-05,
+      "loss": 2.1067,
+      "step": 1674
+    },
+    {
+      "epoch": 0.059995073718287065,
+      "grad_norm": 2.131700277328491,
+      "learning_rate": 4.9995296990983006e-05,
+      "loss": 2.0817,
+      "step": 1705
+    },
+    {
+      "epoch": 0.061085893240437734,
+      "grad_norm": 1.9113484621047974,
+      "learning_rate": 4.999352703566763e-05,
+      "loss": 2.067,
+      "step": 1736
+    },
+    {
+      "epoch": 0.06217671276258841,
+      "grad_norm": 1.8802495002746582,
+      "learning_rate": 4.999147503179668e-05,
+      "loss": 2.0617,
+      "step": 1767
+    },
+    {
+      "epoch": 0.06326753228473908,
+      "grad_norm": 1.6704238653182983,
+      "learning_rate": 4.998914100252672e-05,
+      "loss": 2.0671,
+      "step": 1798
+    },
+    {
+      "epoch": 0.06435835180688976,
+      "grad_norm": 4.303380966186523,
+      "learning_rate": 4.998652497419696e-05,
+      "loss": 2.0436,
+      "step": 1829
+    },
+    {
+      "epoch": 0.06544917132904043,
+      "grad_norm": 1.8054529428482056,
+      "learning_rate": 4.9983626976328927e-05,
+      "loss": 2.0499,
+      "step": 1860
+    },
+    {
+      "epoch": 0.06653999085119111,
+      "grad_norm": 1.663872241973877,
+      "learning_rate": 4.998044704162613e-05,
+      "loss": 2.0227,
+      "step": 1891
+    },
+    {
+      "epoch": 0.06763081037334177,
+      "grad_norm": 10.130581855773926,
+      "learning_rate": 4.9976985205973705e-05,
+      "loss": 2.0022,
+      "step": 1922
+    },
+    {
+      "epoch": 0.06872162989549245,
+      "grad_norm": 3.7727627754211426,
+      "learning_rate": 4.997324150843799e-05,
+      "loss": 2.0172,
+      "step": 1953
+    },
+    {
+      "epoch": 0.06981244941764313,
+      "grad_norm": 1.8669508695602417,
+      "learning_rate": 4.99692159912661e-05,
+      "loss": 2.0214,
+      "step": 1984
+    },
+    {
+      "epoch": 0.0709032689397938,
+      "grad_norm": 17.45224952697754,
+      "learning_rate": 4.996490869988546e-05,
+      "loss": 1.9959,
+      "step": 2015
+    },
+    {
+      "epoch": 0.07199408846194448,
+      "grad_norm": 1.7007793188095093,
+      "learning_rate": 4.996031968290326e-05,
+      "loss": 2.0139,
+      "step": 2046
+    },
+    {
+      "epoch": 0.07308490798409514,
+      "grad_norm": 1.6912076473236084,
+      "learning_rate": 4.995544899210594e-05,
+      "loss": 1.9963,
+      "step": 2077
+    },
+    {
+      "epoch": 0.07417572750624582,
+      "grad_norm": 1.6827666759490967,
+      "learning_rate": 4.9950296682458583e-05,
+      "loss": 1.973,
+      "step": 2108
+    },
+    {
+      "epoch": 0.0752665470283965,
+      "grad_norm": 1.767269253730774,
+      "learning_rate": 4.994486281210429e-05,
+      "loss": 1.9949,
+      "step": 2139
+    },
+    {
+      "epoch": 0.07635736655054717,
+      "grad_norm": 7.507472038269043,
+      "learning_rate": 4.9939147442363566e-05,
+      "loss": 1.9837,
+      "step": 2170
+    },
+    {
+      "epoch": 0.07744818607269784,
+      "grad_norm": 1.6840234994888306,
+      "learning_rate": 4.9933150637733574e-05,
+      "loss": 1.9789,
+      "step": 2201
+    },
+    {
+      "epoch": 0.07853900559484851,
+      "grad_norm": 1.6442159414291382,
+      "learning_rate": 4.992687246588743e-05,
+      "loss": 1.9436,
+      "step": 2232
+    },
+    {
+      "epoch": 0.07962982511699919,
+      "grad_norm": 1.546859622001648,
+      "learning_rate": 4.992031299767347e-05,
+      "loss": 1.9341,
+      "step": 2263
+    },
+    {
+      "epoch": 0.08072064463914987,
+      "grad_norm": 1.4932371377944946,
+      "learning_rate": 4.9913472307114386e-05,
+      "loss": 1.9583,
+      "step": 2294
+    },
+    {
+      "epoch": 0.08181146416130054,
+      "grad_norm": 1.4531840085983276,
+      "learning_rate": 4.9906350471406446e-05,
+      "loss": 1.9414,
+      "step": 2325
+    },
+    {
+      "epoch": 0.0829022836834512,
+      "grad_norm": 1.5285487174987793,
+      "learning_rate": 4.989894757091861e-05,
+      "loss": 1.9502,
+      "step": 2356
+    },
+    {
+      "epoch": 0.08399310320560188,
+      "grad_norm": 1.4159945249557495,
+      "learning_rate": 4.989126368919158e-05,
+      "loss": 1.9299,
+      "step": 2387
+    },
+    {
+      "epoch": 0.08508392272775256,
+      "grad_norm": 1.4361426830291748,
+      "learning_rate": 4.988329891293693e-05,
+      "loss": 1.9266,
+      "step": 2418
+    },
+    {
+      "epoch": 0.08617474224990324,
+      "grad_norm": 1.4310742616653442,
+      "learning_rate": 4.987505333203608e-05,
+      "loss": 1.9116,
+      "step": 2449
+    },
+    {
+      "epoch": 0.08726556177205391,
+      "grad_norm": 1.3780311346054077,
+      "learning_rate": 4.9866527039539276e-05,
+      "loss": 1.9189,
+      "step": 2480
+    },
+    {
+      "epoch": 0.08835638129420458,
+      "grad_norm": 1.3917787075042725,
+      "learning_rate": 4.9857720131664594e-05,
+      "loss": 1.9107,
+      "step": 2511
+    },
+    {
+      "epoch": 0.08944720081635525,
+      "grad_norm": 1.3963998556137085,
+      "learning_rate": 4.9848632707796773e-05,
+      "loss": 1.899,
+      "step": 2542
+    },
+    {
+      "epoch": 0.09053802033850593,
+      "grad_norm": 1.3573299646377563,
+      "learning_rate": 4.9839264870486155e-05,
+      "loss": 1.9084,
+      "step": 2573
+    },
+    {
+      "epoch": 0.0916288398606566,
+      "grad_norm": 1.362552523612976,
+      "learning_rate": 4.9829616725447526e-05,
+      "loss": 1.8954,
+      "step": 2604
+    },
+    {
+      "epoch": 0.09271965938280728,
+      "grad_norm": 1.3538340330123901,
+      "learning_rate": 4.981968838155888e-05,
+      "loss": 1.9035,
+      "step": 2635
+    },
+    {
+      "epoch": 0.09381047890495794,
+      "grad_norm": 1.407291054725647,
+      "learning_rate": 4.980947995086024e-05,
+      "loss": 1.8778,
+      "step": 2666
+    },
+    {
+      "epoch": 0.09490129842710862,
+      "grad_norm": 1.3554202318191528,
+      "learning_rate": 4.979899154855234e-05,
+      "loss": 1.8783,
+      "step": 2697
+    },
+    {
+      "epoch": 0.0959921179492593,
+      "grad_norm": 1.3513182401657104,
+      "learning_rate": 4.9788223292995386e-05,
+      "loss": 1.8857,
+      "step": 2728
+    },
+    {
+      "epoch": 0.09708293747140997,
+      "grad_norm": 1.345706582069397,
+      "learning_rate": 4.977717530570768e-05,
+      "loss": 1.8882,
+      "step": 2759
+    },
+    {
+      "epoch": 0.09817375699356065,
+      "grad_norm": 1.3450254201889038,
+      "learning_rate": 4.976584771136425e-05,
+      "loss": 1.8746,
+      "step": 2790
+    },
+    {
+      "epoch": 0.09926457651571131,
+      "grad_norm": 1.7820961475372314,
+      "learning_rate": 4.975424063779547e-05,
+      "loss": 1.8557,
+      "step": 2821
+    },
+    {
+      "epoch": 0.10035539603786199,
+      "grad_norm": 1.3493785858154297,
+      "learning_rate": 4.974235421598557e-05,
+      "loss": 1.8683,
+      "step": 2852
+    },
+    {
+      "epoch": 0.10144621556001267,
+      "grad_norm": 1.3066306114196777,
+      "learning_rate": 4.973018858007122e-05,
+      "loss": 1.8777,
+      "step": 2883
+    },
+    {
+      "epoch": 0.10253703508216334,
+      "grad_norm": 1.2991000413894653,
+      "learning_rate": 4.9717743867339963e-05,
+      "loss": 1.8605,
+      "step": 2914
+    },
+    {
+      "epoch": 0.10362785460431402,
+      "grad_norm": 1.3748496770858765,
+      "learning_rate": 4.9705020218228695e-05,
+      "loss": 1.8683,
+      "step": 2945
+    },
+    {
+      "epoch": 0.10471867412646468,
+      "grad_norm": 1.3229252099990845,
+      "learning_rate": 4.969201777632205e-05,
+      "loss": 1.858,
+      "step": 2976
+    },
+    {
+      "epoch": 0.10580949364861536,
+      "grad_norm": 1.2874318361282349,
+      "learning_rate": 4.9678736688350846e-05,
+      "loss": 1.8435,
+      "step": 3007
+    },
+    {
+      "epoch": 0.10690031317076604,
+      "grad_norm": 1.3341971635818481,
+      "learning_rate": 4.966517710419033e-05,
+      "loss": 1.8663,
+      "step": 3038
+    },
+    {
+      "epoch": 0.10799113269291671,
+      "grad_norm": 1.276282548904419,
+      "learning_rate": 4.965133917685858e-05,
+      "loss": 1.854,
+      "step": 3069
+    },
+    {
+      "epoch": 0.10908195221506739,
+      "grad_norm": 1.2999404668807983,
+      "learning_rate": 4.9637223062514714e-05,
+      "loss": 1.8498,
+      "step": 3100
+    },
+    {
+      "epoch": 0.11017277173721805,
+      "grad_norm": 1.2905164957046509,
+      "learning_rate": 4.962282892045718e-05,
+      "loss": 1.8436,
+      "step": 3131
+    },
+    {
+      "epoch": 0.11126359125936873,
+      "grad_norm": 1.9952430725097656,
+      "learning_rate": 4.9608156913121904e-05,
+      "loss": 1.8316,
+      "step": 3162
+    },
+    {
+      "epoch": 0.1123544107815194,
+      "grad_norm": 1.2637739181518555,
+      "learning_rate": 4.959320720608049e-05,
+      "loss": 1.8391,
+      "step": 3193
+    },
+    {
+      "epoch": 0.11344523030367008,
+      "grad_norm": 1.3711034059524536,
+      "learning_rate": 4.9577979968038354e-05,
+      "loss": 1.814,
+      "step": 3224
+    },
+    {
+      "epoch": 0.11453604982582076,
+      "grad_norm": 1.3050326108932495,
+      "learning_rate": 4.956247537083282e-05,
+      "loss": 1.8635,
+      "step": 3255
+    },
+    {
+      "epoch": 0.11562686934797142,
+      "grad_norm": 1.230220079421997,
+      "learning_rate": 4.9546693589431145e-05,
+      "loss": 1.8203,
+      "step": 3286
+    },
+    {
+      "epoch": 0.1167176888701221,
+      "grad_norm": 1.2535375356674194,
+      "learning_rate": 4.9530634801928595e-05,
+      "loss": 1.8319,
+      "step": 3317
+    },
+    {
+      "epoch": 0.11780850839227278,
+      "grad_norm": 1.227552890777588,
+      "learning_rate": 4.9514299189546395e-05,
+      "loss": 1.8157,
+      "step": 3348
+    },
+    {
+      "epoch": 0.11889932791442345,
+      "grad_norm": 1.2049622535705566,
+      "learning_rate": 4.949768693662973e-05,
+      "loss": 1.8135,
+      "step": 3379
+    },
+    {
+      "epoch": 0.11999014743657413,
+      "grad_norm": 1.1608529090881348,
+      "learning_rate": 4.948079823064559e-05,
+      "loss": 1.8191,
+      "step": 3410
+    },
+    {
+      "epoch": 0.12108096695872479,
+      "grad_norm": 1.2294845581054688,
+      "learning_rate": 4.946363326218074e-05,
+      "loss": 1.7977,
+      "step": 3441
+    },
+    {
+      "epoch": 0.12217178648087547,
+      "grad_norm": 1.1883920431137085,
+      "learning_rate": 4.9446192224939525e-05,
+      "loss": 1.8153,
+      "step": 3472
+    },
+    {
+      "epoch": 0.12326260600302615,
+      "grad_norm": 1.2770321369171143,
+      "learning_rate": 4.942847531574167e-05,
+      "loss": 1.8064,
+      "step": 3503
+    },
+    {
+      "epoch": 0.12435342552517682,
+      "grad_norm": 1.5442144870758057,
+      "learning_rate": 4.941048273452008e-05,
+      "loss": 1.8134,
+      "step": 3534
+    },
+    {
+      "epoch": 0.12544424504732749,
+      "grad_norm": 1.1753895282745361,
+      "learning_rate": 4.9392214684318605e-05,
+      "loss": 1.7909,
+      "step": 3565
+    },
+    {
+      "epoch": 0.12653506456947816,
+      "grad_norm": 1.2292894124984741,
+      "learning_rate": 4.93736713712897e-05,
+      "loss": 1.7894,
+      "step": 3596
+    },
+    {
+      "epoch": 0.12762588409162884,
+      "grad_norm": 1.1696261167526245,
+      "learning_rate": 4.9354853004692124e-05,
+      "loss": 1.7913,
+      "step": 3627
+    },
+    {
+      "epoch": 0.12871670361377952,
+      "grad_norm": 1.1935744285583496,
+      "learning_rate": 4.93357597968886e-05,
+      "loss": 1.8103,
+      "step": 3658
+    },
+    {
+      "epoch": 0.1298075231359302,
+      "grad_norm": 1.1842865943908691,
+      "learning_rate": 4.931639196334338e-05,
+      "loss": 1.7778,
+      "step": 3689
+    },
+    {
+      "epoch": 0.13089834265808087,
+      "grad_norm": 1.187715768814087,
+      "learning_rate": 4.9296749722619826e-05,
+      "loss": 1.7955,
+      "step": 3720
+    },
+    {
+      "epoch": 0.13198916218023155,
+      "grad_norm": 1.1973644495010376,
+      "learning_rate": 4.9276833296377966e-05,
+      "loss": 1.7786,
+      "step": 3751
+    },
+    {
+      "epoch": 0.13307998170238222,
+      "grad_norm": 1.129618525505066,
+      "learning_rate": 4.925664290937196e-05,
+      "loss": 1.7819,
+      "step": 3782
+    },
+    {
+      "epoch": 0.13417080122453287,
+      "grad_norm": 1.1466953754425049,
+      "learning_rate": 4.9236178789447576e-05,
+      "loss": 1.7732,
+      "step": 3813
+    },
+    {
+      "epoch": 0.13526162074668355,
+      "grad_norm": 1.1432143449783325,
+      "learning_rate": 4.921544116753962e-05,
+      "loss": 1.7872,
+      "step": 3844
+    },
+    {
+      "epoch": 0.13635244026883422,
+      "grad_norm": 1.1669626235961914,
+      "learning_rate": 4.919443027766935e-05,
+      "loss": 1.7708,
+      "step": 3875
+    },
+    {
+      "epoch": 0.1374432597909849,
+      "grad_norm": 1.1273548603057861,
+      "learning_rate": 4.91731463569418e-05,
+      "loss": 1.7767,
+      "step": 3906
+    },
+    {
+      "epoch": 0.13853407931313558,
+      "grad_norm": 1.146063208580017,
+      "learning_rate": 4.915158964554312e-05,
+      "loss": 1.7695,
+      "step": 3937
+    },
+    {
+      "epoch": 0.13962489883528625,
+      "grad_norm": 1.1724731922149658,
+      "learning_rate": 4.912976038673786e-05,
+      "loss": 1.7709,
+      "step": 3968
+    },
+    {
+      "epoch": 0.14071571835743693,
+      "grad_norm": 1.122382402420044,
+      "learning_rate": 4.9107658826866254e-05,
+      "loss": 1.7871,
+      "step": 3999
+    },
+    {
+      "epoch": 0.1418065378795876,
+      "grad_norm": 1.2005928754806519,
+      "learning_rate": 4.908528521534139e-05,
+      "loss": 1.7896,
+      "step": 4030
+    },
+    {
+      "epoch": 0.14289735740173828,
+      "grad_norm": 1.1000254154205322,
+      "learning_rate": 4.906263980464644e-05,
+      "loss": 1.7645,
+      "step": 4061
+    },
+    {
+      "epoch": 0.14398817692388896,
+      "grad_norm": 1.1797596216201782,
+      "learning_rate": 4.903972285033178e-05,
+      "loss": 1.7702,
+      "step": 4092
+    },
+    {
+      "epoch": 0.1450789964460396,
+      "grad_norm": 1.145271897315979,
+      "learning_rate": 4.901653461101213e-05,
+      "loss": 1.7541,
+      "step": 4123
+    },
+    {
+      "epoch": 0.1461698159681903,
+      "grad_norm": 1.1336746215820312,
+      "learning_rate": 4.8993075348363626e-05,
+      "loss": 1.7604,
+      "step": 4154
+    },
+    {
+      "epoch": 0.14726063549034096,
+      "grad_norm": 1.1435718536376953,
+      "learning_rate": 4.896934532712084e-05,
+      "loss": 1.7461,
+      "step": 4185
+    },
+    {
+      "epoch": 0.14835145501249164,
+      "grad_norm": 1.1105029582977295,
+      "learning_rate": 4.8945344815073846e-05,
+      "loss": 1.7691,
+      "step": 4216
+    },
+    {
+      "epoch": 0.14944227453464232,
+      "grad_norm": 1.1397055387496948,
+      "learning_rate": 4.892107408306516e-05,
+      "loss": 1.7599,
+      "step": 4247
+    },
+    {
+      "epoch": 0.150533094056793,
+      "grad_norm": 1.1158910989761353,
+      "learning_rate": 4.889653340498669e-05,
+      "loss": 1.7537,
+      "step": 4278
+    },
+    {
+      "epoch": 0.15162391357894367,
+      "grad_norm": 1.1238468885421753,
+      "learning_rate": 4.8871723057776664e-05,
+      "loss": 1.7672,
+      "step": 4309
+    },
+    {
+      "epoch": 0.15271473310109435,
+      "grad_norm": 1.1303473711013794,
+      "learning_rate": 4.8846643321416476e-05,
+      "loss": 1.7542,
+      "step": 4340
+    },
+    {
+      "epoch": 0.15380555262324502,
+      "grad_norm": 1.117262840270996,
+      "learning_rate": 4.882129447892753e-05,
+      "loss": 1.7378,
+      "step": 4371
+    },
+    {
+      "epoch": 0.15489637214539567,
+      "grad_norm": 1.1086496114730835,
+      "learning_rate": 4.8795676816368076e-05,
+      "loss": 1.7439,
+      "step": 4402
+    },
+    {
+      "epoch": 0.15598719166754635,
+      "grad_norm": 1.276014804840088,
+      "learning_rate": 4.876979062282995e-05,
+      "loss": 1.7699,
+      "step": 4433
+    },
+    {
+      "epoch": 0.15707801118969703,
+      "grad_norm": 1.1294457912445068,
+      "learning_rate": 4.8743636190435325e-05,
+      "loss": 1.7292,
+      "step": 4464
+    },
+    {
+      "epoch": 0.1581688307118477,
+      "grad_norm": 1.1111900806427002,
+      "learning_rate": 4.871721381433344e-05,
+      "loss": 1.7487,
+      "step": 4495
+    },
+    {
+      "epoch": 0.15925965023399838,
+      "grad_norm": 1.0868422985076904,
+      "learning_rate": 4.869052379269719e-05,
+      "loss": 1.7397,
+      "step": 4526
+    },
+    {
+      "epoch": 0.16035046975614906,
+      "grad_norm": 1.0772205591201782,
+      "learning_rate": 4.866356642671985e-05,
+      "loss": 1.7377,
+      "step": 4557
+    },
+    {
+      "epoch": 0.16144128927829973,
+      "grad_norm": 1.0649960041046143,
+      "learning_rate": 4.8636342020611634e-05,
+      "loss": 1.7253,
+      "step": 4588
+    },
+    {
+      "epoch": 0.1625321088004504,
+      "grad_norm": 1.0653575658798218,
+      "learning_rate": 4.860885088159626e-05,
+      "loss": 1.7319,
+      "step": 4619
+    },
+    {
+      "epoch": 0.16362292832260109,
+      "grad_norm": 1.0669118165969849,
+      "learning_rate": 4.858109331990751e-05,
+      "loss": 1.7425,
+      "step": 4650
+    },
+    {
+      "epoch": 0.16471374784475176,
+      "grad_norm": 1.0559724569320679,
+      "learning_rate": 4.855306964878567e-05,
+      "loss": 1.7364,
+      "step": 4681
+    },
+    {
+      "epoch": 0.1658045673669024,
+      "grad_norm": 1.038191318511963,
+      "learning_rate": 4.8524780184474084e-05,
+      "loss": 1.7299,
+      "step": 4712
+    },
+    {
+      "epoch": 0.1668953868890531,
+      "grad_norm": 1.0602952241897583,
+      "learning_rate": 4.8496225246215496e-05,
+      "loss": 1.7256,
+      "step": 4743
+    },
+    {
+      "epoch": 0.16798620641120376,
+      "grad_norm": 1.0466082096099854,
+      "learning_rate": 4.8467405156248505e-05,
+      "loss": 1.7148,
+      "step": 4774
+    },
+    {
+      "epoch": 0.16907702593335444,
+      "grad_norm": 1.051708698272705,
+      "learning_rate": 4.843832023980392e-05,
+      "loss": 1.722,
+      "step": 4805
+    },
+    {
+      "epoch": 0.17016784545550512,
+      "grad_norm": 1.065427541732788,
+      "learning_rate": 4.840897082510106e-05,
+      "loss": 1.7088,
+      "step": 4836
+    },
+    {
+      "epoch": 0.1712586649776558,
+      "grad_norm": 1.0983659029006958,
+      "learning_rate": 4.8379357243344084e-05,
+      "loss": 1.7422,
+      "step": 4867
+    },
+    {
+      "epoch": 0.17234948449980647,
+      "grad_norm": 1.0919371843338013,
+      "learning_rate": 4.8349479828718236e-05,
+      "loss": 1.7253,
+      "step": 4898
+    },
+    {
+      "epoch": 0.17344030402195715,
+      "grad_norm": 1.0881919860839844,
+      "learning_rate": 4.8319338918386075e-05,
+      "loss": 1.7185,
+      "step": 4929
+    },
+    {
+      "epoch": 0.17453112354410782,
+      "grad_norm": 1.0374606847763062,
+      "learning_rate": 4.828893485248369e-05,
+      "loss": 1.7255,
+      "step": 4960
+    },
+    {
+      "epoch": 0.1756219430662585,
+      "grad_norm": 1.0947892665863037,
+      "learning_rate": 4.825826797411682e-05,
+      "loss": 1.7095,
+      "step": 4991
+    },
+    {
+      "epoch": 0.17671276258840915,
+      "grad_norm": 1.1086746454238892,
+      "learning_rate": 4.822733862935702e-05,
+      "loss": 1.7233,
+      "step": 5022
+    },
+    {
+      "epoch": 0.17780358211055983,
+      "grad_norm": 1.0662850141525269,
+      "learning_rate": 4.819614716723775e-05,
+      "loss": 1.7426,
+      "step": 5053
+    },
+    {
+      "epoch": 0.1788944016327105,
+      "grad_norm": 1.0137659311294556,
+      "learning_rate": 4.8164693939750425e-05,
+      "loss": 1.7358,
+      "step": 5084
+    },
+    {
+      "epoch": 0.17998522115486118,
+      "grad_norm": 1.049338698387146,
+      "learning_rate": 4.813297930184042e-05,
+      "loss": 1.6981,
+      "step": 5115
+    },
+    {
+      "epoch": 0.18107604067701186,
+      "grad_norm": 1.08591628074646,
+      "learning_rate": 4.810100361140314e-05,
+      "loss": 1.7178,
+      "step": 5146
+    },
+    {
+      "epoch": 0.18216686019916253,
+      "grad_norm": 1.0983690023422241,
+      "learning_rate": 4.8068767229279885e-05,
+      "loss": 1.7179,
+      "step": 5177
+    },
+    {
+      "epoch": 0.1832576797213132,
+      "grad_norm": 1.0783159732818604,
+      "learning_rate": 4.8036270519253854e-05,
+      "loss": 1.7198,
+      "step": 5208
+    },
+    {
+      "epoch": 0.1843484992434639,
+      "grad_norm": 1.0519956350326538,
+      "learning_rate": 4.8003513848046e-05,
+      "loss": 1.7154,
+      "step": 5239
+    },
+    {
+      "epoch": 0.18543931876561456,
+      "grad_norm": 1.0484226942062378,
+      "learning_rate": 4.79704975853109e-05,
+      "loss": 1.7081,
+      "step": 5270
+    },
+    {
+      "epoch": 0.18653013828776524,
+      "grad_norm": 1.0263608694076538,
+      "learning_rate": 4.793722210363262e-05,
+      "loss": 1.6961,
+      "step": 5301
+    },
+    {
+      "epoch": 0.1876209578099159,
+      "grad_norm": 0.9863409399986267,
+      "learning_rate": 4.7903687778520414e-05,
+      "loss": 1.7198,
+      "step": 5332
+    },
+    {
+      "epoch": 0.18871177733206657,
+      "grad_norm": 1.0293922424316406,
+      "learning_rate": 4.7869894988404593e-05,
+      "loss": 1.6958,
+      "step": 5363
+    },
+    {
+      "epoch": 0.18980259685421724,
+      "grad_norm": 0.9902015924453735,
+      "learning_rate": 4.783584411463221e-05,
+      "loss": 1.7162,
+      "step": 5394
+    },
+    {
+      "epoch": 0.19089341637636792,
+      "grad_norm": 1.0472259521484375,
+      "learning_rate": 4.780153554146274e-05,
+      "loss": 1.7189,
+      "step": 5425
+    },
+    {
+      "epoch": 0.1919842358985186,
+      "grad_norm": 1.0958000421524048,
+      "learning_rate": 4.7766969656063766e-05,
+      "loss": 1.7288,
+      "step": 5456
+    },
+    {
+      "epoch": 0.19307505542066927,
+      "grad_norm": 1.0132781267166138,
+      "learning_rate": 4.773214684850662e-05,
+      "loss": 1.6915,
+      "step": 5487
+    },
+    {
+      "epoch": 0.19416587494281995,
+      "grad_norm": 1.0274685621261597,
+      "learning_rate": 4.769706751176193e-05,
+      "loss": 1.7063,
+      "step": 5518
+    },
+    {
+      "epoch": 0.19525669446497063,
+      "grad_norm": 1.0145214796066284,
+      "learning_rate": 4.7661732041695264e-05,
+      "loss": 1.7072,
+      "step": 5549
+    },
+    {
+      "epoch": 0.1963475139871213,
+      "grad_norm": 1.053489327430725,
+      "learning_rate": 4.762614083706258e-05,
+      "loss": 1.6897,
+      "step": 5580
+    },
+    {
+      "epoch": 0.19743833350927198,
+      "grad_norm": 1.0426928997039795,
+      "learning_rate": 4.759029429950581e-05,
+      "loss": 1.6868,
+      "step": 5611
+    },
+    {
+      "epoch": 0.19852915303142263,
+      "grad_norm": 1.0594595670700073,
+      "learning_rate": 4.7554192833548235e-05,
+      "loss": 1.6978,
+      "step": 5642
+    },
+    {
+      "epoch": 0.1996199725535733,
+      "grad_norm": 1.0251655578613281,
+      "learning_rate": 4.751783684659e-05,
+      "loss": 1.6834,
+      "step": 5673
+    },
+    {
+      "epoch": 0.20071079207572398,
+      "grad_norm": 1.0762938261032104,
+      "learning_rate": 4.748122674890348e-05,
+      "loss": 1.6825,
+      "step": 5704
+    },
+    {
+      "epoch": 0.20180161159787466,
+      "grad_norm": 1.0672742128372192,
+      "learning_rate": 4.7444362953628654e-05,
+      "loss": 1.6811,
+      "step": 5735
+    },
+    {
+      "epoch": 0.20289243112002533,
+      "grad_norm": 1.0267951488494873,
+      "learning_rate": 4.7407245876768424e-05,
+      "loss": 1.7024,
+      "step": 5766
+    },
+    {
+      "epoch": 0.203983250642176,
+      "grad_norm": 1.0520440340042114,
+      "learning_rate": 4.736987593718397e-05,
+      "loss": 1.7008,
+      "step": 5797
+    },
+    {
+      "epoch": 0.2050740701643267,
+      "grad_norm": 1.0106167793273926,
+      "learning_rate": 4.733225355658999e-05,
+      "loss": 1.6721,
+      "step": 5828
+    },
+    {
+      "epoch": 0.20616488968647737,
+      "grad_norm": 0.9883444905281067,
+      "learning_rate": 4.7294379159549926e-05,
+      "loss": 1.6884,
+      "step": 5859
+    },
+    {
+      "epoch": 0.20725570920862804,
+      "grad_norm": 0.9873078465461731,
+      "learning_rate": 4.725625317347119e-05,
+      "loss": 1.7011,
+      "step": 5890
+    },
+    {
+      "epoch": 0.2083465287307787,
+      "grad_norm": 0.9925514459609985,
+      "learning_rate": 4.7217876028600374e-05,
+      "loss": 1.6965,
+      "step": 5921
+    },
+    {
+      "epoch": 0.20943734825292937,
+      "grad_norm": 1.0054575204849243,
+      "learning_rate": 4.717924815801832e-05,
+      "loss": 1.6923,
+      "step": 5952
+    },
+    {
+      "epoch": 0.21052816777508004,
+      "grad_norm": 1.0051021575927734,
+      "learning_rate": 4.714036999763532e-05,
+      "loss": 1.6864,
+      "step": 5983
+    },
+    {
+      "epoch": 0.21161898729723072,
+      "grad_norm": 1.0312145948410034,
+      "learning_rate": 4.7101241986186116e-05,
+      "loss": 1.6776,
+      "step": 6014
+    },
+    {
+      "epoch": 0.2127098068193814,
+      "grad_norm": 0.9964466094970703,
+      "learning_rate": 4.7061864565225e-05,
+      "loss": 1.6811,
+      "step": 6045
+    },
+    {
+      "epoch": 0.21380062634153207,
+      "grad_norm": 0.9997463226318359,
+      "learning_rate": 4.702223817912081e-05,
+      "loss": 1.6805,
+      "step": 6076
+    },
+    {
+      "epoch": 0.21489144586368275,
+      "grad_norm": 0.9945687055587769,
+      "learning_rate": 4.698236327505195e-05,
+      "loss": 1.6746,
+      "step": 6107
+    },
+    {
+      "epoch": 0.21598226538583343,
+      "grad_norm": 1.0496478080749512,
+      "learning_rate": 4.694224030300127e-05,
+      "loss": 1.6791,
+      "step": 6138
+    },
+    {
+      "epoch": 0.2170730849079841,
+      "grad_norm": 1.0148327350616455,
+      "learning_rate": 4.690186971575107e-05,
+      "loss": 1.6848,
+      "step": 6169
+    },
+    {
+      "epoch": 0.21816390443013478,
+      "grad_norm": 0.9963369965553284,
+      "learning_rate": 4.6861251968877916e-05,
+      "loss": 1.7055,
+      "step": 6200
+    },
+    {
+      "epoch": 0.21925472395228543,
+      "grad_norm": 0.9630306959152222,
+      "learning_rate": 4.68203875207476e-05,
+      "loss": 1.6716,
+      "step": 6231
+    },
+    {
+      "epoch": 0.2203455434744361,
+      "grad_norm": 0.9671465158462524,
+      "learning_rate": 4.677927683250983e-05,
+      "loss": 1.6754,
+      "step": 6262
+    },
+    {
+      "epoch": 0.22143636299658678,
+      "grad_norm": 0.9531513452529907,
+      "learning_rate": 4.6737920368093156e-05,
+      "loss": 1.6792,
+      "step": 6293
+    },
+    {
+      "epoch": 0.22252718251873746,
+      "grad_norm": 0.9835436344146729,
+      "learning_rate": 4.669631859419965e-05,
+      "loss": 1.6651,
+      "step": 6324
+    },
+    {
+      "epoch": 0.22361800204088814,
+      "grad_norm": 0.9870143532752991,
+      "learning_rate": 4.6654471980299676e-05,
+      "loss": 1.6903,
+      "step": 6355
+    },
+    {
+      "epoch": 0.2247088215630388,
+      "grad_norm": 1.0126017332077026,
+      "learning_rate": 4.661238099862658e-05,
+      "loss": 1.6883,
+      "step": 6386
+    },
+    {
+      "epoch": 0.2257996410851895,
+      "grad_norm": 1.0292701721191406,
+      "learning_rate": 4.657004612417138e-05,
+      "loss": 1.6841,
+      "step": 6417
+    },
+    {
+      "epoch": 0.22689046060734017,
+      "grad_norm": 0.9697965979576111,
+      "learning_rate": 4.6527467834677374e-05,
+      "loss": 1.684,
+      "step": 6448
+    },
+    {
+      "epoch": 0.22798128012949084,
+      "grad_norm": 0.9756552577018738,
+      "learning_rate": 4.648464661063478e-05,
+      "loss": 1.6756,
+      "step": 6479
+    },
+    {
+      "epoch": 0.22907209965164152,
+      "grad_norm": 1.1156080961227417,
+      "learning_rate": 4.6441582935275264e-05,
+      "loss": 1.6707,
+      "step": 6510
+    },
+    {
+      "epoch": 0.23016291917379217,
+      "grad_norm": 0.975688636302948,
+      "learning_rate": 4.6398277294566586e-05,
+      "loss": 1.6738,
+      "step": 6541
+    },
+    {
+      "epoch": 0.23125373869594285,
+      "grad_norm": 0.9863653779029846,
+      "learning_rate": 4.6354730177207e-05,
+      "loss": 1.6748,
+      "step": 6572
+    },
+    {
+      "epoch": 0.23234455821809352,
+      "grad_norm": 0.9869725108146667,
+      "learning_rate": 4.6310942074619787e-05,
+      "loss": 1.6715,
+      "step": 6603
+    },
+    {
+      "epoch": 0.2334353777402442,
+      "grad_norm": 0.9991948008537292,
+      "learning_rate": 4.626691348094777e-05,
+      "loss": 1.6692,
+      "step": 6634
+    },
+    {
+      "epoch": 0.23452619726239488,
+      "grad_norm": 0.9353803992271423,
+      "learning_rate": 4.622264489304762e-05,
+      "loss": 1.6571,
+      "step": 6665
+    },
+    {
+      "epoch": 0.23561701678454555,
+      "grad_norm": 0.9929242134094238,
+      "learning_rate": 4.617813681048434e-05,
+      "loss": 1.6614,
+      "step": 6696
+    },
+    {
+      "epoch": 0.23670783630669623,
+      "grad_norm": 1.003203272819519,
+      "learning_rate": 4.61333897355256e-05,
+      "loss": 1.6577,
+      "step": 6727
+    },
+    {
+      "epoch": 0.2377986558288469,
+      "grad_norm": 0.9584728479385376,
+      "learning_rate": 4.608840417313604e-05,
+      "loss": 1.6862,
+      "step": 6758
+    },
+    {
+      "epoch": 0.23888947535099758,
+      "grad_norm": 0.9825113415718079,
+      "learning_rate": 4.6043180630971646e-05,
+      "loss": 1.6651,
+      "step": 6789
+    },
+    {
+      "epoch": 0.23998029487314826,
+      "grad_norm": 0.9904153347015381,
+      "learning_rate": 4.599771961937391e-05,
+      "loss": 1.6665,
+      "step": 6820
+    },
+    {
+      "epoch": 0.2410711143952989,
+      "grad_norm": 0.9444073438644409,
+      "learning_rate": 4.5952021651364204e-05,
+      "loss": 1.6591,
+      "step": 6851
+    },
+    {
+      "epoch": 0.24216193391744958,
+      "grad_norm": 0.9723752737045288,
+      "learning_rate": 4.590608724263786e-05,
+      "loss": 1.6711,
+      "step": 6882
+    },
+    {
+      "epoch": 0.24325275343960026,
+      "grad_norm": 1.0078589916229248,
+      "learning_rate": 4.585991691155845e-05,
+      "loss": 1.6764,
+      "step": 6913
+    },
+    {
+      "epoch": 0.24434357296175094,
+      "grad_norm": 0.9442929625511169,
+      "learning_rate": 4.581351117915188e-05,
+      "loss": 1.6484,
+      "step": 6944
+    },
+    {
+      "epoch": 0.24543439248390161,
+      "grad_norm": 0.9573075771331787,
+      "learning_rate": 4.5766870569100534e-05,
+      "loss": 1.6638,
+      "step": 6975
+    },
+    {
+      "epoch": 0.2465252120060523,
+      "grad_norm": 0.9371550679206848,
+      "learning_rate": 4.571999560773736e-05,
+      "loss": 1.6565,
+      "step": 7006
+    },
+    {
+      "epoch": 0.24761603152820297,
+      "grad_norm": 0.9628654718399048,
+      "learning_rate": 4.5672886824039915e-05,
+      "loss": 1.653,
+      "step": 7037
+    },
+    {
+      "epoch": 0.24870685105035364,
+      "grad_norm": 1.265812635421753,
+      "learning_rate": 4.5625544749624435e-05,
+      "loss": 1.6661,
+      "step": 7068
+    },
+    {
+      "epoch": 0.24979767057250432,
+      "grad_norm": 0.9990148544311523,
+      "learning_rate": 4.5577969918739794e-05,
+      "loss": 1.6536,
+      "step": 7099
+    },
+    {
+      "epoch": 0.25088849009465497,
+      "grad_norm": 0.9349009394645691,
+      "learning_rate": 4.5530162868261486e-05,
+      "loss": 1.6578,
+      "step": 7130
+    },
+    {
+      "epoch": 0.25197930961680565,
+      "grad_norm": 0.9215208292007446,
+      "learning_rate": 4.548212413768558e-05,
+      "loss": 1.6454,
+      "step": 7161
+    },
+    {
+      "epoch": 0.2530701291389563,
+      "grad_norm": 0.9580157995223999,
+      "learning_rate": 4.543385426912261e-05,
+      "loss": 1.6643,
+      "step": 7192
+    },
+    {
+      "epoch": 0.254160948661107,
+      "grad_norm": 0.9289986491203308,
+      "learning_rate": 4.53853538072915e-05,
+      "loss": 1.6659,
+      "step": 7223
+    },
+    {
+      "epoch": 0.2552517681832577,
+      "grad_norm": 0.9344154000282288,
+      "learning_rate": 4.533662329951336e-05,
+      "loss": 1.6772,
+      "step": 7254
+    },
+    {
+      "epoch": 0.25634258770540835,
+      "grad_norm": 0.9400781393051147,
+      "learning_rate": 4.528766329570536e-05,
+      "loss": 1.6493,
+      "step": 7285
+    },
+    {
+      "epoch": 0.25743340722755903,
+      "grad_norm": 0.963218092918396,
+      "learning_rate": 4.523847434837447e-05,
+      "loss": 1.6394,
+      "step": 7316
+    },
+    {
+      "epoch": 0.2585242267497097,
+      "grad_norm": 0.9619491696357727,
+      "learning_rate": 4.518905701261128e-05,
+      "loss": 1.6574,
+      "step": 7347
+    },
+    {
+      "epoch": 0.2596150462718604,
+      "grad_norm": 0.9310999512672424,
+      "learning_rate": 4.5139411846083715e-05,
+      "loss": 1.673,
+      "step": 7378
+    },
+    {
+      "epoch": 0.26070586579401106,
+      "grad_norm": 1.1424349546432495,
+      "learning_rate": 4.508953940903073e-05,
+      "loss": 1.6626,
+      "step": 7409
+    },
+    {
+      "epoch": 0.26179668531616174,
+      "grad_norm": 0.9687772393226624,
+      "learning_rate": 4.5039440264255994e-05,
+      "loss": 1.6548,
+      "step": 7440
+    },
+    {
+      "epoch": 0.2628875048383124,
+      "grad_norm": 0.9415249824523926,
+      "learning_rate": 4.498911497712155e-05,
+      "loss": 1.6452,
+      "step": 7471
+    },
+    {
+      "epoch": 0.2639783243604631,
+      "grad_norm": 0.9598653316497803,
+      "learning_rate": 4.493856411554142e-05,
+      "loss": 1.6527,
+      "step": 7502
+    },
+    {
+      "epoch": 0.26506914388261377,
+      "grad_norm": 0.9518615007400513,
+      "learning_rate": 4.4887788249975206e-05,
+      "loss": 1.6445,
+      "step": 7533
+    },
+    {
+      "epoch": 0.26615996340476444,
+      "grad_norm": 0.9153622388839722,
+      "learning_rate": 4.4836787953421656e-05,
+      "loss": 1.6255,
+      "step": 7564
+    },
+    {
+      "epoch": 0.26725078292691506,
+      "grad_norm": 0.9497701525688171,
+      "learning_rate": 4.478556380141218e-05,
+      "loss": 1.6499,
+      "step": 7595
+    },
+    {
+      "epoch": 0.26834160244906574,
+      "grad_norm": 0.9468094706535339,
+      "learning_rate": 4.4734116372004375e-05,
+      "loss": 1.6269,
+      "step": 7626
+    },
+    {
+      "epoch": 0.2694324219712164,
+      "grad_norm": 0.9106606245040894,
+      "learning_rate": 4.4682446245775477e-05,
+      "loss": 1.6396,
+      "step": 7657
+    },
+    {
+      "epoch": 0.2705232414933671,
+      "grad_norm": 0.946415901184082,
+      "learning_rate": 4.463055400581586e-05,
+      "loss": 1.6443,
+      "step": 7688
+    },
+    {
+      "epoch": 0.27161406101551777,
+      "grad_norm": 0.9249156713485718,
+      "learning_rate": 4.4578440237722374e-05,
+      "loss": 1.649,
+      "step": 7719
+    },
+    {
+      "epoch": 0.27270488053766845,
+      "grad_norm": 0.9326067566871643,
+      "learning_rate": 4.452610552959183e-05,
+      "loss": 1.6399,
+      "step": 7750
+    },
+    {
+      "epoch": 0.2737957000598191,
+      "grad_norm": 0.9351608157157898,
+      "learning_rate": 4.447355047201428e-05,
+      "loss": 1.6286,
+      "step": 7781
+    },
+    {
+      "epoch": 0.2748865195819698,
+      "grad_norm": 0.9721508622169495,
+      "learning_rate": 4.4420775658066414e-05,
+      "loss": 1.6503,
+      "step": 7812
+    },
+    {
+      "epoch": 0.2759773391041205,
+      "grad_norm": 0.9394717812538147,
+      "learning_rate": 4.436778168330484e-05,
+      "loss": 1.6514,
+      "step": 7843
+    },
+    {
+      "epoch": 0.27706815862627115,
+      "grad_norm": 0.9202150702476501,
+      "learning_rate": 4.4314569145759353e-05,
+      "loss": 1.6252,
+      "step": 7874
+    },
+    {
+      "epoch": 0.27815897814842183,
+      "grad_norm": 0.9670141339302063,
+      "learning_rate": 4.42611386459262e-05,
+      "loss": 1.6349,
+      "step": 7905
+    },
+    {
+      "epoch": 0.2792497976705725,
+      "grad_norm": 0.9340211749076843,
+      "learning_rate": 4.420749078676133e-05,
+      "loss": 1.642,
+      "step": 7936
+    },
+    {
+      "epoch": 0.2803406171927232,
+      "grad_norm": 0.9478600025177002,
+      "learning_rate": 4.4153626173673516e-05,
+      "loss": 1.6552,
+      "step": 7967
+    },
+    {
+      "epoch": 0.28143143671487386,
+      "grad_norm": 0.9464743733406067,
+      "learning_rate": 4.409954541451762e-05,
+      "loss": 1.6378,
+      "step": 7998
+    },
+    {
+      "epoch": 0.28252225623702454,
+      "grad_norm": 0.9389581084251404,
+      "learning_rate": 4.404524911958764e-05,
+      "loss": 1.6325,
+      "step": 8029
+    },
+    {
+      "epoch": 0.2836130757591752,
+      "grad_norm": 0.9357293248176575,
+      "learning_rate": 4.399073790160989e-05,
+      "loss": 1.6422,
+      "step": 8060
+    },
+    {
+      "epoch": 0.2847038952813259,
+      "grad_norm": 0.9474714398384094,
+      "learning_rate": 4.393601237573607e-05,
+      "loss": 1.6595,
+      "step": 8091
+    },
+    {
+      "epoch": 0.28579471480347657,
+      "grad_norm": 0.9302358031272888,
+      "learning_rate": 4.388107315953628e-05,
+      "loss": 1.6439,
+      "step": 8122
+    },
+    {
+      "epoch": 0.28688553432562724,
+      "grad_norm": 0.948805570602417,
+      "learning_rate": 4.382592087299212e-05,
+      "loss": 1.6459,
+      "step": 8153
+    },
+    {
+      "epoch": 0.2879763538477779,
+      "grad_norm": 0.9055014252662659,
+      "learning_rate": 4.377055613848964e-05,
+      "loss": 1.6427,
+      "step": 8184
+    },
+    {
+      "epoch": 0.28906717336992854,
+      "grad_norm": 0.9128564596176147,
+      "learning_rate": 4.3714979580812355e-05,
+      "loss": 1.6254,
+      "step": 8215
+    },
+    {
+      "epoch": 0.2901579928920792,
+      "grad_norm": 0.8954737782478333,
+      "learning_rate": 4.365919182713416e-05,
+      "loss": 1.6265,
+      "step": 8246
+    },
+    {
+      "epoch": 0.2912488124142299,
+      "grad_norm": 0.9502245783805847,
+      "learning_rate": 4.360319350701226e-05,
+      "loss": 1.6366,
+      "step": 8277
+    },
+    {
+      "epoch": 0.2923396319363806,
+      "grad_norm": 0.907567024230957,
+      "learning_rate": 4.3546985252380115e-05,
+      "loss": 1.6222,
+      "step": 8308
+    },
+    {
+      "epoch": 0.29343045145853125,
+      "grad_norm": 0.9578949809074402,
+      "learning_rate": 4.349056769754021e-05,
+      "loss": 1.6411,
+      "step": 8339
+    },
+    {
+      "epoch": 0.2945212709806819,
+      "grad_norm": 0.9497959613800049,
+      "learning_rate": 4.3433941479156994e-05,
+      "loss": 1.632,
+      "step": 8370
+    },
+    {
+      "epoch": 0.2956120905028326,
+      "grad_norm": 1.1019785404205322,
+      "learning_rate": 4.3377107236249647e-05,
+      "loss": 1.6495,
+      "step": 8401
+    },
+    {
+      "epoch": 0.2967029100249833,
+      "grad_norm": 0.9178378582000732,
+      "learning_rate": 4.332006561018488e-05,
+      "loss": 1.6298,
+      "step": 8432
+    },
+    {
+      "epoch": 0.29779372954713396,
+      "grad_norm": 0.9462074041366577,
+      "learning_rate": 4.3262817244669683e-05,
+      "loss": 1.6327,
+      "step": 8463
+    },
+    {
+      "epoch": 0.29888454906928463,
+      "grad_norm": 0.9369425177574158,
+      "learning_rate": 4.3205362785744083e-05,
+      "loss": 1.6372,
+      "step": 8494
+    },
+    {
+      "epoch": 0.2999753685914353,
+      "grad_norm": 0.918860912322998,
+      "learning_rate": 4.314770288177384e-05,
+      "loss": 1.6205,
+      "step": 8525
+    },
+    {
+      "epoch": 0.301066188113586,
+      "grad_norm": 0.9392362236976624,
+      "learning_rate": 4.308983818344313e-05,
+      "loss": 1.6184,
+      "step": 8556
+    },
+    {
+      "epoch": 0.30215700763573666,
+      "grad_norm": 0.9137156009674072,
+      "learning_rate": 4.3031769343747206e-05,
+      "loss": 1.6253,
+      "step": 8587
+    },
+    {
+      "epoch": 0.30324782715788734,
+      "grad_norm": 0.9086781144142151,
+      "learning_rate": 4.297349701798505e-05,
+      "loss": 1.6264,
+      "step": 8618
+    },
+    {
+      "epoch": 0.304338646680038,
+      "grad_norm": 0.9457340240478516,
+      "learning_rate": 4.2915021863751916e-05,
+      "loss": 1.6098,
+      "step": 8649
+    },
+    {
+      "epoch": 0.3054294662021887,
+      "grad_norm": 0.9216846823692322,
+      "learning_rate": 4.285634454093198e-05,
+      "loss": 1.6325,
+      "step": 8680
+    },
+    {
+      "epoch": 0.30652028572433937,
+      "grad_norm": 0.9189222455024719,
+      "learning_rate": 4.279746571169086e-05,
+      "loss": 1.6164,
+      "step": 8711
+    },
+    {
+      "epoch": 0.30761110524649005,
+      "grad_norm": 0.9216083288192749,
+      "learning_rate": 4.2738386040468136e-05,
+      "loss": 1.6084,
+      "step": 8742
+    },
+    {
+      "epoch": 0.3087019247686407,
+      "grad_norm": 0.9195507764816284,
+      "learning_rate": 4.2679106193969866e-05,
+      "loss": 1.6249,
+      "step": 8773
+    },
+    {
+      "epoch": 0.30979274429079134,
+      "grad_norm": 0.9332253932952881,
+      "learning_rate": 4.261962684116106e-05,
+      "loss": 1.633,
+      "step": 8804
+    },
+    {
+      "epoch": 0.310883563812942,
+      "grad_norm": 0.9223430752754211,
+      "learning_rate": 4.2559948653258145e-05,
+      "loss": 1.6117,
+      "step": 8835
+    },
+    {
+      "epoch": 0.3119743833350927,
+      "grad_norm": 0.8972631692886353,
+      "learning_rate": 4.250007230372134e-05,
+      "loss": 1.5931,
+      "step": 8866
+    },
+    {
+      "epoch": 0.3130652028572434,
+      "grad_norm": 0.8789275288581848,
+      "learning_rate": 4.2439998468247126e-05,
+      "loss": 1.6384,
+      "step": 8897
+    },
+    {
+      "epoch": 0.31415602237939405,
+      "grad_norm": 0.8869777321815491,
+      "learning_rate": 4.2379727824760566e-05,
+      "loss": 1.6043,
+      "step": 8928
+    },
+    {
+      "epoch": 0.3152468419015447,
+      "grad_norm": 0.9047911167144775,
+      "learning_rate": 4.231926105340768e-05,
+      "loss": 1.6301,
+      "step": 8959
+    },
+    {
+      "epoch": 0.3163376614236954,
+      "grad_norm": 0.8834474086761475,
+      "learning_rate": 4.225859883654776e-05,
+      "loss": 1.624,
+      "step": 8990
+    },
+    {
+      "epoch": 0.3174284809458461,
+      "grad_norm": 0.9142968058586121,
+      "learning_rate": 4.219774185874569e-05,
+      "loss": 1.6232,
+      "step": 9021
+    },
+    {
+      "epoch": 0.31851930046799676,
+      "grad_norm": 0.9930256009101868,
+      "learning_rate": 4.213669080676418e-05,
+      "loss": 1.6091,
+      "step": 9052
+    },
+    {
+      "epoch": 0.31961011999014743,
+      "grad_norm": 0.9061794877052307,
+      "learning_rate": 4.2075446369556056e-05,
+      "loss": 1.6468,
+      "step": 9083
+    },
+    {
+      "epoch": 0.3207009395122981,
+      "grad_norm": 0.8935773372650146,
+      "learning_rate": 4.201400923825648e-05,
+      "loss": 1.598,
+      "step": 9114
+    },
+    {
+      "epoch": 0.3217917590344488,
+      "grad_norm": 0.9085298180580139,
+      "learning_rate": 4.195238010617511e-05,
+      "loss": 1.6136,
+      "step": 9145
+    },
+    {
+      "epoch": 0.32288257855659946,
+      "grad_norm": 0.9264605045318604,
+      "learning_rate": 4.1890559668788344e-05,
+      "loss": 1.6174,
+      "step": 9176
+    },
+    {
+      "epoch": 0.32397339807875014,
+      "grad_norm": 0.9291498064994812,
+      "learning_rate": 4.1828548623731405e-05,
+      "loss": 1.6179,
+      "step": 9207
+    },
+    {
+      "epoch": 0.3250642176009008,
+      "grad_norm": 0.8831276893615723,
+      "learning_rate": 4.1766347670790506e-05,
+      "loss": 1.6119,
+      "step": 9238
+    },
+    {
+      "epoch": 0.3261550371230515,
+      "grad_norm": 0.9102134108543396,
+      "learning_rate": 4.170395751189495e-05,
+      "loss": 1.6266,
+      "step": 9269
+    },
+    {
+      "epoch": 0.32724585664520217,
+      "grad_norm": 0.8952730298042297,
+      "learning_rate": 4.164137885110921e-05,
+      "loss": 1.622,
+      "step": 9300
+    },
+    {
+      "epoch": 0.32833667616735285,
+      "grad_norm": 0.9174513220787048,
+      "learning_rate": 4.157861239462495e-05,
+      "loss": 1.6163,
+      "step": 9331
+    },
+    {
+      "epoch": 0.3294274956895035,
+      "grad_norm": 0.880759060382843,
+      "learning_rate": 4.1515658850753114e-05,
+      "loss": 1.5997,
+      "step": 9362
+    },
+    {
+      "epoch": 0.3305183152116542,
+      "grad_norm": 0.8925946950912476,
+      "learning_rate": 4.145251892991588e-05,
+      "loss": 1.5974,
+      "step": 9393
+    },
+    {
+      "epoch": 0.3316091347338048,
+      "grad_norm": 0.9017757773399353,
+      "learning_rate": 4.138919334463868e-05,
+      "loss": 1.6019,
+      "step": 9424
+    },
+    {
+      "epoch": 0.3326999542559555,
+      "grad_norm": 0.9045889377593994,
+      "learning_rate": 4.1325682809542124e-05,
+      "loss": 1.6318,
+      "step": 9455
+    },
+    {
+      "epoch": 0.3337907737781062,
+      "grad_norm": 0.870001494884491,
+      "learning_rate": 4.126198804133398e-05,
+      "loss": 1.6092,
+      "step": 9486
+    },
+    {
+      "epoch": 0.33488159330025685,
+      "grad_norm": 0.8898991942405701,
+      "learning_rate": 4.1198109758801055e-05,
+      "loss": 1.6015,
+      "step": 9517
+    },
+    {
+      "epoch": 0.33597241282240753,
+      "grad_norm": 0.8767693638801575,
+      "learning_rate": 4.113404868280107e-05,
+      "loss": 1.5911,
+      "step": 9548
+    },
+    {
+      "epoch": 0.3370632323445582,
+      "grad_norm": 0.8673516511917114,
+      "learning_rate": 4.106980553625457e-05,
+      "loss": 1.6137,
+      "step": 9579
+    },
+    {
+      "epoch": 0.3381540518667089,
+      "grad_norm": 0.9067351818084717,
+      "learning_rate": 4.100538104413674e-05,
+      "loss": 1.5993,
+      "step": 9610
+    },
+    {
+      "epoch": 0.33924487138885956,
+      "grad_norm": 0.9343692660331726,
+      "learning_rate": 4.09407759334692e-05,
+      "loss": 1.6074,
+      "step": 9641
+    },
+    {
+      "epoch": 0.34033569091101024,
+      "grad_norm": 0.9002503752708435,
+      "learning_rate": 4.087599093331186e-05,
+      "loss": 1.6267,
+      "step": 9672
+    },
+    {
+      "epoch": 0.3414265104331609,
+      "grad_norm": 0.9147412776947021,
+      "learning_rate": 4.081102677475462e-05,
+      "loss": 1.6106,
+      "step": 9703
+    },
+    {
+      "epoch": 0.3425173299553116,
+      "grad_norm": 0.9228988885879517,
+      "learning_rate": 4.0745884190909194e-05,
+      "loss": 1.6258,
+      "step": 9734
+    },
+    {
+      "epoch": 0.34360814947746227,
+      "grad_norm": 0.8599364757537842,
+      "learning_rate": 4.0680563916900796e-05,
+      "loss": 1.6039,
+      "step": 9765
+    },
+    {
+      "epoch": 0.34469896899961294,
+      "grad_norm": 0.844178318977356,
+      "learning_rate": 4.0615066689859815e-05,
+      "loss": 1.5899,
+      "step": 9796
+    },
+    {
+      "epoch": 0.3457897885217636,
+      "grad_norm": 0.9241573810577393,
+      "learning_rate": 4.0549393248913584e-05,
+      "loss": 1.5916,
+      "step": 9827
+    },
+    {
+      "epoch": 0.3468806080439143,
+      "grad_norm": 0.9131301641464233,
+      "learning_rate": 4.048354433517794e-05,
+      "loss": 1.6045,
+      "step": 9858
+    },
+    {
+      "epoch": 0.347971427566065,
+      "grad_norm": 0.8763211965560913,
+      "learning_rate": 4.0417520691748916e-05,
+      "loss": 1.6088,
+      "step": 9889
+    },
+    {
+      "epoch": 0.34906224708821565,
+      "grad_norm": 0.9151899218559265,
+      "learning_rate": 4.035132306369438e-05,
+      "loss": 1.5976,
+      "step": 9920
+    },
+    {
+      "epoch": 0.3501530666103663,
+      "grad_norm": 0.8976767063140869,
+      "learning_rate": 4.028495219804555e-05,
+      "loss": 1.6129,
+      "step": 9951
+    },
+    {
+      "epoch": 0.351243886132517,
+      "grad_norm": 0.8878459930419922,
+      "learning_rate": 4.021840884378864e-05,
+      "loss": 1.5994,
+      "step": 9982
+    },
+    {
+      "epoch": 0.3523347056546677,
+      "grad_norm": 0.8572807312011719,
+      "learning_rate": 4.015169375185633e-05,
+      "loss": 1.6002,
+      "step": 10013
+    },
+    {
+      "epoch": 0.3534255251768183,
+      "grad_norm": 0.8996985554695129,
+      "learning_rate": 4.0084807675119396e-05,
+      "loss": 1.6136,
+      "step": 10044
+    },
+    {
+      "epoch": 0.354516344698969,
+      "grad_norm": 0.8947619795799255,
+      "learning_rate": 4.0017751368378106e-05,
+      "loss": 1.598,
+      "step": 10075
+    },
+    {
+      "epoch": 0.35560716422111965,
+      "grad_norm": 0.9073825478553772,
+      "learning_rate": 3.995052558835377e-05,
+      "loss": 1.6164,
+      "step": 10106
+    },
+    {
+      "epoch": 0.35669798374327033,
+      "grad_norm": 0.8670364022254944,
+      "learning_rate": 3.988313109368017e-05,
+      "loss": 1.6012,
+      "step": 10137
+    },
+    {
+      "epoch": 0.357788803265421,
+      "grad_norm": 0.8530169725418091,
+      "learning_rate": 3.981556864489504e-05,
+      "loss": 1.5947,
+      "step": 10168
+    },
+    {
+      "epoch": 0.3588796227875717,
+      "grad_norm": 0.8809841275215149,
+      "learning_rate": 3.974783900443142e-05,
+      "loss": 1.6033,
+      "step": 10199
+    },
+    {
+      "epoch": 0.35997044230972236,
+      "grad_norm": 0.8582516312599182,
+      "learning_rate": 3.9679942936609095e-05,
+      "loss": 1.6029,
+      "step": 10230
+    },
+    {
+      "epoch": 0.36106126183187304,
+      "grad_norm": 0.8762260675430298,
+      "learning_rate": 3.961188120762596e-05,
+      "loss": 1.5921,
+      "step": 10261
+    },
+    {
+      "epoch": 0.3621520813540237,
+      "grad_norm": 0.8775869011878967,
+      "learning_rate": 3.954365458554938e-05,
+      "loss": 1.6101,
+      "step": 10292
+    },
+    {
+      "epoch": 0.3632429008761744,
+      "grad_norm": 0.9066540002822876,
+      "learning_rate": 3.947526384030751e-05,
+      "loss": 1.5928,
+      "step": 10323
+    },
+    {
+      "epoch": 0.36433372039832507,
+      "grad_norm": 0.9105854630470276,
+      "learning_rate": 3.9406709743680624e-05,
+      "loss": 1.5973,
+      "step": 10354
+    },
+    {
+      "epoch": 0.36542453992047574,
+      "grad_norm": 0.8927069902420044,
+      "learning_rate": 3.9337993069292366e-05,
+      "loss": 1.6159,
+      "step": 10385
+    },
+    {
+      "epoch": 0.3665153594426264,
+      "grad_norm": 0.9006061553955078,
+      "learning_rate": 3.926911459260109e-05,
+      "loss": 1.6111,
+      "step": 10416
+    },
+    {
+      "epoch": 0.3676061789647771,
+      "grad_norm": 0.8990784883499146,
+      "learning_rate": 3.920007509089102e-05,
+      "loss": 1.5975,
+      "step": 10447
+    },
+    {
+      "epoch": 0.3686969984869278,
+      "grad_norm": 0.9229722619056702,
+      "learning_rate": 3.913087534326357e-05,
+      "loss": 1.5962,
+      "step": 10478
+    },
+    {
+      "epoch": 0.36978781800907845,
+      "grad_norm": 0.9110054969787598,
+      "learning_rate": 3.9061516130628475e-05,
+      "loss": 1.6129,
+      "step": 10509
+    },
+    {
+      "epoch": 0.3708786375312291,
+      "grad_norm": 0.917635440826416,
+      "learning_rate": 3.8991998235695025e-05,
+      "loss": 1.5975,
+      "step": 10540
+    },
+    {
+      "epoch": 0.3719694570533798,
+      "grad_norm": 0.8891541957855225,
+      "learning_rate": 3.8922322442963224e-05,
+      "loss": 1.5711,
+      "step": 10571
+    },
+    {
+      "epoch": 0.3730602765755305,
+      "grad_norm": 0.8646354675292969,
+      "learning_rate": 3.885248953871491e-05,
+      "loss": 1.6038,
+      "step": 10602
+    },
+    {
+      "epoch": 0.3741510960976811,
+      "grad_norm": 0.8377805948257446,
+      "learning_rate": 3.8782500311004915e-05,
+      "loss": 1.6113,
+      "step": 10633
+    },
+    {
+      "epoch": 0.3752419156198318,
+      "grad_norm": 0.8636441826820374,
+      "learning_rate": 3.871235554965218e-05,
+      "loss": 1.5802,
+      "step": 10664
+    },
+    {
+      "epoch": 0.37633273514198246,
+      "grad_norm": 0.8898093700408936,
+      "learning_rate": 3.864205604623078e-05,
+      "loss": 1.6054,
+      "step": 10695
+    },
+    {
+      "epoch": 0.37742355466413313,
+      "grad_norm": 0.887256383895874,
+      "learning_rate": 3.857160259406107e-05,
+      "loss": 1.5933,
+      "step": 10726
+    },
+    {
+      "epoch": 0.3785143741862838,
+      "grad_norm": 0.8577413558959961,
+      "learning_rate": 3.8500995988200674e-05,
+      "loss": 1.5875,
+      "step": 10757
+    },
+    {
+      "epoch": 0.3796051937084345,
+      "grad_norm": 0.8893071413040161,
+      "learning_rate": 3.843023702543556e-05,
+      "loss": 1.5857,
+      "step": 10788
+    },
+    {
+      "epoch": 0.38069601323058516,
+      "grad_norm": 0.847111165523529,
+      "learning_rate": 3.8359326504270984e-05,
+      "loss": 1.5837,
+      "step": 10819
+    },
+    {
+      "epoch": 0.38178683275273584,
+      "grad_norm": 0.8827951550483704,
+      "learning_rate": 3.828826522492255e-05,
+      "loss": 1.5748,
+      "step": 10850
+    },
+    {
+      "epoch": 0.3828776522748865,
+      "grad_norm": 0.8470546007156372,
+      "learning_rate": 3.821705398930713e-05,
+      "loss": 1.5995,
+      "step": 10881
+    },
+    {
+      "epoch": 0.3839684717970372,
+      "grad_norm": 0.987573504447937,
+      "learning_rate": 3.814569360103385e-05,
+      "loss": 1.5926,
+      "step": 10912
+    },
+    {
+      "epoch": 0.38505929131918787,
+      "grad_norm": 0.8766013383865356,
+      "learning_rate": 3.807418486539499e-05,
+      "loss": 1.581,
+      "step": 10943
+    },
+    {
+      "epoch": 0.38615011084133855,
+      "grad_norm": 0.9069483876228333,
+      "learning_rate": 3.80025285893569e-05,
+      "loss": 1.5912,
+      "step": 10974
+    },
+    {
+      "epoch": 0.3872409303634892,
+      "grad_norm": 0.9085988998413086,
+      "learning_rate": 3.793072558155093e-05,
+      "loss": 1.5871,
+      "step": 11005
+    },
+    {
+      "epoch": 0.3883317498856399,
+      "grad_norm": 0.9167149066925049,
+      "learning_rate": 3.785877665226426e-05,
+      "loss": 1.5902,
+      "step": 11036
+    },
+    {
+      "epoch": 0.3894225694077906,
+      "grad_norm": 0.8932046294212341,
+      "learning_rate": 3.778668261343079e-05,
+      "loss": 1.6048,
+      "step": 11067
+    },
+    {
+      "epoch": 0.39051338892994125,
+      "grad_norm": 0.8533083200454712,
+      "learning_rate": 3.771444427862192e-05,
+      "loss": 1.5803,
+      "step": 11098
+    },
+    {
+      "epoch": 0.39160420845209193,
+      "grad_norm": 0.8877330422401428,
+      "learning_rate": 3.7642062463037465e-05,
+      "loss": 1.5855,
+      "step": 11129
+    },
+    {
+      "epoch": 0.3926950279742426,
+      "grad_norm": 0.8700180649757385,
+      "learning_rate": 3.7569537983496373e-05,
+      "loss": 1.5843,
+      "step": 11160
+    },
+    {
+      "epoch": 0.3937858474963933,
+      "grad_norm": 0.8378989100456238,
+      "learning_rate": 3.749687165842753e-05,
+      "loss": 1.5664,
+      "step": 11191
+    },
+    {
+      "epoch": 0.39487666701854396,
+      "grad_norm": 0.8885537981987,
+      "learning_rate": 3.7424064307860536e-05,
+      "loss": 1.5822,
+      "step": 11222
+    },
+    {
+      "epoch": 0.3959674865406946,
+      "grad_norm": 0.8644111752510071,
+      "learning_rate": 3.735111675341645e-05,
+      "loss": 1.5893,
+      "step": 11253
+    },
+    {
+      "epoch": 0.39705830606284526,
+      "grad_norm": 0.8942341804504395,
+      "learning_rate": 3.7278029818298524e-05,
+      "loss": 1.5909,
+      "step": 11284
+    },
+    {
+      "epoch": 0.39814912558499593,
+      "grad_norm": 0.858748733997345,
+      "learning_rate": 3.720480432728287e-05,
+      "loss": 1.5832,
+      "step": 11315
+    },
+    {
+      "epoch": 0.3992399451071466,
+      "grad_norm": 0.8919023275375366,
+      "learning_rate": 3.71314411067092e-05,
+      "loss": 1.5804,
+      "step": 11346
+    },
+    {
+      "epoch": 0.4003307646292973,
+      "grad_norm": 0.8735581636428833,
+      "learning_rate": 3.70579409844715e-05,
+      "loss": 1.5856,
+      "step": 11377
+    },
+    {
+      "epoch": 0.40142158415144796,
+      "grad_norm": 0.843586266040802,
+      "learning_rate": 3.698430479000865e-05,
+      "loss": 1.5814,
+      "step": 11408
+    },
+    {
+      "epoch": 0.40251240367359864,
+      "grad_norm": 0.8684964776039124,
+      "learning_rate": 3.691053335429509e-05,
+      "loss": 1.5823,
+      "step": 11439
+    },
+    {
+      "epoch": 0.4036032231957493,
+      "grad_norm": 0.8695327639579773,
+      "learning_rate": 3.683662750983147e-05,
+      "loss": 1.5817,
+      "step": 11470
+    },
+    {
+      "epoch": 0.4046940427179,
+      "grad_norm": 0.9438059329986572,
+      "learning_rate": 3.676258809063518e-05,
+      "loss": 1.6003,
+      "step": 11501
+    },
+    {
+      "epoch": 0.40578486224005067,
+      "grad_norm": 0.8711549043655396,
+      "learning_rate": 3.6688415932231004e-05,
+      "loss": 1.5843,
+      "step": 11532
+    },
+    {
+      "epoch": 0.40687568176220135,
+      "grad_norm": 0.9110082387924194,
+      "learning_rate": 3.661411187164166e-05,
+      "loss": 1.5942,
+      "step": 11563
+    },
+    {
+      "epoch": 0.407966501284352,
+      "grad_norm": 0.8768247961997986,
+      "learning_rate": 3.65396767473784e-05,
+      "loss": 1.6002,
+      "step": 11594
+    },
+    {
+      "epoch": 0.4090573208065027,
+      "grad_norm": 0.8380584120750427,
+      "learning_rate": 3.6465111399431465e-05,
+      "loss": 1.5755,
+      "step": 11625
+    },
+    {
+      "epoch": 0.4101481403286534,
+      "grad_norm": 0.8617690801620483,
+      "learning_rate": 3.6390416669260674e-05,
+      "loss": 1.5817,
+      "step": 11656
+    },
+    {
+      "epoch": 0.41123895985080405,
+      "grad_norm": 0.8809701800346375,
+      "learning_rate": 3.63155933997859e-05,
+      "loss": 1.5779,
+      "step": 11687
+    },
+    {
+      "epoch": 0.41232977937295473,
+      "grad_norm": 0.8623855113983154,
+      "learning_rate": 3.624064243537758e-05,
+      "loss": 1.5749,
+      "step": 11718
+    },
+    {
+      "epoch": 0.4134205988951054,
+      "grad_norm": 0.9026786684989929,
+      "learning_rate": 3.616556462184716e-05,
+      "loss": 1.5676,
+      "step": 11749
+    },
+    {
+      "epoch": 0.4145114184172561,
+      "grad_norm": 0.8784968852996826,
+      "learning_rate": 3.609036080643755e-05,
+      "loss": 1.6103,
+      "step": 11780
+    },
+    {
+      "epoch": 0.41560223793940676,
+      "grad_norm": 0.8578303456306458,
+      "learning_rate": 3.60150318378136e-05,
+      "loss": 1.6004,
+      "step": 11811
+    },
+    {
+      "epoch": 0.4166930574615574,
+      "grad_norm": 0.8620411157608032,
+      "learning_rate": 3.5939578566052465e-05,
+      "loss": 1.5821,
+      "step": 11842
+    },
+    {
+      "epoch": 0.41778387698370806,
+      "grad_norm": 0.8622260093688965,
+      "learning_rate": 3.586400184263408e-05,
+      "loss": 1.5735,
+      "step": 11873
+    },
+    {
+      "epoch": 0.41887469650585873,
+      "grad_norm": 0.871585488319397,
+      "learning_rate": 3.578830252043148e-05,
+      "loss": 1.5705,
+      "step": 11904
+    },
+    {
+      "epoch": 0.4199655160280094,
+      "grad_norm": 0.8741966485977173,
+      "learning_rate": 3.571248145370125e-05,
+      "loss": 1.5898,
+      "step": 11935
+    },
+    {
+      "epoch": 0.4210563355501601,
+      "grad_norm": 0.8671961426734924,
+      "learning_rate": 3.5636539498073794e-05,
+      "loss": 1.5662,
+      "step": 11966
+    },
+    {
+      "epoch": 0.42214715507231076,
+      "grad_norm": 0.8873665928840637,
+      "learning_rate": 3.556047751054378e-05,
+      "loss": 1.5856,
+      "step": 11997
+    },
+    {
+      "epoch": 0.42323797459446144,
+      "grad_norm": 0.8614113926887512,
+      "learning_rate": 3.548429634946039e-05,
+      "loss": 1.5609,
+      "step": 12028
+    },
+    {
+      "epoch": 0.4243287941166121,
+      "grad_norm": 0.8387187719345093,
+      "learning_rate": 3.540799687451768e-05,
+      "loss": 1.5728,
+      "step": 12059
+    },
+    {
+      "epoch": 0.4254196136387628,
+      "grad_norm": 0.8875289559364319,
+      "learning_rate": 3.533157994674485e-05,
+      "loss": 1.5749,
+      "step": 12090
+    },
+    {
+      "epoch": 0.42651043316091347,
+      "grad_norm": 0.8648973107337952,
+      "learning_rate": 3.5255046428496546e-05,
+      "loss": 1.5695,
+      "step": 12121
+    },
+    {
+      "epoch": 0.42760125268306415,
+      "grad_norm": 0.8634358048439026,
+      "learning_rate": 3.517839718344311e-05,
+      "loss": 1.5685,
+      "step": 12152
+    },
+    {
+      "epoch": 0.4286920722052148,
+      "grad_norm": 0.8736028075218201,
+      "learning_rate": 3.510163307656086e-05,
+      "loss": 1.5721,
+      "step": 12183
+    },
+    {
+      "epoch": 0.4297828917273655,
+      "grad_norm": 0.8463747501373291,
+      "learning_rate": 3.5024754974122324e-05,
+      "loss": 1.5759,
+      "step": 12214
+    },
+    {
+      "epoch": 0.4308737112495162,
+      "grad_norm": 0.8596286177635193,
+      "learning_rate": 3.494776374368643e-05,
+      "loss": 1.5906,
+      "step": 12245
+    },
+    {
+      "epoch": 0.43196453077166685,
+      "grad_norm": 0.8681018948554993,
+      "learning_rate": 3.4870660254088724e-05,
+      "loss": 1.5579,
+      "step": 12276
+    },
+    {
+      "epoch": 0.43305535029381753,
+      "grad_norm": 0.9080244302749634,
+      "learning_rate": 3.479344537543164e-05,
+      "loss": 1.5618,
+      "step": 12307
+    },
+    {
+      "epoch": 0.4341461698159682,
+      "grad_norm": 0.8841635584831238,
+      "learning_rate": 3.4716119979074565e-05,
+      "loss": 1.5873,
+      "step": 12338
+    },
+    {
+      "epoch": 0.4352369893381189,
+      "grad_norm": 0.8563128709793091,
+      "learning_rate": 3.463868493762412e-05,
+      "loss": 1.5673,
+      "step": 12369
+    },
+    {
+      "epoch": 0.43632780886026956,
+      "grad_norm": 0.8570665121078491,
+      "learning_rate": 3.456114112492418e-05,
+      "loss": 1.5634,
+      "step": 12400
+    },
+    {
+      "epoch": 0.43741862838242024,
+      "grad_norm": 0.8617071509361267,
+      "learning_rate": 3.4483489416046164e-05,
+      "loss": 1.5555,
+      "step": 12431
+    },
+    {
+      "epoch": 0.43850944790457086,
+      "grad_norm": 0.8495959639549255,
+      "learning_rate": 3.440573068727905e-05,
+      "loss": 1.5792,
+      "step": 12462
+    },
+    {
+      "epoch": 0.43960026742672154,
+      "grad_norm": 0.8845837712287903,
+      "learning_rate": 3.4327865816119495e-05,
+      "loss": 1.5587,
+      "step": 12493
+    },
+    {
+      "epoch": 0.4406910869488722,
+      "grad_norm": 0.8790666460990906,
+      "learning_rate": 3.4249895681262025e-05,
+      "loss": 1.5765,
+      "step": 12524
+    },
+    {
+      "epoch": 0.4417819064710229,
+      "grad_norm": 0.8437421917915344,
+      "learning_rate": 3.417182116258899e-05,
+      "loss": 1.557,
+      "step": 12555
+    },
+    {
+      "epoch": 0.44287272599317357,
+      "grad_norm": 0.868320882320404,
+      "learning_rate": 3.409364314116074e-05,
+      "loss": 1.5656,
+      "step": 12586
+    },
+    {
+      "epoch": 0.44396354551532424,
+      "grad_norm": 0.8495018482208252,
+      "learning_rate": 3.401536249920559e-05,
+      "loss": 1.5709,
+      "step": 12617
+    },
+    {
+      "epoch": 0.4450543650374749,
+      "grad_norm": 0.865176796913147,
+      "learning_rate": 3.393698012010998e-05,
+      "loss": 1.5564,
+      "step": 12648
+    },
+    {
+      "epoch": 0.4461451845596256,
+      "grad_norm": 0.8581182956695557,
+      "learning_rate": 3.385849688840839e-05,
+      "loss": 1.5653,
+      "step": 12679
+    },
+    {
+      "epoch": 0.4472360040817763,
+      "grad_norm": 0.8474507331848145,
+      "learning_rate": 3.3779913689773414e-05,
+      "loss": 1.5645,
+      "step": 12710
+    },
+    {
+      "epoch": 0.44832682360392695,
+      "grad_norm": 0.8472003936767578,
+      "learning_rate": 3.370123141100578e-05,
+      "loss": 1.5511,
+      "step": 12741
+    },
+    {
+      "epoch": 0.4494176431260776,
+      "grad_norm": 0.852480947971344,
+      "learning_rate": 3.3622450940024305e-05,
+      "loss": 1.5502,
+      "step": 12772
+    },
+    {
+      "epoch": 0.4505084626482283,
+      "grad_norm": 0.8494676947593689,
+      "learning_rate": 3.35435731658559e-05,
+      "loss": 1.5574,
+      "step": 12803
+    },
+    {
+      "epoch": 0.451599282170379,
+      "grad_norm": 0.8634653091430664,
+      "learning_rate": 3.346459897862552e-05,
+      "loss": 1.5666,
+      "step": 12834
+    },
+    {
+      "epoch": 0.45269010169252966,
+      "grad_norm": 0.8515731692314148,
+      "learning_rate": 3.338552926954613e-05,
+      "loss": 1.5723,
+      "step": 12865
+    },
+    {
+      "epoch": 0.45378092121468033,
+      "grad_norm": 0.858883261680603,
+      "learning_rate": 3.330636493090868e-05,
+      "loss": 1.5869,
+      "step": 12896
+    },
+    {
+      "epoch": 0.454871740736831,
+      "grad_norm": 0.87376868724823,
+      "learning_rate": 3.322710685607193e-05,
+      "loss": 1.5599,
+      "step": 12927
+    },
+    {
+      "epoch": 0.4559625602589817,
+      "grad_norm": 0.8701228499412537,
+      "learning_rate": 3.314775593945251e-05,
+      "loss": 1.5644,
+      "step": 12958
+    },
+    {
+      "epoch": 0.45705337978113236,
+      "grad_norm": 0.8871962428092957,
+      "learning_rate": 3.3068313076514714e-05,
+      "loss": 1.5628,
+      "step": 12989
+    },
+    {
+      "epoch": 0.45814419930328304,
+      "grad_norm": 0.8973777294158936,
+      "learning_rate": 3.298877916376047e-05,
+      "loss": 1.5506,
+      "step": 13020
+    },
+    {
+      "epoch": 0.4592350188254337,
+      "grad_norm": 0.8526966571807861,
+      "learning_rate": 3.290915509871915e-05,
+      "loss": 1.5692,
+      "step": 13051
+    },
+    {
+      "epoch": 0.46032583834758434,
+      "grad_norm": 0.853767454624176,
+      "learning_rate": 3.282944177993753e-05,
+      "loss": 1.5603,
+      "step": 13082
+    },
+    {
+      "epoch": 0.461416657869735,
+      "grad_norm": 0.868984580039978,
+      "learning_rate": 3.274964010696957e-05,
+      "loss": 1.5692,
+      "step": 13113
+    },
+    {
+      "epoch": 0.4625074773918857,
+      "grad_norm": 0.8377254605293274,
+      "learning_rate": 3.266975098036629e-05,
+      "loss": 1.5627,
+      "step": 13144
+    },
+    {
+      "epoch": 0.46359829691403637,
+      "grad_norm": 0.8568862676620483,
+      "learning_rate": 3.258977530166562e-05,
+      "loss": 1.5593,
+      "step": 13175
+    },
+    {
+      "epoch": 0.46468911643618704,
+      "grad_norm": 0.8657397031784058,
+      "learning_rate": 3.250971397338227e-05,
+      "loss": 1.5449,
+      "step": 13206
+    },
+    {
+      "epoch": 0.4657799359583377,
+      "grad_norm": 0.8855077028274536,
+      "learning_rate": 3.2429567898997404e-05,
+      "loss": 1.57,
+      "step": 13237
+    },
+    {
+      "epoch": 0.4668707554804884,
+      "grad_norm": 0.8459128737449646,
+      "learning_rate": 3.234933798294859e-05,
+      "loss": 1.5474,
+      "step": 13268
+    },
+    {
+      "epoch": 0.4679615750026391,
+      "grad_norm": 0.8592433929443359,
+      "learning_rate": 3.2269025130619535e-05,
+      "loss": 1.5635,
+      "step": 13299
+    },
+    {
+      "epoch": 0.46905239452478975,
+      "grad_norm": 0.8622168898582458,
+      "learning_rate": 3.218863024832985e-05,
+      "loss": 1.5597,
+      "step": 13330
+    },
+    {
+      "epoch": 0.4701432140469404,
+      "grad_norm": 0.8521956205368042,
+      "learning_rate": 3.2108154243324864e-05,
+      "loss": 1.558,
+      "step": 13361
+    },
+    {
+      "epoch": 0.4712340335690911,
+      "grad_norm": 0.8465380072593689,
+      "learning_rate": 3.2027598023765345e-05,
+      "loss": 1.5481,
+      "step": 13392
+    },
+    {
+      "epoch": 0.4723248530912418,
+      "grad_norm": 0.8600775599479675,
+      "learning_rate": 3.194696249871729e-05,
+      "loss": 1.5646,
+      "step": 13423
+    },
+    {
+      "epoch": 0.47341567261339246,
+      "grad_norm": 0.8471152186393738,
+      "learning_rate": 3.186624857814164e-05,
+      "loss": 1.5603,
+      "step": 13454
+    },
+    {
+      "epoch": 0.47450649213554313,
+      "grad_norm": 0.8752865195274353,
+      "learning_rate": 3.178545717288401e-05,
+      "loss": 1.5475,
+      "step": 13485
+    },
+    {
+      "epoch": 0.4755973116576938,
+      "grad_norm": 0.883955717086792,
+      "learning_rate": 3.170458919466444e-05,
+      "loss": 1.5522,
+      "step": 13516
+    },
+    {
+      "epoch": 0.4766881311798445,
+      "grad_norm": 0.864668607711792,
+      "learning_rate": 3.1623645556067063e-05,
+      "loss": 1.5532,
+      "step": 13547
+    },
+    {
+      "epoch": 0.47777895070199516,
+      "grad_norm": 0.823254406452179,
+      "learning_rate": 3.154262717052985e-05,
+      "loss": 1.5464,
+      "step": 13578
+    },
+    {
+      "epoch": 0.47886977022414584,
+      "grad_norm": 0.8613137006759644,
+      "learning_rate": 3.146153495233426e-05,
+      "loss": 1.5492,
+      "step": 13609
+    },
+    {
+      "epoch": 0.4799605897462965,
+      "grad_norm": 0.8392694592475891,
+      "learning_rate": 3.1380369816594944e-05,
+      "loss": 1.5496,
+      "step": 13640
+    },
+    {
+      "epoch": 0.48105140926844714,
+      "grad_norm": 0.8625919222831726,
+      "learning_rate": 3.129913267924946e-05,
+      "loss": 1.5505,
+      "step": 13671
+    },
+    {
+      "epoch": 0.4821422287905978,
+      "grad_norm": 0.8749135732650757,
+      "learning_rate": 3.121782445704782e-05,
+      "loss": 1.5475,
+      "step": 13702
+    },
+    {
+      "epoch": 0.4832330483127485,
+      "grad_norm": 0.8929088115692139,
+      "learning_rate": 3.11364460675423e-05,
+      "loss": 1.5703,
+      "step": 13733
+    },
+    {
+      "epoch": 0.48432386783489917,
+      "grad_norm": 0.8600450158119202,
+      "learning_rate": 3.1054998429076934e-05,
+      "loss": 1.5423,
+      "step": 13764
+    },
+    {
+      "epoch": 0.48541468735704985,
+      "grad_norm": 0.8586206436157227,
+      "learning_rate": 3.097348246077728e-05,
+      "loss": 1.577,
+      "step": 13795
+    },
+    {
+      "epoch": 0.4865055068792005,
+      "grad_norm": 0.8514885306358337,
+      "learning_rate": 3.0891899082539924e-05,
+      "loss": 1.5704,
+      "step": 13826
+    },
+    {
+      "epoch": 0.4875963264013512,
+      "grad_norm": 0.8599662184715271,
+      "learning_rate": 3.0810249215022233e-05,
+      "loss": 1.547,
+      "step": 13857
+    },
+    {
+      "epoch": 0.4886871459235019,
+      "grad_norm": 0.842303454875946,
+      "learning_rate": 3.0728533779631865e-05,
+      "loss": 1.5256,
+      "step": 13888
+    },
+    {
+      "epoch": 0.48977796544565255,
+      "grad_norm": 0.884244978427887,
+      "learning_rate": 3.064675369851637e-05,
+      "loss": 1.558,
+      "step": 13919
+    },
+    {
+      "epoch": 0.49086878496780323,
+      "grad_norm": 0.8688809275627136,
+      "learning_rate": 3.056490989455289e-05,
+      "loss": 1.5322,
+      "step": 13950
+    },
+    {
+      "epoch": 0.4919596044899539,
+      "grad_norm": 0.8296154141426086,
+      "learning_rate": 3.0483003291337596e-05,
+      "loss": 1.5606,
+      "step": 13981
+    },
+    {
+      "epoch": 0.4930504240121046,
+      "grad_norm": 0.8469901084899902,
+      "learning_rate": 3.040103481317539e-05,
+      "loss": 1.5575,
+      "step": 14012
+    },
+    {
+      "epoch": 0.49414124353425526,
+      "grad_norm": 0.8387740254402161,
+      "learning_rate": 3.03190053850694e-05,
+      "loss": 1.5617,
+      "step": 14043
+    },
+    {
+      "epoch": 0.49523206305640594,
+      "grad_norm": 0.8529262542724609,
+      "learning_rate": 3.0236915932710573e-05,
+      "loss": 1.5594,
+      "step": 14074
+    },
+    {
+      "epoch": 0.4963228825785566,
+      "grad_norm": 0.904517650604248,
+      "learning_rate": 3.0154767382467232e-05,
+      "loss": 1.558,
+      "step": 14105
+    },
+    {
+      "epoch": 0.4974137021007073,
+      "grad_norm": 0.8514305949211121,
+      "learning_rate": 3.0072560661374582e-05,
+      "loss": 1.5582,
+      "step": 14136
+    },
+    {
+      "epoch": 0.49850452162285797,
+      "grad_norm": 0.8396731615066528,
+      "learning_rate": 2.999029669712431e-05,
+      "loss": 1.5374,
+      "step": 14167
+    },
+    {
+      "epoch": 0.49959534114500864,
+      "grad_norm": 0.8450112342834473,
+      "learning_rate": 2.990797641805408e-05,
+      "loss": 1.5659,
+      "step": 14198
+    },
+    {
+      "epoch": 0.5006861606671593,
+      "grad_norm": 0.8592528104782104,
+      "learning_rate": 2.982560075313704e-05,
+      "loss": 1.5605,
+      "step": 14229
+    },
+    {
+      "epoch": 0.5017769801893099,
+      "grad_norm": 0.8634563684463501,
+      "learning_rate": 2.9743170631971368e-05,
+      "loss": 1.5529,
+      "step": 14260
+    },
+    {
+      "epoch": 0.5028677997114607,
+      "grad_norm": 0.8532223105430603,
+      "learning_rate": 2.9660686984769792e-05,
+      "loss": 1.5534,
+      "step": 14291
+    },
+    {
+      "epoch": 0.5039586192336113,
+      "grad_norm": 0.8415837287902832,
+      "learning_rate": 2.9578150742349047e-05,
+      "loss": 1.5379,
+      "step": 14322
+    },
+    {
+      "epoch": 0.505049438755762,
+      "grad_norm": 0.8862072825431824,
+      "learning_rate": 2.949556283611942e-05,
+      "loss": 1.55,
+      "step": 14353
+    },
+    {
+      "epoch": 0.5061402582779126,
+      "grad_norm": 0.8563070297241211,
+      "learning_rate": 2.9412924198074206e-05,
+      "loss": 1.5492,
+      "step": 14384
+    },
+    {
+      "epoch": 0.5072310778000634,
+      "grad_norm": 0.8677307963371277,
+      "learning_rate": 2.9330235760779208e-05,
+      "loss": 1.557,
+      "step": 14415
+    },
+    {
+      "epoch": 0.508321897322214,
+      "grad_norm": 0.8541677594184875,
+      "learning_rate": 2.9247498457362188e-05,
+      "loss": 1.5328,
+      "step": 14446
+    },
+    {
+      "epoch": 0.5094127168443647,
+      "grad_norm": 0.8333261013031006,
+      "learning_rate": 2.9164713221502373e-05,
+      "loss": 1.551,
+      "step": 14477
+    },
+    {
+      "epoch": 0.5105035363665154,
+      "grad_norm": 0.8497917056083679,
+      "learning_rate": 2.9081880987419912e-05,
+      "loss": 1.5471,
+      "step": 14508
+    },
+    {
+      "epoch": 0.5115943558886661,
+      "grad_norm": 0.8271819353103638,
+      "learning_rate": 2.8999002689865296e-05,
+      "loss": 1.5568,
+      "step": 14539
+    },
+    {
+      "epoch": 0.5126851754108167,
+      "grad_norm": 0.8571930527687073,
+      "learning_rate": 2.8916079264108852e-05,
+      "loss": 1.5604,
+      "step": 14570
+    },
+    {
+      "epoch": 0.5137759949329673,
+      "grad_norm": 0.8891891241073608,
+      "learning_rate": 2.883311164593017e-05,
+      "loss": 1.5324,
+      "step": 14601
+    },
+    {
+      "epoch": 0.5148668144551181,
+      "grad_norm": 0.8179088234901428,
+      "learning_rate": 2.875010077160754e-05,
+      "loss": 1.55,
+      "step": 14632
+    },
+    {
+      "epoch": 0.5159576339772687,
+      "grad_norm": 0.8480364680290222,
+      "learning_rate": 2.866704757790741e-05,
+      "loss": 1.5279,
+      "step": 14663
+    },
+    {
+      "epoch": 0.5170484534994194,
+      "grad_norm": 0.8580318093299866,
+      "learning_rate": 2.858395300207376e-05,
+      "loss": 1.5502,
+      "step": 14694
+    },
+    {
+      "epoch": 0.51813927302157,
+      "grad_norm": 0.8466590046882629,
+      "learning_rate": 2.8500817981817607e-05,
+      "loss": 1.5418,
+      "step": 14725
+    },
+    {
+      "epoch": 0.5192300925437208,
+      "grad_norm": 0.8700029253959656,
+      "learning_rate": 2.8417643455306336e-05,
+      "loss": 1.5429,
+      "step": 14756
+    },
+    {
+      "epoch": 0.5203209120658714,
+      "grad_norm": 0.8434004187583923,
+      "learning_rate": 2.8334430361153185e-05,
+      "loss": 1.5313,
+      "step": 14787
+    },
+    {
+      "epoch": 0.5214117315880221,
+      "grad_norm": 0.8457748889923096,
+      "learning_rate": 2.8251179638406612e-05,
+      "loss": 1.5397,
+      "step": 14818
+    },
+    {
+      "epoch": 0.5225025511101727,
+      "grad_norm": 0.8471390008926392,
+      "learning_rate": 2.8167892226539704e-05,
+      "loss": 1.5458,
+      "step": 14849
+    },
+    {
+      "epoch": 0.5235933706323235,
+      "grad_norm": 0.8333294987678528,
+      "learning_rate": 2.8084569065439588e-05,
+      "loss": 1.5382,
+      "step": 14880
+    },
+    {
+      "epoch": 0.5246841901544741,
+      "grad_norm": 0.8390504717826843,
+      "learning_rate": 2.8001211095396807e-05,
+      "loss": 1.5209,
+      "step": 14911
+    },
+    {
+      "epoch": 0.5257750096766248,
+      "grad_norm": 0.8801223039627075,
+      "learning_rate": 2.791781925709473e-05,
+      "loss": 1.5539,
+      "step": 14942
+    },
+    {
+      "epoch": 0.5268658291987754,
+      "grad_norm": 0.8821811079978943,
+      "learning_rate": 2.7834394491598908e-05,
+      "loss": 1.5288,
+      "step": 14973
+    },
+    {
+      "epoch": 0.5279566487209262,
+      "grad_norm": 0.8448256254196167,
+      "learning_rate": 2.7750937740346485e-05,
+      "loss": 1.5434,
+      "step": 15004
+    },
+    {
+      "epoch": 0.5290474682430768,
+      "grad_norm": 0.8483582735061646,
+      "learning_rate": 2.7667449945135564e-05,
+      "loss": 1.5408,
+      "step": 15035
+    },
+    {
+      "epoch": 0.5301382877652275,
+      "grad_norm": 0.8402996063232422,
+      "learning_rate": 2.7583932048114557e-05,
+      "loss": 1.5457,
+      "step": 15066
+    },
+    {
+      "epoch": 0.5312291072873782,
+      "grad_norm": 0.868419349193573,
+      "learning_rate": 2.7500384991771587e-05,
+      "loss": 1.5264,
+      "step": 15097
+    },
+    {
+      "epoch": 0.5323199268095289,
+      "grad_norm": 0.8620421290397644,
+      "learning_rate": 2.7416809718923825e-05,
+      "loss": 1.5486,
+      "step": 15128
+    },
+    {
+      "epoch": 0.5334107463316795,
+      "grad_norm": 0.843984067440033,
+      "learning_rate": 2.7333207172706864e-05,
+      "loss": 1.5385,
+      "step": 15159
+    },
+    {
+      "epoch": 0.5345015658538301,
+      "grad_norm": 0.8699086308479309,
+      "learning_rate": 2.7249578296564088e-05,
+      "loss": 1.5473,
+      "step": 15190
+    },
+    {
+      "epoch": 0.5355923853759809,
+      "grad_norm": 0.8395929932594299,
+      "learning_rate": 2.7165924034235973e-05,
+      "loss": 1.5436,
+      "step": 15221
+    },
+    {
+      "epoch": 0.5366832048981315,
+      "grad_norm": 0.8811730146408081,
+      "learning_rate": 2.708224532974953e-05,
+      "loss": 1.5402,
+      "step": 15252
+    }
+  ],
+  "logging_steps": 31,
+  "max_steps": 30517,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 3052,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.065842709765292e+19,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-15260/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0ca846c3dadf09d6ea20e996f3b024f89f025d88b771ce5d9eb5e978edeb732
+size 5304

checkpoint-18312/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/mnt/parscratch/users/acp23ay/private/models/Qwen2.5-7B-Instruct-bn-madlad-mean/",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.0.dev0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 161672
+}

checkpoint-18312/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.44.0.dev0"
+}

checkpoint-18312/model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2af0d04ed33b32f47c209ba4a424b88eb94b55d198d2b0b3d63580322e818418
+size 4842817304

checkpoint-18312/model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:becf3c41c7359877372d1f9bdba9efe52cb2b8dab7330b346e831a36665b8f0e
+size 4998852224

checkpoint-18312/model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad9da13aef49ef9aa84ff7ac6ae375fc2f8c339648214e7663e44e16a6763847
+size 4984124304

checkpoint-18312/model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfc2c86e34819a46908bfe3ad42f3986e7efdfc34f67e43f40f690f77c7b0672
+size 4932743992

checkpoint-18312/model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:891f86a74d6b1791b98b581ff94cbedb16bfdb78595b9697dc3fd2ecc5974ba2
+size 4998852296

checkpoint-18312/model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebc947bee36d6ef8ef24b4969bacb8f73c1cc020f6c06b234fc9a2a4cc935495
+size 3662865184

checkpoint-18312/model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6041268c4a63c8a94917fe2f7a1190a6d9bdc838df6dd9d0f71d20e76efdf44
+size 2317729920

checkpoint-18312/model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 30737946624
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.norm.weight": "model-00006-of-00007.safetensors"
+  }
+}

checkpoint-18312/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f293823c4f525a6d0aba2cf5976f0375165e4e0b0fde4fd21fd9a95d13f4918f
+size 16728842070

checkpoint-18312/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d9cd6a0487226e5bd30d1846894c82af483733ab4381b75bae9c0745e05d405
+size 14244

checkpoint-18312/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0e65c3d6f29e706fd941a38280ce5628189a6998eac6d29abbeab00ad838d00
+size 1064

checkpoint-18312/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0ca846c3dadf09d6ea20e996f3b024f89f025d88b771ce5d9eb5e978edeb732
+size 5304

checkpoint-21364/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/mnt/parscratch/users/acp23ay/private/models/Qwen2.5-7B-Instruct-bn-madlad-mean/",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.0.dev0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 161672
+}

checkpoint-21364/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.44.0.dev0"
+}

checkpoint-21364/model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2f716b288a5a73c5086106d93bc556f88af041716227346068c3bce17a2a460
+size 4842817304

checkpoint-21364/model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:becf3c41c7359877372d1f9bdba9efe52cb2b8dab7330b346e831a36665b8f0e
+size 4998852224

checkpoint-21364/model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad9da13aef49ef9aa84ff7ac6ae375fc2f8c339648214e7663e44e16a6763847
+size 4984124304