Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.1",
+  "use_cache": false,
+  "vocab_size": 131072
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "transformers_version": "4.51.1"
+}

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0770b0313042b531d0813412100df7f3f57113404714aa4e85c8eaede169594b
+size 4865522496

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3642b9d543ac7574bf3525c54f90f215bd0a19e32424fcdf24c88a0787403703
+size 4907529424

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a576e0437175f57765cd1faa8f7f38f9a06e788327562d279aa2093755bef551
+size 4907529456

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b46aff62c718beb23106e060a46509e371c6e784bfa9f931e84915cb6057305
+size 4907529456

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5363fa699cfbe19c21b8a8a775ae32034abbd68a7fa72473e1c2569e9382ca25
+size 4907496272

model.safetensors.index.json

@@ -0,0 +1,370 @@
+{
+  "metadata": {
+    "total_size": 24495564800
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00005-of-00005.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.norm.weight": "model-00005-of-00005.safetensors"
+  }
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59f73a01e7b8613ae3c7333511b597d22b3d19ffc894d51a5d90de5e1d3f802d
+size 1896

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a22625c60bf14250424f99a809ffcecb5f25c776dd8079c8624dc295555b32c0
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b340570070f57738b586f55d75aadf6bf3814fccb0b431875b2d337709f21e0
+size 1000

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0240ce510f08e6c2041724e9043e33be9d251d1e4a4d94eb68cd47b954b61d2
+size 17078292

trainer_state.json

@@ -0,0 +1,3658 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 15,
+  "global_step": 480,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008333333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0,
+      "loss": 1.526,
+      "step": 1
+    },
+    {
+      "epoch": 0.008333333333333333,
+      "eval_loss": 1.5474084615707397,
+      "eval_runtime": 51.0772,
+      "eval_samples_per_second": 6.813,
+      "eval_steps_per_second": 1.703,
+      "step": 1
+    },
+    {
+      "epoch": 0.016666666666666666,
+      "grad_norm": 0.0,
+      "learning_rate": 4.4977777777777776e-07,
+      "loss": 1.5014,
+      "step": 2
+    },
+    {
+      "epoch": 0.025,
+      "grad_norm": 0.0,
+      "learning_rate": 8.995555555555555e-07,
+      "loss": 1.5439,
+      "step": 3
+    },
+    {
+      "epoch": 0.03333333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 1.3493333333333333e-06,
+      "loss": 1.5425,
+      "step": 4
+    },
+    {
+      "epoch": 0.041666666666666664,
+      "grad_norm": 0.0,
+      "learning_rate": 1.799111111111111e-06,
+      "loss": 1.4943,
+      "step": 5
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.0,
+      "learning_rate": 2.2488888888888888e-06,
+      "loss": 1.4754,
+      "step": 6
+    },
+    {
+      "epoch": 0.058333333333333334,
+      "grad_norm": 0.0,
+      "learning_rate": 2.6986666666666667e-06,
+      "loss": 1.512,
+      "step": 7
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 3.148444444444444e-06,
+      "loss": 1.5201,
+      "step": 8
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 0.0,
+      "learning_rate": 3.598222222222222e-06,
+      "loss": 1.5314,
+      "step": 9
+    },
+    {
+      "epoch": 0.08333333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 4.048e-06,
+      "loss": 1.5345,
+      "step": 10
+    },
+    {
+      "epoch": 0.09166666666666666,
+      "grad_norm": 0.0,
+      "learning_rate": 4.4977777777777775e-06,
+      "loss": 1.5249,
+      "step": 11
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.0,
+      "learning_rate": 4.947555555555556e-06,
+      "loss": 1.5374,
+      "step": 12
+    },
+    {
+      "epoch": 0.10833333333333334,
+      "grad_norm": 0.0,
+      "learning_rate": 5.397333333333333e-06,
+      "loss": 1.5302,
+      "step": 13
+    },
+    {
+      "epoch": 0.11666666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 5.84711111111111e-06,
+      "loss": 1.5337,
+      "step": 14
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 0.0,
+      "learning_rate": 6.296888888888888e-06,
+      "loss": 1.5934,
+      "step": 15
+    },
+    {
+      "epoch": 0.125,
+      "eval_loss": 1.5472139120101929,
+      "eval_runtime": 51.0977,
+      "eval_samples_per_second": 6.81,
+      "eval_steps_per_second": 1.703,
+      "step": 15
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 6.746666666666666e-06,
+      "loss": 1.5393,
+      "step": 16
+    },
+    {
+      "epoch": 0.14166666666666666,
+      "grad_norm": 0.0,
+      "learning_rate": 7.196444444444444e-06,
+      "loss": 1.4817,
+      "step": 17
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.0,
+      "learning_rate": 7.646222222222223e-06,
+      "loss": 1.4649,
+      "step": 18
+    },
+    {
+      "epoch": 0.15833333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 8.096e-06,
+      "loss": 1.5251,
+      "step": 19
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 0.0,
+      "learning_rate": 8.545777777777778e-06,
+      "loss": 1.5871,
+      "step": 20
+    },
+    {
+      "epoch": 0.175,
+      "grad_norm": 0.0,
+      "learning_rate": 8.995555555555555e-06,
+      "loss": 1.4913,
+      "step": 21
+    },
+    {
+      "epoch": 0.18333333333333332,
+      "grad_norm": 0.0,
+      "learning_rate": 9.445333333333333e-06,
+      "loss": 1.5087,
+      "step": 22
+    },
+    {
+      "epoch": 0.19166666666666668,
+      "grad_norm": 0.0,
+      "learning_rate": 9.895111111111112e-06,
+      "loss": 1.5496,
+      "step": 23
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.0,
+      "learning_rate": 1.034488888888889e-05,
+      "loss": 1.5448,
+      "step": 24
+    },
+    {
+      "epoch": 0.20833333333333334,
+      "grad_norm": 0.0,
+      "learning_rate": 1.0794666666666667e-05,
+      "loss": 1.5271,
+      "step": 25
+    },
+    {
+      "epoch": 0.21666666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 1.1244444444444443e-05,
+      "loss": 1.4988,
+      "step": 26
+    },
+    {
+      "epoch": 0.225,
+      "grad_norm": 0.0,
+      "learning_rate": 1.169422222222222e-05,
+      "loss": 1.5321,
+      "step": 27
+    },
+    {
+      "epoch": 0.23333333333333334,
+      "grad_norm": 0.0,
+      "learning_rate": 1.2144e-05,
+      "loss": 1.5705,
+      "step": 28
+    },
+    {
+      "epoch": 0.24166666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 1.2593777777777777e-05,
+      "loss": 1.5627,
+      "step": 29
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.0,
+      "learning_rate": 1.3043555555555554e-05,
+      "loss": 1.5242,
+      "step": 30
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 1.5454295873641968,
+      "eval_runtime": 248.2611,
+      "eval_samples_per_second": 1.402,
+      "eval_steps_per_second": 0.35,
+      "step": 30
+    },
+    {
+      "epoch": 0.25833333333333336,
+      "grad_norm": 0.0,
+      "learning_rate": 1.3493333333333332e-05,
+      "loss": 1.518,
+      "step": 31
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.0,
+      "learning_rate": 1.394311111111111e-05,
+      "loss": 1.5061,
+      "step": 32
+    },
+    {
+      "epoch": 0.275,
+      "grad_norm": 0.0,
+      "learning_rate": 1.4392888888888888e-05,
+      "loss": 1.5745,
+      "step": 33
+    },
+    {
+      "epoch": 0.2833333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 1.4842666666666666e-05,
+      "loss": 1.5419,
+      "step": 34
+    },
+    {
+      "epoch": 0.2916666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 1.5292444444444445e-05,
+      "loss": 1.5144,
+      "step": 35
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.0,
+      "learning_rate": 1.574222222222222e-05,
+      "loss": 1.6139,
+      "step": 36
+    },
+    {
+      "epoch": 0.30833333333333335,
+      "grad_norm": 0.0,
+      "learning_rate": 1.6192e-05,
+      "loss": 1.5323,
+      "step": 37
+    },
+    {
+      "epoch": 0.31666666666666665,
+      "grad_norm": 0.0,
+      "learning_rate": 1.6641777777777776e-05,
+      "loss": 1.5314,
+      "step": 38
+    },
+    {
+      "epoch": 0.325,
+      "grad_norm": 0.0,
+      "learning_rate": 1.7091555555555555e-05,
+      "loss": 1.5425,
+      "step": 39
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 1.7541333333333334e-05,
+      "loss": 1.5434,
+      "step": 40
+    },
+    {
+      "epoch": 0.3416666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 1.799111111111111e-05,
+      "loss": 1.4947,
+      "step": 41
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.0,
+      "learning_rate": 1.844088888888889e-05,
+      "loss": 1.5593,
+      "step": 42
+    },
+    {
+      "epoch": 0.35833333333333334,
+      "grad_norm": 0.0,
+      "learning_rate": 1.8890666666666665e-05,
+      "loss": 1.5229,
+      "step": 43
+    },
+    {
+      "epoch": 0.36666666666666664,
+      "grad_norm": 0.0,
+      "learning_rate": 1.9340444444444444e-05,
+      "loss": 1.5871,
+      "step": 44
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 0.0,
+      "learning_rate": 1.9790222222222224e-05,
+      "loss": 1.5296,
+      "step": 45
+    },
+    {
+      "epoch": 0.375,
+      "eval_loss": 1.5407556295394897,
+      "eval_runtime": 52.0428,
+      "eval_samples_per_second": 6.687,
+      "eval_steps_per_second": 1.672,
+      "step": 45
+    },
+    {
+      "epoch": 0.38333333333333336,
+      "grad_norm": 0.0,
+      "learning_rate": 2.024e-05,
+      "loss": 1.4733,
+      "step": 46
+    },
+    {
+      "epoch": 0.39166666666666666,
+      "grad_norm": 0.0,
+      "learning_rate": 2.068977777777778e-05,
+      "loss": 1.4505,
+      "step": 47
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.0,
+      "learning_rate": 2.1139555555555554e-05,
+      "loss": 1.5306,
+      "step": 48
+    },
+    {
+      "epoch": 0.4083333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 2.1589333333333334e-05,
+      "loss": 1.5123,
+      "step": 49
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 2.203911111111111e-05,
+      "loss": 1.5279,
+      "step": 50
+    },
+    {
+      "epoch": 0.425,
+      "grad_norm": 0.0,
+      "learning_rate": 2.2488888888888885e-05,
+      "loss": 1.5022,
+      "step": 51
+    },
+    {
+      "epoch": 0.43333333333333335,
+      "grad_norm": 0.0,
+      "learning_rate": 2.2938666666666664e-05,
+      "loss": 1.4849,
+      "step": 52
+    },
+    {
+      "epoch": 0.44166666666666665,
+      "grad_norm": 0.0,
+      "learning_rate": 2.338844444444444e-05,
+      "loss": 1.53,
+      "step": 53
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.0,
+      "learning_rate": 2.383822222222222e-05,
+      "loss": 1.506,
+      "step": 54
+    },
+    {
+      "epoch": 0.4583333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 2.4288e-05,
+      "loss": 1.464,
+      "step": 55
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 2.4737777777777774e-05,
+      "loss": 1.5027,
+      "step": 56
+    },
+    {
+      "epoch": 0.475,
+      "grad_norm": 0.0,
+      "learning_rate": 2.5187555555555554e-05,
+      "loss": 1.4537,
+      "step": 57
+    },
+    {
+      "epoch": 0.48333333333333334,
+      "grad_norm": 0.0,
+      "learning_rate": 2.5637333333333333e-05,
+      "loss": 1.5195,
+      "step": 58
+    },
+    {
+      "epoch": 0.49166666666666664,
+      "grad_norm": 0.0,
+      "learning_rate": 2.608711111111111e-05,
+      "loss": 1.4885,
+      "step": 59
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.0,
+      "learning_rate": 2.653688888888889e-05,
+      "loss": 1.5087,
+      "step": 60
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 1.5322431325912476,
+      "eval_runtime": 51.1758,
+      "eval_samples_per_second": 6.8,
+      "eval_steps_per_second": 1.7,
+      "step": 60
+    },
+    {
+      "epoch": 0.5083333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 2.6986666666666664e-05,
+      "loss": 1.5306,
+      "step": 61
+    },
+    {
+      "epoch": 0.5166666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 2.7436444444444446e-05,
+      "loss": 1.5116,
+      "step": 62
+    },
+    {
+      "epoch": 0.525,
+      "grad_norm": 0.0,
+      "learning_rate": 2.788622222222222e-05,
+      "loss": 1.4956,
+      "step": 63
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 2.8336e-05,
+      "loss": 1.534,
+      "step": 64
+    },
+    {
+      "epoch": 0.5416666666666666,
+      "grad_norm": 0.0,
+      "learning_rate": 2.8785777777777777e-05,
+      "loss": 1.5333,
+      "step": 65
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.0,
+      "learning_rate": 2.923555555555555e-05,
+      "loss": 1.4466,
+      "step": 66
+    },
+    {
+      "epoch": 0.5583333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 2.9685333333333332e-05,
+      "loss": 1.5071,
+      "step": 67
+    },
+    {
+      "epoch": 0.5666666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 3.0135111111111108e-05,
+      "loss": 1.5856,
+      "step": 68
+    },
+    {
+      "epoch": 0.575,
+      "grad_norm": 0.0,
+      "learning_rate": 3.058488888888889e-05,
+      "loss": 1.4685,
+      "step": 69
+    },
+    {
+      "epoch": 0.5833333333333334,
+      "grad_norm": 0.0,
+      "learning_rate": 3.103466666666666e-05,
+      "loss": 1.4647,
+      "step": 70
+    },
+    {
+      "epoch": 0.5916666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 3.148444444444444e-05,
+      "loss": 1.5198,
+      "step": 71
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.0,
+      "learning_rate": 3.193422222222222e-05,
+      "loss": 1.529,
+      "step": 72
+    },
+    {
+      "epoch": 0.6083333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 3.2384e-05,
+      "loss": 1.5045,
+      "step": 73
+    },
+    {
+      "epoch": 0.6166666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 3.283377777777777e-05,
+      "loss": 1.5076,
+      "step": 74
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 0.0,
+      "learning_rate": 3.328355555555555e-05,
+      "loss": 1.486,
+      "step": 75
+    },
+    {
+      "epoch": 0.625,
+      "eval_loss": 1.518750548362732,
+      "eval_runtime": 252.8012,
+      "eval_samples_per_second": 1.377,
+      "eval_steps_per_second": 0.344,
+      "step": 75
+    },
+    {
+      "epoch": 0.6333333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 3.373333333333333e-05,
+      "loss": 1.4644,
+      "step": 76
+    },
+    {
+      "epoch": 0.6416666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 3.418311111111111e-05,
+      "loss": 1.4745,
+      "step": 77
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.0,
+      "learning_rate": 3.463288888888888e-05,
+      "loss": 1.492,
+      "step": 78
+    },
+    {
+      "epoch": 0.6583333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 3.508266666666667e-05,
+      "loss": 1.4565,
+      "step": 79
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.0,
+      "learning_rate": 3.553244444444444e-05,
+      "loss": 1.4523,
+      "step": 80
+    },
+    {
+      "epoch": 0.675,
+      "grad_norm": 0.0,
+      "learning_rate": 3.598222222222222e-05,
+      "loss": 1.509,
+      "step": 81
+    },
+    {
+      "epoch": 0.6833333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 3.6432e-05,
+      "loss": 1.4881,
+      "step": 82
+    },
+    {
+      "epoch": 0.6916666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 3.688177777777778e-05,
+      "loss": 1.4497,
+      "step": 83
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.0,
+      "learning_rate": 3.733155555555555e-05,
+      "loss": 1.4833,
+      "step": 84
+    },
+    {
+      "epoch": 0.7083333333333334,
+      "grad_norm": 0.0,
+      "learning_rate": 3.778133333333333e-05,
+      "loss": 1.3969,
+      "step": 85
+    },
+    {
+      "epoch": 0.7166666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 3.823111111111111e-05,
+      "loss": 1.5271,
+      "step": 86
+    },
+    {
+      "epoch": 0.725,
+      "grad_norm": 0.0,
+      "learning_rate": 3.868088888888889e-05,
+      "loss": 1.5072,
+      "step": 87
+    },
+    {
+      "epoch": 0.7333333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 3.913066666666666e-05,
+      "loss": 1.501,
+      "step": 88
+    },
+    {
+      "epoch": 0.7416666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 3.958044444444445e-05,
+      "loss": 1.5138,
+      "step": 89
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.0,
+      "learning_rate": 4.003022222222222e-05,
+      "loss": 1.4314,
+      "step": 90
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 1.5005146265029907,
+      "eval_runtime": 52.2623,
+      "eval_samples_per_second": 6.659,
+      "eval_steps_per_second": 1.665,
+      "step": 90
+    },
+    {
+      "epoch": 0.7583333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 4.048e-05,
+      "loss": 1.5189,
+      "step": 91
+    },
+    {
+      "epoch": 0.7666666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 4.092977777777778e-05,
+      "loss": 1.4069,
+      "step": 92
+    },
+    {
+      "epoch": 0.775,
+      "grad_norm": 0.0,
+      "learning_rate": 4.137955555555556e-05,
+      "loss": 1.4648,
+      "step": 93
+    },
+    {
+      "epoch": 0.7833333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 4.182933333333333e-05,
+      "loss": 1.4731,
+      "step": 94
+    },
+    {
+      "epoch": 0.7916666666666666,
+      "grad_norm": 0.0,
+      "learning_rate": 4.227911111111111e-05,
+      "loss": 1.4628,
+      "step": 95
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.0,
+      "learning_rate": 4.272888888888889e-05,
+      "loss": 1.4871,
+      "step": 96
+    },
+    {
+      "epoch": 0.8083333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 4.317866666666667e-05,
+      "loss": 1.4948,
+      "step": 97
+    },
+    {
+      "epoch": 0.8166666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 4.362844444444444e-05,
+      "loss": 1.4728,
+      "step": 98
+    },
+    {
+      "epoch": 0.825,
+      "grad_norm": 0.0,
+      "learning_rate": 4.407822222222222e-05,
+      "loss": 1.4434,
+      "step": 99
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.0,
+      "learning_rate": 4.4528e-05,
+      "loss": 1.5007,
+      "step": 100
+    },
+    {
+      "epoch": 0.8416666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 4.497777777777777e-05,
+      "loss": 1.5316,
+      "step": 101
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.0,
+      "learning_rate": 4.5427555555555556e-05,
+      "loss": 1.4675,
+      "step": 102
+    },
+    {
+      "epoch": 0.8583333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 4.587733333333333e-05,
+      "loss": 1.5065,
+      "step": 103
+    },
+    {
+      "epoch": 0.8666666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 4.632711111111111e-05,
+      "loss": 1.4746,
+      "step": 104
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 0.0,
+      "learning_rate": 4.677688888888888e-05,
+      "loss": 1.4311,
+      "step": 105
+    },
+    {
+      "epoch": 0.875,
+      "eval_loss": 1.4781609773635864,
+      "eval_runtime": 51.7297,
+      "eval_samples_per_second": 6.727,
+      "eval_steps_per_second": 1.682,
+      "step": 105
+    },
+    {
+      "epoch": 0.8833333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 4.7226666666666666e-05,
+      "loss": 1.4664,
+      "step": 106
+    },
+    {
+      "epoch": 0.8916666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 4.767644444444444e-05,
+      "loss": 1.4965,
+      "step": 107
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.0,
+      "learning_rate": 4.812622222222222e-05,
+      "loss": 1.4625,
+      "step": 108
+    },
+    {
+      "epoch": 0.9083333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 4.8576e-05,
+      "loss": 1.4221,
+      "step": 109
+    },
+    {
+      "epoch": 0.9166666666666666,
+      "grad_norm": 0.0,
+      "learning_rate": 4.9025777777777776e-05,
+      "loss": 1.4426,
+      "step": 110
+    },
+    {
+      "epoch": 0.925,
+      "grad_norm": 0.0,
+      "learning_rate": 4.947555555555555e-05,
+      "loss": 1.4328,
+      "step": 111
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 4.9925333333333335e-05,
+      "loss": 1.4366,
+      "step": 112
+    },
+    {
+      "epoch": 0.9416666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 5.037511111111111e-05,
+      "loss": 1.4369,
+      "step": 113
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.0,
+      "learning_rate": 5.0824888888888886e-05,
+      "loss": 1.4578,
+      "step": 114
+    },
+    {
+      "epoch": 0.9583333333333334,
+      "grad_norm": 0.0,
+      "learning_rate": 5.1274666666666665e-05,
+      "loss": 1.4389,
+      "step": 115
+    },
+    {
+      "epoch": 0.9666666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 5.172444444444444e-05,
+      "loss": 1.3922,
+      "step": 116
+    },
+    {
+      "epoch": 0.975,
+      "grad_norm": 0.0,
+      "learning_rate": 5.217422222222222e-05,
+      "loss": 1.4112,
+      "step": 117
+    },
+    {
+      "epoch": 0.9833333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 5.2623999999999996e-05,
+      "loss": 1.3631,
+      "step": 118
+    },
+    {
+      "epoch": 0.9916666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 5.307377777777778e-05,
+      "loss": 1.5094,
+      "step": 119
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.0,
+      "learning_rate": 5.352355555555555e-05,
+      "loss": 1.4532,
+      "step": 120
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.4513498544692993,
+      "eval_runtime": 51.876,
+      "eval_samples_per_second": 6.708,
+      "eval_steps_per_second": 1.677,
+      "step": 120
+    },
+    {
+      "epoch": 1.0083333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 5.397333333333333e-05,
+      "loss": 1.4404,
+      "step": 121
+    },
+    {
+      "epoch": 1.0166666666666666,
+      "grad_norm": 0.0,
+      "learning_rate": 5.442311111111111e-05,
+      "loss": 1.4568,
+      "step": 122
+    },
+    {
+      "epoch": 1.025,
+      "grad_norm": 0.0,
+      "learning_rate": 5.487288888888889e-05,
+      "loss": 1.4,
+      "step": 123
+    },
+    {
+      "epoch": 1.0333333333333334,
+      "grad_norm": 0.0,
+      "learning_rate": 5.532266666666666e-05,
+      "loss": 1.3975,
+      "step": 124
+    },
+    {
+      "epoch": 1.0416666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 5.577244444444444e-05,
+      "loss": 1.4252,
+      "step": 125
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 0.0,
+      "learning_rate": 5.622222222222222e-05,
+      "loss": 1.4129,
+      "step": 126
+    },
+    {
+      "epoch": 1.0583333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 5.6672e-05,
+      "loss": 1.3786,
+      "step": 127
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 5.712177777777777e-05,
+      "loss": 1.3885,
+      "step": 128
+    },
+    {
+      "epoch": 1.075,
+      "grad_norm": 0.0,
+      "learning_rate": 5.7571555555555554e-05,
+      "loss": 1.4003,
+      "step": 129
+    },
+    {
+      "epoch": 1.0833333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 5.802133333333333e-05,
+      "loss": 1.4326,
+      "step": 130
+    },
+    {
+      "epoch": 1.0916666666666666,
+      "grad_norm": 0.0,
+      "learning_rate": 5.84711111111111e-05,
+      "loss": 1.4307,
+      "step": 131
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.0,
+      "learning_rate": 5.8920888888888885e-05,
+      "loss": 1.3825,
+      "step": 132
+    },
+    {
+      "epoch": 1.1083333333333334,
+      "grad_norm": 0.0,
+      "learning_rate": 5.9370666666666664e-05,
+      "loss": 1.386,
+      "step": 133
+    },
+    {
+      "epoch": 1.1166666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 5.982044444444444e-05,
+      "loss": 1.4151,
+      "step": 134
+    },
+    {
+      "epoch": 1.125,
+      "grad_norm": 0.0,
+      "learning_rate": 6.0270222222222215e-05,
+      "loss": 1.4215,
+      "step": 135
+    },
+    {
+      "epoch": 1.125,
+      "eval_loss": 1.4197664260864258,
+      "eval_runtime": 52.8834,
+      "eval_samples_per_second": 6.581,
+      "eval_steps_per_second": 1.645,
+      "step": 135
+    },
+    {
+      "epoch": 1.1333333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 6.0719999999999995e-05,
+      "loss": 1.4243,
+      "step": 136
+    },
+    {
+      "epoch": 1.1416666666666666,
+      "grad_norm": 0.0,
+      "learning_rate": 6.116977777777778e-05,
+      "loss": 1.4043,
+      "step": 137
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 0.0,
+      "learning_rate": 6.161955555555556e-05,
+      "loss": 1.4151,
+      "step": 138
+    },
+    {
+      "epoch": 1.1583333333333332,
+      "grad_norm": 0.0,
+      "learning_rate": 6.206933333333333e-05,
+      "loss": 1.3896,
+      "step": 139
+    },
+    {
+      "epoch": 1.1666666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 6.25191111111111e-05,
+      "loss": 1.3517,
+      "step": 140
+    },
+    {
+      "epoch": 1.175,
+      "grad_norm": 0.0,
+      "learning_rate": 6.296888888888888e-05,
+      "loss": 1.3464,
+      "step": 141
+    },
+    {
+      "epoch": 1.1833333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 6.341866666666666e-05,
+      "loss": 1.3561,
+      "step": 142
+    },
+    {
+      "epoch": 1.1916666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 6.386844444444444e-05,
+      "loss": 1.3916,
+      "step": 143
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.0,
+      "learning_rate": 6.431822222222222e-05,
+      "loss": 1.4341,
+      "step": 144
+    },
+    {
+      "epoch": 1.2083333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 6.4768e-05,
+      "loss": 1.3477,
+      "step": 145
+    },
+    {
+      "epoch": 1.2166666666666668,
+      "grad_norm": 0.0,
+      "learning_rate": 6.521777777777778e-05,
+      "loss": 1.3531,
+      "step": 146
+    },
+    {
+      "epoch": 1.225,
+      "grad_norm": 0.0,
+      "learning_rate": 6.566755555555555e-05,
+      "loss": 1.3493,
+      "step": 147
+    },
+    {
+      "epoch": 1.2333333333333334,
+      "grad_norm": 0.0,
+      "learning_rate": 6.611733333333332e-05,
+      "loss": 1.36,
+      "step": 148
+    },
+    {
+      "epoch": 1.2416666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 6.65671111111111e-05,
+      "loss": 1.4211,
+      "step": 149
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.0,
+      "learning_rate": 6.701688888888888e-05,
+      "loss": 1.3248,
+      "step": 150
+    },
+    {
+      "epoch": 1.25,
+      "eval_loss": 1.3825478553771973,
+      "eval_runtime": 251.4211,
+      "eval_samples_per_second": 1.384,
+      "eval_steps_per_second": 0.346,
+      "step": 150
+    },
+    {
+      "epoch": 1.2583333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 6.746666666666666e-05,
+      "loss": 1.3772,
+      "step": 151
+    },
+    {
+      "epoch": 1.2666666666666666,
+      "grad_norm": 0.0,
+      "learning_rate": 6.791644444444444e-05,
+      "loss": 1.3688,
+      "step": 152
+    },
+    {
+      "epoch": 1.275,
+      "grad_norm": 0.0,
+      "learning_rate": 6.836622222222222e-05,
+      "loss": 1.3748,
+      "step": 153
+    },
+    {
+      "epoch": 1.2833333333333332,
+      "grad_norm": 0.0,
+      "learning_rate": 6.8816e-05,
+      "loss": 1.3449,
+      "step": 154
+    },
+    {
+      "epoch": 1.2916666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 6.926577777777777e-05,
+      "loss": 1.287,
+      "step": 155
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.0,
+      "learning_rate": 6.971555555555554e-05,
+      "loss": 1.3463,
+      "step": 156
+    },
+    {
+      "epoch": 1.3083333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 7.016533333333334e-05,
+      "loss": 1.3471,
+      "step": 157
+    },
+    {
+      "epoch": 1.3166666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 7.061511111111112e-05,
+      "loss": 1.3299,
+      "step": 158
+    },
+    {
+      "epoch": 1.325,
+      "grad_norm": 0.0,
+      "learning_rate": 7.106488888888888e-05,
+      "loss": 1.2756,
+      "step": 159
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 7.151466666666666e-05,
+      "loss": 1.3004,
+      "step": 160
+    },
+    {
+      "epoch": 1.3416666666666668,
+      "grad_norm": 0.0,
+      "learning_rate": 7.196444444444444e-05,
+      "loss": 1.3671,
+      "step": 161
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 0.0,
+      "learning_rate": 7.24142222222222e-05,
+      "loss": 1.3603,
+      "step": 162
+    },
+    {
+      "epoch": 1.3583333333333334,
+      "grad_norm": 0.0,
+      "learning_rate": 7.2864e-05,
+      "loss": 1.2986,
+      "step": 163
+    },
+    {
+      "epoch": 1.3666666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 7.331377777777778e-05,
+      "loss": 1.2886,
+      "step": 164
+    },
+    {
+      "epoch": 1.375,
+      "grad_norm": 0.0,
+      "learning_rate": 7.376355555555556e-05,
+      "loss": 1.2697,
+      "step": 165
+    },
+    {
+      "epoch": 1.375,
+      "eval_loss": 1.3386281728744507,
+      "eval_runtime": 51.4045,
+      "eval_samples_per_second": 6.77,
+      "eval_steps_per_second": 1.692,
+      "step": 165
+    },
+    {
+      "epoch": 1.3833333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 7.421333333333332e-05,
+      "loss": 1.309,
+      "step": 166
+    },
+    {
+      "epoch": 1.3916666666666666,
+      "grad_norm": 0.0,
+      "learning_rate": 7.46631111111111e-05,
+      "loss": 1.3718,
+      "step": 167
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.0,
+      "learning_rate": 7.511288888888888e-05,
+      "loss": 1.3298,
+      "step": 168
+    },
+    {
+      "epoch": 1.4083333333333332,
+      "grad_norm": 0.0,
+      "learning_rate": 7.556266666666666e-05,
+      "loss": 1.3085,
+      "step": 169
+    },
+    {
+      "epoch": 1.4166666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 7.601244444444444e-05,
+      "loss": 1.2769,
+      "step": 170
+    },
+    {
+      "epoch": 1.425,
+      "grad_norm": 0.0,
+      "learning_rate": 7.646222222222222e-05,
+      "loss": 1.2899,
+      "step": 171
+    },
+    {
+      "epoch": 1.4333333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 7.6912e-05,
+      "loss": 1.2973,
+      "step": 172
+    },
+    {
+      "epoch": 1.4416666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 7.736177777777778e-05,
+      "loss": 1.2527,
+      "step": 173
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 0.0,
+      "learning_rate": 7.781155555555554e-05,
+      "loss": 1.2881,
+      "step": 174
+    },
+    {
+      "epoch": 1.4583333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 7.826133333333332e-05,
+      "loss": 1.295,
+      "step": 175
+    },
+    {
+      "epoch": 1.4666666666666668,
+      "grad_norm": 0.0,
+      "learning_rate": 7.87111111111111e-05,
+      "loss": 1.2682,
+      "step": 176
+    },
+    {
+      "epoch": 1.475,
+      "grad_norm": 0.0,
+      "learning_rate": 7.91608888888889e-05,
+      "loss": 1.252,
+      "step": 177
+    },
+    {
+      "epoch": 1.4833333333333334,
+      "grad_norm": 0.0,
+      "learning_rate": 7.961066666666666e-05,
+      "loss": 1.2956,
+      "step": 178
+    },
+    {
+      "epoch": 1.4916666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 8.006044444444444e-05,
+      "loss": 1.2992,
+      "step": 179
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.0,
+      "learning_rate": 8.051022222222222e-05,
+      "loss": 1.3281,
+      "step": 180
+    },
+    {
+      "epoch": 1.5,
+      "eval_loss": 1.2880223989486694,
+      "eval_runtime": 51.0745,
+      "eval_samples_per_second": 6.814,
+      "eval_steps_per_second": 1.703,
+      "step": 180
+    },
+    {
+      "epoch": 1.5083333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 8.096e-05,
+      "loss": 1.2675,
+      "step": 181
+    },
+    {
+      "epoch": 1.5166666666666666,
+      "grad_norm": 0.0,
+      "learning_rate": 8.140977777777776e-05,
+      "loss": 1.2795,
+      "step": 182
+    },
+    {
+      "epoch": 1.525,
+      "grad_norm": 0.0,
+      "learning_rate": 8.185955555555556e-05,
+      "loss": 1.2808,
+      "step": 183
+    },
+    {
+      "epoch": 1.5333333333333332,
+      "grad_norm": 0.0,
+      "learning_rate": 8.230933333333333e-05,
+      "loss": 1.2468,
+      "step": 184
+    },
+    {
+      "epoch": 1.5416666666666665,
+      "grad_norm": 0.0,
+      "learning_rate": 8.275911111111111e-05,
+      "loss": 1.2866,
+      "step": 185
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 0.0,
+      "learning_rate": 8.320888888888888e-05,
+      "loss": 1.2381,
+      "step": 186
+    },
+    {
+      "epoch": 1.5583333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 8.365866666666666e-05,
+      "loss": 1.2302,
+      "step": 187
+    },
+    {
+      "epoch": 1.5666666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 8.410844444444444e-05,
+      "loss": 1.2575,
+      "step": 188
+    },
+    {
+      "epoch": 1.575,
+      "grad_norm": 0.0,
+      "learning_rate": 8.455822222222222e-05,
+      "loss": 1.2615,
+      "step": 189
+    },
+    {
+      "epoch": 1.5833333333333335,
+      "grad_norm": 0.0,
+      "learning_rate": 8.5008e-05,
+      "loss": 1.2348,
+      "step": 190
+    },
+    {
+      "epoch": 1.5916666666666668,
+      "grad_norm": 0.0,
+      "learning_rate": 8.545777777777778e-05,
+      "loss": 1.2485,
+      "step": 191
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.0,
+      "learning_rate": 8.590755555555555e-05,
+      "loss": 1.2423,
+      "step": 192
+    },
+    {
+      "epoch": 1.6083333333333334,
+      "grad_norm": 0.0,
+      "learning_rate": 8.635733333333333e-05,
+      "loss": 1.2538,
+      "step": 193
+    },
+    {
+      "epoch": 1.6166666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 8.68071111111111e-05,
+      "loss": 1.2584,
+      "step": 194
+    },
+    {
+      "epoch": 1.625,
+      "grad_norm": 0.0,
+      "learning_rate": 8.725688888888888e-05,
+      "loss": 1.2428,
+      "step": 195
+    },
+    {
+      "epoch": 1.625,
+      "eval_loss": 1.2295665740966797,
+      "eval_runtime": 50.7122,
+      "eval_samples_per_second": 6.862,
+      "eval_steps_per_second": 1.716,
+      "step": 195
+    },
+    {
+      "epoch": 1.6333333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 8.770666666666666e-05,
+      "loss": 1.2075,
+      "step": 196
+    },
+    {
+      "epoch": 1.6416666666666666,
+      "grad_norm": 0.0,
+      "learning_rate": 8.815644444444444e-05,
+      "loss": 1.2134,
+      "step": 197
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 0.0,
+      "learning_rate": 8.860622222222222e-05,
+      "loss": 1.2102,
+      "step": 198
+    },
+    {
+      "epoch": 1.6583333333333332,
+      "grad_norm": 0.0,
+      "learning_rate": 8.9056e-05,
+      "loss": 1.2551,
+      "step": 199
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.0,
+      "learning_rate": 8.950577777777777e-05,
+      "loss": 1.1577,
+      "step": 200
+    },
+    {
+      "epoch": 1.675,
+      "grad_norm": 0.0,
+      "learning_rate": 8.995555555555554e-05,
+      "loss": 1.204,
+      "step": 201
+    },
+    {
+      "epoch": 1.6833333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 9.040533333333332e-05,
+      "loss": 1.2207,
+      "step": 202
+    },
+    {
+      "epoch": 1.6916666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 9.085511111111111e-05,
+      "loss": 1.2284,
+      "step": 203
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 0.0,
+      "learning_rate": 9.130488888888889e-05,
+      "loss": 1.1487,
+      "step": 204
+    },
+    {
+      "epoch": 1.7083333333333335,
+      "grad_norm": 0.0,
+      "learning_rate": 9.175466666666666e-05,
+      "loss": 1.1269,
+      "step": 205
+    },
+    {
+      "epoch": 1.7166666666666668,
+      "grad_norm": 0.0,
+      "learning_rate": 9.220444444444444e-05,
+      "loss": 1.1483,
+      "step": 206
+    },
+    {
+      "epoch": 1.725,
+      "grad_norm": 0.0,
+      "learning_rate": 9.265422222222222e-05,
+      "loss": 1.1776,
+      "step": 207
+    },
+    {
+      "epoch": 1.7333333333333334,
+      "grad_norm": 0.0,
+      "learning_rate": 9.3104e-05,
+      "loss": 1.1678,
+      "step": 208
+    },
+    {
+      "epoch": 1.7416666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 9.355377777777776e-05,
+      "loss": 1.1634,
+      "step": 209
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.0,
+      "learning_rate": 9.400355555555555e-05,
+      "loss": 1.1533,
+      "step": 210
+    },
+    {
+      "epoch": 1.75,
+      "eval_loss": 1.1595572233200073,
+      "eval_runtime": 50.6903,
+      "eval_samples_per_second": 6.865,
+      "eval_steps_per_second": 1.716,
+      "step": 210
+    },
+    {
+      "epoch": 1.7583333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 9.445333333333333e-05,
+      "loss": 1.1765,
+      "step": 211
+    },
+    {
+      "epoch": 1.7666666666666666,
+      "grad_norm": 0.0,
+      "learning_rate": 9.490311111111111e-05,
+      "loss": 1.1806,
+      "step": 212
+    },
+    {
+      "epoch": 1.775,
+      "grad_norm": 0.0,
+      "learning_rate": 9.535288888888888e-05,
+      "loss": 1.0863,
+      "step": 213
+    },
+    {
+      "epoch": 1.7833333333333332,
+      "grad_norm": 0.0,
+      "learning_rate": 9.580266666666666e-05,
+      "loss": 1.0531,
+      "step": 214
+    },
+    {
+      "epoch": 1.7916666666666665,
+      "grad_norm": 0.0,
+      "learning_rate": 9.625244444444444e-05,
+      "loss": 1.1368,
+      "step": 215
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.0,
+      "learning_rate": 9.670222222222221e-05,
+      "loss": 1.1326,
+      "step": 216
+    },
+    {
+      "epoch": 1.8083333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 9.7152e-05,
+      "loss": 1.0474,
+      "step": 217
+    },
+    {
+      "epoch": 1.8166666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 9.760177777777777e-05,
+      "loss": 1.1472,
+      "step": 218
+    },
+    {
+      "epoch": 1.825,
+      "grad_norm": 0.0,
+      "learning_rate": 9.805155555555555e-05,
+      "loss": 1.0939,
+      "step": 219
+    },
+    {
+      "epoch": 1.8333333333333335,
+      "grad_norm": 0.0,
+      "learning_rate": 9.850133333333333e-05,
+      "loss": 1.1182,
+      "step": 220
+    },
+    {
+      "epoch": 1.8416666666666668,
+      "grad_norm": 0.0,
+      "learning_rate": 9.89511111111111e-05,
+      "loss": 1.0607,
+      "step": 221
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 0.0,
+      "learning_rate": 9.940088888888888e-05,
+      "loss": 1.0638,
+      "step": 222
+    },
+    {
+      "epoch": 1.8583333333333334,
+      "grad_norm": 0.0,
+      "learning_rate": 9.985066666666667e-05,
+      "loss": 1.1084,
+      "step": 223
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00010030044444444445,
+      "loss": 1.1307,
+      "step": 224
+    },
+    {
+      "epoch": 1.875,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00010075022222222221,
+      "loss": 1.1038,
+      "step": 225
+    },
+    {
+      "epoch": 1.875,
+      "eval_loss": 1.0747346878051758,
+      "eval_runtime": 255.4172,
+      "eval_samples_per_second": 1.362,
+      "eval_steps_per_second": 0.341,
+      "step": 225
+    },
+    {
+      "epoch": 1.8833333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001012,
+      "loss": 1.0009,
+      "step": 226
+    },
+    {
+      "epoch": 1.8916666666666666,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00010164977777777777,
+      "loss": 1.0833,
+      "step": 227
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00010209955555555555,
+      "loss": 0.988,
+      "step": 228
+    },
+    {
+      "epoch": 1.9083333333333332,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00010254933333333333,
+      "loss": 1.09,
+      "step": 229
+    },
+    {
+      "epoch": 1.9166666666666665,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001029991111111111,
+      "loss": 1.0349,
+      "step": 230
+    },
+    {
+      "epoch": 1.925,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00010344888888888888,
+      "loss": 1.0041,
+      "step": 231
+    },
+    {
+      "epoch": 1.9333333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00010389866666666665,
+      "loss": 0.9742,
+      "step": 232
+    },
+    {
+      "epoch": 1.9416666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00010434844444444443,
+      "loss": 0.9292,
+      "step": 233
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00010479822222222221,
+      "loss": 0.928,
+      "step": 234
+    },
+    {
+      "epoch": 1.9583333333333335,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00010524799999999999,
+      "loss": 1.0144,
+      "step": 235
+    },
+    {
+      "epoch": 1.9666666666666668,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00010569777777777777,
+      "loss": 1.0108,
+      "step": 236
+    },
+    {
+      "epoch": 1.975,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00010614755555555556,
+      "loss": 1.0626,
+      "step": 237
+    },
+    {
+      "epoch": 1.9833333333333334,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00010659733333333332,
+      "loss": 0.9509,
+      "step": 238
+    },
+    {
+      "epoch": 1.9916666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001070471111111111,
+      "loss": 0.9915,
+      "step": 239
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00010749688888888887,
+      "loss": 1.0226,
+      "step": 240
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.972268283367157,
+      "eval_runtime": 51.4444,
+      "eval_samples_per_second": 6.765,
+      "eval_steps_per_second": 1.691,
+      "step": 240
+    },
+    {
+      "epoch": 2.0083333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00010794666666666665,
+      "loss": 0.9277,
+      "step": 241
+    },
+    {
+      "epoch": 2.0166666666666666,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00010839644444444443,
+      "loss": 0.9722,
+      "step": 242
+    },
+    {
+      "epoch": 2.025,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00010884622222222223,
+      "loss": 0.9218,
+      "step": 243
+    },
+    {
+      "epoch": 2.033333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000109296,
+      "loss": 0.9367,
+      "step": 244
+    },
+    {
+      "epoch": 2.0416666666666665,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00010974577777777778,
+      "loss": 0.8274,
+      "step": 245
+    },
+    {
+      "epoch": 2.05,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00011019555555555554,
+      "loss": 0.8959,
+      "step": 246
+    },
+    {
+      "epoch": 2.058333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00011064533333333332,
+      "loss": 0.9004,
+      "step": 247
+    },
+    {
+      "epoch": 2.066666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001110951111111111,
+      "loss": 0.8918,
+      "step": 248
+    },
+    {
+      "epoch": 2.075,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00011154488888888887,
+      "loss": 0.8621,
+      "step": 249
+    },
+    {
+      "epoch": 2.0833333333333335,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00011199466666666667,
+      "loss": 0.8836,
+      "step": 250
+    },
+    {
+      "epoch": 2.091666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00011244444444444445,
+      "loss": 0.865,
+      "step": 251
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00011289422222222223,
+      "loss": 0.9642,
+      "step": 252
+    },
+    {
+      "epoch": 2.1083333333333334,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000113344,
+      "loss": 0.8609,
+      "step": 253
+    },
+    {
+      "epoch": 2.1166666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00011379377777777776,
+      "loss": 0.8087,
+      "step": 254
+    },
+    {
+      "epoch": 2.125,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00011424355555555554,
+      "loss": 0.8858,
+      "step": 255
+    },
+    {
+      "epoch": 2.125,
+      "eval_loss": 0.846684455871582,
+      "eval_runtime": 51.0779,
+      "eval_samples_per_second": 6.813,
+      "eval_steps_per_second": 1.703,
+      "step": 255
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00011469333333333333,
+      "loss": 0.8042,
+      "step": 256
+    },
+    {
+      "epoch": 2.1416666666666666,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00011514311111111111,
+      "loss": 0.8711,
+      "step": 257
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00011559288888888889,
+      "loss": 0.7992,
+      "step": 258
+    },
+    {
+      "epoch": 2.158333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00011604266666666667,
+      "loss": 0.7791,
+      "step": 259
+    },
+    {
+      "epoch": 2.1666666666666665,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00011649244444444445,
+      "loss": 0.8519,
+      "step": 260
+    },
+    {
+      "epoch": 2.175,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001169422222222222,
+      "loss": 0.8146,
+      "step": 261
+    },
+    {
+      "epoch": 2.183333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00011739199999999999,
+      "loss": 0.7742,
+      "step": 262
+    },
+    {
+      "epoch": 2.191666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00011784177777777777,
+      "loss": 0.7654,
+      "step": 263
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00011829155555555555,
+      "loss": 0.8774,
+      "step": 264
+    },
+    {
+      "epoch": 2.2083333333333335,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00011874133333333333,
+      "loss": 0.7404,
+      "step": 265
+    },
+    {
+      "epoch": 2.216666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00011919111111111111,
+      "loss": 0.7323,
+      "step": 266
+    },
+    {
+      "epoch": 2.225,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00011964088888888889,
+      "loss": 0.7127,
+      "step": 267
+    },
+    {
+      "epoch": 2.2333333333333334,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00012009066666666667,
+      "loss": 0.6607,
+      "step": 268
+    },
+    {
+      "epoch": 2.2416666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00012054044444444443,
+      "loss": 0.646,
+      "step": 269
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00012099022222222221,
+      "loss": 0.6762,
+      "step": 270
+    },
+    {
+      "epoch": 2.25,
+      "eval_loss": 0.7046697735786438,
+      "eval_runtime": 50.8887,
+      "eval_samples_per_second": 6.838,
+      "eval_steps_per_second": 1.71,
+      "step": 270
+    },
+    {
+      "epoch": 2.2583333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00012143999999999999,
+      "loss": 0.6996,
+      "step": 271
+    },
+    {
+      "epoch": 2.2666666666666666,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00012188977777777777,
+      "loss": 0.6455,
+      "step": 272
+    },
+    {
+      "epoch": 2.275,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00012233955555555556,
+      "loss": 0.6921,
+      "step": 273
+    },
+    {
+      "epoch": 2.283333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00012278933333333334,
+      "loss": 0.6742,
+      "step": 274
+    },
+    {
+      "epoch": 2.2916666666666665,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00012323911111111112,
+      "loss": 0.6279,
+      "step": 275
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001236888888888889,
+      "loss": 0.7929,
+      "step": 276
+    },
+    {
+      "epoch": 2.3083333333333336,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00012413866666666665,
+      "loss": 0.6639,
+      "step": 277
+    },
+    {
+      "epoch": 2.3166666666666664,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00012458844444444443,
+      "loss": 0.6605,
+      "step": 278
+    },
+    {
+      "epoch": 2.325,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001250382222222222,
+      "loss": 0.5845,
+      "step": 279
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000125488,
+      "loss": 0.6247,
+      "step": 280
+    },
+    {
+      "epoch": 2.341666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00012593777777777777,
+      "loss": 0.4523,
+      "step": 281
+    },
+    {
+      "epoch": 2.35,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00012638755555555555,
+      "loss": 0.5853,
+      "step": 282
+    },
+    {
+      "epoch": 2.3583333333333334,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00012683733333333333,
+      "loss": 0.6273,
+      "step": 283
+    },
+    {
+      "epoch": 2.3666666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001272871111111111,
+      "loss": 0.5683,
+      "step": 284
+    },
+    {
+      "epoch": 2.375,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00012773688888888888,
+      "loss": 0.6433,
+      "step": 285
+    },
+    {
+      "epoch": 2.375,
+      "eval_loss": 0.5625634789466858,
+      "eval_runtime": 50.9753,
+      "eval_samples_per_second": 6.827,
+      "eval_steps_per_second": 1.707,
+      "step": 285
+    },
+    {
+      "epoch": 2.3833333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00012818666666666666,
+      "loss": 0.5822,
+      "step": 286
+    },
+    {
+      "epoch": 2.3916666666666666,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00012863644444444444,
+      "loss": 0.4468,
+      "step": 287
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00012908622222222222,
+      "loss": 0.5196,
+      "step": 288
+    },
+    {
+      "epoch": 2.408333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000129536,
+      "loss": 0.4841,
+      "step": 289
+    },
+    {
+      "epoch": 2.4166666666666665,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00012998577777777778,
+      "loss": 0.4961,
+      "step": 290
+    },
+    {
+      "epoch": 2.425,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00013043555555555556,
+      "loss": 0.5136,
+      "step": 291
+    },
+    {
+      "epoch": 2.4333333333333336,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001308853333333333,
+      "loss": 0.4812,
+      "step": 292
+    },
+    {
+      "epoch": 2.4416666666666664,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001313351111111111,
+      "loss": 0.4673,
+      "step": 293
+    },
+    {
+      "epoch": 2.45,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00013178488888888887,
+      "loss": 0.5054,
+      "step": 294
+    },
+    {
+      "epoch": 2.4583333333333335,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00013223466666666665,
+      "loss": 0.4696,
+      "step": 295
+    },
+    {
+      "epoch": 2.466666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00013268444444444443,
+      "loss": 0.4592,
+      "step": 296
+    },
+    {
+      "epoch": 2.475,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001331342222222222,
+      "loss": 0.3636,
+      "step": 297
+    },
+    {
+      "epoch": 2.4833333333333334,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000133584,
+      "loss": 0.4435,
+      "step": 298
+    },
+    {
+      "epoch": 2.4916666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00013403377777777777,
+      "loss": 0.3361,
+      "step": 299
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00013448355555555555,
+      "loss": 0.4017,
+      "step": 300
+    },
+    {
+      "epoch": 2.5,
+      "eval_loss": 0.4282567501068115,
+      "eval_runtime": 252.3827,
+      "eval_samples_per_second": 1.379,
+      "eval_steps_per_second": 0.345,
+      "step": 300
+    },
+    {
+      "epoch": 2.5083333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00013493333333333332,
+      "loss": 0.4392,
+      "step": 301
+    },
+    {
+      "epoch": 2.5166666666666666,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001353831111111111,
+      "loss": 0.3808,
+      "step": 302
+    },
+    {
+      "epoch": 2.525,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00013583288888888888,
+      "loss": 0.3371,
+      "step": 303
+    },
+    {
+      "epoch": 2.533333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00013628266666666666,
+      "loss": 0.3787,
+      "step": 304
+    },
+    {
+      "epoch": 2.5416666666666665,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00013673244444444444,
+      "loss": 0.4086,
+      "step": 305
+    },
+    {
+      "epoch": 2.55,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00013718222222222222,
+      "loss": 0.3443,
+      "step": 306
+    },
+    {
+      "epoch": 2.5583333333333336,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000137632,
+      "loss": 0.4022,
+      "step": 307
+    },
+    {
+      "epoch": 2.5666666666666664,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00013808177777777775,
+      "loss": 0.3197,
+      "step": 308
+    },
+    {
+      "epoch": 2.575,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00013853155555555553,
+      "loss": 0.3359,
+      "step": 309
+    },
+    {
+      "epoch": 2.5833333333333335,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001389813333333333,
+      "loss": 0.2779,
+      "step": 310
+    },
+    {
+      "epoch": 2.591666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001394311111111111,
+      "loss": 0.429,
+      "step": 311
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00013988088888888887,
+      "loss": 0.3277,
+      "step": 312
+    },
+    {
+      "epoch": 2.6083333333333334,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00014033066666666667,
+      "loss": 0.2395,
+      "step": 313
+    },
+    {
+      "epoch": 2.6166666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00014078044444444445,
+      "loss": 0.3491,
+      "step": 314
+    },
+    {
+      "epoch": 2.625,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00014123022222222223,
+      "loss": 0.2875,
+      "step": 315
+    },
+    {
+      "epoch": 2.625,
+      "eval_loss": 0.3071797490119934,
+      "eval_runtime": 51.0753,
+      "eval_samples_per_second": 6.813,
+      "eval_steps_per_second": 1.703,
+      "step": 315
+    },
+    {
+      "epoch": 2.6333333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00014167999999999999,
+      "loss": 0.2592,
+      "step": 316
+    },
+    {
+      "epoch": 2.6416666666666666,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00014212977777777776,
+      "loss": 0.2913,
+      "step": 317
+    },
+    {
+      "epoch": 2.65,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00014257955555555554,
+      "loss": 0.2966,
+      "step": 318
+    },
+    {
+      "epoch": 2.658333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00014302933333333332,
+      "loss": 0.2124,
+      "step": 319
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001434791111111111,
+      "loss": 0.2457,
+      "step": 320
+    },
+    {
+      "epoch": 2.675,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00014392888888888888,
+      "loss": 0.2307,
+      "step": 321
+    },
+    {
+      "epoch": 2.6833333333333336,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00014437866666666666,
+      "loss": 0.2576,
+      "step": 322
+    },
+    {
+      "epoch": 2.6916666666666664,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001448284444444444,
+      "loss": 0.2424,
+      "step": 323
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001452782222222222,
+      "loss": 0.1742,
+      "step": 324
+    },
+    {
+      "epoch": 2.7083333333333335,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000145728,
+      "loss": 0.3034,
+      "step": 325
+    },
+    {
+      "epoch": 2.716666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00014617777777777778,
+      "loss": 0.2638,
+      "step": 326
+    },
+    {
+      "epoch": 2.725,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00014662755555555556,
+      "loss": 0.1894,
+      "step": 327
+    },
+    {
+      "epoch": 2.7333333333333334,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00014707733333333334,
+      "loss": 0.2501,
+      "step": 328
+    },
+    {
+      "epoch": 2.7416666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00014752711111111111,
+      "loss": 0.2122,
+      "step": 329
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001479768888888889,
+      "loss": 0.2244,
+      "step": 330
+    },
+    {
+      "epoch": 2.75,
+      "eval_loss": 0.2161068469285965,
+      "eval_runtime": 51.8399,
+      "eval_samples_per_second": 6.713,
+      "eval_steps_per_second": 1.678,
+      "step": 330
+    },
+    {
+      "epoch": 2.7583333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00014842666666666665,
+      "loss": 0.2604,
+      "step": 331
+    },
+    {
+      "epoch": 2.7666666666666666,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00014887644444444443,
+      "loss": 0.1889,
+      "step": 332
+    },
+    {
+      "epoch": 2.775,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001493262222222222,
+      "loss": 0.1788,
+      "step": 333
+    },
+    {
+      "epoch": 2.783333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00014977599999999998,
+      "loss": 0.1456,
+      "step": 334
+    },
+    {
+      "epoch": 2.7916666666666665,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00015022577777777776,
+      "loss": 0.1661,
+      "step": 335
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00015067555555555554,
+      "loss": 0.1385,
+      "step": 336
+    },
+    {
+      "epoch": 2.8083333333333336,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00015112533333333332,
+      "loss": 0.1814,
+      "step": 337
+    },
+    {
+      "epoch": 2.8166666666666664,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001515751111111111,
+      "loss": 0.1759,
+      "step": 338
+    },
+    {
+      "epoch": 2.825,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00015202488888888888,
+      "loss": 0.1617,
+      "step": 339
+    },
+    {
+      "epoch": 2.8333333333333335,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00015247466666666666,
+      "loss": 0.1349,
+      "step": 340
+    },
+    {
+      "epoch": 2.841666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00015292444444444444,
+      "loss": 0.1328,
+      "step": 341
+    },
+    {
+      "epoch": 2.85,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00015337422222222222,
+      "loss": 0.1514,
+      "step": 342
+    },
+    {
+      "epoch": 2.8583333333333334,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000153824,
+      "loss": 0.1381,
+      "step": 343
+    },
+    {
+      "epoch": 2.8666666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00015427377777777778,
+      "loss": 0.1481,
+      "step": 344
+    },
+    {
+      "epoch": 2.875,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00015472355555555555,
+      "loss": 0.1445,
+      "step": 345
+    },
+    {
+      "epoch": 2.875,
+      "eval_loss": 0.15719802677631378,
+      "eval_runtime": 256.0801,
+      "eval_samples_per_second": 1.359,
+      "eval_steps_per_second": 0.34,
+      "step": 345
+    },
+    {
+      "epoch": 2.8833333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00015517333333333333,
+      "loss": 0.1037,
+      "step": 346
+    },
+    {
+      "epoch": 2.8916666666666666,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00015562311111111109,
+      "loss": 0.1447,
+      "step": 347
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00015607288888888887,
+      "loss": 0.1325,
+      "step": 348
+    },
+    {
+      "epoch": 2.908333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00015652266666666664,
+      "loss": 0.1515,
+      "step": 349
+    },
+    {
+      "epoch": 2.9166666666666665,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00015697244444444442,
+      "loss": 0.1425,
+      "step": 350
+    },
+    {
+      "epoch": 2.925,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001574222222222222,
+      "loss": 0.1371,
+      "step": 351
+    },
+    {
+      "epoch": 2.9333333333333336,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00015787199999999998,
+      "loss": 0.1357,
+      "step": 352
+    },
+    {
+      "epoch": 2.9416666666666664,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001583217777777778,
+      "loss": 0.1254,
+      "step": 353
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00015877155555555557,
+      "loss": 0.097,
+      "step": 354
+    },
+    {
+      "epoch": 2.9583333333333335,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00015922133333333332,
+      "loss": 0.0825,
+      "step": 355
+    },
+    {
+      "epoch": 2.966666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001596711111111111,
+      "loss": 0.0993,
+      "step": 356
+    },
+    {
+      "epoch": 2.975,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00016012088888888888,
+      "loss": 0.106,
+      "step": 357
+    },
+    {
+      "epoch": 2.9833333333333334,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00016057066666666666,
+      "loss": 0.1118,
+      "step": 358
+    },
+    {
+      "epoch": 2.9916666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00016102044444444444,
+      "loss": 0.118,
+      "step": 359
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00016147022222222222,
+      "loss": 0.0898,
+      "step": 360
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.11922378093004227,
+      "eval_runtime": 51.7639,
+      "eval_samples_per_second": 6.723,
+      "eval_steps_per_second": 1.681,
+      "step": 360
+    },
+    {
+      "epoch": 3.0083333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00016192,
+      "loss": 0.1172,
+      "step": 361
+    },
+    {
+      "epoch": 3.0166666666666666,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00016236977777777775,
+      "loss": 0.1117,
+      "step": 362
+    },
+    {
+      "epoch": 3.025,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00016281955555555553,
+      "loss": 0.0926,
+      "step": 363
+    },
+    {
+      "epoch": 3.033333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001632693333333333,
+      "loss": 0.0743,
+      "step": 364
+    },
+    {
+      "epoch": 3.0416666666666665,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001637191111111111,
+      "loss": 0.0797,
+      "step": 365
+    },
+    {
+      "epoch": 3.05,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001641688888888889,
+      "loss": 0.0954,
+      "step": 366
+    },
+    {
+      "epoch": 3.058333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00016461866666666667,
+      "loss": 0.086,
+      "step": 367
+    },
+    {
+      "epoch": 3.066666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00016506844444444445,
+      "loss": 0.0932,
+      "step": 368
+    },
+    {
+      "epoch": 3.075,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00016551822222222223,
+      "loss": 0.0999,
+      "step": 369
+    },
+    {
+      "epoch": 3.0833333333333335,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00016596799999999998,
+      "loss": 0.096,
+      "step": 370
+    },
+    {
+      "epoch": 3.091666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00016641777777777776,
+      "loss": 0.0974,
+      "step": 371
+    },
+    {
+      "epoch": 3.1,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00016686755555555554,
+      "loss": 0.0758,
+      "step": 372
+    },
+    {
+      "epoch": 3.1083333333333334,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00016731733333333332,
+      "loss": 0.0613,
+      "step": 373
+    },
+    {
+      "epoch": 3.1166666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001677671111111111,
+      "loss": 0.08,
+      "step": 374
+    },
+    {
+      "epoch": 3.125,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00016821688888888888,
+      "loss": 0.0666,
+      "step": 375
+    },
+    {
+      "epoch": 3.125,
+      "eval_loss": 0.09909001737833023,
+      "eval_runtime": 51.5782,
+      "eval_samples_per_second": 6.747,
+      "eval_steps_per_second": 1.687,
+      "step": 375
+    },
+    {
+      "epoch": 3.1333333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00016866666666666666,
+      "loss": 0.0785,
+      "step": 376
+    },
+    {
+      "epoch": 3.1416666666666666,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00016911644444444443,
+      "loss": 0.0905,
+      "step": 377
+    },
+    {
+      "epoch": 3.15,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00016956622222222221,
+      "loss": 0.0776,
+      "step": 378
+    },
+    {
+      "epoch": 3.158333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000170016,
+      "loss": 0.062,
+      "step": 379
+    },
+    {
+      "epoch": 3.1666666666666665,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00017046577777777777,
+      "loss": 0.0983,
+      "step": 380
+    },
+    {
+      "epoch": 3.175,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00017091555555555555,
+      "loss": 0.0857,
+      "step": 381
+    },
+    {
+      "epoch": 3.183333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00017136533333333333,
+      "loss": 0.0659,
+      "step": 382
+    },
+    {
+      "epoch": 3.191666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001718151111111111,
+      "loss": 0.0618,
+      "step": 383
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001722648888888889,
+      "loss": 0.0526,
+      "step": 384
+    },
+    {
+      "epoch": 3.2083333333333335,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00017271466666666667,
+      "loss": 0.0763,
+      "step": 385
+    },
+    {
+      "epoch": 3.216666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00017316444444444442,
+      "loss": 0.0771,
+      "step": 386
+    },
+    {
+      "epoch": 3.225,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001736142222222222,
+      "loss": 0.066,
+      "step": 387
+    },
+    {
+      "epoch": 3.2333333333333334,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00017406399999999998,
+      "loss": 0.0714,
+      "step": 388
+    },
+    {
+      "epoch": 3.2416666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00017451377777777776,
+      "loss": 0.0555,
+      "step": 389
+    },
+    {
+      "epoch": 3.25,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00017496355555555554,
+      "loss": 0.0605,
+      "step": 390
+    },
+    {
+      "epoch": 3.25,
+      "eval_loss": 0.08554459363222122,
+      "eval_runtime": 52.4745,
+      "eval_samples_per_second": 6.632,
+      "eval_steps_per_second": 1.658,
+      "step": 390
+    },
+    {
+      "epoch": 3.2583333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00017541333333333332,
+      "loss": 0.0689,
+      "step": 391
+    },
+    {
+      "epoch": 3.2666666666666666,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001758631111111111,
+      "loss": 0.0905,
+      "step": 392
+    },
+    {
+      "epoch": 3.275,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00017631288888888887,
+      "loss": 0.0704,
+      "step": 393
+    },
+    {
+      "epoch": 3.283333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00017676266666666665,
+      "loss": 0.078,
+      "step": 394
+    },
+    {
+      "epoch": 3.2916666666666665,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00017721244444444443,
+      "loss": 0.0452,
+      "step": 395
+    },
+    {
+      "epoch": 3.3,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001776622222222222,
+      "loss": 0.0723,
+      "step": 396
+    },
+    {
+      "epoch": 3.3083333333333336,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000178112,
+      "loss": 0.0684,
+      "step": 397
+    },
+    {
+      "epoch": 3.3166666666666664,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00017856177777777777,
+      "loss": 0.0607,
+      "step": 398
+    },
+    {
+      "epoch": 3.325,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00017901155555555555,
+      "loss": 0.0749,
+      "step": 399
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00017946133333333333,
+      "loss": 0.0824,
+      "step": 400
+    },
+    {
+      "epoch": 3.341666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00017991111111111108,
+      "loss": 0.0887,
+      "step": 401
+    },
+    {
+      "epoch": 3.35,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00018036088888888886,
+      "loss": 0.071,
+      "step": 402
+    },
+    {
+      "epoch": 3.3583333333333334,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00018081066666666664,
+      "loss": 0.0612,
+      "step": 403
+    },
+    {
+      "epoch": 3.3666666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00018126044444444442,
+      "loss": 0.0549,
+      "step": 404
+    },
+    {
+      "epoch": 3.375,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00018171022222222223,
+      "loss": 0.0457,
+      "step": 405
+    },
+    {
+      "epoch": 3.375,
+      "eval_loss": 0.07573261111974716,
+      "eval_runtime": 52.4896,
+      "eval_samples_per_second": 6.63,
+      "eval_steps_per_second": 1.657,
+      "step": 405
+    },
+    {
+      "epoch": 3.3833333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00018216,
+      "loss": 0.0722,
+      "step": 406
+    },
+    {
+      "epoch": 3.3916666666666666,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00018260977777777778,
+      "loss": 0.0446,
+      "step": 407
+    },
+    {
+      "epoch": 3.4,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00018305955555555556,
+      "loss": 0.0574,
+      "step": 408
+    },
+    {
+      "epoch": 3.408333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00018350933333333331,
+      "loss": 0.0426,
+      "step": 409
+    },
+    {
+      "epoch": 3.4166666666666665,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001839591111111111,
+      "loss": 0.071,
+      "step": 410
+    },
+    {
+      "epoch": 3.425,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00018440888888888887,
+      "loss": 0.0387,
+      "step": 411
+    },
+    {
+      "epoch": 3.4333333333333336,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00018485866666666665,
+      "loss": 0.0563,
+      "step": 412
+    },
+    {
+      "epoch": 3.4416666666666664,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00018530844444444443,
+      "loss": 0.054,
+      "step": 413
+    },
+    {
+      "epoch": 3.45,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001857582222222222,
+      "loss": 0.056,
+      "step": 414
+    },
+    {
+      "epoch": 3.4583333333333335,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000186208,
+      "loss": 0.0457,
+      "step": 415
+    },
+    {
+      "epoch": 3.466666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00018665777777777777,
+      "loss": 0.0506,
+      "step": 416
+    },
+    {
+      "epoch": 3.475,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00018710755555555552,
+      "loss": 0.0563,
+      "step": 417
+    },
+    {
+      "epoch": 3.4833333333333334,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00018755733333333333,
+      "loss": 0.0605,
+      "step": 418
+    },
+    {
+      "epoch": 3.4916666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001880071111111111,
+      "loss": 0.0414,
+      "step": 419
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00018845688888888889,
+      "loss": 0.052,
+      "step": 420
+    },
+    {
+      "epoch": 3.5,
+      "eval_loss": 0.07001237571239471,
+      "eval_runtime": 254.9703,
+      "eval_samples_per_second": 1.365,
+      "eval_steps_per_second": 0.341,
+      "step": 420
+    },
+    {
+      "epoch": 3.5083333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00018890666666666667,
+      "loss": 0.058,
+      "step": 421
+    },
+    {
+      "epoch": 3.5166666666666666,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00018935644444444444,
+      "loss": 0.0433,
+      "step": 422
+    },
+    {
+      "epoch": 3.525,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00018980622222222222,
+      "loss": 0.0556,
+      "step": 423
+    },
+    {
+      "epoch": 3.533333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019025599999999998,
+      "loss": 0.0416,
+      "step": 424
+    },
+    {
+      "epoch": 3.5416666666666665,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019070577777777775,
+      "loss": 0.043,
+      "step": 425
+    },
+    {
+      "epoch": 3.55,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019115555555555553,
+      "loss": 0.0524,
+      "step": 426
+    },
+    {
+      "epoch": 3.5583333333333336,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001916053333333333,
+      "loss": 0.0512,
+      "step": 427
+    },
+    {
+      "epoch": 3.5666666666666664,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001920551111111111,
+      "loss": 0.0482,
+      "step": 428
+    },
+    {
+      "epoch": 3.575,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019250488888888887,
+      "loss": 0.0727,
+      "step": 429
+    },
+    {
+      "epoch": 3.5833333333333335,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019295466666666665,
+      "loss": 0.068,
+      "step": 430
+    },
+    {
+      "epoch": 3.591666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019340444444444443,
+      "loss": 0.0536,
+      "step": 431
+    },
+    {
+      "epoch": 3.6,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001938542222222222,
+      "loss": 0.0508,
+      "step": 432
+    },
+    {
+      "epoch": 3.6083333333333334,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000194304,
+      "loss": 0.0531,
+      "step": 433
+    },
+    {
+      "epoch": 3.6166666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019475377777777777,
+      "loss": 0.0569,
+      "step": 434
+    },
+    {
+      "epoch": 3.625,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019520355555555555,
+      "loss": 0.0634,
+      "step": 435
+    },
+    {
+      "epoch": 3.625,
+      "eval_loss": 0.06579854339361191,
+      "eval_runtime": 52.0968,
+      "eval_samples_per_second": 6.68,
+      "eval_steps_per_second": 1.67,
+      "step": 435
+    },
+    {
+      "epoch": 3.6333333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019565333333333333,
+      "loss": 0.0535,
+      "step": 436
+    },
+    {
+      "epoch": 3.6416666666666666,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001961031111111111,
+      "loss": 0.051,
+      "step": 437
+    },
+    {
+      "epoch": 3.65,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019655288888888888,
+      "loss": 0.0482,
+      "step": 438
+    },
+    {
+      "epoch": 3.658333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019700266666666666,
+      "loss": 0.0589,
+      "step": 439
+    },
+    {
+      "epoch": 3.6666666666666665,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019745244444444442,
+      "loss": 0.0587,
+      "step": 440
+    },
+    {
+      "epoch": 3.675,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001979022222222222,
+      "loss": 0.0566,
+      "step": 441
+    },
+    {
+      "epoch": 3.6833333333333336,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019835199999999997,
+      "loss": 0.054,
+      "step": 442
+    },
+    {
+      "epoch": 3.6916666666666664,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019880177777777775,
+      "loss": 0.0535,
+      "step": 443
+    },
+    {
+      "epoch": 3.7,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019925155555555553,
+      "loss": 0.0537,
+      "step": 444
+    },
+    {
+      "epoch": 3.7083333333333335,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019970133333333334,
+      "loss": 0.0486,
+      "step": 445
+    },
+    {
+      "epoch": 3.716666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00020015111111111112,
+      "loss": 0.0609,
+      "step": 446
+    },
+    {
+      "epoch": 3.725,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0002006008888888889,
+      "loss": 0.0543,
+      "step": 447
+    },
+    {
+      "epoch": 3.7333333333333334,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00020105066666666665,
+      "loss": 0.0542,
+      "step": 448
+    },
+    {
+      "epoch": 3.7416666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00020150044444444443,
+      "loss": 0.0371,
+      "step": 449
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0002019502222222222,
+      "loss": 0.0364,
+      "step": 450
+    },
+    {
+      "epoch": 3.75,
+      "eval_loss": 0.062348127365112305,
+      "eval_runtime": 52.3744,
+      "eval_samples_per_second": 6.644,
+      "eval_steps_per_second": 1.661,
+      "step": 450
+    },
+    {
+      "epoch": 3.7583333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0002024,
+      "loss": 0.0509,
+      "step": 451
+    },
+    {
+      "epoch": 3.7666666666666666,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00020237780516765434,
+      "loss": 0.0429,
+      "step": 452
+    },
+    {
+      "epoch": 3.775,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00020231123040600446,
+      "loss": 0.0418,
+      "step": 453
+    },
+    {
+      "epoch": 3.783333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00020220030491694107,
+      "loss": 0.0622,
+      "step": 454
+    },
+    {
+      "epoch": 3.7916666666666665,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00020204507735604982,
+      "loss": 0.0509,
+      "step": 455
+    },
+    {
+      "epoch": 3.8,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00020184561581126925,
+      "loss": 0.044,
+      "step": 456
+    },
+    {
+      "epoch": 3.8083333333333336,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00020160200777302517,
+      "loss": 0.0497,
+      "step": 457
+    },
+    {
+      "epoch": 3.8166666666666664,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0002013143600958544,
+      "loss": 0.036,
+      "step": 458
+    },
+    {
+      "epoch": 3.825,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00020098279895153508,
+      "loss": 0.0518,
+      "step": 459
+    },
+    {
+      "epoch": 3.8333333333333335,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0002006074697737433,
+      "loss": 0.0458,
+      "step": 460
+    },
+    {
+      "epoch": 3.841666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00020018853719426112,
+      "loss": 0.0518,
+      "step": 461
+    },
+    {
+      "epoch": 3.85,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001997261849707638,
+      "loss": 0.0572,
+      "step": 462
+    },
+    {
+      "epoch": 3.8583333333333334,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019922061590621745,
+      "loss": 0.038,
+      "step": 463
+    },
+    {
+      "epoch": 3.8666666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000198672051759923,
+      "loss": 0.0456,
+      "step": 464
+    },
+    {
+      "epoch": 3.875,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019808073315024519,
+      "loss": 0.045,
+      "step": 465
+    },
+    {
+      "epoch": 3.875,
+      "eval_loss": 0.060108914971351624,
+      "eval_runtime": 52.0507,
+      "eval_samples_per_second": 6.686,
+      "eval_steps_per_second": 1.671,
+      "step": 465
+    },
+    {
+      "epoch": 3.8833333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019744691944906953,
+      "loss": 0.0451,
+      "step": 466
+    },
+    {
+      "epoch": 3.8916666666666666,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019677088866803307,
+      "loss": 0.0555,
+      "step": 467
+    },
+    {
+      "epoch": 3.9,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019605293733657942,
+      "loss": 0.0441,
+      "step": 468
+    },
+    {
+      "epoch": 3.908333333333333,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019529338037189102,
+      "loss": 0.0437,
+      "step": 469
+    },
+    {
+      "epoch": 3.9166666666666665,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019449255094075623,
+      "loss": 0.0395,
+      "step": 470
+    },
+    {
+      "epoch": 3.925,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019365080031343119,
+      "loss": 0.0519,
+      "step": 471
+    },
+    {
+      "epoch": 3.9333333333333336,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019276849770956118,
+      "loss": 0.0554,
+      "step": 472
+    },
+    {
+      "epoch": 3.9416666666666664,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019184603013622857,
+      "loss": 0.0543,
+      "step": 473
+    },
+    {
+      "epoch": 3.95,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019088380221819892,
+      "loss": 0.052,
+      "step": 474
+    },
+    {
+      "epoch": 3.9583333333333335,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00018988223602043897,
+      "loss": 0.0478,
+      "step": 475
+    },
+    {
+      "epoch": 3.966666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00018884177086298518,
+      "loss": 0.0423,
+      "step": 476
+    },
+    {
+      "epoch": 3.975,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00018776286312824326,
+      "loss": 0.0601,
+      "step": 477
+    },
+    {
+      "epoch": 3.9833333333333334,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001866459860608039,
+      "loss": 0.0463,
+      "step": 478
+    },
+    {
+      "epoch": 3.9916666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00018549162955986206,
+      "loss": 0.0335,
+      "step": 479
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00018430029996433083,
+      "loss": 0.0395,
+      "step": 480
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.05822588875889778,
+      "eval_runtime": 52.1323,
+      "eval_samples_per_second": 6.675,
+      "eval_steps_per_second": 1.669,
+      "step": 480
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 600,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 120,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.3912481583857664e+18,
+  "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 sha256:834d9c09dd737d8296bf1d9f8e6dc2d5bbb82993ab8e4483eec68d12fa59aeb9
+size 10552