Training in progress, step 398, checkpoint

checkpoint-398/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 2,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.36.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

checkpoint-398/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.36.0.dev0"
+}

checkpoint-398/model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfb4e7464e276b6d23a8a2f8ef19ace0cb4d4210f2703547df3e678d600b9a73
+size 4943162336

checkpoint-398/model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0a03e122f1146d9ffdeb7aa00b004130f8865e5ea3bdd551ae3e36308028a0c
+size 4999819336

checkpoint-398/model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1c25557a83599b86737a2971380c5e570703a5ad0f443a4a09b6832e33a469b
+size 4540516344

checkpoint-398/model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 14483464192
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

checkpoint-398/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7841637a5f39b255fe8b4989aaf0fb180633a33f7dba9a3735378ddc60c4ae12
+size 14512103560

checkpoint-398/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08282b46825aa78d10fe10e3fea89555c5b5a691b261a3ddfd58fcb58370edff
+size 15984

checkpoint-398/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbab71d98a3a9a92df82a6bba463947327c3a1bcf35cd9f4f46114641fc42dd9
+size 15984

checkpoint-398/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caac82d57d878d30219a4f9ec289a97ff90c53afc160b968f251b3fd3454b8d8
+size 15984

checkpoint-398/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19762d2d370222b01817da11bbaa6665d542293373186d66f754e7246bb861ed
+size 15984

checkpoint-398/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00c7508b346a7d3c5c23392845f1d013331114ade778794b76e919cb3ed5d33e
+size 15984

checkpoint-398/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b89de7d14dd20a191f56b74c816ef8b7fe5c171e31efbeadbf321c4539ed68c3
+size 15984

checkpoint-398/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c71152053553e6e22d670fbc4fd7550bf8a046b54cad7b71869787986a6a42c
+size 15984

checkpoint-398/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b67db12a26a26ffe03d9afc84a43857eb2e5b2fec2dd189653b415f74208190
+size 15984

checkpoint-398/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:354c6e1f0c1593c9a355bd337ec4d2e78152ff86359c50bd9c6c8af224e59dda
+size 1064

checkpoint-398/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-398/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

checkpoint-398/tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

checkpoint-398/trainer_state.json

@@ -0,0 +1,2424 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.04173657718120805,
+  "eval_steps": 199,
+  "global_step": 398,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.0986358866736623e-08,
+      "loss": 2.1261,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.1972717733473246e-08,
+      "loss": 2.0696,
+      "step": 2
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 6.295907660020988e-08,
+      "loss": 2.0664,
+      "step": 3
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 8.394543546694649e-08,
+      "loss": 2.0793,
+      "step": 4
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.0493179433368311e-07,
+      "loss": 1.9493,
+      "step": 5
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.2591815320041975e-07,
+      "loss": 2.0603,
+      "step": 6
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.4690451206715635e-07,
+      "loss": 2.2201,
+      "step": 7
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.6789087093389298e-07,
+      "loss": 2.0475,
+      "step": 8
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.888772298006296e-07,
+      "loss": 1.8393,
+      "step": 9
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.0986358866736621e-07,
+      "loss": 2.1082,
+      "step": 10
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.3084994753410284e-07,
+      "loss": 2.0846,
+      "step": 11
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.518363064008395e-07,
+      "loss": 2.2172,
+      "step": 12
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.7282266526757613e-07,
+      "loss": 2.0091,
+      "step": 13
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.938090241343127e-07,
+      "loss": 2.1092,
+      "step": 14
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 3.1479538300104934e-07,
+      "loss": 2.0882,
+      "step": 15
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 3.3578174186778596e-07,
+      "loss": 2.0103,
+      "step": 16
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 3.567681007345226e-07,
+      "loss": 2.119,
+      "step": 17
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 3.777544596012592e-07,
+      "loss": 2.005,
+      "step": 18
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 3.9874081846799585e-07,
+      "loss": 2.0261,
+      "step": 19
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.1972717733473243e-07,
+      "loss": 1.8976,
+      "step": 20
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.407135362014691e-07,
+      "loss": 2.0584,
+      "step": 21
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.616998950682057e-07,
+      "loss": 1.9565,
+      "step": 22
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.826862539349423e-07,
+      "loss": 2.1067,
+      "step": 23
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 5.03672612801679e-07,
+      "loss": 1.9939,
+      "step": 24
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 5.246589716684156e-07,
+      "loss": 1.9337,
+      "step": 25
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 5.456453305351523e-07,
+      "loss": 2.0869,
+      "step": 26
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 5.666316894018888e-07,
+      "loss": 2.0134,
+      "step": 27
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 5.876180482686254e-07,
+      "loss": 1.5282,
+      "step": 28
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 6.086044071353621e-07,
+      "loss": 1.8605,
+      "step": 29
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 6.295907660020987e-07,
+      "loss": 1.9561,
+      "step": 30
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 6.505771248688352e-07,
+      "loss": 1.9562,
+      "step": 31
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 6.715634837355719e-07,
+      "loss": 1.9124,
+      "step": 32
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 6.925498426023086e-07,
+      "loss": 1.908,
+      "step": 33
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 7.135362014690452e-07,
+      "loss": 1.9148,
+      "step": 34
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 7.345225603357818e-07,
+      "loss": 1.9861,
+      "step": 35
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 7.555089192025184e-07,
+      "loss": 1.8246,
+      "step": 36
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 7.76495278069255e-07,
+      "loss": 1.9355,
+      "step": 37
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 7.974816369359917e-07,
+      "loss": 1.9849,
+      "step": 38
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 8.184679958027284e-07,
+      "loss": 1.8894,
+      "step": 39
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 8.394543546694649e-07,
+      "loss": 1.9615,
+      "step": 40
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 8.604407135362015e-07,
+      "loss": 1.8815,
+      "step": 41
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 8.814270724029382e-07,
+      "loss": 1.9888,
+      "step": 42
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 9.024134312696747e-07,
+      "loss": 1.8663,
+      "step": 43
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 9.233997901364114e-07,
+      "loss": 1.8711,
+      "step": 44
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 9.443861490031481e-07,
+      "loss": 1.8709,
+      "step": 45
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 9.653725078698846e-07,
+      "loss": 1.8837,
+      "step": 46
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 9.863588667366212e-07,
+      "loss": 1.9386,
+      "step": 47
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.007345225603358e-06,
+      "loss": 1.8926,
+      "step": 48
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.0283315844700944e-06,
+      "loss": 1.8623,
+      "step": 49
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.0493179433368312e-06,
+      "loss": 1.9017,
+      "step": 50
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.0703043022035677e-06,
+      "loss": 1.883,
+      "step": 51
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.0912906610703045e-06,
+      "loss": 2.0128,
+      "step": 52
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.1122770199370409e-06,
+      "loss": 1.9405,
+      "step": 53
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.1332633788037777e-06,
+      "loss": 2.1205,
+      "step": 54
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.1542497376705142e-06,
+      "loss": 1.8373,
+      "step": 55
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.1752360965372508e-06,
+      "loss": 1.9386,
+      "step": 56
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.1962224554039876e-06,
+      "loss": 1.831,
+      "step": 57
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.2172088142707242e-06,
+      "loss": 1.8523,
+      "step": 58
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.2381951731374608e-06,
+      "loss": 1.8641,
+      "step": 59
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.2591815320041973e-06,
+      "loss": 1.8386,
+      "step": 60
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.280167890870934e-06,
+      "loss": 1.8628,
+      "step": 61
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.3011542497376705e-06,
+      "loss": 1.8578,
+      "step": 62
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.3221406086044073e-06,
+      "loss": 1.868,
+      "step": 63
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.3431269674711439e-06,
+      "loss": 1.9356,
+      "step": 64
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.3641133263378806e-06,
+      "loss": 1.7525,
+      "step": 65
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.3850996852046172e-06,
+      "loss": 1.8815,
+      "step": 66
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.4060860440713536e-06,
+      "loss": 1.8752,
+      "step": 67
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.4270724029380904e-06,
+      "loss": 1.8017,
+      "step": 68
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.448058761804827e-06,
+      "loss": 1.8209,
+      "step": 69
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.4690451206715635e-06,
+      "loss": 1.7979,
+      "step": 70
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.4900314795383003e-06,
+      "loss": 1.8267,
+      "step": 71
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.511017838405037e-06,
+      "loss": 1.862,
+      "step": 72
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.5320041972717733e-06,
+      "loss": 1.8278,
+      "step": 73
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.55299055613851e-06,
+      "loss": 1.816,
+      "step": 74
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.5739769150052466e-06,
+      "loss": 1.8465,
+      "step": 75
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.5949632738719834e-06,
+      "loss": 1.7981,
+      "step": 76
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.61594963273872e-06,
+      "loss": 1.9075,
+      "step": 77
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.6369359916054568e-06,
+      "loss": 1.7548,
+      "step": 78
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.6579223504721931e-06,
+      "loss": 1.8585,
+      "step": 79
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.6789087093389297e-06,
+      "loss": 1.7725,
+      "step": 80
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.6998950682056665e-06,
+      "loss": 1.8273,
+      "step": 81
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.720881427072403e-06,
+      "loss": 1.777,
+      "step": 82
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.7418677859391397e-06,
+      "loss": 1.8077,
+      "step": 83
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.7628541448058764e-06,
+      "loss": 1.821,
+      "step": 84
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.783840503672613e-06,
+      "loss": 1.8287,
+      "step": 85
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.8048268625393494e-06,
+      "loss": 1.7358,
+      "step": 86
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.8258132214060862e-06,
+      "loss": 1.7546,
+      "step": 87
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.8467995802728228e-06,
+      "loss": 1.8147,
+      "step": 88
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.8677859391395595e-06,
+      "loss": 1.8309,
+      "step": 89
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.8887722980062961e-06,
+      "loss": 1.6292,
+      "step": 90
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.909758656873033e-06,
+      "loss": 1.7222,
+      "step": 91
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.9307450157397693e-06,
+      "loss": 1.809,
+      "step": 92
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.951731374606506e-06,
+      "loss": 1.8691,
+      "step": 93
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.9727177334732424e-06,
+      "loss": 1.8777,
+      "step": 94
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.9937040923399792e-06,
+      "loss": 1.7701,
+      "step": 95
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.014690451206716e-06,
+      "loss": 1.885,
+      "step": 96
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.0356768100734524e-06,
+      "loss": 1.7737,
+      "step": 97
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.0566631689401887e-06,
+      "loss": 1.7554,
+      "step": 98
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.0776495278069255e-06,
+      "loss": 1.8553,
+      "step": 99
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.0986358866736623e-06,
+      "loss": 1.8386,
+      "step": 100
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.119622245540399e-06,
+      "loss": 1.8325,
+      "step": 101
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.1406086044071355e-06,
+      "loss": 1.7812,
+      "step": 102
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.1615949632738722e-06,
+      "loss": 1.7537,
+      "step": 103
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.182581322140609e-06,
+      "loss": 1.7558,
+      "step": 104
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.2035676810073454e-06,
+      "loss": 1.7278,
+      "step": 105
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.2245540398740818e-06,
+      "loss": 1.761,
+      "step": 106
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.2455403987408186e-06,
+      "loss": 1.792,
+      "step": 107
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.2665267576075553e-06,
+      "loss": 1.7965,
+      "step": 108
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.287513116474292e-06,
+      "loss": 1.7624,
+      "step": 109
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.3084994753410285e-06,
+      "loss": 1.7744,
+      "step": 110
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.329485834207765e-06,
+      "loss": 1.7691,
+      "step": 111
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.3504721930745016e-06,
+      "loss": 1.8194,
+      "step": 112
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.3714585519412384e-06,
+      "loss": 1.691,
+      "step": 113
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.3924449108079752e-06,
+      "loss": 1.7505,
+      "step": 114
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.4134312696747116e-06,
+      "loss": 1.7492,
+      "step": 115
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.4344176285414484e-06,
+      "loss": 1.8426,
+      "step": 116
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.4554039874081847e-06,
+      "loss": 1.855,
+      "step": 117
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.4763903462749215e-06,
+      "loss": 1.7778,
+      "step": 118
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.497376705141658e-06,
+      "loss": 1.7715,
+      "step": 119
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.5183630640083947e-06,
+      "loss": 1.7382,
+      "step": 120
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.5393494228751315e-06,
+      "loss": 1.7027,
+      "step": 121
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.560335781741868e-06,
+      "loss": 1.7508,
+      "step": 122
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.5813221406086046e-06,
+      "loss": 1.7119,
+      "step": 123
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.602308499475341e-06,
+      "loss": 1.8291,
+      "step": 124
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.623294858342078e-06,
+      "loss": 1.7568,
+      "step": 125
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.6442812172088146e-06,
+      "loss": 1.9176,
+      "step": 126
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.665267576075551e-06,
+      "loss": 1.7036,
+      "step": 127
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.6862539349422877e-06,
+      "loss": 1.7842,
+      "step": 128
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.707240293809024e-06,
+      "loss": 1.7883,
+      "step": 129
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.7282266526757613e-06,
+      "loss": 1.7662,
+      "step": 130
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.7492130115424977e-06,
+      "loss": 1.5587,
+      "step": 131
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.7701993704092344e-06,
+      "loss": 1.7486,
+      "step": 132
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.791185729275971e-06,
+      "loss": 1.7515,
+      "step": 133
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.812172088142707e-06,
+      "loss": 1.7668,
+      "step": 134
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.8331584470094444e-06,
+      "loss": 1.7895,
+      "step": 135
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.8541448058761808e-06,
+      "loss": 1.7961,
+      "step": 136
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.8751311647429175e-06,
+      "loss": 1.6693,
+      "step": 137
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.896117523609654e-06,
+      "loss": 1.776,
+      "step": 138
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.9171038824763903e-06,
+      "loss": 1.7422,
+      "step": 139
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.938090241343127e-06,
+      "loss": 1.7845,
+      "step": 140
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.959076600209864e-06,
+      "loss": 1.8011,
+      "step": 141
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.9800629590766006e-06,
+      "loss": 1.6759,
+      "step": 142
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 3.001049317943337e-06,
+      "loss": 1.7367,
+      "step": 143
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.022035676810074e-06,
+      "loss": 1.7511,
+      "step": 144
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.04302203567681e-06,
+      "loss": 1.779,
+      "step": 145
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.0640083945435465e-06,
+      "loss": 1.7542,
+      "step": 146
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.0849947534102837e-06,
+      "loss": 1.742,
+      "step": 147
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.10598111227702e-06,
+      "loss": 1.7408,
+      "step": 148
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.126967471143757e-06,
+      "loss": 1.6937,
+      "step": 149
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.1479538300104932e-06,
+      "loss": 1.7198,
+      "step": 150
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.1689401888772305e-06,
+      "loss": 1.674,
+      "step": 151
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.189926547743967e-06,
+      "loss": 1.7469,
+      "step": 152
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.210912906610703e-06,
+      "loss": 1.7192,
+      "step": 153
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.23189926547744e-06,
+      "loss": 1.9507,
+      "step": 154
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.2528856243441763e-06,
+      "loss": 1.8311,
+      "step": 155
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.2738719832109136e-06,
+      "loss": 1.7125,
+      "step": 156
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.29485834207765e-06,
+      "loss": 1.8235,
+      "step": 157
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.3158447009443863e-06,
+      "loss": 1.7358,
+      "step": 158
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.336831059811123e-06,
+      "loss": 1.774,
+      "step": 159
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.3578174186778594e-06,
+      "loss": 1.7717,
+      "step": 160
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.3788037775445962e-06,
+      "loss": 1.6815,
+      "step": 161
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.399790136411333e-06,
+      "loss": 1.6993,
+      "step": 162
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.42077649527807e-06,
+      "loss": 1.5911,
+      "step": 163
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.441762854144806e-06,
+      "loss": 1.7484,
+      "step": 164
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.4627492130115425e-06,
+      "loss": 1.8047,
+      "step": 165
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.4837355718782793e-06,
+      "loss": 1.7397,
+      "step": 166
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.5047219307450157e-06,
+      "loss": 1.7384,
+      "step": 167
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.525708289611753e-06,
+      "loss": 1.7369,
+      "step": 168
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.5466946484784893e-06,
+      "loss": 1.7013,
+      "step": 169
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.567681007345226e-06,
+      "loss": 1.6896,
+      "step": 170
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.5886673662119624e-06,
+      "loss": 1.6953,
+      "step": 171
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.6096537250786988e-06,
+      "loss": 1.7638,
+      "step": 172
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.630640083945436e-06,
+      "loss": 1.6814,
+      "step": 173
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.6516264428121724e-06,
+      "loss": 1.6938,
+      "step": 174
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.672612801678909e-06,
+      "loss": 1.8404,
+      "step": 175
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.6935991605456455e-06,
+      "loss": 1.7429,
+      "step": 176
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.714585519412382e-06,
+      "loss": 1.7408,
+      "step": 177
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.735571878279119e-06,
+      "loss": 1.6916,
+      "step": 178
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.7565582371458554e-06,
+      "loss": 1.7668,
+      "step": 179
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.7775445960125922e-06,
+      "loss": 1.7444,
+      "step": 180
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.7985309548793286e-06,
+      "loss": 1.7478,
+      "step": 181
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.819517313746066e-06,
+      "loss": 1.7812,
+      "step": 182
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.840503672612802e-06,
+      "loss": 1.7029,
+      "step": 183
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.8614900314795385e-06,
+      "loss": 1.66,
+      "step": 184
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.882476390346275e-06,
+      "loss": 1.7375,
+      "step": 185
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.903462749213012e-06,
+      "loss": 1.7702,
+      "step": 186
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.924449108079749e-06,
+      "loss": 1.7368,
+      "step": 187
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.945435466946485e-06,
+      "loss": 1.7121,
+      "step": 188
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.966421825813222e-06,
+      "loss": 1.7639,
+      "step": 189
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.9874081846799584e-06,
+      "loss": 1.6665,
+      "step": 190
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.008394543546694e-06,
+      "loss": 1.6536,
+      "step": 191
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.029380902413432e-06,
+      "loss": 1.7049,
+      "step": 192
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.050367261280168e-06,
+      "loss": 1.8199,
+      "step": 193
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.071353620146905e-06,
+      "loss": 1.747,
+      "step": 194
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.0923399790136415e-06,
+      "loss": 1.7382,
+      "step": 195
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.1133263378803775e-06,
+      "loss": 1.6958,
+      "step": 196
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.134312696747115e-06,
+      "loss": 1.6974,
+      "step": 197
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.155299055613851e-06,
+      "loss": 1.6909,
+      "step": 198
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.176285414480588e-06,
+      "loss": 1.6995,
+      "step": 199
+    },
+    {
+      "epoch": 0.02,
+      "eval_loss": 1.7673084735870361,
+      "eval_runtime": 77.3397,
+      "eval_samples_per_second": 1.668,
+      "eval_steps_per_second": 0.116,
+      "step": 199
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.197271773347325e-06,
+      "loss": 1.6732,
+      "step": 200
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.218258132214061e-06,
+      "loss": 1.7269,
+      "step": 201
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.239244491080798e-06,
+      "loss": 1.6493,
+      "step": 202
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.260230849947534e-06,
+      "loss": 1.6544,
+      "step": 203
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.281217208814271e-06,
+      "loss": 1.8876,
+      "step": 204
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.302203567681008e-06,
+      "loss": 1.7196,
+      "step": 205
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.3231899265477445e-06,
+      "loss": 1.7659,
+      "step": 206
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.344176285414481e-06,
+      "loss": 1.7129,
+      "step": 207
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.365162644281218e-06,
+      "loss": 1.7269,
+      "step": 208
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.386149003147954e-06,
+      "loss": 1.7957,
+      "step": 209
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.407135362014691e-06,
+      "loss": 1.681,
+      "step": 210
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.428121720881428e-06,
+      "loss": 1.7112,
+      "step": 211
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.4491080797481635e-06,
+      "loss": 1.7149,
+      "step": 212
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.470094438614901e-06,
+      "loss": 1.6928,
+      "step": 213
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.491080797481637e-06,
+      "loss": 1.6171,
+      "step": 214
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.512067156348374e-06,
+      "loss": 1.7275,
+      "step": 215
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.533053515215111e-06,
+      "loss": 1.7502,
+      "step": 216
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.554039874081847e-06,
+      "loss": 1.7948,
+      "step": 217
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.575026232948584e-06,
+      "loss": 1.8349,
+      "step": 218
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.59601259181532e-06,
+      "loss": 1.6717,
+      "step": 219
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.616998950682057e-06,
+      "loss": 1.7387,
+      "step": 220
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.637985309548794e-06,
+      "loss": 1.836,
+      "step": 221
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.65897166841553e-06,
+      "loss": 1.7285,
+      "step": 222
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.679958027282267e-06,
+      "loss": 1.6988,
+      "step": 223
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.700944386149003e-06,
+      "loss": 1.642,
+      "step": 224
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.72193074501574e-06,
+      "loss": 1.7184,
+      "step": 225
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.742917103882477e-06,
+      "loss": 1.6935,
+      "step": 226
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.763903462749214e-06,
+      "loss": 1.7593,
+      "step": 227
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.7848898216159504e-06,
+      "loss": 1.6854,
+      "step": 228
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.805876180482686e-06,
+      "loss": 1.7047,
+      "step": 229
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.826862539349423e-06,
+      "loss": 1.6543,
+      "step": 230
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.84784889821616e-06,
+      "loss": 1.6321,
+      "step": 231
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.868835257082897e-06,
+      "loss": 1.6938,
+      "step": 232
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.889821615949633e-06,
+      "loss": 1.725,
+      "step": 233
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.9108079748163695e-06,
+      "loss": 1.7119,
+      "step": 234
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.931794333683106e-06,
+      "loss": 1.7741,
+      "step": 235
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.952780692549843e-06,
+      "loss": 1.702,
+      "step": 236
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.97376705141658e-06,
+      "loss": 1.6566,
+      "step": 237
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.994753410283316e-06,
+      "loss": 1.7506,
+      "step": 238
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.0157397691500534e-06,
+      "loss": 1.7185,
+      "step": 239
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.036726128016789e-06,
+      "loss": 1.8174,
+      "step": 240
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.057712486883526e-06,
+      "loss": 1.6781,
+      "step": 241
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.078698845750263e-06,
+      "loss": 1.7818,
+      "step": 242
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.099685204617e-06,
+      "loss": 1.6647,
+      "step": 243
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.120671563483736e-06,
+      "loss": 1.6918,
+      "step": 244
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.1416579223504725e-06,
+      "loss": 1.7119,
+      "step": 245
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.162644281217209e-06,
+      "loss": 1.612,
+      "step": 246
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.183630640083945e-06,
+      "loss": 1.5301,
+      "step": 247
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.204616998950682e-06,
+      "loss": 1.7407,
+      "step": 248
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.22560335781742e-06,
+      "loss": 1.7838,
+      "step": 249
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.246589716684156e-06,
+      "loss": 1.6825,
+      "step": 250
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.267576075550892e-06,
+      "loss": 1.6821,
+      "step": 251
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.288562434417629e-06,
+      "loss": 1.6712,
+      "step": 252
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.309548793284366e-06,
+      "loss": 1.6599,
+      "step": 253
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.330535152151102e-06,
+      "loss": 1.7009,
+      "step": 254
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.351521511017839e-06,
+      "loss": 1.6845,
+      "step": 255
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.3725078698845754e-06,
+      "loss": 1.6832,
+      "step": 256
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.393494228751312e-06,
+      "loss": 1.8023,
+      "step": 257
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.414480587618048e-06,
+      "loss": 1.718,
+      "step": 258
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.435466946484785e-06,
+      "loss": 1.602,
+      "step": 259
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.456453305351523e-06,
+      "loss": 1.6133,
+      "step": 260
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.4774396642182585e-06,
+      "loss": 1.704,
+      "step": 261
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.498426023084995e-06,
+      "loss": 1.6702,
+      "step": 262
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.519412381951732e-06,
+      "loss": 1.7256,
+      "step": 263
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.540398740818469e-06,
+      "loss": 1.7384,
+      "step": 264
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.561385099685205e-06,
+      "loss": 1.6504,
+      "step": 265
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.582371458551942e-06,
+      "loss": 1.6896,
+      "step": 266
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.603357817418678e-06,
+      "loss": 1.6566,
+      "step": 267
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.624344176285414e-06,
+      "loss": 1.7107,
+      "step": 268
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.645330535152151e-06,
+      "loss": 1.6883,
+      "step": 269
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.666316894018889e-06,
+      "loss": 1.74,
+      "step": 270
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.6873032528856256e-06,
+      "loss": 1.7273,
+      "step": 271
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.7082896117523615e-06,
+      "loss": 1.7397,
+      "step": 272
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.729275970619098e-06,
+      "loss": 1.723,
+      "step": 273
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.750262329485835e-06,
+      "loss": 1.6811,
+      "step": 274
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.771248688352571e-06,
+      "loss": 1.7044,
+      "step": 275
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.792235047219308e-06,
+      "loss": 1.6937,
+      "step": 276
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.813221406086045e-06,
+      "loss": 1.5984,
+      "step": 277
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.8342077649527805e-06,
+      "loss": 1.7853,
+      "step": 278
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.855194123819517e-06,
+      "loss": 1.6742,
+      "step": 279
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.876180482686254e-06,
+      "loss": 1.5612,
+      "step": 280
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.897166841552992e-06,
+      "loss": 1.6945,
+      "step": 281
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.918153200419728e-06,
+      "loss": 1.6618,
+      "step": 282
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.9391395592864645e-06,
+      "loss": 1.6928,
+      "step": 283
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.960125918153201e-06,
+      "loss": 1.7438,
+      "step": 284
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.981112277019937e-06,
+      "loss": 1.5858,
+      "step": 285
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.002098635886674e-06,
+      "loss": 1.6936,
+      "step": 286
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.023084994753411e-06,
+      "loss": 1.6522,
+      "step": 287
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.044071353620148e-06,
+      "loss": 1.7174,
+      "step": 288
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.0650577124868835e-06,
+      "loss": 1.6747,
+      "step": 289
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.08604407135362e-06,
+      "loss": 1.6525,
+      "step": 290
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.107030430220358e-06,
+      "loss": 1.6615,
+      "step": 291
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.128016789087093e-06,
+      "loss": 1.7633,
+      "step": 292
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.149003147953831e-06,
+      "loss": 1.6597,
+      "step": 293
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.1699895068205675e-06,
+      "loss": 1.6356,
+      "step": 294
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.190975865687304e-06,
+      "loss": 1.5906,
+      "step": 295
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.21196222455404e-06,
+      "loss": 1.7179,
+      "step": 296
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.232948583420777e-06,
+      "loss": 1.6571,
+      "step": 297
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.253934942287514e-06,
+      "loss": 1.655,
+      "step": 298
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.27492130115425e-06,
+      "loss": 1.6705,
+      "step": 299
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.2959076600209865e-06,
+      "loss": 1.6931,
+      "step": 300
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.316894018887723e-06,
+      "loss": 1.6721,
+      "step": 301
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.337880377754461e-06,
+      "loss": 1.6573,
+      "step": 302
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.358866736621197e-06,
+      "loss": 1.7316,
+      "step": 303
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.379853095487934e-06,
+      "loss": 1.6635,
+      "step": 304
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.4008394543546704e-06,
+      "loss": 1.7145,
+      "step": 305
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.421825813221406e-06,
+      "loss": 1.6044,
+      "step": 306
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.442812172088143e-06,
+      "loss": 1.6659,
+      "step": 307
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.46379853095488e-06,
+      "loss": 1.6645,
+      "step": 308
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.484784889821617e-06,
+      "loss": 1.6803,
+      "step": 309
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.505771248688353e-06,
+      "loss": 1.6705,
+      "step": 310
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.5267576075550895e-06,
+      "loss": 1.6768,
+      "step": 311
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.547743966421827e-06,
+      "loss": 1.6768,
+      "step": 312
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.568730325288562e-06,
+      "loss": 1.6345,
+      "step": 313
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.5897166841553e-06,
+      "loss": 1.6363,
+      "step": 314
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.610703043022037e-06,
+      "loss": 1.6689,
+      "step": 315
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.6316894018887726e-06,
+      "loss": 1.6641,
+      "step": 316
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.652675760755509e-06,
+      "loss": 1.7221,
+      "step": 317
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.673662119622246e-06,
+      "loss": 1.6427,
+      "step": 318
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.694648478488983e-06,
+      "loss": 1.6451,
+      "step": 319
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.715634837355719e-06,
+      "loss": 1.8635,
+      "step": 320
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.736621196222456e-06,
+      "loss": 1.6825,
+      "step": 321
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.7576075550891924e-06,
+      "loss": 1.7618,
+      "step": 322
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.778593913955928e-06,
+      "loss": 1.776,
+      "step": 323
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.799580272822666e-06,
+      "loss": 1.6075,
+      "step": 324
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.820566631689403e-06,
+      "loss": 1.5783,
+      "step": 325
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.84155299055614e-06,
+      "loss": 1.6573,
+      "step": 326
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.8625393494228755e-06,
+      "loss": 1.6736,
+      "step": 327
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.883525708289612e-06,
+      "loss": 1.7454,
+      "step": 328
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.904512067156349e-06,
+      "loss": 1.658,
+      "step": 329
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.925498426023085e-06,
+      "loss": 1.645,
+      "step": 330
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.946484784889822e-06,
+      "loss": 1.6697,
+      "step": 331
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.967471143756559e-06,
+      "loss": 1.633,
+      "step": 332
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.988457502623296e-06,
+      "loss": 1.879,
+      "step": 333
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.009443861490031e-06,
+      "loss": 1.6834,
+      "step": 334
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.030430220356769e-06,
+      "loss": 1.6658,
+      "step": 335
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.051416579223506e-06,
+      "loss": 1.6606,
+      "step": 336
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.072402938090242e-06,
+      "loss": 1.6488,
+      "step": 337
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.0933892969569785e-06,
+      "loss": 1.6356,
+      "step": 338
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.114375655823715e-06,
+      "loss": 1.6584,
+      "step": 339
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.135362014690452e-06,
+      "loss": 1.6851,
+      "step": 340
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.156348373557188e-06,
+      "loss": 1.5969,
+      "step": 341
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.177334732423925e-06,
+      "loss": 1.6009,
+      "step": 342
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.198321091290662e-06,
+      "loss": 1.6188,
+      "step": 343
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.2193074501573976e-06,
+      "loss": 1.6295,
+      "step": 344
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.240293809024135e-06,
+      "loss": 1.7956,
+      "step": 345
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.261280167890872e-06,
+      "loss": 1.7044,
+      "step": 346
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.282266526757609e-06,
+      "loss": 1.6785,
+      "step": 347
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.303252885624345e-06,
+      "loss": 1.6323,
+      "step": 348
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.3242392444910815e-06,
+      "loss": 1.5752,
+      "step": 349
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.345225603357818e-06,
+      "loss": 1.5829,
+      "step": 350
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.366211962224554e-06,
+      "loss": 1.6529,
+      "step": 351
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.387198321091291e-06,
+      "loss": 1.7484,
+      "step": 352
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.408184679958028e-06,
+      "loss": 1.6692,
+      "step": 353
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.429171038824764e-06,
+      "loss": 1.6153,
+      "step": 354
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.4501573976915005e-06,
+      "loss": 1.6408,
+      "step": 355
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.471143756558238e-06,
+      "loss": 1.5987,
+      "step": 356
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.492130115424975e-06,
+      "loss": 1.6204,
+      "step": 357
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.513116474291711e-06,
+      "loss": 1.6793,
+      "step": 358
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.534102833158448e-06,
+      "loss": 1.6736,
+      "step": 359
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.5550891920251845e-06,
+      "loss": 1.6899,
+      "step": 360
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.57607555089192e-06,
+      "loss": 1.668,
+      "step": 361
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.597061909758657e-06,
+      "loss": 1.6286,
+      "step": 362
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.618048268625394e-06,
+      "loss": 1.6475,
+      "step": 363
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.639034627492132e-06,
+      "loss": 1.6378,
+      "step": 364
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.660020986358867e-06,
+      "loss": 1.6705,
+      "step": 365
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.681007345225604e-06,
+      "loss": 1.5835,
+      "step": 366
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.70199370409234e-06,
+      "loss": 1.7316,
+      "step": 367
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.722980062959077e-06,
+      "loss": 1.6678,
+      "step": 368
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.743966421825814e-06,
+      "loss": 1.6155,
+      "step": 369
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.76495278069255e-06,
+      "loss": 1.6493,
+      "step": 370
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.785939139559287e-06,
+      "loss": 1.6038,
+      "step": 371
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.806925498426024e-06,
+      "loss": 1.6313,
+      "step": 372
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.827911857292761e-06,
+      "loss": 1.5703,
+      "step": 373
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.848898216159498e-06,
+      "loss": 1.7095,
+      "step": 374
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.869884575026233e-06,
+      "loss": 1.6805,
+      "step": 375
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.89087093389297e-06,
+      "loss": 1.6683,
+      "step": 376
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.911857292759706e-06,
+      "loss": 1.6528,
+      "step": 377
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.932843651626443e-06,
+      "loss": 1.6633,
+      "step": 378
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.95383001049318e-06,
+      "loss": 1.722,
+      "step": 379
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.974816369359917e-06,
+      "loss": 1.6455,
+      "step": 380
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.995802728226654e-06,
+      "loss": 1.7223,
+      "step": 381
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.016789087093389e-06,
+      "loss": 1.7372,
+      "step": 382
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.037775445960127e-06,
+      "loss": 1.7798,
+      "step": 383
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.058761804826864e-06,
+      "loss": 1.5855,
+      "step": 384
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.079748163693599e-06,
+      "loss": 1.651,
+      "step": 385
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.100734522560336e-06,
+      "loss": 1.6762,
+      "step": 386
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.121720881427073e-06,
+      "loss": 1.6231,
+      "step": 387
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.14270724029381e-06,
+      "loss": 1.6123,
+      "step": 388
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.163693599160546e-06,
+      "loss": 1.6126,
+      "step": 389
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.184679958027283e-06,
+      "loss": 1.6737,
+      "step": 390
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.20566631689402e-06,
+      "loss": 1.788,
+      "step": 391
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.226652675760755e-06,
+      "loss": 1.6406,
+      "step": 392
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.247639034627493e-06,
+      "loss": 1.6647,
+      "step": 393
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.26862539349423e-06,
+      "loss": 1.6685,
+      "step": 394
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.289611752360967e-06,
+      "loss": 1.6328,
+      "step": 395
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.310598111227702e-06,
+      "loss": 1.5943,
+      "step": 396
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.331584470094439e-06,
+      "loss": 1.8615,
+      "step": 397
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.352570828961176e-06,
+      "loss": 1.6949,
+      "step": 398
+    },
+    {
+      "epoch": 0.04,
+      "eval_loss": 1.6879847049713135,
+      "eval_runtime": 77.2874,
+      "eval_samples_per_second": 1.669,
+      "eval_steps_per_second": 0.116,
+      "step": 398
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 9536,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9223372036854775807,
+  "save_steps": 398,
+  "total_flos": 1.780508923972603e+19,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-398/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4651a93cc01565784d01cabcc25e18b1250dbe9aba2246e9cf4e96cb779c6cdf
+size 4728