Add files using upload-large-folder tool

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "BAAI/Emu3-Stage1",
+  "architectures": [
+    "Emu3ForCausalLM"
+  ],
+  "attention_dropout": 0.1,
+  "auto_map": {
+    "AutoConfig": "BAAI/Emu3-Stage1--configuration_emu3.Emu3Config",
+    "AutoModelForCausalLM": "BAAI/Emu3-Stage1--modeling_emu3.Emu3ForCausalLM"
+  },
+  "boi_token_id": 151852,
+  "bos_token_id": 151849,
+  "eof_token_id": 151847,
+  "eoi_token_id": 151853,
+  "eol_token_id": 151846,
+  "eos_token_id": 151850,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "image_area": 65536,
+  "img_token_id": 151851,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 4300,
+  "model_type": "Emu3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.0",
+  "use_cache": false,
+  "vocab_size": 184622
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151849,
+  "eos_token_id": 151850,
+  "pad_token_id": 151643,
+  "transformers_version": "4.44.0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dee4c881898b04889af77d98d5ef9819a1ebf6fc7f929e43c8bb1d59c38625c1
+size 4884766656

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d1110b5aa67303776110fd4f0cf6fa58600c884dbdd8a6f6365d8eb1f60504a
+size 4999819320

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62c515136fe0a64bf39e611c740dcd55bf4cff961369d747ec1be1851ae26a2b
+size 4915916184

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:759fa7aee4d22b338a9a73e88eff550658a60ce14b711aadcbe52ac861b740cc
+size 2183554760

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 16984023040
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb8c4ff6150af5c4404850197cc258f26c4ad9e7dcbfde5bd04ef48348a8e7bc
+size 15984

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:920b1a527f382c4e88a9e41e5d990f29500d1bd3bae324b2ba8c2b95a3cc79d7
+size 15984

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:328095a6eb8c9f206020edde74c487ba2ba53ee542b2ed559bfca19375b591df
+size 15984

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af16de993ae025ae87f5babac3ac05e4ad9a38aec36017505074a535b43f5f63
+size 15984

rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e079df849cbb8f38befdac6aeb8b8df9b5d8cda43df066badbb217572fd25ebb
+size 15984

rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5f9594a254c012711e0ecd1e3341923be9ce49e778a11799654fc0fb981b975
+size 15984

rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:610a7539050fe09ced608df019b82d519b6c82963641f113ab07a212dafc6e95
+size 15984

rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6177d047deebb5e927d7623cb26084e062662713ed1254868b5bd9835729c6c
+size 15984

trainer_state.json

@@ -0,0 +1,3745 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.637104849091689,
+  "eval_steps": 400,
+  "global_step": 23200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.014304105278214848,
+      "grad_norm": 4.381897472506865,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 4.333,
+      "step": 50
+    },
+    {
+      "epoch": 0.028608210556429696,
+      "grad_norm": 5.747764242911294,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 3.5701,
+      "step": 100
+    },
+    {
+      "epoch": 0.04291231583464454,
+      "grad_norm": 5.963549459328992,
+      "learning_rate": 5e-06,
+      "loss": 2.7847,
+      "step": 150
+    },
+    {
+      "epoch": 0.05721642111285939,
+      "grad_norm": 11.127446150543912,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 2.5742,
+      "step": 200
+    },
+    {
+      "epoch": 0.07152052639107424,
+      "grad_norm": 3.9613017534642814,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 2.4695,
+      "step": 250
+    },
+    {
+      "epoch": 0.08582463166928908,
+      "grad_norm": 3.641857826346019,
+      "learning_rate": 1e-05,
+      "loss": 2.3974,
+      "step": 300
+    },
+    {
+      "epoch": 0.10012873694750393,
+      "grad_norm": 5.994311420384253,
+      "learning_rate": 9.999953760295448e-06,
+      "loss": 2.2789,
+      "step": 350
+    },
+    {
+      "epoch": 0.11443284222571878,
+      "grad_norm": 2.3599387781179795,
+      "learning_rate": 9.999815042132062e-06,
+      "loss": 2.2133,
+      "step": 400
+    },
+    {
+      "epoch": 0.11443284222571878,
+      "eval_loss": 2.138951301574707,
+      "eval_runtime": 13.19,
+      "eval_samples_per_second": 75.815,
+      "eval_steps_per_second": 2.426,
+      "step": 400
+    },
+    {
+      "epoch": 0.12873694750393364,
+      "grad_norm": 5.356575743204386,
+      "learning_rate": 9.999583848360633e-06,
+      "loss": 2.1596,
+      "step": 450
+    },
+    {
+      "epoch": 0.1430410527821485,
+      "grad_norm": 3.842440081655673,
+      "learning_rate": 9.999260183732424e-06,
+      "loss": 2.1221,
+      "step": 500
+    },
+    {
+      "epoch": 0.1573451580603633,
+      "grad_norm": 2.3704079011821495,
+      "learning_rate": 9.998844054899058e-06,
+      "loss": 2.0815,
+      "step": 550
+    },
+    {
+      "epoch": 0.17164926333857816,
+      "grad_norm": 1.8440320920841848,
+      "learning_rate": 9.998335470412393e-06,
+      "loss": 2.0687,
+      "step": 600
+    },
+    {
+      "epoch": 0.185953368616793,
+      "grad_norm": 6.305609267274029,
+      "learning_rate": 9.997734440724333e-06,
+      "loss": 2.0513,
+      "step": 650
+    },
+    {
+      "epoch": 0.20025747389500786,
+      "grad_norm": 2.1140529899847054,
+      "learning_rate": 9.997040978186633e-06,
+      "loss": 2.0241,
+      "step": 700
+    },
+    {
+      "epoch": 0.21456157917322272,
+      "grad_norm": 3.884579646553787,
+      "learning_rate": 9.996255097050624e-06,
+      "loss": 2.0084,
+      "step": 750
+    },
+    {
+      "epoch": 0.22886568445143757,
+      "grad_norm": 3.1240890876667695,
+      "learning_rate": 9.995376813466934e-06,
+      "loss": 1.9989,
+      "step": 800
+    },
+    {
+      "epoch": 0.22886568445143757,
+      "eval_loss": 1.9693105220794678,
+      "eval_runtime": 13.1024,
+      "eval_samples_per_second": 76.322,
+      "eval_steps_per_second": 2.442,
+      "step": 800
+    },
+    {
+      "epoch": 0.24316978972965242,
+      "grad_norm": 2.3200436251519827,
+      "learning_rate": 9.994406145485151e-06,
+      "loss": 1.9917,
+      "step": 850
+    },
+    {
+      "epoch": 0.25747389500786727,
+      "grad_norm": 2.6496743450852738,
+      "learning_rate": 9.993343113053454e-06,
+      "loss": 1.9746,
+      "step": 900
+    },
+    {
+      "epoch": 0.2717780002860821,
+      "grad_norm": 2.536170754608615,
+      "learning_rate": 9.992187738018203e-06,
+      "loss": 1.9737,
+      "step": 950
+    },
+    {
+      "epoch": 0.286082105564297,
+      "grad_norm": 1.6713049324071942,
+      "learning_rate": 9.99094004412348e-06,
+      "loss": 1.9602,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3003862108425118,
+      "grad_norm": 2.9333959535896064,
+      "learning_rate": 9.989600057010625e-06,
+      "loss": 1.9535,
+      "step": 1050
+    },
+    {
+      "epoch": 0.3146903161207266,
+      "grad_norm": 1.8676266291905814,
+      "learning_rate": 9.988167804217682e-06,
+      "loss": 1.9416,
+      "step": 1100
+    },
+    {
+      "epoch": 0.3289944213989415,
+      "grad_norm": 1.2680641471071183,
+      "learning_rate": 9.986643315178848e-06,
+      "loss": 1.9307,
+      "step": 1150
+    },
+    {
+      "epoch": 0.3432985266771563,
+      "grad_norm": 2.9062506982476073,
+      "learning_rate": 9.98502662122387e-06,
+      "loss": 1.9378,
+      "step": 1200
+    },
+    {
+      "epoch": 0.3432985266771563,
+      "eval_loss": 1.9051591157913208,
+      "eval_runtime": 13.1019,
+      "eval_samples_per_second": 76.325,
+      "eval_steps_per_second": 2.442,
+      "step": 1200
+    },
+    {
+      "epoch": 0.3576026319553712,
+      "grad_norm": 2.156043900815843,
+      "learning_rate": 9.983317755577392e-06,
+      "loss": 1.9187,
+      "step": 1250
+    },
+    {
+      "epoch": 0.371906737233586,
+      "grad_norm": 2.8852879306242203,
+      "learning_rate": 9.981516753358274e-06,
+      "loss": 1.9251,
+      "step": 1300
+    },
+    {
+      "epoch": 0.3862108425118009,
+      "grad_norm": 1.6778445737708942,
+      "learning_rate": 9.979623651578881e-06,
+      "loss": 1.9058,
+      "step": 1350
+    },
+    {
+      "epoch": 0.40051494779001573,
+      "grad_norm": 1.4368646478597216,
+      "learning_rate": 9.977638489144308e-06,
+      "loss": 1.9119,
+      "step": 1400
+    },
+    {
+      "epoch": 0.4148190530682306,
+      "grad_norm": 1.466116857478951,
+      "learning_rate": 9.975561306851585e-06,
+      "loss": 1.9036,
+      "step": 1450
+    },
+    {
+      "epoch": 0.42912315834644543,
+      "grad_norm": 1.4471173596729103,
+      "learning_rate": 9.973392147388847e-06,
+      "loss": 1.9058,
+      "step": 1500
+    },
+    {
+      "epoch": 0.4434272636246603,
+      "grad_norm": 1.015831804058714,
+      "learning_rate": 9.971131055334445e-06,
+      "loss": 1.8931,
+      "step": 1550
+    },
+    {
+      "epoch": 0.45773136890287514,
+      "grad_norm": 1.6593036538850372,
+      "learning_rate": 9.968778077156035e-06,
+      "loss": 1.8928,
+      "step": 1600
+    },
+    {
+      "epoch": 0.45773136890287514,
+      "eval_loss": 1.8654637336730957,
+      "eval_runtime": 13.1276,
+      "eval_samples_per_second": 76.176,
+      "eval_steps_per_second": 2.438,
+      "step": 1600
+    },
+    {
+      "epoch": 0.47203547418109,
+      "grad_norm": 1.2836506785865125,
+      "learning_rate": 9.966333261209625e-06,
+      "loss": 1.8886,
+      "step": 1650
+    },
+    {
+      "epoch": 0.48633957945930484,
+      "grad_norm": 1.2135189666496888,
+      "learning_rate": 9.96379665773858e-06,
+      "loss": 1.8866,
+      "step": 1700
+    },
+    {
+      "epoch": 0.5006436847375196,
+      "grad_norm": 1.274525834510866,
+      "learning_rate": 9.961168318872583e-06,
+      "loss": 1.8786,
+      "step": 1750
+    },
+    {
+      "epoch": 0.5149477900157345,
+      "grad_norm": 1.3030666538156304,
+      "learning_rate": 9.958448298626576e-06,
+      "loss": 1.8803,
+      "step": 1800
+    },
+    {
+      "epoch": 0.5292518952939493,
+      "grad_norm": 1.9481826276041598,
+      "learning_rate": 9.95563665289964e-06,
+      "loss": 1.8661,
+      "step": 1850
+    },
+    {
+      "epoch": 0.5435560005721642,
+      "grad_norm": 1.184161907280642,
+      "learning_rate": 9.952733439473847e-06,
+      "loss": 1.8717,
+      "step": 1900
+    },
+    {
+      "epoch": 0.557860105850379,
+      "grad_norm": 2.035585736840807,
+      "learning_rate": 9.94973871801308e-06,
+      "loss": 1.8696,
+      "step": 1950
+    },
+    {
+      "epoch": 0.572164211128594,
+      "grad_norm": 1.0097164190087617,
+      "learning_rate": 9.946652550061798e-06,
+      "loss": 1.8525,
+      "step": 2000
+    },
+    {
+      "epoch": 0.572164211128594,
+      "eval_loss": 1.8354862928390503,
+      "eval_runtime": 13.0943,
+      "eval_samples_per_second": 76.369,
+      "eval_steps_per_second": 2.444,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5864683164068087,
+      "grad_norm": 2.0497282273050517,
+      "learning_rate": 9.943474999043775e-06,
+      "loss": 1.8572,
+      "step": 2050
+    },
+    {
+      "epoch": 0.6007724216850236,
+      "grad_norm": 1.4485387654596187,
+      "learning_rate": 9.9402061302608e-06,
+      "loss": 1.8557,
+      "step": 2100
+    },
+    {
+      "epoch": 0.6150765269632384,
+      "grad_norm": 1.4726888297829959,
+      "learning_rate": 9.93684601089133e-06,
+      "loss": 1.8476,
+      "step": 2150
+    },
+    {
+      "epoch": 0.6293806322414532,
+      "grad_norm": 1.2546088847317722,
+      "learning_rate": 9.933394709989109e-06,
+      "loss": 1.8535,
+      "step": 2200
+    },
+    {
+      "epoch": 0.6436847375196681,
+      "grad_norm": 1.442306090060256,
+      "learning_rate": 9.92985229848175e-06,
+      "loss": 1.8383,
+      "step": 2250
+    },
+    {
+      "epoch": 0.657988842797883,
+      "grad_norm": 1.3986536095496256,
+      "learning_rate": 9.926218849169284e-06,
+      "loss": 1.8468,
+      "step": 2300
+    },
+    {
+      "epoch": 0.6722929480760979,
+      "grad_norm": 1.3568137487712886,
+      "learning_rate": 9.922494436722653e-06,
+      "loss": 1.8376,
+      "step": 2350
+    },
+    {
+      "epoch": 0.6865970533543126,
+      "grad_norm": 1.2996414194536055,
+      "learning_rate": 9.91867913768218e-06,
+      "loss": 1.8272,
+      "step": 2400
+    },
+    {
+      "epoch": 0.6865970533543126,
+      "eval_loss": 1.8150951862335205,
+      "eval_runtime": 13.1089,
+      "eval_samples_per_second": 76.284,
+      "eval_steps_per_second": 2.441,
+      "step": 2400
+    },
+    {
+      "epoch": 0.7009011586325276,
+      "grad_norm": 1.2871997517148228,
+      "learning_rate": 9.914773030456001e-06,
+      "loss": 1.8317,
+      "step": 2450
+    },
+    {
+      "epoch": 0.7152052639107424,
+      "grad_norm": 1.200976481369304,
+      "learning_rate": 9.910776195318448e-06,
+      "loss": 1.8392,
+      "step": 2500
+    },
+    {
+      "epoch": 0.7295093691889573,
+      "grad_norm": 1.4537260955148985,
+      "learning_rate": 9.906688714408396e-06,
+      "loss": 1.8414,
+      "step": 2550
+    },
+    {
+      "epoch": 0.743813474467172,
+      "grad_norm": 1.3619012866591573,
+      "learning_rate": 9.902510671727583e-06,
+      "loss": 1.8243,
+      "step": 2600
+    },
+    {
+      "epoch": 0.758117579745387,
+      "grad_norm": 1.468758050868889,
+      "learning_rate": 9.898242153138882e-06,
+      "loss": 1.8208,
+      "step": 2650
+    },
+    {
+      "epoch": 0.7724216850236018,
+      "grad_norm": 1.5941916432437884,
+      "learning_rate": 9.89388324636453e-06,
+      "loss": 1.8274,
+      "step": 2700
+    },
+    {
+      "epoch": 0.7867257903018167,
+      "grad_norm": 1.4358813545146656,
+      "learning_rate": 9.889434040984333e-06,
+      "loss": 1.815,
+      "step": 2750
+    },
+    {
+      "epoch": 0.8010298955800315,
+      "grad_norm": 1.0044194890872669,
+      "learning_rate": 9.88489462843382e-06,
+      "loss": 1.8204,
+      "step": 2800
+    },
+    {
+      "epoch": 0.8010298955800315,
+      "eval_loss": 1.7972140312194824,
+      "eval_runtime": 13.1016,
+      "eval_samples_per_second": 76.326,
+      "eval_steps_per_second": 2.442,
+      "step": 2800
+    },
+    {
+      "epoch": 0.8153340008582464,
+      "grad_norm": 1.0780986139085367,
+      "learning_rate": 9.880265102002369e-06,
+      "loss": 1.8027,
+      "step": 2850
+    },
+    {
+      "epoch": 0.8296381061364612,
+      "grad_norm": 0.7267417717678716,
+      "learning_rate": 9.875545556831283e-06,
+      "loss": 1.8156,
+      "step": 2900
+    },
+    {
+      "epoch": 0.843942211414676,
+      "grad_norm": 1.1249209768789774,
+      "learning_rate": 9.870736089911836e-06,
+      "loss": 1.8149,
+      "step": 2950
+    },
+    {
+      "epoch": 0.8582463166928909,
+      "grad_norm": 1.183808055306546,
+      "learning_rate": 9.865836800083291e-06,
+      "loss": 1.8158,
+      "step": 3000
+    },
+    {
+      "epoch": 0.8725504219711057,
+      "grad_norm": 0.9727019343602256,
+      "learning_rate": 9.860847788030852e-06,
+      "loss": 1.8101,
+      "step": 3050
+    },
+    {
+      "epoch": 0.8868545272493206,
+      "grad_norm": 1.229205403976205,
+      "learning_rate": 9.855769156283604e-06,
+      "loss": 1.8122,
+      "step": 3100
+    },
+    {
+      "epoch": 0.9011586325275354,
+      "grad_norm": 1.2130780208525513,
+      "learning_rate": 9.850601009212408e-06,
+      "loss": 1.8064,
+      "step": 3150
+    },
+    {
+      "epoch": 0.9154627378057503,
+      "grad_norm": 1.093239130702269,
+      "learning_rate": 9.845343453027747e-06,
+      "loss": 1.8103,
+      "step": 3200
+    },
+    {
+      "epoch": 0.9154627378057503,
+      "eval_loss": 1.7855333089828491,
+      "eval_runtime": 13.1799,
+      "eval_samples_per_second": 75.873,
+      "eval_steps_per_second": 2.428,
+      "step": 3200
+    },
+    {
+      "epoch": 0.9297668430839651,
+      "grad_norm": 1.0418651496232376,
+      "learning_rate": 9.839996595777552e-06,
+      "loss": 1.8023,
+      "step": 3250
+    },
+    {
+      "epoch": 0.94407094836218,
+      "grad_norm": 1.2712498822645788,
+      "learning_rate": 9.83456054734498e-06,
+      "loss": 1.7953,
+      "step": 3300
+    },
+    {
+      "epoch": 0.9583750536403948,
+      "grad_norm": 0.984132611369419,
+      "learning_rate": 9.829035419446156e-06,
+      "loss": 1.8015,
+      "step": 3350
+    },
+    {
+      "epoch": 0.9726791589186097,
+      "grad_norm": 1.0418825994644219,
+      "learning_rate": 9.823421325627865e-06,
+      "loss": 1.8054,
+      "step": 3400
+    },
+    {
+      "epoch": 0.9869832641968245,
+      "grad_norm": 1.336436926729505,
+      "learning_rate": 9.81771838126524e-06,
+      "loss": 1.7937,
+      "step": 3450
+    },
+    {
+      "epoch": 1.0012873694750393,
+      "grad_norm": 1.0819159062735473,
+      "learning_rate": 9.811926703559374e-06,
+      "loss": 1.7868,
+      "step": 3500
+    },
+    {
+      "epoch": 1.0155914747532542,
+      "grad_norm": 1.2714689918837065,
+      "learning_rate": 9.806046411534916e-06,
+      "loss": 1.7731,
+      "step": 3550
+    },
+    {
+      "epoch": 1.029895580031469,
+      "grad_norm": 1.0129411367063064,
+      "learning_rate": 9.800077626037633e-06,
+      "loss": 1.7834,
+      "step": 3600
+    },
+    {
+      "epoch": 1.029895580031469,
+      "eval_loss": 1.7756215333938599,
+      "eval_runtime": 13.1841,
+      "eval_samples_per_second": 75.849,
+      "eval_steps_per_second": 2.427,
+      "step": 3600
+    },
+    {
+      "epoch": 1.044199685309684,
+      "grad_norm": 0.8678146485976415,
+      "learning_rate": 9.794020469731915e-06,
+      "loss": 1.7858,
+      "step": 3650
+    },
+    {
+      "epoch": 1.0585037905878987,
+      "grad_norm": 1.1072231200441955,
+      "learning_rate": 9.787875067098257e-06,
+      "loss": 1.7873,
+      "step": 3700
+    },
+    {
+      "epoch": 1.0728078958661136,
+      "grad_norm": 0.8959989844152632,
+      "learning_rate": 9.781641544430703e-06,
+      "loss": 1.7928,
+      "step": 3750
+    },
+    {
+      "epoch": 1.0871120011443285,
+      "grad_norm": 1.6994487358359982,
+      "learning_rate": 9.775320029834255e-06,
+      "loss": 1.7729,
+      "step": 3800
+    },
+    {
+      "epoch": 1.1014161064225432,
+      "grad_norm": 1.1169687397960077,
+      "learning_rate": 9.76891065322223e-06,
+      "loss": 1.7814,
+      "step": 3850
+    },
+    {
+      "epoch": 1.115720211700758,
+      "grad_norm": 1.0104167054836963,
+      "learning_rate": 9.762413546313597e-06,
+      "loss": 1.7783,
+      "step": 3900
+    },
+    {
+      "epoch": 1.130024316978973,
+      "grad_norm": 0.8241889545988433,
+      "learning_rate": 9.755828842630269e-06,
+      "loss": 1.7716,
+      "step": 3950
+    },
+    {
+      "epoch": 1.144328422257188,
+      "grad_norm": 1.0453927825295828,
+      "learning_rate": 9.749156677494357e-06,
+      "loss": 1.787,
+      "step": 4000
+    },
+    {
+      "epoch": 1.144328422257188,
+      "eval_loss": 1.7660154104232788,
+      "eval_runtime": 13.0607,
+      "eval_samples_per_second": 76.566,
+      "eval_steps_per_second": 2.45,
+      "step": 4000
+    },
+    {
+      "epoch": 1.1586325275354026,
+      "grad_norm": 1.5781005025322197,
+      "learning_rate": 9.742397188025394e-06,
+      "loss": 1.777,
+      "step": 4050
+    },
+    {
+      "epoch": 1.1729366328136175,
+      "grad_norm": 0.6663813498785218,
+      "learning_rate": 9.735550513137513e-06,
+      "loss": 1.7627,
+      "step": 4100
+    },
+    {
+      "epoch": 1.1872407380918324,
+      "grad_norm": 1.16263114208236,
+      "learning_rate": 9.728616793536588e-06,
+      "loss": 1.7706,
+      "step": 4150
+    },
+    {
+      "epoch": 1.2015448433700473,
+      "grad_norm": 0.8049406818849929,
+      "learning_rate": 9.721596171717352e-06,
+      "loss": 1.7732,
+      "step": 4200
+    },
+    {
+      "epoch": 1.215848948648262,
+      "grad_norm": 1.1897294605157323,
+      "learning_rate": 9.714488791960463e-06,
+      "loss": 1.7785,
+      "step": 4250
+    },
+    {
+      "epoch": 1.230153053926477,
+      "grad_norm": 0.7890939227616143,
+      "learning_rate": 9.707294800329536e-06,
+      "loss": 1.7743,
+      "step": 4300
+    },
+    {
+      "epoch": 1.2444571592046918,
+      "grad_norm": 1.0535327717977379,
+      "learning_rate": 9.700014344668152e-06,
+      "loss": 1.7655,
+      "step": 4350
+    },
+    {
+      "epoch": 1.2587612644829065,
+      "grad_norm": 1.0253301557877903,
+      "learning_rate": 9.692647574596803e-06,
+      "loss": 1.7695,
+      "step": 4400
+    },
+    {
+      "epoch": 1.2587612644829065,
+      "eval_loss": 1.7592908143997192,
+      "eval_runtime": 13.0236,
+      "eval_samples_per_second": 76.784,
+      "eval_steps_per_second": 2.457,
+      "step": 4400
+    },
+    {
+      "epoch": 1.2730653697611214,
+      "grad_norm": 1.1457150793499635,
+      "learning_rate": 9.685194641509837e-06,
+      "loss": 1.7741,
+      "step": 4450
+    },
+    {
+      "epoch": 1.2873694750393363,
+      "grad_norm": 1.1289748771161727,
+      "learning_rate": 9.677655698572326e-06,
+      "loss": 1.7613,
+      "step": 4500
+    },
+    {
+      "epoch": 1.3016735803175512,
+      "grad_norm": 1.2805821960586556,
+      "learning_rate": 9.670030900716941e-06,
+      "loss": 1.7608,
+      "step": 4550
+    },
+    {
+      "epoch": 1.3159776855957661,
+      "grad_norm": 1.116003748141364,
+      "learning_rate": 9.662320404640743e-06,
+      "loss": 1.7623,
+      "step": 4600
+    },
+    {
+      "epoch": 1.3302817908739808,
+      "grad_norm": 0.915054519499902,
+      "learning_rate": 9.654524368801982e-06,
+      "loss": 1.7684,
+      "step": 4650
+    },
+    {
+      "epoch": 1.3445858961521957,
+      "grad_norm": 1.158670382611452,
+      "learning_rate": 9.646642953416835e-06,
+      "loss": 1.7587,
+      "step": 4700
+    },
+    {
+      "epoch": 1.3588900014304106,
+      "grad_norm": 0.6334518545999203,
+      "learning_rate": 9.638676320456109e-06,
+      "loss": 1.7666,
+      "step": 4750
+    },
+    {
+      "epoch": 1.3731941067086253,
+      "grad_norm": 0.7291754825374577,
+      "learning_rate": 9.630624633641918e-06,
+      "loss": 1.759,
+      "step": 4800
+    },
+    {
+      "epoch": 1.3731941067086253,
+      "eval_loss": 1.7522927522659302,
+      "eval_runtime": 13.0698,
+      "eval_samples_per_second": 76.512,
+      "eval_steps_per_second": 2.448,
+      "step": 4800
+    },
+    {
+      "epoch": 1.3874982119868402,
+      "grad_norm": 0.8676602094607595,
+      "learning_rate": 9.622488058444313e-06,
+      "loss": 1.7585,
+      "step": 4850
+    },
+    {
+      "epoch": 1.401802317265055,
+      "grad_norm": 0.6268701284946427,
+      "learning_rate": 9.614266762077891e-06,
+      "loss": 1.758,
+      "step": 4900
+    },
+    {
+      "epoch": 1.4161064225432698,
+      "grad_norm": 0.7954138791876184,
+      "learning_rate": 9.605960913498342e-06,
+      "loss": 1.7528,
+      "step": 4950
+    },
+    {
+      "epoch": 1.4304105278214847,
+      "grad_norm": 0.9805674870268231,
+      "learning_rate": 9.597570683398996e-06,
+      "loss": 1.7652,
+      "step": 5000
+    },
+    {
+      "epoch": 1.4447146330996996,
+      "grad_norm": 1.2416998933826209,
+      "learning_rate": 9.5890962442073e-06,
+      "loss": 1.7497,
+      "step": 5050
+    },
+    {
+      "epoch": 1.4590187383779145,
+      "grad_norm": 0.9438154318623259,
+      "learning_rate": 9.580537770081285e-06,
+      "loss": 1.7486,
+      "step": 5100
+    },
+    {
+      "epoch": 1.4733228436561294,
+      "grad_norm": 0.7575703670207814,
+      "learning_rate": 9.57189543690598e-06,
+      "loss": 1.7557,
+      "step": 5150
+    },
+    {
+      "epoch": 1.487626948934344,
+      "grad_norm": 0.8709256334977673,
+      "learning_rate": 9.563169422289798e-06,
+      "loss": 1.7493,
+      "step": 5200
+    },
+    {
+      "epoch": 1.487626948934344,
+      "eval_loss": 1.746894359588623,
+      "eval_runtime": 13.0332,
+      "eval_samples_per_second": 76.727,
+      "eval_steps_per_second": 2.455,
+      "step": 5200
+    },
+    {
+      "epoch": 1.501931054212559,
+      "grad_norm": 0.990313135807005,
+      "learning_rate": 9.554359905560887e-06,
+      "loss": 1.7526,
+      "step": 5250
+    },
+    {
+      "epoch": 1.516235159490774,
+      "grad_norm": 1.3585589462134218,
+      "learning_rate": 9.54546706776345e-06,
+      "loss": 1.7477,
+      "step": 5300
+    },
+    {
+      "epoch": 1.5305392647689886,
+      "grad_norm": 1.0080284138615836,
+      "learning_rate": 9.536491091654018e-06,
+      "loss": 1.7398,
+      "step": 5350
+    },
+    {
+      "epoch": 1.5448433700472035,
+      "grad_norm": 0.6122020478330652,
+      "learning_rate": 9.527432161697696e-06,
+      "loss": 1.7556,
+      "step": 5400
+    },
+    {
+      "epoch": 1.5591474753254184,
+      "grad_norm": 0.8555908841043908,
+      "learning_rate": 9.518290464064365e-06,
+      "loss": 1.7402,
+      "step": 5450
+    },
+    {
+      "epoch": 1.573451580603633,
+      "grad_norm": 0.7605282500535738,
+      "learning_rate": 9.509066186624872e-06,
+      "loss": 1.7433,
+      "step": 5500
+    },
+    {
+      "epoch": 1.5877556858818482,
+      "grad_norm": 0.7684854850117561,
+      "learning_rate": 9.499759518947156e-06,
+      "loss": 1.7447,
+      "step": 5550
+    },
+    {
+      "epoch": 1.602059791160063,
+      "grad_norm": 1.2011176682075966,
+      "learning_rate": 9.490370652292357e-06,
+      "loss": 1.7461,
+      "step": 5600
+    },
+    {
+      "epoch": 1.602059791160063,
+      "eval_loss": 1.7409335374832153,
+      "eval_runtime": 13.0714,
+      "eval_samples_per_second": 76.503,
+      "eval_steps_per_second": 2.448,
+      "step": 5600
+    },
+    {
+      "epoch": 1.6163638964382778,
+      "grad_norm": 0.9371628453607871,
+      "learning_rate": 9.480899779610883e-06,
+      "loss": 1.7541,
+      "step": 5650
+    },
+    {
+      "epoch": 1.6306680017164927,
+      "grad_norm": 0.7143343954612081,
+      "learning_rate": 9.471347095538448e-06,
+      "loss": 1.7392,
+      "step": 5700
+    },
+    {
+      "epoch": 1.6449721069947074,
+      "grad_norm": 0.9557461607608252,
+      "learning_rate": 9.461712796392067e-06,
+      "loss": 1.7476,
+      "step": 5750
+    },
+    {
+      "epoch": 1.6592762122729223,
+      "grad_norm": 0.9598758061093912,
+      "learning_rate": 9.45199708016603e-06,
+      "loss": 1.747,
+      "step": 5800
+    },
+    {
+      "epoch": 1.6735803175511372,
+      "grad_norm": 1.1359595669153315,
+      "learning_rate": 9.442200146527824e-06,
+      "loss": 1.7379,
+      "step": 5850
+    },
+    {
+      "epoch": 1.687884422829352,
+      "grad_norm": 0.7961067517193703,
+      "learning_rate": 9.432322196814032e-06,
+      "loss": 1.7371,
+      "step": 5900
+    },
+    {
+      "epoch": 1.7021885281075668,
+      "grad_norm": 0.9958451010134263,
+      "learning_rate": 9.422363434026205e-06,
+      "loss": 1.7404,
+      "step": 5950
+    },
+    {
+      "epoch": 1.7164926333857817,
+      "grad_norm": 0.9090957659949102,
+      "learning_rate": 9.41232406282667e-06,
+      "loss": 1.7392,
+      "step": 6000
+    },
+    {
+      "epoch": 1.7164926333857817,
+      "eval_loss": 1.7344313859939575,
+      "eval_runtime": 13.0691,
+      "eval_samples_per_second": 76.516,
+      "eval_steps_per_second": 2.449,
+      "step": 6000
+    },
+    {
+      "epoch": 1.7307967386639964,
+      "grad_norm": 1.1213090245292214,
+      "learning_rate": 9.402204289534344e-06,
+      "loss": 1.7302,
+      "step": 6050
+    },
+    {
+      "epoch": 1.7451008439422115,
+      "grad_norm": 0.8031846181876277,
+      "learning_rate": 9.392004322120484e-06,
+      "loss": 1.734,
+      "step": 6100
+    },
+    {
+      "epoch": 1.7594049492204262,
+      "grad_norm": 0.8951992445159495,
+      "learning_rate": 9.381724370204414e-06,
+      "loss": 1.7271,
+      "step": 6150
+    },
+    {
+      "epoch": 1.7737090544986411,
+      "grad_norm": 0.6356844624225287,
+      "learning_rate": 9.371364645049216e-06,
+      "loss": 1.7343,
+      "step": 6200
+    },
+    {
+      "epoch": 1.788013159776856,
+      "grad_norm": 0.9354771107489174,
+      "learning_rate": 9.360925359557397e-06,
+      "loss": 1.7213,
+      "step": 6250
+    },
+    {
+      "epoch": 1.8023172650550707,
+      "grad_norm": 0.8683866672638255,
+      "learning_rate": 9.3504067282665e-06,
+      "loss": 1.7456,
+      "step": 6300
+    },
+    {
+      "epoch": 1.8166213703332856,
+      "grad_norm": 0.7256479046632077,
+      "learning_rate": 9.339808967344701e-06,
+      "loss": 1.7334,
+      "step": 6350
+    },
+    {
+      "epoch": 1.8309254756115005,
+      "grad_norm": 0.9100891545758867,
+      "learning_rate": 9.329132294586374e-06,
+      "loss": 1.7305,
+      "step": 6400
+    },
+    {
+      "epoch": 1.8309254756115005,
+      "eval_loss": 1.7306665182113647,
+      "eval_runtime": 13.0681,
+      "eval_samples_per_second": 76.522,
+      "eval_steps_per_second": 2.449,
+      "step": 6400
+    },
+    {
+      "epoch": 1.8452295808897152,
+      "grad_norm": 0.7131708711024103,
+      "learning_rate": 9.318376929407606e-06,
+      "loss": 1.7262,
+      "step": 6450
+    },
+    {
+      "epoch": 1.8595336861679304,
+      "grad_norm": 0.6762253904995256,
+      "learning_rate": 9.307543092841688e-06,
+      "loss": 1.7263,
+      "step": 6500
+    },
+    {
+      "epoch": 1.873837791446145,
+      "grad_norm": 0.8848356010504166,
+      "learning_rate": 9.296631007534576e-06,
+      "loss": 1.7291,
+      "step": 6550
+    },
+    {
+      "epoch": 1.8881418967243597,
+      "grad_norm": 0.8254328432524617,
+      "learning_rate": 9.285640897740316e-06,
+      "loss": 1.7248,
+      "step": 6600
+    },
+    {
+      "epoch": 1.9024460020025749,
+      "grad_norm": 0.8328557115282507,
+      "learning_rate": 9.27457298931643e-06,
+      "loss": 1.7379,
+      "step": 6650
+    },
+    {
+      "epoch": 1.9167501072807895,
+      "grad_norm": 0.6959225186429033,
+      "learning_rate": 9.263427509719287e-06,
+      "loss": 1.7217,
+      "step": 6700
+    },
+    {
+      "epoch": 1.9310542125590044,
+      "grad_norm": 0.7948142001263543,
+      "learning_rate": 9.252204687999401e-06,
+      "loss": 1.7348,
+      "step": 6750
+    },
+    {
+      "epoch": 1.9453583178372194,
+      "grad_norm": 0.9097813983094877,
+      "learning_rate": 9.240904754796767e-06,
+      "loss": 1.7323,
+      "step": 6800
+    },
+    {
+      "epoch": 1.9453583178372194,
+      "eval_loss": 1.7259055376052856,
+      "eval_runtime": 13.0454,
+      "eval_samples_per_second": 76.656,
+      "eval_steps_per_second": 2.453,
+      "step": 6800
+    },
+    {
+      "epoch": 1.959662423115434,
+      "grad_norm": 0.9853743080642359,
+      "learning_rate": 9.22952794233608e-06,
+      "loss": 1.7367,
+      "step": 6850
+    },
+    {
+      "epoch": 1.973966528393649,
+      "grad_norm": 0.7062853621991527,
+      "learning_rate": 9.218074484421977e-06,
+      "loss": 1.7222,
+      "step": 6900
+    },
+    {
+      "epoch": 1.9882706336718639,
+      "grad_norm": 0.7105578463978743,
+      "learning_rate": 9.206544616434249e-06,
+      "loss": 1.7214,
+      "step": 6950
+    },
+    {
+      "epoch": 2.0025747389500785,
+      "grad_norm": 0.9464929135027466,
+      "learning_rate": 9.194938575322973e-06,
+      "loss": 1.7175,
+      "step": 7000
+    },
+    {
+      "epoch": 2.0168788442282937,
+      "grad_norm": 0.7023281633842239,
+      "learning_rate": 9.183256599603672e-06,
+      "loss": 1.7088,
+      "step": 7050
+    },
+    {
+      "epoch": 2.0311829495065084,
+      "grad_norm": 0.6102272480325144,
+      "learning_rate": 9.171498929352388e-06,
+      "loss": 1.7067,
+      "step": 7100
+    },
+    {
+      "epoch": 2.045487054784723,
+      "grad_norm": 0.855210847731902,
+      "learning_rate": 9.159665806200766e-06,
+      "loss": 1.7069,
+      "step": 7150
+    },
+    {
+      "epoch": 2.059791160062938,
+      "grad_norm": 0.6906731860604268,
+      "learning_rate": 9.147757473331082e-06,
+      "loss": 1.7066,
+      "step": 7200
+    },
+    {
+      "epoch": 2.059791160062938,
+      "eval_loss": 1.722530722618103,
+      "eval_runtime": 13.0737,
+      "eval_samples_per_second": 76.489,
+      "eval_steps_per_second": 2.448,
+      "step": 7200
+    },
+    {
+      "epoch": 2.074095265341153,
+      "grad_norm": 1.0171875730793354,
+      "learning_rate": 9.135774175471244e-06,
+      "loss": 1.7112,
+      "step": 7250
+    },
+    {
+      "epoch": 2.088399370619368,
+      "grad_norm": 0.718919260784006,
+      "learning_rate": 9.123716158889765e-06,
+      "loss": 1.6947,
+      "step": 7300
+    },
+    {
+      "epoch": 2.1027034758975827,
+      "grad_norm": 0.8725712344270407,
+      "learning_rate": 9.111583671390697e-06,
+      "loss": 1.6921,
+      "step": 7350
+    },
+    {
+      "epoch": 2.1170075811757973,
+      "grad_norm": 0.9117880050064536,
+      "learning_rate": 9.09937696230855e-06,
+      "loss": 1.7062,
+      "step": 7400
+    },
+    {
+      "epoch": 2.1313116864540125,
+      "grad_norm": 0.816392919836334,
+      "learning_rate": 9.087096282503152e-06,
+      "loss": 1.6993,
+      "step": 7450
+    },
+    {
+      "epoch": 2.145615791732227,
+      "grad_norm": 0.7035389418244336,
+      "learning_rate": 9.074741884354507e-06,
+      "loss": 1.7022,
+      "step": 7500
+    },
+    {
+      "epoch": 2.159919897010442,
+      "grad_norm": 0.7867250841208043,
+      "learning_rate": 9.062314021757603e-06,
+      "loss": 1.7022,
+      "step": 7550
+    },
+    {
+      "epoch": 2.174224002288657,
+      "grad_norm": 0.5829241671744307,
+      "learning_rate": 9.049812950117191e-06,
+      "loss": 1.6875,
+      "step": 7600
+    },
+    {
+      "epoch": 2.174224002288657,
+      "eval_loss": 1.7198066711425781,
+      "eval_runtime": 13.1757,
+      "eval_samples_per_second": 75.897,
+      "eval_steps_per_second": 2.429,
+      "step": 7600
+    },
+    {
+      "epoch": 2.1885281075668717,
+      "grad_norm": 1.1249011702012237,
+      "learning_rate": 9.037238926342544e-06,
+      "loss": 1.7058,
+      "step": 7650
+    },
+    {
+      "epoch": 2.2028322128450863,
+      "grad_norm": 1.004023688704636,
+      "learning_rate": 9.02459220884217e-06,
+      "loss": 1.6977,
+      "step": 7700
+    },
+    {
+      "epoch": 2.2171363181233015,
+      "grad_norm": 0.9785901369627025,
+      "learning_rate": 9.011873057518503e-06,
+      "loss": 1.7067,
+      "step": 7750
+    },
+    {
+      "epoch": 2.231440423401516,
+      "grad_norm": 0.7641084413348023,
+      "learning_rate": 8.999081733762568e-06,
+      "loss": 1.7038,
+      "step": 7800
+    },
+    {
+      "epoch": 2.2457445286797313,
+      "grad_norm": 0.7283443537665686,
+      "learning_rate": 8.986218500448598e-06,
+      "loss": 1.713,
+      "step": 7850
+    },
+    {
+      "epoch": 2.260048633957946,
+      "grad_norm": 0.9539540219253599,
+      "learning_rate": 8.973283621928644e-06,
+      "loss": 1.706,
+      "step": 7900
+    },
+    {
+      "epoch": 2.2743527392361607,
+      "grad_norm": 0.8106080829599567,
+      "learning_rate": 8.96027736402713e-06,
+      "loss": 1.6958,
+      "step": 7950
+    },
+    {
+      "epoch": 2.288656844514376,
+      "grad_norm": 0.8882476907898474,
+      "learning_rate": 8.947199994035402e-06,
+      "loss": 1.6901,
+      "step": 8000
+    },
+    {
+      "epoch": 2.288656844514376,
+      "eval_loss": 1.7156543731689453,
+      "eval_runtime": 13.0298,
+      "eval_samples_per_second": 76.747,
+      "eval_steps_per_second": 2.456,
+      "step": 8000
+    },
+    {
+      "epoch": 2.3029609497925905,
+      "grad_norm": 0.9762766790404122,
+      "learning_rate": 8.934051780706226e-06,
+      "loss": 1.6917,
+      "step": 8050
+    },
+    {
+      "epoch": 2.317265055070805,
+      "grad_norm": 0.6971489481173876,
+      "learning_rate": 8.920832994248268e-06,
+      "loss": 1.6994,
+      "step": 8100
+    },
+    {
+      "epoch": 2.3315691603490203,
+      "grad_norm": 0.5820566152621507,
+      "learning_rate": 8.907543906320542e-06,
+      "loss": 1.7065,
+      "step": 8150
+    },
+    {
+      "epoch": 2.345873265627235,
+      "grad_norm": 0.645459754550139,
+      "learning_rate": 8.894184790026823e-06,
+      "loss": 1.6908,
+      "step": 8200
+    },
+    {
+      "epoch": 2.3601773709054497,
+      "grad_norm": 1.0593884241082467,
+      "learning_rate": 8.880755919910048e-06,
+      "loss": 1.692,
+      "step": 8250
+    },
+    {
+      "epoch": 2.374481476183665,
+      "grad_norm": 0.6598732077733668,
+      "learning_rate": 8.867257571946646e-06,
+      "loss": 1.7046,
+      "step": 8300
+    },
+    {
+      "epoch": 2.3887855814618795,
+      "grad_norm": 0.8135828323323933,
+      "learning_rate": 8.853690023540898e-06,
+      "loss": 1.6983,
+      "step": 8350
+    },
+    {
+      "epoch": 2.4030896867400946,
+      "grad_norm": 0.6292103166156576,
+      "learning_rate": 8.840053553519216e-06,
+      "loss": 1.6911,
+      "step": 8400
+    },
+    {
+      "epoch": 2.4030896867400946,
+      "eval_loss": 1.7090901136398315,
+      "eval_runtime": 13.0474,
+      "eval_samples_per_second": 76.644,
+      "eval_steps_per_second": 2.453,
+      "step": 8400
+    },
+    {
+      "epoch": 2.4173937920183093,
+      "grad_norm": 0.8817911559963482,
+      "learning_rate": 8.82634844212442e-06,
+      "loss": 1.6933,
+      "step": 8450
+    },
+    {
+      "epoch": 2.431697897296524,
+      "grad_norm": 0.7934805421221099,
+      "learning_rate": 8.81257497100998e-06,
+      "loss": 1.6895,
+      "step": 8500
+    },
+    {
+      "epoch": 2.446002002574739,
+      "grad_norm": 0.855182243732375,
+      "learning_rate": 8.79873342323422e-06,
+      "loss": 1.6945,
+      "step": 8550
+    },
+    {
+      "epoch": 2.460306107852954,
+      "grad_norm": 0.6125900217722975,
+      "learning_rate": 8.78482408325451e-06,
+      "loss": 1.6906,
+      "step": 8600
+    },
+    {
+      "epoch": 2.4746102131311685,
+      "grad_norm": 0.6660364707065795,
+      "learning_rate": 8.770847236921412e-06,
+      "loss": 1.6922,
+      "step": 8650
+    },
+    {
+      "epoch": 2.4889143184093836,
+      "grad_norm": 0.7819064185488933,
+      "learning_rate": 8.756803171472817e-06,
+      "loss": 1.6927,
+      "step": 8700
+    },
+    {
+      "epoch": 2.5032184236875983,
+      "grad_norm": 0.6307439119404958,
+      "learning_rate": 8.742692175528027e-06,
+      "loss": 1.6989,
+      "step": 8750
+    },
+    {
+      "epoch": 2.517522528965813,
+      "grad_norm": 0.6293488618510799,
+      "learning_rate": 8.728514539081837e-06,
+      "loss": 1.6837,
+      "step": 8800
+    },
+    {
+      "epoch": 2.517522528965813,
+      "eval_loss": 1.7051697969436646,
+      "eval_runtime": 13.0509,
+      "eval_samples_per_second": 76.623,
+      "eval_steps_per_second": 2.452,
+      "step": 8800
+    },
+    {
+      "epoch": 2.531826634244028,
+      "grad_norm": 0.7311550336703251,
+      "learning_rate": 8.714270553498567e-06,
+      "loss": 1.6836,
+      "step": 8850
+    },
+    {
+      "epoch": 2.546130739522243,
+      "grad_norm": 0.560283624336398,
+      "learning_rate": 8.699960511506077e-06,
+      "loss": 1.6977,
+      "step": 8900
+    },
+    {
+      "epoch": 2.560434844800458,
+      "grad_norm": 0.6106667827565102,
+      "learning_rate": 8.685584707189749e-06,
+      "loss": 1.6904,
+      "step": 8950
+    },
+    {
+      "epoch": 2.5747389500786726,
+      "grad_norm": 0.7552955271738838,
+      "learning_rate": 8.671143435986447e-06,
+      "loss": 1.69,
+      "step": 9000
+    },
+    {
+      "epoch": 2.5890430553568873,
+      "grad_norm": 0.6855807066717469,
+      "learning_rate": 8.656636994678447e-06,
+      "loss": 1.6995,
+      "step": 9050
+    },
+    {
+      "epoch": 2.6033471606351024,
+      "grad_norm": 0.8814483730904599,
+      "learning_rate": 8.642065681387329e-06,
+      "loss": 1.6919,
+      "step": 9100
+    },
+    {
+      "epoch": 2.617651265913317,
+      "grad_norm": 0.6710277536844194,
+      "learning_rate": 8.627429795567858e-06,
+      "loss": 1.6862,
+      "step": 9150
+    },
+    {
+      "epoch": 2.6319553711915322,
+      "grad_norm": 0.887320880133999,
+      "learning_rate": 8.61272963800183e-06,
+      "loss": 1.6859,
+      "step": 9200
+    },
+    {
+      "epoch": 2.6319553711915322,
+      "eval_loss": 1.7010042667388916,
+      "eval_runtime": 13.0596,
+      "eval_samples_per_second": 76.572,
+      "eval_steps_per_second": 2.45,
+      "step": 9200
+    },
+    {
+      "epoch": 2.646259476469747,
+      "grad_norm": 0.6062615724604773,
+      "learning_rate": 8.597965510791883e-06,
+      "loss": 1.6957,
+      "step": 9250
+    },
+    {
+      "epoch": 2.6605635817479616,
+      "grad_norm": 0.9356074049979478,
+      "learning_rate": 8.5831377173553e-06,
+      "loss": 1.6811,
+      "step": 9300
+    },
+    {
+      "epoch": 2.6748676870261763,
+      "grad_norm": 0.905579588189196,
+      "learning_rate": 8.568246562417762e-06,
+      "loss": 1.6879,
+      "step": 9350
+    },
+    {
+      "epoch": 2.6891717923043914,
+      "grad_norm": 0.7739005916322703,
+      "learning_rate": 8.553292352007096e-06,
+      "loss": 1.6879,
+      "step": 9400
+    },
+    {
+      "epoch": 2.703475897582606,
+      "grad_norm": 0.8473371714356891,
+      "learning_rate": 8.538275393446976e-06,
+      "loss": 1.6907,
+      "step": 9450
+    },
+    {
+      "epoch": 2.717780002860821,
+      "grad_norm": 0.6586208831165219,
+      "learning_rate": 8.523195995350613e-06,
+      "loss": 1.6886,
+      "step": 9500
+    },
+    {
+      "epoch": 2.732084108139036,
+      "grad_norm": 0.827548888966318,
+      "learning_rate": 8.508054467614417e-06,
+      "loss": 1.6855,
+      "step": 9550
+    },
+    {
+      "epoch": 2.7463882134172506,
+      "grad_norm": 0.702203100476128,
+      "learning_rate": 8.492851121411614e-06,
+      "loss": 1.6832,
+      "step": 9600
+    },
+    {
+      "epoch": 2.7463882134172506,
+      "eval_loss": 1.6964640617370605,
+      "eval_runtime": 13.1004,
+      "eval_samples_per_second": 76.334,
+      "eval_steps_per_second": 2.443,
+      "step": 9600
+    },
+    {
+      "epoch": 2.7606923186954657,
+      "grad_norm": 0.7172738684998019,
+      "learning_rate": 8.477586269185868e-06,
+      "loss": 1.6824,
+      "step": 9650
+    },
+    {
+      "epoch": 2.7749964239736804,
+      "grad_norm": 0.6634870837445137,
+      "learning_rate": 8.462260224644848e-06,
+      "loss": 1.6821,
+      "step": 9700
+    },
+    {
+      "epoch": 2.7893005292518955,
+      "grad_norm": 0.6916121607750829,
+      "learning_rate": 8.446873302753783e-06,
+      "loss": 1.6909,
+      "step": 9750
+    },
+    {
+      "epoch": 2.80360463453011,
+      "grad_norm": 0.7324116907371762,
+      "learning_rate": 8.431425819728998e-06,
+      "loss": 1.6909,
+      "step": 9800
+    },
+    {
+      "epoch": 2.817908739808325,
+      "grad_norm": 0.6843560320392789,
+      "learning_rate": 8.415918093031403e-06,
+      "loss": 1.6786,
+      "step": 9850
+    },
+    {
+      "epoch": 2.8322128450865396,
+      "grad_norm": 0.752892823321002,
+      "learning_rate": 8.400350441359976e-06,
+      "loss": 1.6728,
+      "step": 9900
+    },
+    {
+      "epoch": 2.8465169503647547,
+      "grad_norm": 0.9700342755779745,
+      "learning_rate": 8.384723184645211e-06,
+      "loss": 1.6783,
+      "step": 9950
+    },
+    {
+      "epoch": 2.8608210556429694,
+      "grad_norm": 0.7767564698368711,
+      "learning_rate": 8.369036644042546e-06,
+      "loss": 1.6675,
+      "step": 10000
+    },
+    {
+      "epoch": 2.8608210556429694,
+      "eval_loss": 1.693839192390442,
+      "eval_runtime": 13.0504,
+      "eval_samples_per_second": 76.626,
+      "eval_steps_per_second": 2.452,
+      "step": 10000
+    },
+    {
+      "epoch": 2.8751251609211845,
+      "grad_norm": 0.6772095075860332,
+      "learning_rate": 8.353291141925763e-06,
+      "loss": 1.6721,
+      "step": 10050
+    },
+    {
+      "epoch": 2.889429266199399,
+      "grad_norm": 0.6382340661083454,
+      "learning_rate": 8.337487001880353e-06,
+      "loss": 1.6842,
+      "step": 10100
+    },
+    {
+      "epoch": 2.903733371477614,
+      "grad_norm": 0.7870530454186793,
+      "learning_rate": 8.32162454869688e-06,
+      "loss": 1.6764,
+      "step": 10150
+    },
+    {
+      "epoch": 2.918037476755829,
+      "grad_norm": 0.7725000837437397,
+      "learning_rate": 8.305704108364301e-06,
+      "loss": 1.6795,
+      "step": 10200
+    },
+    {
+      "epoch": 2.9323415820340437,
+      "grad_norm": 0.6068764021560474,
+      "learning_rate": 8.289726008063265e-06,
+      "loss": 1.6783,
+      "step": 10250
+    },
+    {
+      "epoch": 2.946645687312259,
+      "grad_norm": 0.9395553539153366,
+      "learning_rate": 8.273690576159383e-06,
+      "loss": 1.68,
+      "step": 10300
+    },
+    {
+      "epoch": 2.9609497925904735,
+      "grad_norm": 0.7531796928086886,
+      "learning_rate": 8.257598142196496e-06,
+      "loss": 1.6669,
+      "step": 10350
+    },
+    {
+      "epoch": 2.975253897868688,
+      "grad_norm": 0.6247104825883635,
+      "learning_rate": 8.241449036889892e-06,
+      "loss": 1.6718,
+      "step": 10400
+    },
+    {
+      "epoch": 2.975253897868688,
+      "eval_loss": 1.6905415058135986,
+      "eval_runtime": 13.0826,
+      "eval_samples_per_second": 76.438,
+      "eval_steps_per_second": 2.446,
+      "step": 10400
+    },
+    {
+      "epoch": 2.989558003146903,
+      "grad_norm": 0.546997508440891,
+      "learning_rate": 8.225243592119501e-06,
+      "loss": 1.6805,
+      "step": 10450
+    },
+    {
+      "epoch": 3.003862108425118,
+      "grad_norm": 0.7776889636138464,
+      "learning_rate": 8.208982140923095e-06,
+      "loss": 1.6707,
+      "step": 10500
+    },
+    {
+      "epoch": 3.0181662137033327,
+      "grad_norm": 0.7998275166017301,
+      "learning_rate": 8.192665017489431e-06,
+      "loss": 1.6397,
+      "step": 10550
+    },
+    {
+      "epoch": 3.032470318981548,
+      "grad_norm": 0.7459803419055197,
+      "learning_rate": 8.17629255715138e-06,
+      "loss": 1.6611,
+      "step": 10600
+    },
+    {
+      "epoch": 3.0467744242597625,
+      "grad_norm": 0.6817944157156409,
+      "learning_rate": 8.159865096379046e-06,
+      "loss": 1.6375,
+      "step": 10650
+    },
+    {
+      "epoch": 3.061078529537977,
+      "grad_norm": 0.6959338742861377,
+      "learning_rate": 8.14338297277284e-06,
+      "loss": 1.6392,
+      "step": 10700
+    },
+    {
+      "epoch": 3.0753826348161923,
+      "grad_norm": 0.7388183617279478,
+      "learning_rate": 8.126846525056555e-06,
+      "loss": 1.6424,
+      "step": 10750
+    },
+    {
+      "epoch": 3.089686740094407,
+      "grad_norm": 0.6981074857483759,
+      "learning_rate": 8.110256093070393e-06,
+      "loss": 1.6592,
+      "step": 10800
+    },
+    {
+      "epoch": 3.089686740094407,
+      "eval_loss": 1.6885778903961182,
+      "eval_runtime": 13.0832,
+      "eval_samples_per_second": 76.434,
+      "eval_steps_per_second": 2.446,
+      "step": 10800
+    },
+    {
+      "epoch": 3.103990845372622,
+      "grad_norm": 0.7805391928889925,
+      "learning_rate": 8.093612017763986e-06,
+      "loss": 1.6437,
+      "step": 10850
+    },
+    {
+      "epoch": 3.118294950650837,
+      "grad_norm": 0.7246045663324853,
+      "learning_rate": 8.076914641189388e-06,
+      "loss": 1.6557,
+      "step": 10900
+    },
+    {
+      "epoch": 3.1325990559290515,
+      "grad_norm": 0.7387863523438669,
+      "learning_rate": 8.060164306494052e-06,
+      "loss": 1.6397,
+      "step": 10950
+    },
+    {
+      "epoch": 3.1469031612072667,
+      "grad_norm": 0.6210712373332249,
+      "learning_rate": 8.043361357913763e-06,
+      "loss": 1.6413,
+      "step": 11000
+    },
+    {
+      "epoch": 3.1612072664854813,
+      "grad_norm": 0.9802329165310913,
+      "learning_rate": 8.026506140765581e-06,
+      "loss": 1.6453,
+      "step": 11050
+    },
+    {
+      "epoch": 3.175511371763696,
+      "grad_norm": 0.6431933255522037,
+      "learning_rate": 8.009599001440733e-06,
+      "loss": 1.6499,
+      "step": 11100
+    },
+    {
+      "epoch": 3.189815477041911,
+      "grad_norm": 0.6689757471837987,
+      "learning_rate": 7.992640287397498e-06,
+      "loss": 1.6464,
+      "step": 11150
+    },
+    {
+      "epoch": 3.204119582320126,
+      "grad_norm": 0.5745449183320485,
+      "learning_rate": 7.975630347154062e-06,
+      "loss": 1.6458,
+      "step": 11200
+    },
+    {
+      "epoch": 3.204119582320126,
+      "eval_loss": 1.68647038936615,
+      "eval_runtime": 13.0514,
+      "eval_samples_per_second": 76.62,
+      "eval_steps_per_second": 2.452,
+      "step": 11200
+    },
+    {
+      "epoch": 3.2184236875983405,
+      "grad_norm": 0.7776825101072233,
+      "learning_rate": 7.958569530281369e-06,
+      "loss": 1.6423,
+      "step": 11250
+    },
+    {
+      "epoch": 3.2327277928765557,
+      "grad_norm": 0.7074657527331386,
+      "learning_rate": 7.941458187395918e-06,
+      "loss": 1.6402,
+      "step": 11300
+    },
+    {
+      "epoch": 3.2470318981547703,
+      "grad_norm": 0.6882685901776942,
+      "learning_rate": 7.924296670152573e-06,
+      "loss": 1.6413,
+      "step": 11350
+    },
+    {
+      "epoch": 3.2613360034329855,
+      "grad_norm": 0.7352534174047116,
+      "learning_rate": 7.907085331237328e-06,
+      "loss": 1.6535,
+      "step": 11400
+    },
+    {
+      "epoch": 3.2756401087112,
+      "grad_norm": 0.6752564589976222,
+      "learning_rate": 7.889824524360058e-06,
+      "loss": 1.6502,
+      "step": 11450
+    },
+    {
+      "epoch": 3.289944213989415,
+      "grad_norm": 0.7781753735420677,
+      "learning_rate": 7.872514604247261e-06,
+      "loss": 1.6503,
+      "step": 11500
+    },
+    {
+      "epoch": 3.30424831926763,
+      "grad_norm": 0.7069554958978874,
+      "learning_rate": 7.855155926634755e-06,
+      "loss": 1.6521,
+      "step": 11550
+    },
+    {
+      "epoch": 3.3185524245458446,
+      "grad_norm": 0.8017576198027669,
+      "learning_rate": 7.837748848260372e-06,
+      "loss": 1.6518,
+      "step": 11600
+    },
+    {
+      "epoch": 3.3185524245458446,
+      "eval_loss": 1.6823465824127197,
+      "eval_runtime": 13.0525,
+      "eval_samples_per_second": 76.614,
+      "eval_steps_per_second": 2.452,
+      "step": 11600
+    },
+    {
+      "epoch": 3.3328565298240593,
+      "grad_norm": 0.7088855521224748,
+      "learning_rate": 7.820293726856625e-06,
+      "loss": 1.6422,
+      "step": 11650
+    },
+    {
+      "epoch": 3.3471606351022745,
+      "grad_norm": 0.6674161498231996,
+      "learning_rate": 7.802790921143367e-06,
+      "loss": 1.6477,
+      "step": 11700
+    },
+    {
+      "epoch": 3.361464740380489,
+      "grad_norm": 0.7617355475219582,
+      "learning_rate": 7.785240790820403e-06,
+      "loss": 1.6424,
+      "step": 11750
+    },
+    {
+      "epoch": 3.375768845658704,
+      "grad_norm": 0.5922876479830514,
+      "learning_rate": 7.767643696560103e-06,
+      "loss": 1.6286,
+      "step": 11800
+    },
+    {
+      "epoch": 3.390072950936919,
+      "grad_norm": 0.6014516421402848,
+      "learning_rate": 7.75e-06,
+      "loss": 1.6507,
+      "step": 11850
+    },
+    {
+      "epoch": 3.4043770562151336,
+      "grad_norm": 0.623953970052767,
+      "learning_rate": 7.732310063735346e-06,
+      "loss": 1.6348,
+      "step": 11900
+    },
+    {
+      "epoch": 3.4186811614933488,
+      "grad_norm": 0.8360426729514715,
+      "learning_rate": 7.71457425131166e-06,
+      "loss": 1.6276,
+      "step": 11950
+    },
+    {
+      "epoch": 3.4329852667715635,
+      "grad_norm": 0.6464266491022174,
+      "learning_rate": 7.696792927217266e-06,
+      "loss": 1.6391,
+      "step": 12000
+    },
+    {
+      "epoch": 3.4329852667715635,
+      "eval_loss": 1.678931474685669,
+      "eval_runtime": 13.0631,
+      "eval_samples_per_second": 76.551,
+      "eval_steps_per_second": 2.45,
+      "step": 12000
+    },
+    {
+      "epoch": 3.447289372049778,
+      "grad_norm": 0.6126546460094165,
+      "learning_rate": 7.6789664568758e-06,
+      "loss": 1.6287,
+      "step": 12050
+    },
+    {
+      "epoch": 3.4615934773279933,
+      "grad_norm": 0.5960230832976515,
+      "learning_rate": 7.661095206638688e-06,
+      "loss": 1.6433,
+      "step": 12100
+    },
+    {
+      "epoch": 3.475897582606208,
+      "grad_norm": 0.6761717944619002,
+      "learning_rate": 7.643179543777636e-06,
+      "loss": 1.649,
+      "step": 12150
+    },
+    {
+      "epoch": 3.4902016878844226,
+      "grad_norm": 0.9634933236219494,
+      "learning_rate": 7.625219836477073e-06,
+      "loss": 1.6417,
+      "step": 12200
+    },
+    {
+      "epoch": 3.5045057931626378,
+      "grad_norm": 0.7034969394806604,
+      "learning_rate": 7.607216453826575e-06,
+      "loss": 1.6393,
+      "step": 12250
+    },
+    {
+      "epoch": 3.5188098984408525,
+      "grad_norm": 0.6731018596913478,
+      "learning_rate": 7.589169765813298e-06,
+      "loss": 1.647,
+      "step": 12300
+    },
+    {
+      "epoch": 3.533114003719067,
+      "grad_norm": 0.6118854498537465,
+      "learning_rate": 7.571080143314362e-06,
+      "loss": 1.6309,
+      "step": 12350
+    },
+    {
+      "epoch": 3.5474181089972823,
+      "grad_norm": 0.5833382042357486,
+      "learning_rate": 7.552947958089234e-06,
+      "loss": 1.6261,
+      "step": 12400
+    },
+    {
+      "epoch": 3.5474181089972823,
+      "eval_loss": 1.6743122339248657,
+      "eval_runtime": 13.0457,
+      "eval_samples_per_second": 76.653,
+      "eval_steps_per_second": 2.453,
+      "step": 12400
+    },
+    {
+      "epoch": 3.561722214275497,
+      "grad_norm": 0.6661614205378471,
+      "learning_rate": 7.534773582772087e-06,
+      "loss": 1.6351,
+      "step": 12450
+    },
+    {
+      "epoch": 3.576026319553712,
+      "grad_norm": 0.714289109336214,
+      "learning_rate": 7.51655739086414e-06,
+      "loss": 1.6422,
+      "step": 12500
+    },
+    {
+      "epoch": 3.5903304248319268,
+      "grad_norm": 0.6101362453032799,
+      "learning_rate": 7.498299756725984e-06,
+      "loss": 1.6447,
+      "step": 12550
+    },
+    {
+      "epoch": 3.6046345301101415,
+      "grad_norm": 0.5358085065496345,
+      "learning_rate": 7.480001055569892e-06,
+      "loss": 1.6356,
+      "step": 12600
+    },
+    {
+      "epoch": 3.6189386353883566,
+      "grad_norm": 0.5759734399751635,
+      "learning_rate": 7.4616616634521e-06,
+      "loss": 1.64,
+      "step": 12650
+    },
+    {
+      "epoch": 3.6332427406665713,
+      "grad_norm": 0.7053847123624982,
+      "learning_rate": 7.443281957265086e-06,
+      "loss": 1.6335,
+      "step": 12700
+    },
+    {
+      "epoch": 3.6475468459447864,
+      "grad_norm": 0.6269316120083251,
+      "learning_rate": 7.424862314729819e-06,
+      "loss": 1.6359,
+      "step": 12750
+    },
+    {
+      "epoch": 3.661850951223001,
+      "grad_norm": 0.7414178784729023,
+      "learning_rate": 7.406403114388003e-06,
+      "loss": 1.6344,
+      "step": 12800
+    },
+    {
+      "epoch": 3.661850951223001,
+      "eval_loss": 1.67084538936615,
+      "eval_runtime": 13.0507,
+      "eval_samples_per_second": 76.624,
+      "eval_steps_per_second": 2.452,
+      "step": 12800
+    },
+    {
+      "epoch": 3.6761550565012158,
+      "grad_norm": 0.739429421422803,
+      "learning_rate": 7.387904735594291e-06,
+      "loss": 1.6338,
+      "step": 12850
+    },
+    {
+      "epoch": 3.6904591617794305,
+      "grad_norm": 0.6194546733603346,
+      "learning_rate": 7.36936755850849e-06,
+      "loss": 1.644,
+      "step": 12900
+    },
+    {
+      "epoch": 3.7047632670576456,
+      "grad_norm": 0.5969848608399483,
+      "learning_rate": 7.3507919640877535e-06,
+      "loss": 1.64,
+      "step": 12950
+    },
+    {
+      "epoch": 3.7190673723358603,
+      "grad_norm": 0.6934857883840727,
+      "learning_rate": 7.332178334078746e-06,
+      "loss": 1.6384,
+      "step": 13000
+    },
+    {
+      "epoch": 3.7333714776140754,
+      "grad_norm": 0.635352435508875,
+      "learning_rate": 7.313527051009803e-06,
+      "loss": 1.6367,
+      "step": 13050
+    },
+    {
+      "epoch": 3.74767558289229,
+      "grad_norm": 0.6676277653287923,
+      "learning_rate": 7.2948384981830655e-06,
+      "loss": 1.6332,
+      "step": 13100
+    },
+    {
+      "epoch": 3.7619796881705048,
+      "grad_norm": 0.5981093667238178,
+      "learning_rate": 7.2761130596666045e-06,
+      "loss": 1.6243,
+      "step": 13150
+    },
+    {
+      "epoch": 3.77628379344872,
+      "grad_norm": 0.6546784259139526,
+      "learning_rate": 7.25735112028653e-06,
+      "loss": 1.6331,
+      "step": 13200
+    },
+    {
+      "epoch": 3.77628379344872,
+      "eval_loss": 1.6657731533050537,
+      "eval_runtime": 13.0681,
+      "eval_samples_per_second": 76.522,
+      "eval_steps_per_second": 2.449,
+      "step": 13200
+    },
+    {
+      "epoch": 3.7905878987269346,
+      "grad_norm": 1.1022867143082844,
+      "learning_rate": 7.2385530656190785e-06,
+      "loss": 1.6221,
+      "step": 13250
+    },
+    {
+      "epoch": 3.8048920040051497,
+      "grad_norm": 0.7046788263112277,
+      "learning_rate": 7.219719281982694e-06,
+      "loss": 1.6263,
+      "step": 13300
+    },
+    {
+      "epoch": 3.8191961092833644,
+      "grad_norm": 0.7089454605909015,
+      "learning_rate": 7.20085015643008e-06,
+      "loss": 1.6245,
+      "step": 13350
+    },
+    {
+      "epoch": 3.833500214561579,
+      "grad_norm": 0.7801822159411739,
+      "learning_rate": 7.181946076740257e-06,
+      "loss": 1.6231,
+      "step": 13400
+    },
+    {
+      "epoch": 3.8478043198397938,
+      "grad_norm": 0.6644382304711074,
+      "learning_rate": 7.163007431410583e-06,
+      "loss": 1.632,
+      "step": 13450
+    },
+    {
+      "epoch": 3.862108425118009,
+      "grad_norm": 0.7162696862257913,
+      "learning_rate": 7.144034609648779e-06,
+      "loss": 1.6379,
+      "step": 13500
+    },
+    {
+      "epoch": 3.8764125303962236,
+      "grad_norm": 0.66835417830248,
+      "learning_rate": 7.125028001364918e-06,
+      "loss": 1.6265,
+      "step": 13550
+    },
+    {
+      "epoch": 3.8907166356744387,
+      "grad_norm": 0.8073668698442618,
+      "learning_rate": 7.105987997163424e-06,
+      "loss": 1.6305,
+      "step": 13600
+    },
+    {
+      "epoch": 3.8907166356744387,
+      "eval_loss": 1.6642513275146484,
+      "eval_runtime": 13.0315,
+      "eval_samples_per_second": 76.737,
+      "eval_steps_per_second": 2.456,
+      "step": 13600
+    },
+    {
+      "epoch": 3.9050207409526534,
+      "grad_norm": 0.8129075896081209,
+      "learning_rate": 7.086914988335039e-06,
+      "loss": 1.6334,
+      "step": 13650
+    },
+    {
+      "epoch": 3.919324846230868,
+      "grad_norm": 0.6722996060245693,
+      "learning_rate": 7.0678093668487836e-06,
+      "loss": 1.6378,
+      "step": 13700
+    },
+    {
+      "epoch": 3.933628951509083,
+      "grad_norm": 0.6234556338573759,
+      "learning_rate": 7.048671525343898e-06,
+      "loss": 1.6157,
+      "step": 13750
+    },
+    {
+      "epoch": 3.947933056787298,
+      "grad_norm": 0.674127005602253,
+      "learning_rate": 7.029501857121776e-06,
+      "loss": 1.6237,
+      "step": 13800
+    },
+    {
+      "epoch": 3.962237162065513,
+      "grad_norm": 0.6848190186027889,
+      "learning_rate": 7.010300756137882e-06,
+      "loss": 1.6167,
+      "step": 13850
+    },
+    {
+      "epoch": 3.9765412673437277,
+      "grad_norm": 0.7866991878129077,
+      "learning_rate": 6.991068616993655e-06,
+      "loss": 1.6264,
+      "step": 13900
+    },
+    {
+      "epoch": 3.9908453726219424,
+      "grad_norm": 0.6764477676367477,
+      "learning_rate": 6.971805834928399e-06,
+      "loss": 1.6198,
+      "step": 13950
+    },
+    {
+      "epoch": 4.005149477900157,
+      "grad_norm": 0.561303007679291,
+      "learning_rate": 6.952512805811156e-06,
+      "loss": 1.6281,
+      "step": 14000
+    },
+    {
+      "epoch": 4.005149477900157,
+      "eval_loss": 1.6613872051239014,
+      "eval_runtime": 13.0547,
+      "eval_samples_per_second": 76.601,
+      "eval_steps_per_second": 2.451,
+      "step": 14000
+    },
+    {
+      "epoch": 4.019453583178372,
+      "grad_norm": 0.8593165537427608,
+      "learning_rate": 6.933189926132581e-06,
+      "loss": 1.5957,
+      "step": 14050
+    },
+    {
+      "epoch": 4.033757688456587,
+      "grad_norm": 0.7007147184136575,
+      "learning_rate": 6.913837592996783e-06,
+      "loss": 1.5881,
+      "step": 14100
+    },
+    {
+      "epoch": 4.048061793734802,
+      "grad_norm": 0.770003508592736,
+      "learning_rate": 6.894456204113167e-06,
+      "loss": 1.605,
+      "step": 14150
+    },
+    {
+      "epoch": 4.062365899013017,
+      "grad_norm": 0.6226702180817224,
+      "learning_rate": 6.875046157788267e-06,
+      "loss": 1.5911,
+      "step": 14200
+    },
+    {
+      "epoch": 4.076670004291231,
+      "grad_norm": 0.7639202802814479,
+      "learning_rate": 6.855607852917555e-06,
+      "loss": 1.604,
+      "step": 14250
+    },
+    {
+      "epoch": 4.090974109569446,
+      "grad_norm": 0.882721244152998,
+      "learning_rate": 6.836141688977238e-06,
+      "loss": 1.6012,
+      "step": 14300
+    },
+    {
+      "epoch": 4.105278214847662,
+      "grad_norm": 0.6636212731955713,
+      "learning_rate": 6.816648066016059e-06,
+      "loss": 1.6104,
+      "step": 14350
+    },
+    {
+      "epoch": 4.119582320125876,
+      "grad_norm": 0.600373299209649,
+      "learning_rate": 6.7971273846470696e-06,
+      "loss": 1.5809,
+      "step": 14400
+    },
+    {
+      "epoch": 4.119582320125876,
+      "eval_loss": 1.6590399742126465,
+      "eval_runtime": 13.0488,
+      "eval_samples_per_second": 76.635,
+      "eval_steps_per_second": 2.452,
+      "step": 14400
+    },
+    {
+      "epoch": 4.133886425404091,
+      "grad_norm": 0.5838739816681767,
+      "learning_rate": 6.777580046039399e-06,
+      "loss": 1.5936,
+      "step": 14450
+    },
+    {
+      "epoch": 4.148190530682306,
+      "grad_norm": 0.8054046294072329,
+      "learning_rate": 6.758006451910008e-06,
+      "loss": 1.5943,
+      "step": 14500
+    },
+    {
+      "epoch": 4.16249463596052,
+      "grad_norm": 0.6586960505758862,
+      "learning_rate": 6.738407004515434e-06,
+      "loss": 1.5972,
+      "step": 14550
+    },
+    {
+      "epoch": 4.176798741238736,
+      "grad_norm": 0.614285360390926,
+      "learning_rate": 6.718782106643524e-06,
+      "loss": 1.5987,
+      "step": 14600
+    },
+    {
+      "epoch": 4.191102846516951,
+      "grad_norm": 0.7672522315210418,
+      "learning_rate": 6.699132161605158e-06,
+      "loss": 1.5989,
+      "step": 14650
+    },
+    {
+      "epoch": 4.205406951795165,
+      "grad_norm": 0.6095862804856478,
+      "learning_rate": 6.679457573225961e-06,
+      "loss": 1.5927,
+      "step": 14700
+    },
+    {
+      "epoch": 4.21971105707338,
+      "grad_norm": 0.5725548623370728,
+      "learning_rate": 6.659758745837998e-06,
+      "loss": 1.5944,
+      "step": 14750
+    },
+    {
+      "epoch": 4.234015162351595,
+      "grad_norm": 0.6763995208415444,
+      "learning_rate": 6.640036084271477e-06,
+      "loss": 1.5856,
+      "step": 14800
+    },
+    {
+      "epoch": 4.234015162351595,
+      "eval_loss": 1.6558407545089722,
+      "eval_runtime": 13.0633,
+      "eval_samples_per_second": 76.55,
+      "eval_steps_per_second": 2.45,
+      "step": 14800
+    },
+    {
+      "epoch": 4.248319267629809,
+      "grad_norm": 0.5816921920934364,
+      "learning_rate": 6.620289993846416e-06,
+      "loss": 1.5894,
+      "step": 14850
+    },
+    {
+      "epoch": 4.262623372908025,
+      "grad_norm": 0.5963950247380321,
+      "learning_rate": 6.600520880364318e-06,
+      "loss": 1.5877,
+      "step": 14900
+    },
+    {
+      "epoch": 4.27692747818624,
+      "grad_norm": 0.7244641422220082,
+      "learning_rate": 6.5807291500998385e-06,
+      "loss": 1.5984,
+      "step": 14950
+    },
+    {
+      "epoch": 4.291231583464454,
+      "grad_norm": 0.6891578076550495,
+      "learning_rate": 6.560915209792424e-06,
+      "loss": 1.5811,
+      "step": 15000
+    },
+    {
+      "epoch": 4.305535688742669,
+      "grad_norm": 0.6285344026946775,
+      "learning_rate": 6.541079466637962e-06,
+      "loss": 1.5963,
+      "step": 15050
+    },
+    {
+      "epoch": 4.319839794020884,
+      "grad_norm": 0.6315690680101345,
+      "learning_rate": 6.52122232828041e-06,
+      "loss": 1.5957,
+      "step": 15100
+    },
+    {
+      "epoch": 4.334143899299098,
+      "grad_norm": 0.5748378429144894,
+      "learning_rate": 6.501344202803415e-06,
+      "loss": 1.5931,
+      "step": 15150
+    },
+    {
+      "epoch": 4.348448004577314,
+      "grad_norm": 0.7552352391145764,
+      "learning_rate": 6.4814454987219355e-06,
+      "loss": 1.5945,
+      "step": 15200
+    },
+    {
+      "epoch": 4.348448004577314,
+      "eval_loss": 1.6537083387374878,
+      "eval_runtime": 13.0367,
+      "eval_samples_per_second": 76.707,
+      "eval_steps_per_second": 2.455,
+      "step": 15200
+    },
+    {
+      "epoch": 4.362752109855529,
+      "grad_norm": 0.6302273947646538,
+      "learning_rate": 6.461526624973836e-06,
+      "loss": 1.5949,
+      "step": 15250
+    },
+    {
+      "epoch": 4.377056215133743,
+      "grad_norm": 0.7279773630417031,
+      "learning_rate": 6.441587990911489e-06,
+      "loss": 1.5955,
+      "step": 15300
+    },
+    {
+      "epoch": 4.391360320411958,
+      "grad_norm": 0.7564493394180175,
+      "learning_rate": 6.421630006293359e-06,
+      "loss": 1.5784,
+      "step": 15350
+    },
+    {
+      "epoch": 4.405664425690173,
+      "grad_norm": 0.6547475070066977,
+      "learning_rate": 6.401653081275586e-06,
+      "loss": 1.5815,
+      "step": 15400
+    },
+    {
+      "epoch": 4.419968530968388,
+      "grad_norm": 0.6231989802641532,
+      "learning_rate": 6.38165762640355e-06,
+      "loss": 1.5898,
+      "step": 15450
+    },
+    {
+      "epoch": 4.434272636246603,
+      "grad_norm": 0.6634320872185652,
+      "learning_rate": 6.361644052603445e-06,
+      "loss": 1.5857,
+      "step": 15500
+    },
+    {
+      "epoch": 4.448576741524818,
+      "grad_norm": 0.585640805907106,
+      "learning_rate": 6.341612771173817e-06,
+      "loss": 1.5944,
+      "step": 15550
+    },
+    {
+      "epoch": 4.462880846803032,
+      "grad_norm": 0.6816841693204327,
+      "learning_rate": 6.321564193777129e-06,
+      "loss": 1.5847,
+      "step": 15600
+    },
+    {
+      "epoch": 4.462880846803032,
+      "eval_loss": 1.6510008573532104,
+      "eval_runtime": 13.0513,
+      "eval_samples_per_second": 76.621,
+      "eval_steps_per_second": 2.452,
+      "step": 15600
+    },
+    {
+      "epoch": 4.477184952081247,
+      "grad_norm": 0.6053048902545912,
+      "learning_rate": 6.301498732431287e-06,
+      "loss": 1.595,
+      "step": 15650
+    },
+    {
+      "epoch": 4.491489057359463,
+      "grad_norm": 0.5846349328081588,
+      "learning_rate": 6.281416799501188e-06,
+      "loss": 1.5829,
+      "step": 15700
+    },
+    {
+      "epoch": 4.505793162637677,
+      "grad_norm": 0.6663370815014324,
+      "learning_rate": 6.261318807690223e-06,
+      "loss": 1.5913,
+      "step": 15750
+    },
+    {
+      "epoch": 4.520097267915892,
+      "grad_norm": 0.6707807397421404,
+      "learning_rate": 6.24120517003182e-06,
+      "loss": 1.5855,
+      "step": 15800
+    },
+    {
+      "epoch": 4.534401373194107,
+      "grad_norm": 0.6936942245291033,
+      "learning_rate": 6.221076299880939e-06,
+      "loss": 1.5836,
+      "step": 15850
+    },
+    {
+      "epoch": 4.548705478472321,
+      "grad_norm": 0.5972670709526067,
+      "learning_rate": 6.200932610905584e-06,
+      "loss": 1.5983,
+      "step": 15900
+    },
+    {
+      "epoch": 4.563009583750537,
+      "grad_norm": 0.7073631469228808,
+      "learning_rate": 6.180774517078301e-06,
+      "loss": 1.5801,
+      "step": 15950
+    },
+    {
+      "epoch": 4.577313689028752,
+      "grad_norm": 0.6700094336440139,
+      "learning_rate": 6.160602432667668e-06,
+      "loss": 1.5788,
+      "step": 16000
+    },
+    {
+      "epoch": 4.577313689028752,
+      "eval_loss": 1.6471811532974243,
+      "eval_runtime": 13.0567,
+      "eval_samples_per_second": 76.589,
+      "eval_steps_per_second": 2.451,
+      "step": 16000
+    },
+    {
+      "epoch": 4.591617794306966,
+      "grad_norm": 0.6135192274092318,
+      "learning_rate": 6.140416772229785e-06,
+      "loss": 1.59,
+      "step": 16050
+    },
+    {
+      "epoch": 4.605921899585181,
+      "grad_norm": 0.6341044144664583,
+      "learning_rate": 6.12021795059975e-06,
+      "loss": 1.5846,
+      "step": 16100
+    },
+    {
+      "epoch": 4.620226004863396,
+      "grad_norm": 0.724534964828596,
+      "learning_rate": 6.10000638288314e-06,
+      "loss": 1.59,
+      "step": 16150
+    },
+    {
+      "epoch": 4.63453011014161,
+      "grad_norm": 0.6113074334486132,
+      "learning_rate": 6.079782484447475e-06,
+      "loss": 1.575,
+      "step": 16200
+    },
+    {
+      "epoch": 4.648834215419825,
+      "grad_norm": 0.6386331564571069,
+      "learning_rate": 6.059546670913684e-06,
+      "loss": 1.5872,
+      "step": 16250
+    },
+    {
+      "epoch": 4.663138320698041,
+      "grad_norm": 0.7261941546202135,
+      "learning_rate": 6.03929935814756e-06,
+      "loss": 1.5784,
+      "step": 16300
+    },
+    {
+      "epoch": 4.677442425976255,
+      "grad_norm": 0.6351322658943287,
+      "learning_rate": 6.01904096225122e-06,
+      "loss": 1.5765,
+      "step": 16350
+    },
+    {
+      "epoch": 4.69174653125447,
+      "grad_norm": 0.5996478129830516,
+      "learning_rate": 5.998771899554551e-06,
+      "loss": 1.58,
+      "step": 16400
+    },
+    {
+      "epoch": 4.69174653125447,
+      "eval_loss": 1.6419577598571777,
+      "eval_runtime": 13.0531,
+      "eval_samples_per_second": 76.61,
+      "eval_steps_per_second": 2.452,
+      "step": 16400
+    },
+    {
+      "epoch": 4.706050636532685,
+      "grad_norm": 0.8110729150452963,
+      "learning_rate": 5.978492586606647e-06,
+      "loss": 1.5815,
+      "step": 16450
+    },
+    {
+      "epoch": 4.720354741810899,
+      "grad_norm": 0.7079172508860698,
+      "learning_rate": 5.958203440167261e-06,
+      "loss": 1.5735,
+      "step": 16500
+    },
+    {
+      "epoch": 4.734658847089115,
+      "grad_norm": 0.7437188489635005,
+      "learning_rate": 5.93790487719823e-06,
+      "loss": 1.5816,
+      "step": 16550
+    },
+    {
+      "epoch": 4.74896295236733,
+      "grad_norm": 0.6429721202094572,
+      "learning_rate": 5.917597314854914e-06,
+      "loss": 1.5735,
+      "step": 16600
+    },
+    {
+      "epoch": 4.763267057645544,
+      "grad_norm": 0.7341831677461502,
+      "learning_rate": 5.897281170477614e-06,
+      "loss": 1.5851,
+      "step": 16650
+    },
+    {
+      "epoch": 4.777571162923759,
+      "grad_norm": 0.6108465449546007,
+      "learning_rate": 5.876956861583007e-06,
+      "loss": 1.5671,
+      "step": 16700
+    },
+    {
+      "epoch": 4.791875268201974,
+      "grad_norm": 0.6989820941323435,
+      "learning_rate": 5.856624805855548e-06,
+      "loss": 1.5844,
+      "step": 16750
+    },
+    {
+      "epoch": 4.806179373480189,
+      "grad_norm": 0.697409967231527,
+      "learning_rate": 5.83628542113891e-06,
+      "loss": 1.5913,
+      "step": 16800
+    },
+    {
+      "epoch": 4.806179373480189,
+      "eval_loss": 1.640140175819397,
+      "eval_runtime": 13.0618,
+      "eval_samples_per_second": 76.559,
+      "eval_steps_per_second": 2.45,
+      "step": 16800
+    },
+    {
+      "epoch": 4.820483478758404,
+      "grad_norm": 0.7126977088350184,
+      "learning_rate": 5.815939125427373e-06,
+      "loss": 1.5789,
+      "step": 16850
+    },
+    {
+      "epoch": 4.834787584036619,
+      "grad_norm": 0.6711423839732361,
+      "learning_rate": 5.795586336857253e-06,
+      "loss": 1.569,
+      "step": 16900
+    },
+    {
+      "epoch": 4.849091689314833,
+      "grad_norm": 0.6873244551411083,
+      "learning_rate": 5.775227473698294e-06,
+      "loss": 1.5836,
+      "step": 16950
+    },
+    {
+      "epoch": 4.863395794593048,
+      "grad_norm": 0.6568926452793338,
+      "learning_rate": 5.754862954345081e-06,
+      "loss": 1.5768,
+      "step": 17000
+    },
+    {
+      "epoch": 4.8776998998712635,
+      "grad_norm": 0.6866802641183569,
+      "learning_rate": 5.734493197308442e-06,
+      "loss": 1.5818,
+      "step": 17050
+    },
+    {
+      "epoch": 4.892004005149478,
+      "grad_norm": 0.7569171940676707,
+      "learning_rate": 5.714118621206843e-06,
+      "loss": 1.5744,
+      "step": 17100
+    },
+    {
+      "epoch": 4.906308110427693,
+      "grad_norm": 0.7437917330435557,
+      "learning_rate": 5.693739644757781e-06,
+      "loss": 1.5871,
+      "step": 17150
+    },
+    {
+      "epoch": 4.920612215705908,
+      "grad_norm": 0.6919341126692011,
+      "learning_rate": 5.673356686769194e-06,
+      "loss": 1.5653,
+      "step": 17200
+    },
+    {
+      "epoch": 4.920612215705908,
+      "eval_loss": 1.637027382850647,
+      "eval_runtime": 13.0268,
+      "eval_samples_per_second": 76.765,
+      "eval_steps_per_second": 2.456,
+      "step": 17200
+    },
+    {
+      "epoch": 4.934916320984122,
+      "grad_norm": 0.7285248772831358,
+      "learning_rate": 5.6529701661308415e-06,
+      "loss": 1.5756,
+      "step": 17250
+    },
+    {
+      "epoch": 4.949220426262337,
+      "grad_norm": 0.8182466871622013,
+      "learning_rate": 5.632580501805692e-06,
+      "loss": 1.5798,
+      "step": 17300
+    },
+    {
+      "epoch": 4.9635245315405525,
+      "grad_norm": 0.6755432735906193,
+      "learning_rate": 5.612188112821328e-06,
+      "loss": 1.5854,
+      "step": 17350
+    },
+    {
+      "epoch": 4.977828636818767,
+      "grad_norm": 0.7612962134476555,
+      "learning_rate": 5.591793418261326e-06,
+      "loss": 1.5812,
+      "step": 17400
+    },
+    {
+      "epoch": 4.992132742096982,
+      "grad_norm": 0.7563925945387832,
+      "learning_rate": 5.571396837256637e-06,
+      "loss": 1.5806,
+      "step": 17450
+    },
+    {
+      "epoch": 5.006436847375197,
+      "grad_norm": 0.7029518743960665,
+      "learning_rate": 5.550998788976988e-06,
+      "loss": 1.5687,
+      "step": 17500
+    },
+    {
+      "epoch": 5.020740952653411,
+      "grad_norm": 0.7224515281262691,
+      "learning_rate": 5.530599692622257e-06,
+      "loss": 1.5522,
+      "step": 17550
+    },
+    {
+      "epoch": 5.035045057931626,
+      "grad_norm": 0.8254883333638792,
+      "learning_rate": 5.510199967413862e-06,
+      "loss": 1.5572,
+      "step": 17600
+    },
+    {
+      "epoch": 5.035045057931626,
+      "eval_loss": 1.63729989528656,
+      "eval_runtime": 13.0559,
+      "eval_samples_per_second": 76.594,
+      "eval_steps_per_second": 2.451,
+      "step": 17600
+    },
+    {
+      "epoch": 5.0493491632098415,
+      "grad_norm": 0.6284889071588916,
+      "learning_rate": 5.489800032586141e-06,
+      "loss": 1.5535,
+      "step": 17650
+    },
+    {
+      "epoch": 5.063653268488056,
+      "grad_norm": 0.6963650817698085,
+      "learning_rate": 5.4694003073777446e-06,
+      "loss": 1.5374,
+      "step": 17700
+    },
+    {
+      "epoch": 5.077957373766271,
+      "grad_norm": 0.6004647370129266,
+      "learning_rate": 5.449001211023014e-06,
+      "loss": 1.543,
+      "step": 17750
+    },
+    {
+      "epoch": 5.092261479044486,
+      "grad_norm": 0.6944143227347761,
+      "learning_rate": 5.428603162743365e-06,
+      "loss": 1.5583,
+      "step": 17800
+    },
+    {
+      "epoch": 5.1065655843227,
+      "grad_norm": 0.7245627077876122,
+      "learning_rate": 5.408206581738677e-06,
+      "loss": 1.5574,
+      "step": 17850
+    },
+    {
+      "epoch": 5.120869689600916,
+      "grad_norm": 0.7745536996539171,
+      "learning_rate": 5.387811887178673e-06,
+      "loss": 1.5496,
+      "step": 17900
+    },
+    {
+      "epoch": 5.1351737948791305,
+      "grad_norm": 0.7093989927463052,
+      "learning_rate": 5.367419498194309e-06,
+      "loss": 1.5381,
+      "step": 17950
+    },
+    {
+      "epoch": 5.149477900157345,
+      "grad_norm": 0.6956109502422128,
+      "learning_rate": 5.347029833869161e-06,
+      "loss": 1.5394,
+      "step": 18000
+    },
+    {
+      "epoch": 5.149477900157345,
+      "eval_loss": 1.6354469060897827,
+      "eval_runtime": 13.0565,
+      "eval_samples_per_second": 76.59,
+      "eval_steps_per_second": 2.451,
+      "step": 18000
+    },
+    {
+      "epoch": 5.16378200543556,
+      "grad_norm": 0.7605217226459633,
+      "learning_rate": 5.326643313230806e-06,
+      "loss": 1.5505,
+      "step": 18050
+    },
+    {
+      "epoch": 5.178086110713775,
+      "grad_norm": 0.6731289587679541,
+      "learning_rate": 5.306260355242221e-06,
+      "loss": 1.5441,
+      "step": 18100
+    },
+    {
+      "epoch": 5.19239021599199,
+      "grad_norm": 0.7738376161828003,
+      "learning_rate": 5.2858813787931605e-06,
+      "loss": 1.5488,
+      "step": 18150
+    },
+    {
+      "epoch": 5.206694321270205,
+      "grad_norm": 0.6448049532055088,
+      "learning_rate": 5.26550680269156e-06,
+      "loss": 1.5445,
+      "step": 18200
+    },
+    {
+      "epoch": 5.2209984265484195,
+      "grad_norm": 0.7299526472618546,
+      "learning_rate": 5.24513704565492e-06,
+      "loss": 1.5609,
+      "step": 18250
+    },
+    {
+      "epoch": 5.235302531826634,
+      "grad_norm": 0.5655434829319671,
+      "learning_rate": 5.224772526301709e-06,
+      "loss": 1.5415,
+      "step": 18300
+    },
+    {
+      "epoch": 5.249606637104849,
+      "grad_norm": 0.6828352502019638,
+      "learning_rate": 5.20441366314275e-06,
+      "loss": 1.551,
+      "step": 18350
+    },
+    {
+      "epoch": 5.263910742383064,
+      "grad_norm": 0.6899243489061619,
+      "learning_rate": 5.184060874572628e-06,
+      "loss": 1.5474,
+      "step": 18400
+    },
+    {
+      "epoch": 5.263910742383064,
+      "eval_loss": 1.6314454078674316,
+      "eval_runtime": 13.0795,
+      "eval_samples_per_second": 76.456,
+      "eval_steps_per_second": 2.447,
+      "step": 18400
+    },
+    {
+      "epoch": 5.278214847661279,
+      "grad_norm": 0.628576725087854,
+      "learning_rate": 5.163714578861091e-06,
+      "loss": 1.5486,
+      "step": 18450
+    },
+    {
+      "epoch": 5.292518952939494,
+      "grad_norm": 0.706107114608977,
+      "learning_rate": 5.143375194144452e-06,
+      "loss": 1.5479,
+      "step": 18500
+    },
+    {
+      "epoch": 5.3068230582177085,
+      "grad_norm": 0.6327910082547722,
+      "learning_rate": 5.123043138416996e-06,
+      "loss": 1.5391,
+      "step": 18550
+    },
+    {
+      "epoch": 5.321127163495923,
+      "grad_norm": 0.568499467391358,
+      "learning_rate": 5.102718829522387e-06,
+      "loss": 1.5509,
+      "step": 18600
+    },
+    {
+      "epoch": 5.335431268774138,
+      "grad_norm": 0.8702897561054348,
+      "learning_rate": 5.082402685145088e-06,
+      "loss": 1.5435,
+      "step": 18650
+    },
+    {
+      "epoch": 5.3497353740523526,
+      "grad_norm": 0.6355124491870009,
+      "learning_rate": 5.062095122801771e-06,
+      "loss": 1.5414,
+      "step": 18700
+    },
+    {
+      "epoch": 5.364039479330568,
+      "grad_norm": 0.6120850516489263,
+      "learning_rate": 5.041796559832742e-06,
+      "loss": 1.5407,
+      "step": 18750
+    },
+    {
+      "epoch": 5.378343584608783,
+      "grad_norm": 0.6006051140188372,
+      "learning_rate": 5.021507413393355e-06,
+      "loss": 1.5478,
+      "step": 18800
+    },
+    {
+      "epoch": 5.378343584608783,
+      "eval_loss": 1.6297167539596558,
+      "eval_runtime": 13.0407,
+      "eval_samples_per_second": 76.683,
+      "eval_steps_per_second": 2.454,
+      "step": 18800
+    },
+    {
+      "epoch": 5.3926476898869975,
+      "grad_norm": 0.7084773759381873,
+      "learning_rate": 5.001228100445451e-06,
+      "loss": 1.5424,
+      "step": 18850
+    },
+    {
+      "epoch": 5.406951795165212,
+      "grad_norm": 0.5971059413940708,
+      "learning_rate": 4.9809590377487795e-06,
+      "loss": 1.5314,
+      "step": 18900
+    },
+    {
+      "epoch": 5.421255900443427,
+      "grad_norm": 0.5962124201350092,
+      "learning_rate": 4.960700641852442e-06,
+      "loss": 1.5314,
+      "step": 18950
+    },
+    {
+      "epoch": 5.435560005721642,
+      "grad_norm": 0.6073154183244449,
+      "learning_rate": 4.9404533290863186e-06,
+      "loss": 1.5367,
+      "step": 19000
+    },
+    {
+      "epoch": 5.449864110999857,
+      "grad_norm": 0.6297680093724757,
+      "learning_rate": 4.920217515552526e-06,
+      "loss": 1.545,
+      "step": 19050
+    },
+    {
+      "epoch": 5.464168216278072,
+      "grad_norm": 0.749372754113139,
+      "learning_rate": 4.8999936171168615e-06,
+      "loss": 1.5492,
+      "step": 19100
+    },
+    {
+      "epoch": 5.4784723215562865,
+      "grad_norm": 0.682579385636617,
+      "learning_rate": 4.879782049400251e-06,
+      "loss": 1.5397,
+      "step": 19150
+    },
+    {
+      "epoch": 5.492776426834501,
+      "grad_norm": 0.6954586182506544,
+      "learning_rate": 4.8595832277702175e-06,
+      "loss": 1.5389,
+      "step": 19200
+    },
+    {
+      "epoch": 5.492776426834501,
+      "eval_loss": 1.6279715299606323,
+      "eval_runtime": 13.0459,
+      "eval_samples_per_second": 76.652,
+      "eval_steps_per_second": 2.453,
+      "step": 19200
+    },
+    {
+      "epoch": 5.507080532112717,
+      "grad_norm": 0.6469401414528775,
+      "learning_rate": 4.839397567332334e-06,
+      "loss": 1.5469,
+      "step": 19250
+    },
+    {
+      "epoch": 5.521384637390931,
+      "grad_norm": 0.636821133963489,
+      "learning_rate": 4.8192254829217e-06,
+      "loss": 1.5486,
+      "step": 19300
+    },
+    {
+      "epoch": 5.535688742669146,
+      "grad_norm": 0.610319715798064,
+      "learning_rate": 4.799067389094416e-06,
+      "loss": 1.5509,
+      "step": 19350
+    },
+    {
+      "epoch": 5.549992847947361,
+      "grad_norm": 0.650269389983184,
+      "learning_rate": 4.7789237001190624e-06,
+      "loss": 1.5358,
+      "step": 19400
+    },
+    {
+      "epoch": 5.5642969532255755,
+      "grad_norm": 0.6575088715253904,
+      "learning_rate": 4.758794829968181e-06,
+      "loss": 1.5407,
+      "step": 19450
+    },
+    {
+      "epoch": 5.578601058503791,
+      "grad_norm": 0.6355112107332087,
+      "learning_rate": 4.738681192309778e-06,
+      "loss": 1.5333,
+      "step": 19500
+    },
+    {
+      "epoch": 5.592905163782006,
+      "grad_norm": 0.6135031882811945,
+      "learning_rate": 4.718583200498814e-06,
+      "loss": 1.5439,
+      "step": 19550
+    },
+    {
+      "epoch": 5.60720926906022,
+      "grad_norm": 0.6378261785255617,
+      "learning_rate": 4.698501267568713e-06,
+      "loss": 1.5416,
+      "step": 19600
+    },
+    {
+      "epoch": 5.60720926906022,
+      "eval_loss": 1.625309944152832,
+      "eval_runtime": 13.0618,
+      "eval_samples_per_second": 76.559,
+      "eval_steps_per_second": 2.45,
+      "step": 19600
+    },
+    {
+      "epoch": 5.621513374338435,
+      "grad_norm": 0.5909607083593297,
+      "learning_rate": 4.678435806222873e-06,
+      "loss": 1.5382,
+      "step": 19650
+    },
+    {
+      "epoch": 5.63581747961665,
+      "grad_norm": 0.832324820293914,
+      "learning_rate": 4.658387228826185e-06,
+      "loss": 1.5296,
+      "step": 19700
+    },
+    {
+      "epoch": 5.6501215848948645,
+      "grad_norm": 0.6654181517394939,
+      "learning_rate": 4.638355947396557e-06,
+      "loss": 1.5365,
+      "step": 19750
+    },
+    {
+      "epoch": 5.664425690173079,
+      "grad_norm": 0.7104547419601024,
+      "learning_rate": 4.61834237359645e-06,
+      "loss": 1.5346,
+      "step": 19800
+    },
+    {
+      "epoch": 5.678729795451295,
+      "grad_norm": 0.633545438014888,
+      "learning_rate": 4.598346918724417e-06,
+      "loss": 1.5407,
+      "step": 19850
+    },
+    {
+      "epoch": 5.693033900729509,
+      "grad_norm": 0.5890661999938378,
+      "learning_rate": 4.578369993706643e-06,
+      "loss": 1.5373,
+      "step": 19900
+    },
+    {
+      "epoch": 5.707338006007724,
+      "grad_norm": 0.637951277031103,
+      "learning_rate": 4.5584120090885125e-06,
+      "loss": 1.5282,
+      "step": 19950
+    },
+    {
+      "epoch": 5.721642111285939,
+      "grad_norm": 0.6472843394713724,
+      "learning_rate": 4.538473375026164e-06,
+      "loss": 1.548,
+      "step": 20000
+    },
+    {
+      "epoch": 5.721642111285939,
+      "eval_loss": 1.6252117156982422,
+      "eval_runtime": 13.0484,
+      "eval_samples_per_second": 76.638,
+      "eval_steps_per_second": 2.452,
+      "step": 20000
+    },
+    {
+      "epoch": 5.7359462165641535,
+      "grad_norm": 0.6374488654344161,
+      "learning_rate": 4.518554501278064e-06,
+      "loss": 1.537,
+      "step": 20050
+    },
+    {
+      "epoch": 5.750250321842369,
+      "grad_norm": 0.7263690060852047,
+      "learning_rate": 4.498655797196586e-06,
+      "loss": 1.5381,
+      "step": 20100
+    },
+    {
+      "epoch": 5.764554427120584,
+      "grad_norm": 1.3376477550151467,
+      "learning_rate": 4.478777671719593e-06,
+      "loss": 1.5477,
+      "step": 20150
+    },
+    {
+      "epoch": 5.778858532398798,
+      "grad_norm": 0.76295043090899,
+      "learning_rate": 4.458920533362039e-06,
+      "loss": 1.53,
+      "step": 20200
+    },
+    {
+      "epoch": 5.793162637677013,
+      "grad_norm": 0.6797846613142751,
+      "learning_rate": 4.439084790207577e-06,
+      "loss": 1.5401,
+      "step": 20250
+    },
+    {
+      "epoch": 5.807466742955228,
+      "grad_norm": 0.6556861114177075,
+      "learning_rate": 4.419270849900164e-06,
+      "loss": 1.5426,
+      "step": 20300
+    },
+    {
+      "epoch": 5.821770848233443,
+      "grad_norm": 0.565436300232366,
+      "learning_rate": 4.399479119635683e-06,
+      "loss": 1.5389,
+      "step": 20350
+    },
+    {
+      "epoch": 5.836074953511658,
+      "grad_norm": 0.6159081983823488,
+      "learning_rate": 4.3797100061535856e-06,
+      "loss": 1.5311,
+      "step": 20400
+    },
+    {
+      "epoch": 5.836074953511658,
+      "eval_loss": 1.6201008558273315,
+      "eval_runtime": 13.0502,
+      "eval_samples_per_second": 76.627,
+      "eval_steps_per_second": 2.452,
+      "step": 20400
+    },
+    {
+      "epoch": 5.850379058789873,
+      "grad_norm": 0.6190309487124844,
+      "learning_rate": 4.359963915728523e-06,
+      "loss": 1.5325,
+      "step": 20450
+    },
+    {
+      "epoch": 5.864683164068087,
+      "grad_norm": 0.6611190737566248,
+      "learning_rate": 4.340241254162004e-06,
+      "loss": 1.5305,
+      "step": 20500
+    },
+    {
+      "epoch": 5.878987269346302,
+      "grad_norm": 0.6514457613600558,
+      "learning_rate": 4.320542426774042e-06,
+      "loss": 1.5336,
+      "step": 20550
+    },
+    {
+      "epoch": 5.893291374624518,
+      "grad_norm": 0.6924675673668805,
+      "learning_rate": 4.300867838394843e-06,
+      "loss": 1.5298,
+      "step": 20600
+    },
+    {
+      "epoch": 5.907595479902732,
+      "grad_norm": 0.6540592216580202,
+      "learning_rate": 4.281217893356478e-06,
+      "loss": 1.5485,
+      "step": 20650
+    },
+    {
+      "epoch": 5.921899585180947,
+      "grad_norm": 0.6264707853146376,
+      "learning_rate": 4.261592995484567e-06,
+      "loss": 1.5378,
+      "step": 20700
+    },
+    {
+      "epoch": 5.936203690459162,
+      "grad_norm": 0.6421715782621594,
+      "learning_rate": 4.241993548089994e-06,
+      "loss": 1.5413,
+      "step": 20750
+    },
+    {
+      "epoch": 5.950507795737376,
+      "grad_norm": 0.6578038881504726,
+      "learning_rate": 4.2224199539606026e-06,
+      "loss": 1.5194,
+      "step": 20800
+    },
+    {
+      "epoch": 5.950507795737376,
+      "eval_loss": 1.6188734769821167,
+      "eval_runtime": 13.0595,
+      "eval_samples_per_second": 76.573,
+      "eval_steps_per_second": 2.45,
+      "step": 20800
+    },
+    {
+      "epoch": 5.964811901015591,
+      "grad_norm": 0.6402919621847346,
+      "learning_rate": 4.202872615352932e-06,
+      "loss": 1.528,
+      "step": 20850
+    },
+    {
+      "epoch": 5.979116006293807,
+      "grad_norm": 0.742025387237335,
+      "learning_rate": 4.183351933983942e-06,
+      "loss": 1.5284,
+      "step": 20900
+    },
+    {
+      "epoch": 5.993420111572021,
+      "grad_norm": 0.6048884436986522,
+      "learning_rate": 4.163858311022765e-06,
+      "loss": 1.5451,
+      "step": 20950
+    },
+    {
+      "epoch": 6.007724216850236,
+      "grad_norm": 0.6289709056828559,
+      "learning_rate": 4.144392147082447e-06,
+      "loss": 1.5107,
+      "step": 21000
+    },
+    {
+      "epoch": 6.022028322128451,
+      "grad_norm": 0.6471758653277588,
+      "learning_rate": 4.124953842211733e-06,
+      "loss": 1.506,
+      "step": 21050
+    },
+    {
+      "epoch": 6.036332427406665,
+      "grad_norm": 0.6996218844366202,
+      "learning_rate": 4.105543795886834e-06,
+      "loss": 1.5067,
+      "step": 21100
+    },
+    {
+      "epoch": 6.050636532684881,
+      "grad_norm": 0.678635702735469,
+      "learning_rate": 4.086162407003219e-06,
+      "loss": 1.5057,
+      "step": 21150
+    },
+    {
+      "epoch": 6.064940637963096,
+      "grad_norm": 0.6494644257414226,
+      "learning_rate": 4.066810073867421e-06,
+      "loss": 1.5034,
+      "step": 21200
+    },
+    {
+      "epoch": 6.064940637963096,
+      "eval_loss": 1.6190376281738281,
+      "eval_runtime": 13.0287,
+      "eval_samples_per_second": 76.754,
+      "eval_steps_per_second": 2.456,
+      "step": 21200
+    },
+    {
+      "epoch": 6.07924474324131,
+      "grad_norm": 0.7186266557106407,
+      "learning_rate": 4.047487194188846e-06,
+      "loss": 1.5205,
+      "step": 21250
+    },
+    {
+      "epoch": 6.093548848519525,
+      "grad_norm": 0.6089706165419941,
+      "learning_rate": 4.028194165071603e-06,
+      "loss": 1.5129,
+      "step": 21300
+    },
+    {
+      "epoch": 6.10785295379774,
+      "grad_norm": 0.6175038547603215,
+      "learning_rate": 4.008931383006345e-06,
+      "loss": 1.5108,
+      "step": 21350
+    },
+    {
+      "epoch": 6.122157059075954,
+      "grad_norm": 0.6201507762475741,
+      "learning_rate": 3.9896992438621195e-06,
+      "loss": 1.506,
+      "step": 21400
+    },
+    {
+      "epoch": 6.13646116435417,
+      "grad_norm": 0.6913855915669275,
+      "learning_rate": 3.9704981428782255e-06,
+      "loss": 1.5136,
+      "step": 21450
+    },
+    {
+      "epoch": 6.150765269632385,
+      "grad_norm": 0.6974461674384657,
+      "learning_rate": 3.951328474656103e-06,
+      "loss": 1.4987,
+      "step": 21500
+    },
+    {
+      "epoch": 6.165069374910599,
+      "grad_norm": 0.7123196760206585,
+      "learning_rate": 3.932190633151217e-06,
+      "loss": 1.5108,
+      "step": 21550
+    },
+    {
+      "epoch": 6.179373480188814,
+      "grad_norm": 0.7227553144793848,
+      "learning_rate": 3.913085011664961e-06,
+      "loss": 1.5104,
+      "step": 21600
+    },
+    {
+      "epoch": 6.179373480188814,
+      "eval_loss": 1.6167041063308716,
+      "eval_runtime": 13.036,
+      "eval_samples_per_second": 76.711,
+      "eval_steps_per_second": 2.455,
+      "step": 21600
+    },
+    {
+      "epoch": 6.193677585467029,
+      "grad_norm": 0.6216671150889475,
+      "learning_rate": 3.894012002836578e-06,
+      "loss": 1.5188,
+      "step": 21650
+    },
+    {
+      "epoch": 6.207981690745244,
+      "grad_norm": 0.7278814291091744,
+      "learning_rate": 3.874971998635083e-06,
+      "loss": 1.5143,
+      "step": 21700
+    },
+    {
+      "epoch": 6.222285796023459,
+      "grad_norm": 0.6307202506878695,
+      "learning_rate": 3.855965390351222e-06,
+      "loss": 1.4979,
+      "step": 21750
+    },
+    {
+      "epoch": 6.236589901301674,
+      "grad_norm": 0.6083347722601917,
+      "learning_rate": 3.836992568589417e-06,
+      "loss": 1.5033,
+      "step": 21800
+    },
+    {
+      "epoch": 6.250894006579888,
+      "grad_norm": 0.593706378652035,
+      "learning_rate": 3.818053923259745e-06,
+      "loss": 1.5085,
+      "step": 21850
+    },
+    {
+      "epoch": 6.265198111858103,
+      "grad_norm": 0.6691895285161337,
+      "learning_rate": 3.7991498435699213e-06,
+      "loss": 1.5097,
+      "step": 21900
+    },
+    {
+      "epoch": 6.279502217136318,
+      "grad_norm": 0.566540248295759,
+      "learning_rate": 3.780280718017307e-06,
+      "loss": 1.508,
+      "step": 21950
+    },
+    {
+      "epoch": 6.293806322414533,
+      "grad_norm": 0.6905981084599578,
+      "learning_rate": 3.7614469343809208e-06,
+      "loss": 1.5119,
+      "step": 22000
+    },
+    {
+      "epoch": 6.293806322414533,
+      "eval_loss": 1.6159523725509644,
+      "eval_runtime": 13.0728,
+      "eval_samples_per_second": 76.495,
+      "eval_steps_per_second": 2.448,
+      "step": 22000
+    },
+    {
+      "epoch": 6.308110427692748,
+      "grad_norm": 0.6309552003300433,
+      "learning_rate": 3.7426488797134706e-06,
+      "loss": 1.5149,
+      "step": 22050
+    },
+    {
+      "epoch": 6.322414532970963,
+      "grad_norm": 0.6866414179862734,
+      "learning_rate": 3.7238869403333965e-06,
+      "loss": 1.5102,
+      "step": 22100
+    },
+    {
+      "epoch": 6.336718638249177,
+      "grad_norm": 0.6758297767770832,
+      "learning_rate": 3.7051615018169363e-06,
+      "loss": 1.5126,
+      "step": 22150
+    },
+    {
+      "epoch": 6.351022743527392,
+      "grad_norm": 0.6154738835020432,
+      "learning_rate": 3.686472948990198e-06,
+      "loss": 1.5153,
+      "step": 22200
+    },
+    {
+      "epoch": 6.365326848805608,
+      "grad_norm": 0.5955039617182454,
+      "learning_rate": 3.6678216659212546e-06,
+      "loss": 1.5057,
+      "step": 22250
+    },
+    {
+      "epoch": 6.379630954083822,
+      "grad_norm": 0.6316539378588951,
+      "learning_rate": 3.6492080359122487e-06,
+      "loss": 1.5067,
+      "step": 22300
+    },
+    {
+      "epoch": 6.393935059362037,
+      "grad_norm": 0.7239174813640408,
+      "learning_rate": 3.630632441491512e-06,
+      "loss": 1.506,
+      "step": 22350
+    },
+    {
+      "epoch": 6.408239164640252,
+      "grad_norm": 0.6016482488616182,
+      "learning_rate": 3.6120952644057104e-06,
+      "loss": 1.5086,
+      "step": 22400
+    },
+    {
+      "epoch": 6.408239164640252,
+      "eval_loss": 1.6131460666656494,
+      "eval_runtime": 13.0489,
+      "eval_samples_per_second": 76.635,
+      "eval_steps_per_second": 2.452,
+      "step": 22400
+    },
+    {
+      "epoch": 6.422543269918466,
+      "grad_norm": 0.6200355982351727,
+      "learning_rate": 3.593596885611997e-06,
+      "loss": 1.4978,
+      "step": 22450
+    },
+    {
+      "epoch": 6.436847375196681,
+      "grad_norm": 0.6627467949276453,
+      "learning_rate": 3.575137685270182e-06,
+      "loss": 1.5049,
+      "step": 22500
+    },
+    {
+      "epoch": 6.451151480474897,
+      "grad_norm": 0.6630247347111464,
+      "learning_rate": 3.556718042734915e-06,
+      "loss": 1.5024,
+      "step": 22550
+    },
+    {
+      "epoch": 6.465455585753111,
+      "grad_norm": 0.578637148715836,
+      "learning_rate": 3.538338336547902e-06,
+      "loss": 1.5056,
+      "step": 22600
+    },
+    {
+      "epoch": 6.479759691031326,
+      "grad_norm": 0.6081113534912403,
+      "learning_rate": 3.5199989444301082e-06,
+      "loss": 1.4992,
+      "step": 22650
+    },
+    {
+      "epoch": 6.494063796309541,
+      "grad_norm": 0.645971244239988,
+      "learning_rate": 3.5017002432740164e-06,
+      "loss": 1.5036,
+      "step": 22700
+    },
+    {
+      "epoch": 6.508367901587755,
+      "grad_norm": 0.8375742154924346,
+      "learning_rate": 3.483442609135862e-06,
+      "loss": 1.5069,
+      "step": 22750
+    },
+    {
+      "epoch": 6.522672006865971,
+      "grad_norm": 0.7527902242571896,
+      "learning_rate": 3.4652264172279153e-06,
+      "loss": 1.4954,
+      "step": 22800
+    },
+    {
+      "epoch": 6.522672006865971,
+      "eval_loss": 1.6127830743789673,
+      "eval_runtime": 13.0733,
+      "eval_samples_per_second": 76.492,
+      "eval_steps_per_second": 2.448,
+      "step": 22800
+    },
+    {
+      "epoch": 6.536976112144186,
+      "grad_norm": 0.6163133571971323,
+      "learning_rate": 3.4470520419107667e-06,
+      "loss": 1.4933,
+      "step": 22850
+    },
+    {
+      "epoch": 6.5512802174224,
+      "grad_norm": 0.60263575714622,
+      "learning_rate": 3.4289198566856396e-06,
+      "loss": 1.502,
+      "step": 22900
+    },
+    {
+      "epoch": 6.565584322700615,
+      "grad_norm": 0.5907178448045188,
+      "learning_rate": 3.4108302341867045e-06,
+      "loss": 1.5028,
+      "step": 22950
+    },
+    {
+      "epoch": 6.57988842797883,
+      "grad_norm": 0.6016802089690424,
+      "learning_rate": 3.392783546173426e-06,
+      "loss": 1.5008,
+      "step": 23000
+    },
+    {
+      "epoch": 6.594192533257045,
+      "grad_norm": 0.7082966142480123,
+      "learning_rate": 3.374780163522929e-06,
+      "loss": 1.5001,
+      "step": 23050
+    },
+    {
+      "epoch": 6.60849663853526,
+      "grad_norm": 0.6200747482117794,
+      "learning_rate": 3.356820456222362e-06,
+      "loss": 1.5124,
+      "step": 23100
+    },
+    {
+      "epoch": 6.622800743813475,
+      "grad_norm": 0.6742752996052469,
+      "learning_rate": 3.338904793361314e-06,
+      "loss": 1.503,
+      "step": 23150
+    },
+    {
+      "epoch": 6.637104849091689,
+      "grad_norm": 0.6805824676109162,
+      "learning_rate": 3.321033543124202e-06,
+      "loss": 1.5041,
+      "step": 23200
+    },
+    {
+      "epoch": 6.637104849091689,
+      "eval_loss": 1.6102803945541382,
+      "eval_runtime": 13.0416,
+      "eval_samples_per_second": 76.678,
+      "eval_steps_per_second": 2.454,
+      "step": 23200
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 34950,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 800,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.063156613690163e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49bdf616e6157fe414279bf89f5e78ad856b63409ae7ec9fb1d222a6a4f9d641
+size 7224