Add files using upload-large-folder tool

checkpoint-304/config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 11,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 770,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "unsloth_version": "2024.9",
+  "use_cache": false,
+  "vocab_size": 32768
+}

checkpoint-304/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 11,
+  "max_length": 32768,
+  "pad_token_id": 770,
+  "transformers_version": "4.51.3"
+}

checkpoint-304/model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0b14885f943acc2708e9566aaad7ef85de800f1597c6ac0516696422315ff2e
+size 4949453792

checkpoint-304/model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0f7c105d7763a6e131d9f71d6b3243d22083cc683b922071235fd722c33252c
+size 4999819336

checkpoint-304/model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6f1e8d5335f248425c05cbb9a5c4d7435fa7fd956d6d28cc229f43c0d8a257a
+size 4546807800

checkpoint-304/model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 14496047104
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

checkpoint-304/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e2853c5ac60da87e62054b95f2662aadef4b9817cae4e64b4a576650d079e08
+size 28992288510

checkpoint-304/pytorch_model_fsdp.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd8eed501f04fd6683670b78314ee32bacf7d63bcc594e61548308374d270ba0
+size 14496203157

checkpoint-304/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad792af33c7cfa8b15298ecc9d976ebdcdeb444ca0e704c7b0657f41ee6547eb
+size 14512

checkpoint-304/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:722c924fceffd85f8ab1a5445f1ea1e6c502644b6a42e2ff6b5a9a76ea26e1fe
+size 14512

checkpoint-304/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dbc599ef7f0cc1e70ab9a24d54921de07b373f12ec567339851026072f201a4
+size 1064

checkpoint-304/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[control_768]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-304/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93e01cb5f215abfe797344a3b7bf0e874b49708177a8b115bbdde722983e3948
+size 587414

checkpoint-304/trainer_state.json

@@ -0,0 +1,2162 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.25136950904392763,
+  "eval_steps": 500,
+  "global_step": 304,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0008268733850129199,
+      "grad_norm": 9.3125,
+      "learning_rate": 0.0,
+      "loss": 0.7807,
+      "step": 1
+    },
+    {
+      "epoch": 0.0016537467700258397,
+      "grad_norm": 10.0625,
+      "learning_rate": 1.3888888888888888e-07,
+      "loss": 0.807,
+      "step": 2
+    },
+    {
+      "epoch": 0.00248062015503876,
+      "grad_norm": 10.125,
+      "learning_rate": 2.7777777777777776e-07,
+      "loss": 0.7777,
+      "step": 3
+    },
+    {
+      "epoch": 0.0033074935400516795,
+      "grad_norm": 9.4375,
+      "learning_rate": 4.1666666666666667e-07,
+      "loss": 0.8004,
+      "step": 4
+    },
+    {
+      "epoch": 0.004134366925064599,
+      "grad_norm": 9.5,
+      "learning_rate": 5.555555555555555e-07,
+      "loss": 0.758,
+      "step": 5
+    },
+    {
+      "epoch": 0.00496124031007752,
+      "grad_norm": 9.375,
+      "learning_rate": 6.944444444444446e-07,
+      "loss": 0.7734,
+      "step": 6
+    },
+    {
+      "epoch": 0.005788113695090439,
+      "grad_norm": 9.4375,
+      "learning_rate": 8.333333333333333e-07,
+      "loss": 0.7796,
+      "step": 7
+    },
+    {
+      "epoch": 0.006614987080103359,
+      "grad_norm": 9.125,
+      "learning_rate": 9.722222222222224e-07,
+      "loss": 0.7286,
+      "step": 8
+    },
+    {
+      "epoch": 0.0074418604651162795,
+      "grad_norm": 6.53125,
+      "learning_rate": 1.111111111111111e-06,
+      "loss": 0.7508,
+      "step": 9
+    },
+    {
+      "epoch": 0.008268733850129198,
+      "grad_norm": 5.0625,
+      "learning_rate": 1.25e-06,
+      "loss": 0.7876,
+      "step": 10
+    },
+    {
+      "epoch": 0.00909560723514212,
+      "grad_norm": 4.65625,
+      "learning_rate": 1.3888888888888892e-06,
+      "loss": 0.7366,
+      "step": 11
+    },
+    {
+      "epoch": 0.00992248062015504,
+      "grad_norm": 4.375,
+      "learning_rate": 1.527777777777778e-06,
+      "loss": 0.7202,
+      "step": 12
+    },
+    {
+      "epoch": 0.010749354005167959,
+      "grad_norm": 4.125,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 0.7474,
+      "step": 13
+    },
+    {
+      "epoch": 0.011576227390180879,
+      "grad_norm": 3.65625,
+      "learning_rate": 1.8055555555555557e-06,
+      "loss": 0.7167,
+      "step": 14
+    },
+    {
+      "epoch": 0.012403100775193798,
+      "grad_norm": 3.234375,
+      "learning_rate": 1.944444444444445e-06,
+      "loss": 0.6981,
+      "step": 15
+    },
+    {
+      "epoch": 0.013229974160206718,
+      "grad_norm": 2.8125,
+      "learning_rate": 2.0833333333333334e-06,
+      "loss": 0.7024,
+      "step": 16
+    },
+    {
+      "epoch": 0.014056847545219638,
+      "grad_norm": 2.40625,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 0.6872,
+      "step": 17
+    },
+    {
+      "epoch": 0.014883720930232559,
+      "grad_norm": 2.421875,
+      "learning_rate": 2.361111111111111e-06,
+      "loss": 0.6761,
+      "step": 18
+    },
+    {
+      "epoch": 0.015710594315245477,
+      "grad_norm": 2.359375,
+      "learning_rate": 2.5e-06,
+      "loss": 0.6718,
+      "step": 19
+    },
+    {
+      "epoch": 0.016537467700258397,
+      "grad_norm": 2.1875,
+      "learning_rate": 2.6388888888888893e-06,
+      "loss": 0.6712,
+      "step": 20
+    },
+    {
+      "epoch": 0.017364341085271316,
+      "grad_norm": 1.984375,
+      "learning_rate": 2.7777777777777783e-06,
+      "loss": 0.6373,
+      "step": 21
+    },
+    {
+      "epoch": 0.01819121447028424,
+      "grad_norm": 1.96875,
+      "learning_rate": 2.916666666666667e-06,
+      "loss": 0.6671,
+      "step": 22
+    },
+    {
+      "epoch": 0.01901808785529716,
+      "grad_norm": 1.921875,
+      "learning_rate": 3.055555555555556e-06,
+      "loss": 0.6594,
+      "step": 23
+    },
+    {
+      "epoch": 0.01984496124031008,
+      "grad_norm": 1.9140625,
+      "learning_rate": 3.1944444444444443e-06,
+      "loss": 0.6327,
+      "step": 24
+    },
+    {
+      "epoch": 0.020671834625323,
+      "grad_norm": 1.9140625,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.6183,
+      "step": 25
+    },
+    {
+      "epoch": 0.021498708010335918,
+      "grad_norm": 1.9296875,
+      "learning_rate": 3.4722222222222224e-06,
+      "loss": 0.6796,
+      "step": 26
+    },
+    {
+      "epoch": 0.022325581395348838,
+      "grad_norm": 1.8203125,
+      "learning_rate": 3.6111111111111115e-06,
+      "loss": 0.5912,
+      "step": 27
+    },
+    {
+      "epoch": 0.023152454780361757,
+      "grad_norm": 2.015625,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.6317,
+      "step": 28
+    },
+    {
+      "epoch": 0.023979328165374677,
+      "grad_norm": 1.6953125,
+      "learning_rate": 3.88888888888889e-06,
+      "loss": 0.6158,
+      "step": 29
+    },
+    {
+      "epoch": 0.024806201550387597,
+      "grad_norm": 1.84375,
+      "learning_rate": 4.027777777777779e-06,
+      "loss": 0.6281,
+      "step": 30
+    },
+    {
+      "epoch": 0.025633074935400516,
+      "grad_norm": 1.78125,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 0.6514,
+      "step": 31
+    },
+    {
+      "epoch": 0.026459948320413436,
+      "grad_norm": 1.78125,
+      "learning_rate": 4.305555555555556e-06,
+      "loss": 0.6462,
+      "step": 32
+    },
+    {
+      "epoch": 0.027286821705426356,
+      "grad_norm": 1.671875,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 0.5989,
+      "step": 33
+    },
+    {
+      "epoch": 0.028113695090439275,
+      "grad_norm": 1.78125,
+      "learning_rate": 4.583333333333333e-06,
+      "loss": 0.6209,
+      "step": 34
+    },
+    {
+      "epoch": 0.028940568475452195,
+      "grad_norm": 1.7109375,
+      "learning_rate": 4.722222222222222e-06,
+      "loss": 0.5746,
+      "step": 35
+    },
+    {
+      "epoch": 0.029767441860465118,
+      "grad_norm": 1.9296875,
+      "learning_rate": 4.861111111111111e-06,
+      "loss": 0.6193,
+      "step": 36
+    },
+    {
+      "epoch": 0.030594315245478038,
+      "grad_norm": 2.09375,
+      "learning_rate": 5e-06,
+      "loss": 0.5964,
+      "step": 37
+    },
+    {
+      "epoch": 0.031421188630490954,
+      "grad_norm": 1.75,
+      "learning_rate": 5.138888888888889e-06,
+      "loss": 0.6042,
+      "step": 38
+    },
+    {
+      "epoch": 0.03224806201550388,
+      "grad_norm": 1.9921875,
+      "learning_rate": 5.2777777777777785e-06,
+      "loss": 0.6279,
+      "step": 39
+    },
+    {
+      "epoch": 0.03307493540051679,
+      "grad_norm": 1.8984375,
+      "learning_rate": 5.416666666666667e-06,
+      "loss": 0.5817,
+      "step": 40
+    },
+    {
+      "epoch": 0.033901808785529716,
+      "grad_norm": 1.984375,
+      "learning_rate": 5.555555555555557e-06,
+      "loss": 0.5953,
+      "step": 41
+    },
+    {
+      "epoch": 0.03472868217054263,
+      "grad_norm": 1.96875,
+      "learning_rate": 5.694444444444445e-06,
+      "loss": 0.643,
+      "step": 42
+    },
+    {
+      "epoch": 0.035555555555555556,
+      "grad_norm": 2.1875,
+      "learning_rate": 5.833333333333334e-06,
+      "loss": 0.5623,
+      "step": 43
+    },
+    {
+      "epoch": 0.03638242894056848,
+      "grad_norm": 1.8515625,
+      "learning_rate": 5.972222222222222e-06,
+      "loss": 0.6095,
+      "step": 44
+    },
+    {
+      "epoch": 0.037209302325581395,
+      "grad_norm": 2.046875,
+      "learning_rate": 6.111111111111112e-06,
+      "loss": 0.6041,
+      "step": 45
+    },
+    {
+      "epoch": 0.03803617571059432,
+      "grad_norm": 1.78125,
+      "learning_rate": 6.25e-06,
+      "loss": 0.5822,
+      "step": 46
+    },
+    {
+      "epoch": 0.038863049095607234,
+      "grad_norm": 1.921875,
+      "learning_rate": 6.3888888888888885e-06,
+      "loss": 0.6468,
+      "step": 47
+    },
+    {
+      "epoch": 0.03968992248062016,
+      "grad_norm": 1.8984375,
+      "learning_rate": 6.5277777777777784e-06,
+      "loss": 0.5941,
+      "step": 48
+    },
+    {
+      "epoch": 0.04051679586563307,
+      "grad_norm": 1.84375,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.5688,
+      "step": 49
+    },
+    {
+      "epoch": 0.041343669250646,
+      "grad_norm": 1.8671875,
+      "learning_rate": 6.8055555555555566e-06,
+      "loss": 0.5625,
+      "step": 50
+    },
+    {
+      "epoch": 0.04217054263565891,
+      "grad_norm": 1.8203125,
+      "learning_rate": 6.944444444444445e-06,
+      "loss": 0.593,
+      "step": 51
+    },
+    {
+      "epoch": 0.042997416020671836,
+      "grad_norm": 1.8359375,
+      "learning_rate": 7.083333333333335e-06,
+      "loss": 0.6545,
+      "step": 52
+    },
+    {
+      "epoch": 0.04382428940568475,
+      "grad_norm": 1.765625,
+      "learning_rate": 7.222222222222223e-06,
+      "loss": 0.5607,
+      "step": 53
+    },
+    {
+      "epoch": 0.044651162790697675,
+      "grad_norm": 1.9765625,
+      "learning_rate": 7.361111111111112e-06,
+      "loss": 0.6131,
+      "step": 54
+    },
+    {
+      "epoch": 0.04547803617571059,
+      "grad_norm": 1.796875,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.5849,
+      "step": 55
+    },
+    {
+      "epoch": 0.046304909560723514,
+      "grad_norm": 1.90625,
+      "learning_rate": 7.638888888888888e-06,
+      "loss": 0.6018,
+      "step": 56
+    },
+    {
+      "epoch": 0.04713178294573643,
+      "grad_norm": 1.625,
+      "learning_rate": 7.77777777777778e-06,
+      "loss": 0.5435,
+      "step": 57
+    },
+    {
+      "epoch": 0.047958656330749354,
+      "grad_norm": 1.90625,
+      "learning_rate": 7.916666666666667e-06,
+      "loss": 0.5463,
+      "step": 58
+    },
+    {
+      "epoch": 0.04878552971576228,
+      "grad_norm": 1.8125,
+      "learning_rate": 8.055555555555557e-06,
+      "loss": 0.5828,
+      "step": 59
+    },
+    {
+      "epoch": 0.04961240310077519,
+      "grad_norm": 1.734375,
+      "learning_rate": 8.194444444444445e-06,
+      "loss": 0.6034,
+      "step": 60
+    },
+    {
+      "epoch": 0.050439276485788116,
+      "grad_norm": 1.6328125,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.5516,
+      "step": 61
+    },
+    {
+      "epoch": 0.05126614987080103,
+      "grad_norm": 1.7890625,
+      "learning_rate": 8.472222222222223e-06,
+      "loss": 0.5926,
+      "step": 62
+    },
+    {
+      "epoch": 0.052093023255813956,
+      "grad_norm": 1.703125,
+      "learning_rate": 8.611111111111112e-06,
+      "loss": 0.5966,
+      "step": 63
+    },
+    {
+      "epoch": 0.05291989664082687,
+      "grad_norm": 1.8359375,
+      "learning_rate": 8.750000000000001e-06,
+      "loss": 0.5601,
+      "step": 64
+    },
+    {
+      "epoch": 0.053746770025839795,
+      "grad_norm": 1.9296875,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 0.5873,
+      "step": 65
+    },
+    {
+      "epoch": 0.05457364341085271,
+      "grad_norm": 1.7734375,
+      "learning_rate": 9.027777777777779e-06,
+      "loss": 0.5693,
+      "step": 66
+    },
+    {
+      "epoch": 0.055400516795865634,
+      "grad_norm": 1.7109375,
+      "learning_rate": 9.166666666666666e-06,
+      "loss": 0.5481,
+      "step": 67
+    },
+    {
+      "epoch": 0.05622739018087855,
+      "grad_norm": 2.09375,
+      "learning_rate": 9.305555555555557e-06,
+      "loss": 0.5821,
+      "step": 68
+    },
+    {
+      "epoch": 0.05705426356589147,
+      "grad_norm": 1.796875,
+      "learning_rate": 9.444444444444445e-06,
+      "loss": 0.5947,
+      "step": 69
+    },
+    {
+      "epoch": 0.05788113695090439,
+      "grad_norm": 2.4375,
+      "learning_rate": 9.583333333333335e-06,
+      "loss": 0.5564,
+      "step": 70
+    },
+    {
+      "epoch": 0.05870801033591731,
+      "grad_norm": 1.8828125,
+      "learning_rate": 9.722222222222223e-06,
+      "loss": 0.6348,
+      "step": 71
+    },
+    {
+      "epoch": 0.059534883720930236,
+      "grad_norm": 2.046875,
+      "learning_rate": 9.861111111111112e-06,
+      "loss": 0.5784,
+      "step": 72
+    },
+    {
+      "epoch": 0.06036175710594315,
+      "grad_norm": 1.90625,
+      "learning_rate": 1e-05,
+      "loss": 0.5513,
+      "step": 73
+    },
+    {
+      "epoch": 0.061188630490956075,
+      "grad_norm": 2.15625,
+      "learning_rate": 9.995737425404945e-06,
+      "loss": 0.6001,
+      "step": 74
+    },
+    {
+      "epoch": 0.06201550387596899,
+      "grad_norm": 2.171875,
+      "learning_rate": 9.99147485080989e-06,
+      "loss": 0.5978,
+      "step": 75
+    },
+    {
+      "epoch": 0.06284237726098191,
+      "grad_norm": 1.734375,
+      "learning_rate": 9.987212276214835e-06,
+      "loss": 0.5617,
+      "step": 76
+    },
+    {
+      "epoch": 0.06366925064599484,
+      "grad_norm": 1.9375,
+      "learning_rate": 9.98294970161978e-06,
+      "loss": 0.5891,
+      "step": 77
+    },
+    {
+      "epoch": 0.06449612403100775,
+      "grad_norm": 1.953125,
+      "learning_rate": 9.978687127024723e-06,
+      "loss": 0.5594,
+      "step": 78
+    },
+    {
+      "epoch": 0.06532299741602067,
+      "grad_norm": 1.8359375,
+      "learning_rate": 9.974424552429668e-06,
+      "loss": 0.575,
+      "step": 79
+    },
+    {
+      "epoch": 0.06614987080103359,
+      "grad_norm": 1.890625,
+      "learning_rate": 9.970161977834612e-06,
+      "loss": 0.5653,
+      "step": 80
+    },
+    {
+      "epoch": 0.06697674418604652,
+      "grad_norm": 1.7265625,
+      "learning_rate": 9.965899403239558e-06,
+      "loss": 0.6024,
+      "step": 81
+    },
+    {
+      "epoch": 0.06780361757105943,
+      "grad_norm": 1.75,
+      "learning_rate": 9.961636828644502e-06,
+      "loss": 0.5823,
+      "step": 82
+    },
+    {
+      "epoch": 0.06863049095607235,
+      "grad_norm": 1.8359375,
+      "learning_rate": 9.957374254049446e-06,
+      "loss": 0.6131,
+      "step": 83
+    },
+    {
+      "epoch": 0.06945736434108526,
+      "grad_norm": 1.7265625,
+      "learning_rate": 9.953111679454392e-06,
+      "loss": 0.5958,
+      "step": 84
+    },
+    {
+      "epoch": 0.0702842377260982,
+      "grad_norm": 1.6875,
+      "learning_rate": 9.948849104859336e-06,
+      "loss": 0.5665,
+      "step": 85
+    },
+    {
+      "epoch": 0.07111111111111111,
+      "grad_norm": 1.9609375,
+      "learning_rate": 9.944586530264282e-06,
+      "loss": 0.5641,
+      "step": 86
+    },
+    {
+      "epoch": 0.07193798449612403,
+      "grad_norm": 1.921875,
+      "learning_rate": 9.940323955669226e-06,
+      "loss": 0.5881,
+      "step": 87
+    },
+    {
+      "epoch": 0.07276485788113696,
+      "grad_norm": 1.8203125,
+      "learning_rate": 9.93606138107417e-06,
+      "loss": 0.5541,
+      "step": 88
+    },
+    {
+      "epoch": 0.07359173126614987,
+      "grad_norm": 1.90625,
+      "learning_rate": 9.931798806479114e-06,
+      "loss": 0.5806,
+      "step": 89
+    },
+    {
+      "epoch": 0.07441860465116279,
+      "grad_norm": 1.8203125,
+      "learning_rate": 9.927536231884058e-06,
+      "loss": 0.6086,
+      "step": 90
+    },
+    {
+      "epoch": 0.0752454780361757,
+      "grad_norm": 1.59375,
+      "learning_rate": 9.923273657289003e-06,
+      "loss": 0.5989,
+      "step": 91
+    },
+    {
+      "epoch": 0.07607235142118864,
+      "grad_norm": 1.765625,
+      "learning_rate": 9.919011082693947e-06,
+      "loss": 0.598,
+      "step": 92
+    },
+    {
+      "epoch": 0.07689922480620155,
+      "grad_norm": 1.4765625,
+      "learning_rate": 9.914748508098893e-06,
+      "loss": 0.5301,
+      "step": 93
+    },
+    {
+      "epoch": 0.07772609819121447,
+      "grad_norm": 1.84375,
+      "learning_rate": 9.910485933503837e-06,
+      "loss": 0.5893,
+      "step": 94
+    },
+    {
+      "epoch": 0.07855297157622738,
+      "grad_norm": 1.8203125,
+      "learning_rate": 9.906223358908781e-06,
+      "loss": 0.548,
+      "step": 95
+    },
+    {
+      "epoch": 0.07937984496124031,
+      "grad_norm": 1.859375,
+      "learning_rate": 9.901960784313727e-06,
+      "loss": 0.5771,
+      "step": 96
+    },
+    {
+      "epoch": 0.08020671834625323,
+      "grad_norm": 1.75,
+      "learning_rate": 9.897698209718671e-06,
+      "loss": 0.5414,
+      "step": 97
+    },
+    {
+      "epoch": 0.08103359173126615,
+      "grad_norm": 1.78125,
+      "learning_rate": 9.893435635123615e-06,
+      "loss": 0.5142,
+      "step": 98
+    },
+    {
+      "epoch": 0.08186046511627906,
+      "grad_norm": 2.0,
+      "learning_rate": 9.889173060528559e-06,
+      "loss": 0.5402,
+      "step": 99
+    },
+    {
+      "epoch": 0.082687338501292,
+      "grad_norm": 1.7890625,
+      "learning_rate": 9.884910485933505e-06,
+      "loss": 0.5796,
+      "step": 100
+    },
+    {
+      "epoch": 0.08351421188630491,
+      "grad_norm": 1.7578125,
+      "learning_rate": 9.880647911338449e-06,
+      "loss": 0.5927,
+      "step": 101
+    },
+    {
+      "epoch": 0.08434108527131783,
+      "grad_norm": 1.59375,
+      "learning_rate": 9.876385336743394e-06,
+      "loss": 0.5672,
+      "step": 102
+    },
+    {
+      "epoch": 0.08516795865633076,
+      "grad_norm": 1.5703125,
+      "learning_rate": 9.872122762148338e-06,
+      "loss": 0.5527,
+      "step": 103
+    },
+    {
+      "epoch": 0.08599483204134367,
+      "grad_norm": 1.6953125,
+      "learning_rate": 9.867860187553282e-06,
+      "loss": 0.5714,
+      "step": 104
+    },
+    {
+      "epoch": 0.08682170542635659,
+      "grad_norm": 1.7265625,
+      "learning_rate": 9.863597612958228e-06,
+      "loss": 0.5783,
+      "step": 105
+    },
+    {
+      "epoch": 0.0876485788113695,
+      "grad_norm": 1.7890625,
+      "learning_rate": 9.859335038363172e-06,
+      "loss": 0.5413,
+      "step": 106
+    },
+    {
+      "epoch": 0.08847545219638243,
+      "grad_norm": 1.7734375,
+      "learning_rate": 9.855072463768118e-06,
+      "loss": 0.6038,
+      "step": 107
+    },
+    {
+      "epoch": 0.08930232558139535,
+      "grad_norm": 1.6875,
+      "learning_rate": 9.85080988917306e-06,
+      "loss": 0.5866,
+      "step": 108
+    },
+    {
+      "epoch": 0.09012919896640827,
+      "grad_norm": 1.546875,
+      "learning_rate": 9.846547314578006e-06,
+      "loss": 0.5656,
+      "step": 109
+    },
+    {
+      "epoch": 0.09095607235142118,
+      "grad_norm": 1.8046875,
+      "learning_rate": 9.84228473998295e-06,
+      "loss": 0.5878,
+      "step": 110
+    },
+    {
+      "epoch": 0.09178294573643411,
+      "grad_norm": 1.796875,
+      "learning_rate": 9.838022165387896e-06,
+      "loss": 0.5432,
+      "step": 111
+    },
+    {
+      "epoch": 0.09260981912144703,
+      "grad_norm": 1.625,
+      "learning_rate": 9.83375959079284e-06,
+      "loss": 0.5594,
+      "step": 112
+    },
+    {
+      "epoch": 0.09343669250645995,
+      "grad_norm": 1.6875,
+      "learning_rate": 9.829497016197784e-06,
+      "loss": 0.5726,
+      "step": 113
+    },
+    {
+      "epoch": 0.09426356589147286,
+      "grad_norm": 1.828125,
+      "learning_rate": 9.82523444160273e-06,
+      "loss": 0.5447,
+      "step": 114
+    },
+    {
+      "epoch": 0.09509043927648579,
+      "grad_norm": 1.7265625,
+      "learning_rate": 9.820971867007673e-06,
+      "loss": 0.5868,
+      "step": 115
+    },
+    {
+      "epoch": 0.09591731266149871,
+      "grad_norm": 1.6875,
+      "learning_rate": 9.81670929241262e-06,
+      "loss": 0.5808,
+      "step": 116
+    },
+    {
+      "epoch": 0.09674418604651162,
+      "grad_norm": 1.9296875,
+      "learning_rate": 9.812446717817563e-06,
+      "loss": 0.5609,
+      "step": 117
+    },
+    {
+      "epoch": 0.09757105943152455,
+      "grad_norm": 1.6484375,
+      "learning_rate": 9.808184143222507e-06,
+      "loss": 0.5715,
+      "step": 118
+    },
+    {
+      "epoch": 0.09839793281653747,
+      "grad_norm": 1.921875,
+      "learning_rate": 9.803921568627451e-06,
+      "loss": 0.5701,
+      "step": 119
+    },
+    {
+      "epoch": 0.09922480620155039,
+      "grad_norm": 1.765625,
+      "learning_rate": 9.799658994032395e-06,
+      "loss": 0.5941,
+      "step": 120
+    },
+    {
+      "epoch": 0.1000516795865633,
+      "grad_norm": 1.6640625,
+      "learning_rate": 9.795396419437341e-06,
+      "loss": 0.5867,
+      "step": 121
+    },
+    {
+      "epoch": 0.10087855297157623,
+      "grad_norm": 1.7578125,
+      "learning_rate": 9.791133844842285e-06,
+      "loss": 0.5947,
+      "step": 122
+    },
+    {
+      "epoch": 0.10170542635658915,
+      "grad_norm": 1.5234375,
+      "learning_rate": 9.78687127024723e-06,
+      "loss": 0.5555,
+      "step": 123
+    },
+    {
+      "epoch": 0.10253229974160206,
+      "grad_norm": 1.7109375,
+      "learning_rate": 9.782608695652175e-06,
+      "loss": 0.5515,
+      "step": 124
+    },
+    {
+      "epoch": 0.10335917312661498,
+      "grad_norm": 1.625,
+      "learning_rate": 9.778346121057119e-06,
+      "loss": 0.5983,
+      "step": 125
+    },
+    {
+      "epoch": 0.10418604651162791,
+      "grad_norm": 1.5546875,
+      "learning_rate": 9.774083546462064e-06,
+      "loss": 0.5474,
+      "step": 126
+    },
+    {
+      "epoch": 0.10501291989664083,
+      "grad_norm": 1.8671875,
+      "learning_rate": 9.769820971867009e-06,
+      "loss": 0.5726,
+      "step": 127
+    },
+    {
+      "epoch": 0.10583979328165374,
+      "grad_norm": 1.515625,
+      "learning_rate": 9.765558397271953e-06,
+      "loss": 0.5806,
+      "step": 128
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 2.015625,
+      "learning_rate": 9.761295822676897e-06,
+      "loss": 0.5551,
+      "step": 129
+    },
+    {
+      "epoch": 0.10749354005167959,
+      "grad_norm": 1.8125,
+      "learning_rate": 9.757033248081842e-06,
+      "loss": 0.5502,
+      "step": 130
+    },
+    {
+      "epoch": 0.1083204134366925,
+      "grad_norm": 1.671875,
+      "learning_rate": 9.752770673486786e-06,
+      "loss": 0.5904,
+      "step": 131
+    },
+    {
+      "epoch": 0.10914728682170542,
+      "grad_norm": 1.9140625,
+      "learning_rate": 9.748508098891732e-06,
+      "loss": 0.5645,
+      "step": 132
+    },
+    {
+      "epoch": 0.10997416020671835,
+      "grad_norm": 1.640625,
+      "learning_rate": 9.744245524296676e-06,
+      "loss": 0.5512,
+      "step": 133
+    },
+    {
+      "epoch": 0.11080103359173127,
+      "grad_norm": 1.546875,
+      "learning_rate": 9.73998294970162e-06,
+      "loss": 0.6102,
+      "step": 134
+    },
+    {
+      "epoch": 0.11162790697674418,
+      "grad_norm": 1.609375,
+      "learning_rate": 9.735720375106566e-06,
+      "loss": 0.5675,
+      "step": 135
+    },
+    {
+      "epoch": 0.1124547803617571,
+      "grad_norm": 1.6640625,
+      "learning_rate": 9.73145780051151e-06,
+      "loss": 0.5955,
+      "step": 136
+    },
+    {
+      "epoch": 0.11328165374677003,
+      "grad_norm": 1.4921875,
+      "learning_rate": 9.727195225916456e-06,
+      "loss": 0.5625,
+      "step": 137
+    },
+    {
+      "epoch": 0.11410852713178295,
+      "grad_norm": 1.8515625,
+      "learning_rate": 9.722932651321398e-06,
+      "loss": 0.5638,
+      "step": 138
+    },
+    {
+      "epoch": 0.11493540051679586,
+      "grad_norm": 1.6640625,
+      "learning_rate": 9.718670076726344e-06,
+      "loss": 0.5705,
+      "step": 139
+    },
+    {
+      "epoch": 0.11576227390180878,
+      "grad_norm": 1.609375,
+      "learning_rate": 9.714407502131288e-06,
+      "loss": 0.5565,
+      "step": 140
+    },
+    {
+      "epoch": 0.11658914728682171,
+      "grad_norm": 1.6953125,
+      "learning_rate": 9.710144927536233e-06,
+      "loss": 0.5858,
+      "step": 141
+    },
+    {
+      "epoch": 0.11741602067183463,
+      "grad_norm": 1.5703125,
+      "learning_rate": 9.705882352941177e-06,
+      "loss": 0.5468,
+      "step": 142
+    },
+    {
+      "epoch": 0.11824289405684754,
+      "grad_norm": 1.765625,
+      "learning_rate": 9.701619778346121e-06,
+      "loss": 0.5761,
+      "step": 143
+    },
+    {
+      "epoch": 0.11906976744186047,
+      "grad_norm": 1.5078125,
+      "learning_rate": 9.697357203751067e-06,
+      "loss": 0.5948,
+      "step": 144
+    },
+    {
+      "epoch": 0.11989664082687339,
+      "grad_norm": 1.8046875,
+      "learning_rate": 9.693094629156011e-06,
+      "loss": 0.5517,
+      "step": 145
+    },
+    {
+      "epoch": 0.1207235142118863,
+      "grad_norm": 1.5625,
+      "learning_rate": 9.688832054560957e-06,
+      "loss": 0.5369,
+      "step": 146
+    },
+    {
+      "epoch": 0.12155038759689922,
+      "grad_norm": 1.609375,
+      "learning_rate": 9.6845694799659e-06,
+      "loss": 0.5562,
+      "step": 147
+    },
+    {
+      "epoch": 0.12237726098191215,
+      "grad_norm": 1.7265625,
+      "learning_rate": 9.680306905370845e-06,
+      "loss": 0.5819,
+      "step": 148
+    },
+    {
+      "epoch": 0.12320413436692507,
+      "grad_norm": 1.515625,
+      "learning_rate": 9.676044330775789e-06,
+      "loss": 0.6278,
+      "step": 149
+    },
+    {
+      "epoch": 0.12403100775193798,
+      "grad_norm": 1.640625,
+      "learning_rate": 9.671781756180733e-06,
+      "loss": 0.5894,
+      "step": 150
+    },
+    {
+      "epoch": 0.1248578811369509,
+      "grad_norm": 1.5625,
+      "learning_rate": 9.667519181585679e-06,
+      "loss": 0.5729,
+      "step": 151
+    },
+    {
+      "epoch": 0.12568475452196382,
+      "grad_norm": 1.8203125,
+      "learning_rate": 9.663256606990623e-06,
+      "loss": 0.5785,
+      "step": 152
+    },
+    {
+      "epoch": 0.12651162790697673,
+      "grad_norm": 1.6171875,
+      "learning_rate": 9.658994032395568e-06,
+      "loss": 0.555,
+      "step": 153
+    },
+    {
+      "epoch": 0.12733850129198968,
+      "grad_norm": 1.671875,
+      "learning_rate": 9.654731457800512e-06,
+      "loss": 0.5665,
+      "step": 154
+    },
+    {
+      "epoch": 0.1281653746770026,
+      "grad_norm": 1.6796875,
+      "learning_rate": 9.650468883205456e-06,
+      "loss": 0.5741,
+      "step": 155
+    },
+    {
+      "epoch": 0.1289922480620155,
+      "grad_norm": 1.5390625,
+      "learning_rate": 9.646206308610402e-06,
+      "loss": 0.5461,
+      "step": 156
+    },
+    {
+      "epoch": 0.12981912144702842,
+      "grad_norm": 1.5703125,
+      "learning_rate": 9.641943734015346e-06,
+      "loss": 0.5283,
+      "step": 157
+    },
+    {
+      "epoch": 0.13064599483204134,
+      "grad_norm": 1.5,
+      "learning_rate": 9.63768115942029e-06,
+      "loss": 0.5671,
+      "step": 158
+    },
+    {
+      "epoch": 0.13147286821705426,
+      "grad_norm": 1.671875,
+      "learning_rate": 9.633418584825234e-06,
+      "loss": 0.5495,
+      "step": 159
+    },
+    {
+      "epoch": 0.13229974160206717,
+      "grad_norm": 1.4921875,
+      "learning_rate": 9.62915601023018e-06,
+      "loss": 0.6013,
+      "step": 160
+    },
+    {
+      "epoch": 0.13312661498708012,
+      "grad_norm": 1.546875,
+      "learning_rate": 9.624893435635124e-06,
+      "loss": 0.5546,
+      "step": 161
+    },
+    {
+      "epoch": 0.13395348837209303,
+      "grad_norm": 1.6484375,
+      "learning_rate": 9.62063086104007e-06,
+      "loss": 0.5795,
+      "step": 162
+    },
+    {
+      "epoch": 0.13478036175710595,
+      "grad_norm": 1.5625,
+      "learning_rate": 9.616368286445014e-06,
+      "loss": 0.5111,
+      "step": 163
+    },
+    {
+      "epoch": 0.13560723514211886,
+      "grad_norm": 1.5703125,
+      "learning_rate": 9.612105711849958e-06,
+      "loss": 0.54,
+      "step": 164
+    },
+    {
+      "epoch": 0.13643410852713178,
+      "grad_norm": 1.5390625,
+      "learning_rate": 9.607843137254903e-06,
+      "loss": 0.5552,
+      "step": 165
+    },
+    {
+      "epoch": 0.1372609819121447,
+      "grad_norm": 1.7109375,
+      "learning_rate": 9.603580562659847e-06,
+      "loss": 0.5654,
+      "step": 166
+    },
+    {
+      "epoch": 0.1380878552971576,
+      "grad_norm": 1.4765625,
+      "learning_rate": 9.599317988064793e-06,
+      "loss": 0.5415,
+      "step": 167
+    },
+    {
+      "epoch": 0.13891472868217053,
+      "grad_norm": 1.6171875,
+      "learning_rate": 9.595055413469735e-06,
+      "loss": 0.5889,
+      "step": 168
+    },
+    {
+      "epoch": 0.13974160206718347,
+      "grad_norm": 1.5859375,
+      "learning_rate": 9.590792838874681e-06,
+      "loss": 0.5061,
+      "step": 169
+    },
+    {
+      "epoch": 0.1405684754521964,
+      "grad_norm": 1.6953125,
+      "learning_rate": 9.586530264279625e-06,
+      "loss": 0.5817,
+      "step": 170
+    },
+    {
+      "epoch": 0.1413953488372093,
+      "grad_norm": 1.53125,
+      "learning_rate": 9.582267689684571e-06,
+      "loss": 0.5782,
+      "step": 171
+    },
+    {
+      "epoch": 0.14222222222222222,
+      "grad_norm": 1.6015625,
+      "learning_rate": 9.578005115089515e-06,
+      "loss": 0.599,
+      "step": 172
+    },
+    {
+      "epoch": 0.14304909560723514,
+      "grad_norm": 1.5859375,
+      "learning_rate": 9.573742540494459e-06,
+      "loss": 0.5415,
+      "step": 173
+    },
+    {
+      "epoch": 0.14387596899224805,
+      "grad_norm": 1.59375,
+      "learning_rate": 9.569479965899405e-06,
+      "loss": 0.5285,
+      "step": 174
+    },
+    {
+      "epoch": 0.14470284237726097,
+      "grad_norm": 1.53125,
+      "learning_rate": 9.565217391304349e-06,
+      "loss": 0.5509,
+      "step": 175
+    },
+    {
+      "epoch": 0.14552971576227391,
+      "grad_norm": 1.5625,
+      "learning_rate": 9.560954816709294e-06,
+      "loss": 0.5926,
+      "step": 176
+    },
+    {
+      "epoch": 0.14635658914728683,
+      "grad_norm": 1.5859375,
+      "learning_rate": 9.556692242114238e-06,
+      "loss": 0.5526,
+      "step": 177
+    },
+    {
+      "epoch": 0.14718346253229975,
+      "grad_norm": 1.4453125,
+      "learning_rate": 9.552429667519182e-06,
+      "loss": 0.5732,
+      "step": 178
+    },
+    {
+      "epoch": 0.14801033591731266,
+      "grad_norm": 1.46875,
+      "learning_rate": 9.548167092924126e-06,
+      "loss": 0.5627,
+      "step": 179
+    },
+    {
+      "epoch": 0.14883720930232558,
+      "grad_norm": 1.53125,
+      "learning_rate": 9.54390451832907e-06,
+      "loss": 0.5616,
+      "step": 180
+    },
+    {
+      "epoch": 0.1496640826873385,
+      "grad_norm": 1.6484375,
+      "learning_rate": 9.539641943734016e-06,
+      "loss": 0.5397,
+      "step": 181
+    },
+    {
+      "epoch": 0.1504909560723514,
+      "grad_norm": 1.5234375,
+      "learning_rate": 9.53537936913896e-06,
+      "loss": 0.5287,
+      "step": 182
+    },
+    {
+      "epoch": 0.15131782945736433,
+      "grad_norm": 1.796875,
+      "learning_rate": 9.531116794543906e-06,
+      "loss": 0.5463,
+      "step": 183
+    },
+    {
+      "epoch": 0.15214470284237727,
+      "grad_norm": 1.6875,
+      "learning_rate": 9.52685421994885e-06,
+      "loss": 0.58,
+      "step": 184
+    },
+    {
+      "epoch": 0.1529715762273902,
+      "grad_norm": 1.5546875,
+      "learning_rate": 9.522591645353794e-06,
+      "loss": 0.5781,
+      "step": 185
+    },
+    {
+      "epoch": 0.1537984496124031,
+      "grad_norm": 1.6171875,
+      "learning_rate": 9.51832907075874e-06,
+      "loss": 0.5884,
+      "step": 186
+    },
+    {
+      "epoch": 0.15462532299741602,
+      "grad_norm": 1.5234375,
+      "learning_rate": 9.514066496163684e-06,
+      "loss": 0.5665,
+      "step": 187
+    },
+    {
+      "epoch": 0.15545219638242894,
+      "grad_norm": 1.640625,
+      "learning_rate": 9.509803921568628e-06,
+      "loss": 0.6015,
+      "step": 188
+    },
+    {
+      "epoch": 0.15627906976744185,
+      "grad_norm": 1.5625,
+      "learning_rate": 9.505541346973572e-06,
+      "loss": 0.5758,
+      "step": 189
+    },
+    {
+      "epoch": 0.15710594315245477,
+      "grad_norm": 1.6953125,
+      "learning_rate": 9.501278772378517e-06,
+      "loss": 0.5482,
+      "step": 190
+    },
+    {
+      "epoch": 0.1579328165374677,
+      "grad_norm": 1.546875,
+      "learning_rate": 9.497016197783462e-06,
+      "loss": 0.5702,
+      "step": 191
+    },
+    {
+      "epoch": 0.15875968992248063,
+      "grad_norm": 1.640625,
+      "learning_rate": 9.492753623188407e-06,
+      "loss": 0.5684,
+      "step": 192
+    },
+    {
+      "epoch": 0.15958656330749355,
+      "grad_norm": 1.625,
+      "learning_rate": 9.488491048593351e-06,
+      "loss": 0.5742,
+      "step": 193
+    },
+    {
+      "epoch": 0.16041343669250646,
+      "grad_norm": 1.671875,
+      "learning_rate": 9.484228473998295e-06,
+      "loss": 0.5751,
+      "step": 194
+    },
+    {
+      "epoch": 0.16124031007751938,
+      "grad_norm": 1.6015625,
+      "learning_rate": 9.479965899403241e-06,
+      "loss": 0.5678,
+      "step": 195
+    },
+    {
+      "epoch": 0.1620671834625323,
+      "grad_norm": 1.453125,
+      "learning_rate": 9.475703324808185e-06,
+      "loss": 0.5053,
+      "step": 196
+    },
+    {
+      "epoch": 0.1628940568475452,
+      "grad_norm": 1.609375,
+      "learning_rate": 9.47144075021313e-06,
+      "loss": 0.5837,
+      "step": 197
+    },
+    {
+      "epoch": 0.16372093023255813,
+      "grad_norm": 1.5078125,
+      "learning_rate": 9.467178175618073e-06,
+      "loss": 0.5579,
+      "step": 198
+    },
+    {
+      "epoch": 0.16454780361757107,
+      "grad_norm": 1.4453125,
+      "learning_rate": 9.462915601023019e-06,
+      "loss": 0.571,
+      "step": 199
+    },
+    {
+      "epoch": 0.165374677002584,
+      "grad_norm": 1.5078125,
+      "learning_rate": 9.458653026427963e-06,
+      "loss": 0.5302,
+      "step": 200
+    },
+    {
+      "epoch": 0.1662015503875969,
+      "grad_norm": 1.5859375,
+      "learning_rate": 9.454390451832909e-06,
+      "loss": 0.5409,
+      "step": 201
+    },
+    {
+      "epoch": 0.16702842377260982,
+      "grad_norm": 1.6796875,
+      "learning_rate": 9.450127877237853e-06,
+      "loss": 0.6042,
+      "step": 202
+    },
+    {
+      "epoch": 0.16785529715762273,
+      "grad_norm": 1.4375,
+      "learning_rate": 9.445865302642797e-06,
+      "loss": 0.5902,
+      "step": 203
+    },
+    {
+      "epoch": 0.16868217054263565,
+      "grad_norm": 1.515625,
+      "learning_rate": 9.441602728047742e-06,
+      "loss": 0.5542,
+      "step": 204
+    },
+    {
+      "epoch": 0.16950904392764857,
+      "grad_norm": 1.453125,
+      "learning_rate": 9.437340153452686e-06,
+      "loss": 0.5515,
+      "step": 205
+    },
+    {
+      "epoch": 0.1703359173126615,
+      "grad_norm": 1.53125,
+      "learning_rate": 9.433077578857632e-06,
+      "loss": 0.6025,
+      "step": 206
+    },
+    {
+      "epoch": 0.17116279069767443,
+      "grad_norm": 1.625,
+      "learning_rate": 9.428815004262576e-06,
+      "loss": 0.5495,
+      "step": 207
+    },
+    {
+      "epoch": 0.17198966408268734,
+      "grad_norm": 1.40625,
+      "learning_rate": 9.42455242966752e-06,
+      "loss": 0.5598,
+      "step": 208
+    },
+    {
+      "epoch": 0.17281653746770026,
+      "grad_norm": 1.4765625,
+      "learning_rate": 9.420289855072464e-06,
+      "loss": 0.5368,
+      "step": 209
+    },
+    {
+      "epoch": 0.17364341085271318,
+      "grad_norm": 1.59375,
+      "learning_rate": 9.416027280477408e-06,
+      "loss": 0.5879,
+      "step": 210
+    },
+    {
+      "epoch": 0.1744702842377261,
+      "grad_norm": 1.5546875,
+      "learning_rate": 9.411764705882354e-06,
+      "loss": 0.632,
+      "step": 211
+    },
+    {
+      "epoch": 0.175297157622739,
+      "grad_norm": 1.59375,
+      "learning_rate": 9.407502131287298e-06,
+      "loss": 0.577,
+      "step": 212
+    },
+    {
+      "epoch": 0.17612403100775192,
+      "grad_norm": 1.46875,
+      "learning_rate": 9.403239556692244e-06,
+      "loss": 0.5793,
+      "step": 213
+    },
+    {
+      "epoch": 0.17695090439276487,
+      "grad_norm": 1.578125,
+      "learning_rate": 9.398976982097188e-06,
+      "loss": 0.5671,
+      "step": 214
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 1.5078125,
+      "learning_rate": 9.394714407502132e-06,
+      "loss": 0.5092,
+      "step": 215
+    },
+    {
+      "epoch": 0.1786046511627907,
+      "grad_norm": 1.4375,
+      "learning_rate": 9.390451832907077e-06,
+      "loss": 0.5474,
+      "step": 216
+    },
+    {
+      "epoch": 0.17943152454780362,
+      "grad_norm": 1.4765625,
+      "learning_rate": 9.386189258312021e-06,
+      "loss": 0.5455,
+      "step": 217
+    },
+    {
+      "epoch": 0.18025839793281653,
+      "grad_norm": 1.4765625,
+      "learning_rate": 9.381926683716965e-06,
+      "loss": 0.5659,
+      "step": 218
+    },
+    {
+      "epoch": 0.18108527131782945,
+      "grad_norm": 1.46875,
+      "learning_rate": 9.37766410912191e-06,
+      "loss": 0.542,
+      "step": 219
+    },
+    {
+      "epoch": 0.18191214470284237,
+      "grad_norm": 1.4375,
+      "learning_rate": 9.373401534526855e-06,
+      "loss": 0.4909,
+      "step": 220
+    },
+    {
+      "epoch": 0.1827390180878553,
+      "grad_norm": 1.453125,
+      "learning_rate": 9.369138959931799e-06,
+      "loss": 0.5891,
+      "step": 221
+    },
+    {
+      "epoch": 0.18356589147286823,
+      "grad_norm": 1.5,
+      "learning_rate": 9.364876385336745e-06,
+      "loss": 0.5387,
+      "step": 222
+    },
+    {
+      "epoch": 0.18439276485788114,
+      "grad_norm": 1.3984375,
+      "learning_rate": 9.360613810741689e-06,
+      "loss": 0.5262,
+      "step": 223
+    },
+    {
+      "epoch": 0.18521963824289406,
+      "grad_norm": 1.5859375,
+      "learning_rate": 9.356351236146633e-06,
+      "loss": 0.572,
+      "step": 224
+    },
+    {
+      "epoch": 0.18604651162790697,
+      "grad_norm": 1.421875,
+      "learning_rate": 9.352088661551579e-06,
+      "loss": 0.5528,
+      "step": 225
+    },
+    {
+      "epoch": 0.1868733850129199,
+      "grad_norm": 1.6640625,
+      "learning_rate": 9.347826086956523e-06,
+      "loss": 0.5928,
+      "step": 226
+    },
+    {
+      "epoch": 0.1877002583979328,
+      "grad_norm": 1.4609375,
+      "learning_rate": 9.343563512361468e-06,
+      "loss": 0.5656,
+      "step": 227
+    },
+    {
+      "epoch": 0.18852713178294572,
+      "grad_norm": 1.6640625,
+      "learning_rate": 9.33930093776641e-06,
+      "loss": 0.5646,
+      "step": 228
+    },
+    {
+      "epoch": 0.18935400516795867,
+      "grad_norm": 1.5390625,
+      "learning_rate": 9.335038363171356e-06,
+      "loss": 0.525,
+      "step": 229
+    },
+    {
+      "epoch": 0.19018087855297158,
+      "grad_norm": 1.609375,
+      "learning_rate": 9.3307757885763e-06,
+      "loss": 0.547,
+      "step": 230
+    },
+    {
+      "epoch": 0.1910077519379845,
+      "grad_norm": 1.65625,
+      "learning_rate": 9.326513213981246e-06,
+      "loss": 0.5762,
+      "step": 231
+    },
+    {
+      "epoch": 0.19183462532299742,
+      "grad_norm": 1.609375,
+      "learning_rate": 9.32225063938619e-06,
+      "loss": 0.5248,
+      "step": 232
+    },
+    {
+      "epoch": 0.19266149870801033,
+      "grad_norm": 2.4375,
+      "learning_rate": 9.317988064791134e-06,
+      "loss": 0.5127,
+      "step": 233
+    },
+    {
+      "epoch": 0.19348837209302325,
+      "grad_norm": 1.609375,
+      "learning_rate": 9.31372549019608e-06,
+      "loss": 0.508,
+      "step": 234
+    },
+    {
+      "epoch": 0.19431524547803616,
+      "grad_norm": 1.4453125,
+      "learning_rate": 9.309462915601024e-06,
+      "loss": 0.5567,
+      "step": 235
+    },
+    {
+      "epoch": 0.1951421188630491,
+      "grad_norm": 1.5546875,
+      "learning_rate": 9.30520034100597e-06,
+      "loss": 0.6026,
+      "step": 236
+    },
+    {
+      "epoch": 0.19596899224806202,
+      "grad_norm": 1.5234375,
+      "learning_rate": 9.300937766410914e-06,
+      "loss": 0.5514,
+      "step": 237
+    },
+    {
+      "epoch": 0.19679586563307494,
+      "grad_norm": 1.453125,
+      "learning_rate": 9.296675191815858e-06,
+      "loss": 0.5806,
+      "step": 238
+    },
+    {
+      "epoch": 0.19762273901808786,
+      "grad_norm": 1.75,
+      "learning_rate": 9.292412617220802e-06,
+      "loss": 0.592,
+      "step": 239
+    },
+    {
+      "epoch": 0.19844961240310077,
+      "grad_norm": 1.4453125,
+      "learning_rate": 9.288150042625746e-06,
+      "loss": 0.5198,
+      "step": 240
+    },
+    {
+      "epoch": 0.1992764857881137,
+      "grad_norm": 1.4296875,
+      "learning_rate": 9.283887468030691e-06,
+      "loss": 0.5488,
+      "step": 241
+    },
+    {
+      "epoch": 0.2001033591731266,
+      "grad_norm": 1.5390625,
+      "learning_rate": 9.279624893435635e-06,
+      "loss": 0.5306,
+      "step": 242
+    },
+    {
+      "epoch": 0.20093023255813955,
+      "grad_norm": 1.546875,
+      "learning_rate": 9.275362318840581e-06,
+      "loss": 0.5467,
+      "step": 243
+    },
+    {
+      "epoch": 0.20175710594315246,
+      "grad_norm": 1.3984375,
+      "learning_rate": 9.271099744245525e-06,
+      "loss": 0.5444,
+      "step": 244
+    },
+    {
+      "epoch": 0.20258397932816538,
+      "grad_norm": 1.53125,
+      "learning_rate": 9.26683716965047e-06,
+      "loss": 0.5286,
+      "step": 245
+    },
+    {
+      "epoch": 0.2034108527131783,
+      "grad_norm": 1.5,
+      "learning_rate": 9.262574595055415e-06,
+      "loss": 0.5965,
+      "step": 246
+    },
+    {
+      "epoch": 0.2042377260981912,
+      "grad_norm": 1.453125,
+      "learning_rate": 9.258312020460359e-06,
+      "loss": 0.532,
+      "step": 247
+    },
+    {
+      "epoch": 0.20506459948320413,
+      "grad_norm": 1.4375,
+      "learning_rate": 9.254049445865303e-06,
+      "loss": 0.5107,
+      "step": 248
+    },
+    {
+      "epoch": 0.20589147286821705,
+      "grad_norm": 1.3828125,
+      "learning_rate": 9.249786871270247e-06,
+      "loss": 0.5696,
+      "step": 249
+    },
+    {
+      "epoch": 0.20671834625322996,
+      "grad_norm": 1.5078125,
+      "learning_rate": 9.245524296675193e-06,
+      "loss": 0.5902,
+      "step": 250
+    },
+    {
+      "epoch": 0.2075452196382429,
+      "grad_norm": 1.4375,
+      "learning_rate": 9.241261722080137e-06,
+      "loss": 0.5349,
+      "step": 251
+    },
+    {
+      "epoch": 0.20837209302325582,
+      "grad_norm": 1.5078125,
+      "learning_rate": 9.236999147485082e-06,
+      "loss": 0.5458,
+      "step": 252
+    },
+    {
+      "epoch": 0.20919896640826874,
+      "grad_norm": 1.5390625,
+      "learning_rate": 9.232736572890026e-06,
+      "loss": 0.5239,
+      "step": 253
+    },
+    {
+      "epoch": 0.21002583979328165,
+      "grad_norm": 1.4609375,
+      "learning_rate": 9.22847399829497e-06,
+      "loss": 0.5634,
+      "step": 254
+    },
+    {
+      "epoch": 0.21085271317829457,
+      "grad_norm": 1.5,
+      "learning_rate": 9.224211423699916e-06,
+      "loss": 0.5557,
+      "step": 255
+    },
+    {
+      "epoch": 0.2116795865633075,
+      "grad_norm": 1.4765625,
+      "learning_rate": 9.21994884910486e-06,
+      "loss": 0.5513,
+      "step": 256
+    },
+    {
+      "epoch": 0.2125064599483204,
+      "grad_norm": 1.4296875,
+      "learning_rate": 9.215686274509804e-06,
+      "loss": 0.5685,
+      "step": 257
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 1.5,
+      "learning_rate": 9.211423699914748e-06,
+      "loss": 0.5946,
+      "step": 258
+    },
+    {
+      "epoch": 0.21416020671834626,
+      "grad_norm": 1.484375,
+      "learning_rate": 9.207161125319694e-06,
+      "loss": 0.5498,
+      "step": 259
+    },
+    {
+      "epoch": 0.21498708010335918,
+      "grad_norm": 1.5234375,
+      "learning_rate": 9.202898550724638e-06,
+      "loss": 0.5409,
+      "step": 260
+    },
+    {
+      "epoch": 0.2158139534883721,
+      "grad_norm": 1.3671875,
+      "learning_rate": 9.198635976129584e-06,
+      "loss": 0.549,
+      "step": 261
+    },
+    {
+      "epoch": 0.216640826873385,
+      "grad_norm": 1.890625,
+      "learning_rate": 9.194373401534528e-06,
+      "loss": 0.6063,
+      "step": 262
+    },
+    {
+      "epoch": 0.21746770025839793,
+      "grad_norm": 1.5234375,
+      "learning_rate": 9.190110826939472e-06,
+      "loss": 0.5595,
+      "step": 263
+    },
+    {
+      "epoch": 0.21829457364341084,
+      "grad_norm": 1.4375,
+      "learning_rate": 9.185848252344417e-06,
+      "loss": 0.5713,
+      "step": 264
+    },
+    {
+      "epoch": 0.21912144702842376,
+      "grad_norm": 1.6015625,
+      "learning_rate": 9.181585677749362e-06,
+      "loss": 0.5665,
+      "step": 265
+    },
+    {
+      "epoch": 0.2199483204134367,
+      "grad_norm": 1.4453125,
+      "learning_rate": 9.177323103154307e-06,
+      "loss": 0.5006,
+      "step": 266
+    },
+    {
+      "epoch": 0.22077519379844962,
+      "grad_norm": 1.5234375,
+      "learning_rate": 9.17306052855925e-06,
+      "loss": 0.5815,
+      "step": 267
+    },
+    {
+      "epoch": 0.22160206718346254,
+      "grad_norm": 1.75,
+      "learning_rate": 9.168797953964195e-06,
+      "loss": 0.567,
+      "step": 268
+    },
+    {
+      "epoch": 0.22242894056847545,
+      "grad_norm": 1.4140625,
+      "learning_rate": 9.16453537936914e-06,
+      "loss": 0.5538,
+      "step": 269
+    },
+    {
+      "epoch": 0.22325581395348837,
+      "grad_norm": 1.5859375,
+      "learning_rate": 9.160272804774083e-06,
+      "loss": 0.5602,
+      "step": 270
+    },
+    {
+      "epoch": 0.22408268733850129,
+      "grad_norm": 1.5078125,
+      "learning_rate": 9.156010230179029e-06,
+      "loss": 0.556,
+      "step": 271
+    },
+    {
+      "epoch": 0.2249095607235142,
+      "grad_norm": 1.3984375,
+      "learning_rate": 9.151747655583973e-06,
+      "loss": 0.5395,
+      "step": 272
+    },
+    {
+      "epoch": 0.22573643410852715,
+      "grad_norm": 1.59375,
+      "learning_rate": 9.147485080988919e-06,
+      "loss": 0.5405,
+      "step": 273
+    },
+    {
+      "epoch": 0.22656330749354006,
+      "grad_norm": 1.453125,
+      "learning_rate": 9.143222506393863e-06,
+      "loss": 0.5249,
+      "step": 274
+    },
+    {
+      "epoch": 0.22739018087855298,
+      "grad_norm": 1.4765625,
+      "learning_rate": 9.138959931798807e-06,
+      "loss": 0.5361,
+      "step": 275
+    },
+    {
+      "epoch": 0.2282170542635659,
+      "grad_norm": 1.4453125,
+      "learning_rate": 9.134697357203753e-06,
+      "loss": 0.5761,
+      "step": 276
+    },
+    {
+      "epoch": 0.2290439276485788,
+      "grad_norm": 1.46875,
+      "learning_rate": 9.130434782608697e-06,
+      "loss": 0.5722,
+      "step": 277
+    },
+    {
+      "epoch": 0.22987080103359173,
+      "grad_norm": 1.390625,
+      "learning_rate": 9.12617220801364e-06,
+      "loss": 0.5481,
+      "step": 278
+    },
+    {
+      "epoch": 0.23069767441860464,
+      "grad_norm": 1.5546875,
+      "learning_rate": 9.121909633418585e-06,
+      "loss": 0.5455,
+      "step": 279
+    },
+    {
+      "epoch": 0.23152454780361756,
+      "grad_norm": 1.3515625,
+      "learning_rate": 9.11764705882353e-06,
+      "loss": 0.5168,
+      "step": 280
+    },
+    {
+      "epoch": 0.2323514211886305,
+      "grad_norm": 1.328125,
+      "learning_rate": 9.113384484228474e-06,
+      "loss": 0.564,
+      "step": 281
+    },
+    {
+      "epoch": 0.23317829457364342,
+      "grad_norm": 1.390625,
+      "learning_rate": 9.10912190963342e-06,
+      "loss": 0.5747,
+      "step": 282
+    },
+    {
+      "epoch": 0.23400516795865633,
+      "grad_norm": 1.3984375,
+      "learning_rate": 9.104859335038364e-06,
+      "loss": 0.5543,
+      "step": 283
+    },
+    {
+      "epoch": 0.23483204134366925,
+      "grad_norm": 1.484375,
+      "learning_rate": 9.100596760443308e-06,
+      "loss": 0.5222,
+      "step": 284
+    },
+    {
+      "epoch": 0.23565891472868217,
+      "grad_norm": 1.921875,
+      "learning_rate": 9.096334185848254e-06,
+      "loss": 0.5809,
+      "step": 285
+    },
+    {
+      "epoch": 0.23648578811369508,
+      "grad_norm": 1.4375,
+      "learning_rate": 9.092071611253198e-06,
+      "loss": 0.5408,
+      "step": 286
+    },
+    {
+      "epoch": 0.237312661498708,
+      "grad_norm": 1.4453125,
+      "learning_rate": 9.087809036658142e-06,
+      "loss": 0.5426,
+      "step": 287
+    },
+    {
+      "epoch": 0.23813953488372094,
+      "grad_norm": 1.390625,
+      "learning_rate": 9.083546462063086e-06,
+      "loss": 0.5592,
+      "step": 288
+    },
+    {
+      "epoch": 0.23896640826873386,
+      "grad_norm": 1.46875,
+      "learning_rate": 9.079283887468032e-06,
+      "loss": 0.5664,
+      "step": 289
+    },
+    {
+      "epoch": 0.23979328165374678,
+      "grad_norm": 1.4375,
+      "learning_rate": 9.075021312872976e-06,
+      "loss": 0.5509,
+      "step": 290
+    },
+    {
+      "epoch": 0.2406201550387597,
+      "grad_norm": 1.4296875,
+      "learning_rate": 9.070758738277921e-06,
+      "loss": 0.5863,
+      "step": 291
+    },
+    {
+      "epoch": 0.2414470284237726,
+      "grad_norm": 1.46875,
+      "learning_rate": 9.066496163682865e-06,
+      "loss": 0.5757,
+      "step": 292
+    },
+    {
+      "epoch": 0.24227390180878552,
+      "grad_norm": 1.4140625,
+      "learning_rate": 9.06223358908781e-06,
+      "loss": 0.5344,
+      "step": 293
+    },
+    {
+      "epoch": 0.24310077519379844,
+      "grad_norm": 1.625,
+      "learning_rate": 9.057971014492755e-06,
+      "loss": 0.5545,
+      "step": 294
+    },
+    {
+      "epoch": 0.24392764857881136,
+      "grad_norm": 1.4921875,
+      "learning_rate": 9.053708439897699e-06,
+      "loss": 0.568,
+      "step": 295
+    },
+    {
+      "epoch": 0.2447545219638243,
+      "grad_norm": 1.3984375,
+      "learning_rate": 9.049445865302645e-06,
+      "loss": 0.5555,
+      "step": 296
+    },
+    {
+      "epoch": 0.24558139534883722,
+      "grad_norm": 1.375,
+      "learning_rate": 9.045183290707587e-06,
+      "loss": 0.551,
+      "step": 297
+    },
+    {
+      "epoch": 0.24640826873385013,
+      "grad_norm": 1.5078125,
+      "learning_rate": 9.040920716112533e-06,
+      "loss": 0.5729,
+      "step": 298
+    },
+    {
+      "epoch": 0.24723514211886305,
+      "grad_norm": 1.4296875,
+      "learning_rate": 9.036658141517477e-06,
+      "loss": 0.5513,
+      "step": 299
+    },
+    {
+      "epoch": 0.24806201550387597,
+      "grad_norm": 1.484375,
+      "learning_rate": 9.032395566922421e-06,
+      "loss": 0.5587,
+      "step": 300
+    },
+    {
+      "epoch": 0.24888888888888888,
+      "grad_norm": 1.4375,
+      "learning_rate": 9.028132992327367e-06,
+      "loss": 0.5753,
+      "step": 301
+    },
+    {
+      "epoch": 0.2497157622739018,
+      "grad_norm": 1.4296875,
+      "learning_rate": 9.02387041773231e-06,
+      "loss": 0.5658,
+      "step": 302
+    },
+    {
+      "epoch": 0.2505426356589147,
+      "grad_norm": 1.4609375,
+      "learning_rate": 9.019607843137256e-06,
+      "loss": 0.4941,
+      "step": 303
+    },
+    {
+      "epoch": 0.25136950904392763,
+      "grad_norm": 1.5078125,
+      "learning_rate": 9.0153452685422e-06,
+      "loss": 0.5505,
+      "step": 304
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 2418,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 152,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.465558152429175e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-304/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b8b70bdd6844cbc575a210bfbaeeb5f4c70cbdff738b68a67f3400f40348d0c
+size 7096

checkpoint-456/config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 11,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 770,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "unsloth_version": "2024.9",
+  "use_cache": false,
+  "vocab_size": 32768
+}

checkpoint-456/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 11,
+  "max_length": 32768,
+  "pad_token_id": 770,
+  "transformers_version": "4.51.3"
+}

checkpoint-456/model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38b0a1971b3ccbd089a96a17cdba04425b78c376fc08b5f1d97e72f4335d856b
+size 4949453792

checkpoint-456/model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23c4277cd8a589fa715f8358ab78604c6a2249368a793d60eacd8e675f2d47e5
+size 4999819336

checkpoint-456/model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3791da485cdf26ccc43b4d575c3dd9cb767978c9cee79b08b12f86c8136cbe76
+size 4546807800

checkpoint-456/model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 14496047104
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

checkpoint-456/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:518158477988e1566f65725f7f47725bff6b2b71eec154f5430e10df251f10ac
+size 28992288510

checkpoint-456/pytorch_model_fsdp.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:498ef0e3c7ef2198d266cf18104e4186ec4ac87f9921c4c1c336dad992c185c0
+size 14496203157

checkpoint-456/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad792af33c7cfa8b15298ecc9d976ebdcdeb444ca0e704c7b0657f41ee6547eb
+size 14512

checkpoint-456/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:722c924fceffd85f8ab1a5445f1ea1e6c502644b6a42e2ff6b5a9a76ea26e1fe
+size 14512

checkpoint-456/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e378bd61666a1b20b8211478d894ea593565a9653828d0fde1d07159b64397b
+size 1064

checkpoint-456/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[control_768]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-456/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93e01cb5f215abfe797344a3b7bf0e874b49708177a8b115bbdde722983e3948
+size 587414

checkpoint-456/trainer_state.json

@@ -0,0 +1,3226 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.37705426356589145,
+  "eval_steps": 500,
+  "global_step": 456,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0008268733850129199,
+      "grad_norm": 9.3125,
+      "learning_rate": 0.0,
+      "loss": 0.7807,
+      "step": 1
+    },
+    {
+      "epoch": 0.0016537467700258397,
+      "grad_norm": 10.0625,
+      "learning_rate": 1.3888888888888888e-07,
+      "loss": 0.807,
+      "step": 2
+    },
+    {
+      "epoch": 0.00248062015503876,
+      "grad_norm": 10.125,
+      "learning_rate": 2.7777777777777776e-07,
+      "loss": 0.7777,
+      "step": 3
+    },
+    {
+      "epoch": 0.0033074935400516795,
+      "grad_norm": 9.4375,
+      "learning_rate": 4.1666666666666667e-07,
+      "loss": 0.8004,
+      "step": 4
+    },
+    {
+      "epoch": 0.004134366925064599,
+      "grad_norm": 9.5,
+      "learning_rate": 5.555555555555555e-07,
+      "loss": 0.758,
+      "step": 5
+    },
+    {
+      "epoch": 0.00496124031007752,
+      "grad_norm": 9.375,
+      "learning_rate": 6.944444444444446e-07,
+      "loss": 0.7734,
+      "step": 6
+    },
+    {
+      "epoch": 0.005788113695090439,
+      "grad_norm": 9.4375,
+      "learning_rate": 8.333333333333333e-07,
+      "loss": 0.7796,
+      "step": 7
+    },
+    {
+      "epoch": 0.006614987080103359,
+      "grad_norm": 9.125,
+      "learning_rate": 9.722222222222224e-07,
+      "loss": 0.7286,
+      "step": 8
+    },
+    {
+      "epoch": 0.0074418604651162795,
+      "grad_norm": 6.53125,
+      "learning_rate": 1.111111111111111e-06,
+      "loss": 0.7508,
+      "step": 9
+    },
+    {
+      "epoch": 0.008268733850129198,
+      "grad_norm": 5.0625,
+      "learning_rate": 1.25e-06,
+      "loss": 0.7876,
+      "step": 10
+    },
+    {
+      "epoch": 0.00909560723514212,
+      "grad_norm": 4.65625,
+      "learning_rate": 1.3888888888888892e-06,
+      "loss": 0.7366,
+      "step": 11
+    },
+    {
+      "epoch": 0.00992248062015504,
+      "grad_norm": 4.375,
+      "learning_rate": 1.527777777777778e-06,
+      "loss": 0.7202,
+      "step": 12
+    },
+    {
+      "epoch": 0.010749354005167959,
+      "grad_norm": 4.125,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 0.7474,
+      "step": 13
+    },
+    {
+      "epoch": 0.011576227390180879,
+      "grad_norm": 3.65625,
+      "learning_rate": 1.8055555555555557e-06,
+      "loss": 0.7167,
+      "step": 14
+    },
+    {
+      "epoch": 0.012403100775193798,
+      "grad_norm": 3.234375,
+      "learning_rate": 1.944444444444445e-06,
+      "loss": 0.6981,
+      "step": 15
+    },
+    {
+      "epoch": 0.013229974160206718,
+      "grad_norm": 2.8125,
+      "learning_rate": 2.0833333333333334e-06,
+      "loss": 0.7024,
+      "step": 16
+    },
+    {
+      "epoch": 0.014056847545219638,
+      "grad_norm": 2.40625,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 0.6872,
+      "step": 17
+    },
+    {
+      "epoch": 0.014883720930232559,
+      "grad_norm": 2.421875,
+      "learning_rate": 2.361111111111111e-06,
+      "loss": 0.6761,
+      "step": 18
+    },
+    {
+      "epoch": 0.015710594315245477,
+      "grad_norm": 2.359375,
+      "learning_rate": 2.5e-06,
+      "loss": 0.6718,
+      "step": 19
+    },
+    {
+      "epoch": 0.016537467700258397,
+      "grad_norm": 2.1875,
+      "learning_rate": 2.6388888888888893e-06,
+      "loss": 0.6712,
+      "step": 20
+    },
+    {
+      "epoch": 0.017364341085271316,
+      "grad_norm": 1.984375,
+      "learning_rate": 2.7777777777777783e-06,
+      "loss": 0.6373,
+      "step": 21
+    },
+    {
+      "epoch": 0.01819121447028424,
+      "grad_norm": 1.96875,
+      "learning_rate": 2.916666666666667e-06,
+      "loss": 0.6671,
+      "step": 22
+    },
+    {
+      "epoch": 0.01901808785529716,
+      "grad_norm": 1.921875,
+      "learning_rate": 3.055555555555556e-06,
+      "loss": 0.6594,
+      "step": 23
+    },
+    {
+      "epoch": 0.01984496124031008,
+      "grad_norm": 1.9140625,
+      "learning_rate": 3.1944444444444443e-06,
+      "loss": 0.6327,
+      "step": 24
+    },
+    {
+      "epoch": 0.020671834625323,
+      "grad_norm": 1.9140625,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.6183,
+      "step": 25
+    },
+    {
+      "epoch": 0.021498708010335918,
+      "grad_norm": 1.9296875,
+      "learning_rate": 3.4722222222222224e-06,
+      "loss": 0.6796,
+      "step": 26
+    },
+    {
+      "epoch": 0.022325581395348838,
+      "grad_norm": 1.8203125,
+      "learning_rate": 3.6111111111111115e-06,
+      "loss": 0.5912,
+      "step": 27
+    },
+    {
+      "epoch": 0.023152454780361757,
+      "grad_norm": 2.015625,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.6317,
+      "step": 28
+    },
+    {
+      "epoch": 0.023979328165374677,
+      "grad_norm": 1.6953125,
+      "learning_rate": 3.88888888888889e-06,
+      "loss": 0.6158,
+      "step": 29
+    },
+    {
+      "epoch": 0.024806201550387597,
+      "grad_norm": 1.84375,
+      "learning_rate": 4.027777777777779e-06,
+      "loss": 0.6281,
+      "step": 30
+    },
+    {
+      "epoch": 0.025633074935400516,
+      "grad_norm": 1.78125,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 0.6514,
+      "step": 31
+    },
+    {
+      "epoch": 0.026459948320413436,
+      "grad_norm": 1.78125,
+      "learning_rate": 4.305555555555556e-06,
+      "loss": 0.6462,
+      "step": 32
+    },
+    {
+      "epoch": 0.027286821705426356,
+      "grad_norm": 1.671875,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 0.5989,
+      "step": 33
+    },
+    {
+      "epoch": 0.028113695090439275,
+      "grad_norm": 1.78125,
+      "learning_rate": 4.583333333333333e-06,
+      "loss": 0.6209,
+      "step": 34
+    },
+    {
+      "epoch": 0.028940568475452195,
+      "grad_norm": 1.7109375,
+      "learning_rate": 4.722222222222222e-06,
+      "loss": 0.5746,
+      "step": 35
+    },
+    {
+      "epoch": 0.029767441860465118,
+      "grad_norm": 1.9296875,
+      "learning_rate": 4.861111111111111e-06,
+      "loss": 0.6193,
+      "step": 36
+    },
+    {
+      "epoch": 0.030594315245478038,
+      "grad_norm": 2.09375,
+      "learning_rate": 5e-06,
+      "loss": 0.5964,
+      "step": 37
+    },
+    {
+      "epoch": 0.031421188630490954,
+      "grad_norm": 1.75,
+      "learning_rate": 5.138888888888889e-06,
+      "loss": 0.6042,
+      "step": 38
+    },
+    {
+      "epoch": 0.03224806201550388,
+      "grad_norm": 1.9921875,
+      "learning_rate": 5.2777777777777785e-06,
+      "loss": 0.6279,
+      "step": 39
+    },
+    {
+      "epoch": 0.03307493540051679,
+      "grad_norm": 1.8984375,
+      "learning_rate": 5.416666666666667e-06,
+      "loss": 0.5817,
+      "step": 40
+    },
+    {
+      "epoch": 0.033901808785529716,
+      "grad_norm": 1.984375,
+      "learning_rate": 5.555555555555557e-06,
+      "loss": 0.5953,
+      "step": 41
+    },
+    {
+      "epoch": 0.03472868217054263,
+      "grad_norm": 1.96875,
+      "learning_rate": 5.694444444444445e-06,
+      "loss": 0.643,
+      "step": 42
+    },
+    {
+      "epoch": 0.035555555555555556,
+      "grad_norm": 2.1875,
+      "learning_rate": 5.833333333333334e-06,
+      "loss": 0.5623,
+      "step": 43
+    },
+    {
+      "epoch": 0.03638242894056848,
+      "grad_norm": 1.8515625,
+      "learning_rate": 5.972222222222222e-06,
+      "loss": 0.6095,
+      "step": 44
+    },
+    {
+      "epoch": 0.037209302325581395,
+      "grad_norm": 2.046875,
+      "learning_rate": 6.111111111111112e-06,
+      "loss": 0.6041,
+      "step": 45
+    },
+    {
+      "epoch": 0.03803617571059432,
+      "grad_norm": 1.78125,
+      "learning_rate": 6.25e-06,
+      "loss": 0.5822,
+      "step": 46
+    },
+    {
+      "epoch": 0.038863049095607234,
+      "grad_norm": 1.921875,
+      "learning_rate": 6.3888888888888885e-06,
+      "loss": 0.6468,
+      "step": 47
+    },
+    {
+      "epoch": 0.03968992248062016,
+      "grad_norm": 1.8984375,
+      "learning_rate": 6.5277777777777784e-06,
+      "loss": 0.5941,
+      "step": 48
+    },
+    {
+      "epoch": 0.04051679586563307,
+      "grad_norm": 1.84375,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.5688,
+      "step": 49
+    },
+    {
+      "epoch": 0.041343669250646,
+      "grad_norm": 1.8671875,
+      "learning_rate": 6.8055555555555566e-06,
+      "loss": 0.5625,
+      "step": 50
+    },
+    {
+      "epoch": 0.04217054263565891,
+      "grad_norm": 1.8203125,
+      "learning_rate": 6.944444444444445e-06,
+      "loss": 0.593,
+      "step": 51
+    },
+    {
+      "epoch": 0.042997416020671836,
+      "grad_norm": 1.8359375,
+      "learning_rate": 7.083333333333335e-06,
+      "loss": 0.6545,
+      "step": 52
+    },
+    {
+      "epoch": 0.04382428940568475,
+      "grad_norm": 1.765625,
+      "learning_rate": 7.222222222222223e-06,
+      "loss": 0.5607,
+      "step": 53
+    },
+    {
+      "epoch": 0.044651162790697675,
+      "grad_norm": 1.9765625,
+      "learning_rate": 7.361111111111112e-06,
+      "loss": 0.6131,
+      "step": 54
+    },
+    {
+      "epoch": 0.04547803617571059,
+      "grad_norm": 1.796875,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.5849,
+      "step": 55
+    },
+    {
+      "epoch": 0.046304909560723514,
+      "grad_norm": 1.90625,
+      "learning_rate": 7.638888888888888e-06,
+      "loss": 0.6018,
+      "step": 56
+    },
+    {
+      "epoch": 0.04713178294573643,
+      "grad_norm": 1.625,
+      "learning_rate": 7.77777777777778e-06,
+      "loss": 0.5435,
+      "step": 57
+    },
+    {
+      "epoch": 0.047958656330749354,
+      "grad_norm": 1.90625,
+      "learning_rate": 7.916666666666667e-06,
+      "loss": 0.5463,
+      "step": 58
+    },
+    {
+      "epoch": 0.04878552971576228,
+      "grad_norm": 1.8125,
+      "learning_rate": 8.055555555555557e-06,
+      "loss": 0.5828,
+      "step": 59
+    },
+    {
+      "epoch": 0.04961240310077519,
+      "grad_norm": 1.734375,
+      "learning_rate": 8.194444444444445e-06,
+      "loss": 0.6034,
+      "step": 60
+    },
+    {
+      "epoch": 0.050439276485788116,
+      "grad_norm": 1.6328125,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.5516,
+      "step": 61
+    },
+    {
+      "epoch": 0.05126614987080103,
+      "grad_norm": 1.7890625,
+      "learning_rate": 8.472222222222223e-06,
+      "loss": 0.5926,
+      "step": 62
+    },
+    {
+      "epoch": 0.052093023255813956,
+      "grad_norm": 1.703125,
+      "learning_rate": 8.611111111111112e-06,
+      "loss": 0.5966,
+      "step": 63
+    },
+    {
+      "epoch": 0.05291989664082687,
+      "grad_norm": 1.8359375,
+      "learning_rate": 8.750000000000001e-06,
+      "loss": 0.5601,
+      "step": 64
+    },
+    {
+      "epoch": 0.053746770025839795,
+      "grad_norm": 1.9296875,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 0.5873,
+      "step": 65
+    },
+    {
+      "epoch": 0.05457364341085271,
+      "grad_norm": 1.7734375,
+      "learning_rate": 9.027777777777779e-06,
+      "loss": 0.5693,
+      "step": 66
+    },
+    {
+      "epoch": 0.055400516795865634,
+      "grad_norm": 1.7109375,
+      "learning_rate": 9.166666666666666e-06,
+      "loss": 0.5481,
+      "step": 67
+    },
+    {
+      "epoch": 0.05622739018087855,
+      "grad_norm": 2.09375,
+      "learning_rate": 9.305555555555557e-06,
+      "loss": 0.5821,
+      "step": 68
+    },
+    {
+      "epoch": 0.05705426356589147,
+      "grad_norm": 1.796875,
+      "learning_rate": 9.444444444444445e-06,
+      "loss": 0.5947,
+      "step": 69
+    },
+    {
+      "epoch": 0.05788113695090439,
+      "grad_norm": 2.4375,
+      "learning_rate": 9.583333333333335e-06,
+      "loss": 0.5564,
+      "step": 70
+    },
+    {
+      "epoch": 0.05870801033591731,
+      "grad_norm": 1.8828125,
+      "learning_rate": 9.722222222222223e-06,
+      "loss": 0.6348,
+      "step": 71
+    },
+    {
+      "epoch": 0.059534883720930236,
+      "grad_norm": 2.046875,
+      "learning_rate": 9.861111111111112e-06,
+      "loss": 0.5784,
+      "step": 72
+    },
+    {
+      "epoch": 0.06036175710594315,
+      "grad_norm": 1.90625,
+      "learning_rate": 1e-05,
+      "loss": 0.5513,
+      "step": 73
+    },
+    {
+      "epoch": 0.061188630490956075,
+      "grad_norm": 2.15625,
+      "learning_rate": 9.995737425404945e-06,
+      "loss": 0.6001,
+      "step": 74
+    },
+    {
+      "epoch": 0.06201550387596899,
+      "grad_norm": 2.171875,
+      "learning_rate": 9.99147485080989e-06,
+      "loss": 0.5978,
+      "step": 75
+    },
+    {
+      "epoch": 0.06284237726098191,
+      "grad_norm": 1.734375,
+      "learning_rate": 9.987212276214835e-06,
+      "loss": 0.5617,
+      "step": 76
+    },
+    {
+      "epoch": 0.06366925064599484,
+      "grad_norm": 1.9375,
+      "learning_rate": 9.98294970161978e-06,
+      "loss": 0.5891,
+      "step": 77
+    },
+    {
+      "epoch": 0.06449612403100775,
+      "grad_norm": 1.953125,
+      "learning_rate": 9.978687127024723e-06,
+      "loss": 0.5594,
+      "step": 78
+    },
+    {
+      "epoch": 0.06532299741602067,
+      "grad_norm": 1.8359375,
+      "learning_rate": 9.974424552429668e-06,
+      "loss": 0.575,
+      "step": 79
+    },
+    {
+      "epoch": 0.06614987080103359,
+      "grad_norm": 1.890625,
+      "learning_rate": 9.970161977834612e-06,
+      "loss": 0.5653,
+      "step": 80
+    },
+    {
+      "epoch": 0.06697674418604652,
+      "grad_norm": 1.7265625,
+      "learning_rate": 9.965899403239558e-06,
+      "loss": 0.6024,
+      "step": 81
+    },
+    {
+      "epoch": 0.06780361757105943,
+      "grad_norm": 1.75,
+      "learning_rate": 9.961636828644502e-06,
+      "loss": 0.5823,
+      "step": 82
+    },
+    {
+      "epoch": 0.06863049095607235,
+      "grad_norm": 1.8359375,
+      "learning_rate": 9.957374254049446e-06,
+      "loss": 0.6131,
+      "step": 83
+    },
+    {
+      "epoch": 0.06945736434108526,
+      "grad_norm": 1.7265625,
+      "learning_rate": 9.953111679454392e-06,
+      "loss": 0.5958,
+      "step": 84
+    },
+    {
+      "epoch": 0.0702842377260982,
+      "grad_norm": 1.6875,
+      "learning_rate": 9.948849104859336e-06,
+      "loss": 0.5665,
+      "step": 85
+    },
+    {
+      "epoch": 0.07111111111111111,
+      "grad_norm": 1.9609375,
+      "learning_rate": 9.944586530264282e-06,
+      "loss": 0.5641,
+      "step": 86
+    },
+    {
+      "epoch": 0.07193798449612403,
+      "grad_norm": 1.921875,
+      "learning_rate": 9.940323955669226e-06,
+      "loss": 0.5881,
+      "step": 87
+    },
+    {
+      "epoch": 0.07276485788113696,
+      "grad_norm": 1.8203125,
+      "learning_rate": 9.93606138107417e-06,
+      "loss": 0.5541,
+      "step": 88
+    },
+    {
+      "epoch": 0.07359173126614987,
+      "grad_norm": 1.90625,
+      "learning_rate": 9.931798806479114e-06,
+      "loss": 0.5806,
+      "step": 89
+    },
+    {
+      "epoch": 0.07441860465116279,
+      "grad_norm": 1.8203125,
+      "learning_rate": 9.927536231884058e-06,
+      "loss": 0.6086,
+      "step": 90
+    },
+    {
+      "epoch": 0.0752454780361757,
+      "grad_norm": 1.59375,
+      "learning_rate": 9.923273657289003e-06,
+      "loss": 0.5989,
+      "step": 91
+    },
+    {
+      "epoch": 0.07607235142118864,
+      "grad_norm": 1.765625,
+      "learning_rate": 9.919011082693947e-06,
+      "loss": 0.598,
+      "step": 92
+    },
+    {
+      "epoch": 0.07689922480620155,
+      "grad_norm": 1.4765625,
+      "learning_rate": 9.914748508098893e-06,
+      "loss": 0.5301,
+      "step": 93
+    },
+    {
+      "epoch": 0.07772609819121447,
+      "grad_norm": 1.84375,
+      "learning_rate": 9.910485933503837e-06,
+      "loss": 0.5893,
+      "step": 94
+    },
+    {
+      "epoch": 0.07855297157622738,
+      "grad_norm": 1.8203125,
+      "learning_rate": 9.906223358908781e-06,
+      "loss": 0.548,
+      "step": 95
+    },
+    {
+      "epoch": 0.07937984496124031,
+      "grad_norm": 1.859375,
+      "learning_rate": 9.901960784313727e-06,
+      "loss": 0.5771,
+      "step": 96
+    },
+    {
+      "epoch": 0.08020671834625323,
+      "grad_norm": 1.75,
+      "learning_rate": 9.897698209718671e-06,
+      "loss": 0.5414,
+      "step": 97
+    },
+    {
+      "epoch": 0.08103359173126615,
+      "grad_norm": 1.78125,
+      "learning_rate": 9.893435635123615e-06,
+      "loss": 0.5142,
+      "step": 98
+    },
+    {
+      "epoch": 0.08186046511627906,
+      "grad_norm": 2.0,
+      "learning_rate": 9.889173060528559e-06,
+      "loss": 0.5402,
+      "step": 99
+    },
+    {
+      "epoch": 0.082687338501292,
+      "grad_norm": 1.7890625,
+      "learning_rate": 9.884910485933505e-06,
+      "loss": 0.5796,
+      "step": 100
+    },
+    {
+      "epoch": 0.08351421188630491,
+      "grad_norm": 1.7578125,
+      "learning_rate": 9.880647911338449e-06,
+      "loss": 0.5927,
+      "step": 101
+    },
+    {
+      "epoch": 0.08434108527131783,
+      "grad_norm": 1.59375,
+      "learning_rate": 9.876385336743394e-06,
+      "loss": 0.5672,
+      "step": 102
+    },
+    {
+      "epoch": 0.08516795865633076,
+      "grad_norm": 1.5703125,
+      "learning_rate": 9.872122762148338e-06,
+      "loss": 0.5527,
+      "step": 103
+    },
+    {
+      "epoch": 0.08599483204134367,
+      "grad_norm": 1.6953125,
+      "learning_rate": 9.867860187553282e-06,
+      "loss": 0.5714,
+      "step": 104
+    },
+    {
+      "epoch": 0.08682170542635659,
+      "grad_norm": 1.7265625,
+      "learning_rate": 9.863597612958228e-06,
+      "loss": 0.5783,
+      "step": 105
+    },
+    {
+      "epoch": 0.0876485788113695,
+      "grad_norm": 1.7890625,
+      "learning_rate": 9.859335038363172e-06,
+      "loss": 0.5413,
+      "step": 106
+    },
+    {
+      "epoch": 0.08847545219638243,
+      "grad_norm": 1.7734375,
+      "learning_rate": 9.855072463768118e-06,
+      "loss": 0.6038,
+      "step": 107
+    },
+    {
+      "epoch": 0.08930232558139535,
+      "grad_norm": 1.6875,
+      "learning_rate": 9.85080988917306e-06,
+      "loss": 0.5866,
+      "step": 108
+    },
+    {
+      "epoch": 0.09012919896640827,
+      "grad_norm": 1.546875,
+      "learning_rate": 9.846547314578006e-06,
+      "loss": 0.5656,
+      "step": 109
+    },
+    {
+      "epoch": 0.09095607235142118,
+      "grad_norm": 1.8046875,
+      "learning_rate": 9.84228473998295e-06,
+      "loss": 0.5878,
+      "step": 110
+    },
+    {
+      "epoch": 0.09178294573643411,
+      "grad_norm": 1.796875,
+      "learning_rate": 9.838022165387896e-06,
+      "loss": 0.5432,
+      "step": 111
+    },
+    {
+      "epoch": 0.09260981912144703,
+      "grad_norm": 1.625,
+      "learning_rate": 9.83375959079284e-06,
+      "loss": 0.5594,
+      "step": 112
+    },
+    {
+      "epoch": 0.09343669250645995,
+      "grad_norm": 1.6875,
+      "learning_rate": 9.829497016197784e-06,
+      "loss": 0.5726,
+      "step": 113
+    },
+    {
+      "epoch": 0.09426356589147286,
+      "grad_norm": 1.828125,
+      "learning_rate": 9.82523444160273e-06,
+      "loss": 0.5447,
+      "step": 114
+    },
+    {
+      "epoch": 0.09509043927648579,
+      "grad_norm": 1.7265625,
+      "learning_rate": 9.820971867007673e-06,
+      "loss": 0.5868,
+      "step": 115
+    },
+    {
+      "epoch": 0.09591731266149871,
+      "grad_norm": 1.6875,
+      "learning_rate": 9.81670929241262e-06,
+      "loss": 0.5808,
+      "step": 116
+    },
+    {
+      "epoch": 0.09674418604651162,
+      "grad_norm": 1.9296875,
+      "learning_rate": 9.812446717817563e-06,
+      "loss": 0.5609,
+      "step": 117
+    },
+    {
+      "epoch": 0.09757105943152455,
+      "grad_norm": 1.6484375,
+      "learning_rate": 9.808184143222507e-06,
+      "loss": 0.5715,
+      "step": 118
+    },
+    {
+      "epoch": 0.09839793281653747,
+      "grad_norm": 1.921875,
+      "learning_rate": 9.803921568627451e-06,
+      "loss": 0.5701,
+      "step": 119
+    },
+    {
+      "epoch": 0.09922480620155039,
+      "grad_norm": 1.765625,
+      "learning_rate": 9.799658994032395e-06,
+      "loss": 0.5941,
+      "step": 120
+    },
+    {
+      "epoch": 0.1000516795865633,
+      "grad_norm": 1.6640625,
+      "learning_rate": 9.795396419437341e-06,
+      "loss": 0.5867,
+      "step": 121
+    },
+    {
+      "epoch": 0.10087855297157623,
+      "grad_norm": 1.7578125,
+      "learning_rate": 9.791133844842285e-06,
+      "loss": 0.5947,
+      "step": 122
+    },
+    {
+      "epoch": 0.10170542635658915,
+      "grad_norm": 1.5234375,
+      "learning_rate": 9.78687127024723e-06,
+      "loss": 0.5555,
+      "step": 123
+    },
+    {
+      "epoch": 0.10253229974160206,
+      "grad_norm": 1.7109375,
+      "learning_rate": 9.782608695652175e-06,
+      "loss": 0.5515,
+      "step": 124
+    },
+    {
+      "epoch": 0.10335917312661498,
+      "grad_norm": 1.625,
+      "learning_rate": 9.778346121057119e-06,
+      "loss": 0.5983,
+      "step": 125
+    },
+    {
+      "epoch": 0.10418604651162791,
+      "grad_norm": 1.5546875,
+      "learning_rate": 9.774083546462064e-06,
+      "loss": 0.5474,
+      "step": 126
+    },
+    {
+      "epoch": 0.10501291989664083,
+      "grad_norm": 1.8671875,
+      "learning_rate": 9.769820971867009e-06,
+      "loss": 0.5726,
+      "step": 127
+    },
+    {
+      "epoch": 0.10583979328165374,
+      "grad_norm": 1.515625,
+      "learning_rate": 9.765558397271953e-06,
+      "loss": 0.5806,
+      "step": 128
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 2.015625,
+      "learning_rate": 9.761295822676897e-06,
+      "loss": 0.5551,
+      "step": 129
+    },
+    {
+      "epoch": 0.10749354005167959,
+      "grad_norm": 1.8125,
+      "learning_rate": 9.757033248081842e-06,
+      "loss": 0.5502,
+      "step": 130
+    },
+    {
+      "epoch": 0.1083204134366925,
+      "grad_norm": 1.671875,
+      "learning_rate": 9.752770673486786e-06,
+      "loss": 0.5904,
+      "step": 131
+    },
+    {
+      "epoch": 0.10914728682170542,
+      "grad_norm": 1.9140625,
+      "learning_rate": 9.748508098891732e-06,
+      "loss": 0.5645,
+      "step": 132
+    },
+    {
+      "epoch": 0.10997416020671835,
+      "grad_norm": 1.640625,
+      "learning_rate": 9.744245524296676e-06,
+      "loss": 0.5512,
+      "step": 133
+    },
+    {
+      "epoch": 0.11080103359173127,
+      "grad_norm": 1.546875,
+      "learning_rate": 9.73998294970162e-06,
+      "loss": 0.6102,
+      "step": 134
+    },
+    {
+      "epoch": 0.11162790697674418,
+      "grad_norm": 1.609375,
+      "learning_rate": 9.735720375106566e-06,
+      "loss": 0.5675,
+      "step": 135
+    },
+    {
+      "epoch": 0.1124547803617571,
+      "grad_norm": 1.6640625,
+      "learning_rate": 9.73145780051151e-06,
+      "loss": 0.5955,
+      "step": 136
+    },
+    {
+      "epoch": 0.11328165374677003,
+      "grad_norm": 1.4921875,
+      "learning_rate": 9.727195225916456e-06,
+      "loss": 0.5625,
+      "step": 137
+    },
+    {
+      "epoch": 0.11410852713178295,
+      "grad_norm": 1.8515625,
+      "learning_rate": 9.722932651321398e-06,
+      "loss": 0.5638,
+      "step": 138
+    },
+    {
+      "epoch": 0.11493540051679586,
+      "grad_norm": 1.6640625,
+      "learning_rate": 9.718670076726344e-06,
+      "loss": 0.5705,
+      "step": 139
+    },
+    {
+      "epoch": 0.11576227390180878,
+      "grad_norm": 1.609375,
+      "learning_rate": 9.714407502131288e-06,
+      "loss": 0.5565,
+      "step": 140
+    },
+    {
+      "epoch": 0.11658914728682171,
+      "grad_norm": 1.6953125,
+      "learning_rate": 9.710144927536233e-06,
+      "loss": 0.5858,
+      "step": 141
+    },
+    {
+      "epoch": 0.11741602067183463,
+      "grad_norm": 1.5703125,
+      "learning_rate": 9.705882352941177e-06,
+      "loss": 0.5468,
+      "step": 142
+    },
+    {
+      "epoch": 0.11824289405684754,
+      "grad_norm": 1.765625,
+      "learning_rate": 9.701619778346121e-06,
+      "loss": 0.5761,
+      "step": 143
+    },
+    {
+      "epoch": 0.11906976744186047,
+      "grad_norm": 1.5078125,
+      "learning_rate": 9.697357203751067e-06,
+      "loss": 0.5948,
+      "step": 144
+    },
+    {
+      "epoch": 0.11989664082687339,
+      "grad_norm": 1.8046875,
+      "learning_rate": 9.693094629156011e-06,
+      "loss": 0.5517,
+      "step": 145
+    },
+    {
+      "epoch": 0.1207235142118863,
+      "grad_norm": 1.5625,
+      "learning_rate": 9.688832054560957e-06,
+      "loss": 0.5369,
+      "step": 146
+    },
+    {
+      "epoch": 0.12155038759689922,
+      "grad_norm": 1.609375,
+      "learning_rate": 9.6845694799659e-06,
+      "loss": 0.5562,
+      "step": 147
+    },
+    {
+      "epoch": 0.12237726098191215,
+      "grad_norm": 1.7265625,
+      "learning_rate": 9.680306905370845e-06,
+      "loss": 0.5819,
+      "step": 148
+    },
+    {
+      "epoch": 0.12320413436692507,
+      "grad_norm": 1.515625,
+      "learning_rate": 9.676044330775789e-06,
+      "loss": 0.6278,
+      "step": 149
+    },
+    {
+      "epoch": 0.12403100775193798,
+      "grad_norm": 1.640625,
+      "learning_rate": 9.671781756180733e-06,
+      "loss": 0.5894,
+      "step": 150
+    },
+    {
+      "epoch": 0.1248578811369509,
+      "grad_norm": 1.5625,
+      "learning_rate": 9.667519181585679e-06,
+      "loss": 0.5729,
+      "step": 151
+    },
+    {
+      "epoch": 0.12568475452196382,
+      "grad_norm": 1.8203125,
+      "learning_rate": 9.663256606990623e-06,
+      "loss": 0.5785,
+      "step": 152
+    },
+    {
+      "epoch": 0.12651162790697673,
+      "grad_norm": 1.6171875,
+      "learning_rate": 9.658994032395568e-06,
+      "loss": 0.555,
+      "step": 153
+    },
+    {
+      "epoch": 0.12733850129198968,
+      "grad_norm": 1.671875,
+      "learning_rate": 9.654731457800512e-06,
+      "loss": 0.5665,
+      "step": 154
+    },
+    {
+      "epoch": 0.1281653746770026,
+      "grad_norm": 1.6796875,
+      "learning_rate": 9.650468883205456e-06,
+      "loss": 0.5741,
+      "step": 155
+    },
+    {
+      "epoch": 0.1289922480620155,
+      "grad_norm": 1.5390625,
+      "learning_rate": 9.646206308610402e-06,
+      "loss": 0.5461,
+      "step": 156
+    },
+    {
+      "epoch": 0.12981912144702842,
+      "grad_norm": 1.5703125,
+      "learning_rate": 9.641943734015346e-06,
+      "loss": 0.5283,
+      "step": 157
+    },
+    {
+      "epoch": 0.13064599483204134,
+      "grad_norm": 1.5,
+      "learning_rate": 9.63768115942029e-06,
+      "loss": 0.5671,
+      "step": 158
+    },
+    {
+      "epoch": 0.13147286821705426,
+      "grad_norm": 1.671875,
+      "learning_rate": 9.633418584825234e-06,
+      "loss": 0.5495,
+      "step": 159
+    },
+    {
+      "epoch": 0.13229974160206717,
+      "grad_norm": 1.4921875,
+      "learning_rate": 9.62915601023018e-06,
+      "loss": 0.6013,
+      "step": 160
+    },
+    {
+      "epoch": 0.13312661498708012,
+      "grad_norm": 1.546875,
+      "learning_rate": 9.624893435635124e-06,
+      "loss": 0.5546,
+      "step": 161
+    },
+    {
+      "epoch": 0.13395348837209303,
+      "grad_norm": 1.6484375,
+      "learning_rate": 9.62063086104007e-06,
+      "loss": 0.5795,
+      "step": 162
+    },
+    {
+      "epoch": 0.13478036175710595,
+      "grad_norm": 1.5625,
+      "learning_rate": 9.616368286445014e-06,
+      "loss": 0.5111,
+      "step": 163
+    },
+    {
+      "epoch": 0.13560723514211886,
+      "grad_norm": 1.5703125,
+      "learning_rate": 9.612105711849958e-06,
+      "loss": 0.54,
+      "step": 164
+    },
+    {
+      "epoch": 0.13643410852713178,
+      "grad_norm": 1.5390625,
+      "learning_rate": 9.607843137254903e-06,
+      "loss": 0.5552,
+      "step": 165
+    },
+    {
+      "epoch": 0.1372609819121447,
+      "grad_norm": 1.7109375,
+      "learning_rate": 9.603580562659847e-06,
+      "loss": 0.5654,
+      "step": 166
+    },
+    {
+      "epoch": 0.1380878552971576,
+      "grad_norm": 1.4765625,
+      "learning_rate": 9.599317988064793e-06,
+      "loss": 0.5415,
+      "step": 167
+    },
+    {
+      "epoch": 0.13891472868217053,
+      "grad_norm": 1.6171875,
+      "learning_rate": 9.595055413469735e-06,
+      "loss": 0.5889,
+      "step": 168
+    },
+    {
+      "epoch": 0.13974160206718347,
+      "grad_norm": 1.5859375,
+      "learning_rate": 9.590792838874681e-06,
+      "loss": 0.5061,
+      "step": 169
+    },
+    {
+      "epoch": 0.1405684754521964,
+      "grad_norm": 1.6953125,
+      "learning_rate": 9.586530264279625e-06,
+      "loss": 0.5817,
+      "step": 170
+    },
+    {
+      "epoch": 0.1413953488372093,
+      "grad_norm": 1.53125,
+      "learning_rate": 9.582267689684571e-06,
+      "loss": 0.5782,
+      "step": 171
+    },
+    {
+      "epoch": 0.14222222222222222,
+      "grad_norm": 1.6015625,
+      "learning_rate": 9.578005115089515e-06,
+      "loss": 0.599,
+      "step": 172
+    },
+    {
+      "epoch": 0.14304909560723514,
+      "grad_norm": 1.5859375,
+      "learning_rate": 9.573742540494459e-06,
+      "loss": 0.5415,
+      "step": 173
+    },
+    {
+      "epoch": 0.14387596899224805,
+      "grad_norm": 1.59375,
+      "learning_rate": 9.569479965899405e-06,
+      "loss": 0.5285,
+      "step": 174
+    },
+    {
+      "epoch": 0.14470284237726097,
+      "grad_norm": 1.53125,
+      "learning_rate": 9.565217391304349e-06,
+      "loss": 0.5509,
+      "step": 175
+    },
+    {
+      "epoch": 0.14552971576227391,
+      "grad_norm": 1.5625,
+      "learning_rate": 9.560954816709294e-06,
+      "loss": 0.5926,
+      "step": 176
+    },
+    {
+      "epoch": 0.14635658914728683,
+      "grad_norm": 1.5859375,
+      "learning_rate": 9.556692242114238e-06,
+      "loss": 0.5526,
+      "step": 177
+    },
+    {
+      "epoch": 0.14718346253229975,
+      "grad_norm": 1.4453125,
+      "learning_rate": 9.552429667519182e-06,
+      "loss": 0.5732,
+      "step": 178
+    },
+    {
+      "epoch": 0.14801033591731266,
+      "grad_norm": 1.46875,
+      "learning_rate": 9.548167092924126e-06,
+      "loss": 0.5627,
+      "step": 179
+    },
+    {
+      "epoch": 0.14883720930232558,
+      "grad_norm": 1.53125,
+      "learning_rate": 9.54390451832907e-06,
+      "loss": 0.5616,
+      "step": 180
+    },
+    {
+      "epoch": 0.1496640826873385,
+      "grad_norm": 1.6484375,
+      "learning_rate": 9.539641943734016e-06,
+      "loss": 0.5397,
+      "step": 181
+    },
+    {
+      "epoch": 0.1504909560723514,
+      "grad_norm": 1.5234375,
+      "learning_rate": 9.53537936913896e-06,
+      "loss": 0.5287,
+      "step": 182
+    },
+    {
+      "epoch": 0.15131782945736433,
+      "grad_norm": 1.796875,
+      "learning_rate": 9.531116794543906e-06,
+      "loss": 0.5463,
+      "step": 183
+    },
+    {
+      "epoch": 0.15214470284237727,
+      "grad_norm": 1.6875,
+      "learning_rate": 9.52685421994885e-06,
+      "loss": 0.58,
+      "step": 184
+    },
+    {
+      "epoch": 0.1529715762273902,
+      "grad_norm": 1.5546875,
+      "learning_rate": 9.522591645353794e-06,
+      "loss": 0.5781,
+      "step": 185
+    },
+    {
+      "epoch": 0.1537984496124031,
+      "grad_norm": 1.6171875,
+      "learning_rate": 9.51832907075874e-06,
+      "loss": 0.5884,
+      "step": 186
+    },
+    {
+      "epoch": 0.15462532299741602,
+      "grad_norm": 1.5234375,
+      "learning_rate": 9.514066496163684e-06,
+      "loss": 0.5665,
+      "step": 187
+    },
+    {
+      "epoch": 0.15545219638242894,
+      "grad_norm": 1.640625,
+      "learning_rate": 9.509803921568628e-06,
+      "loss": 0.6015,
+      "step": 188
+    },
+    {
+      "epoch": 0.15627906976744185,
+      "grad_norm": 1.5625,
+      "learning_rate": 9.505541346973572e-06,
+      "loss": 0.5758,
+      "step": 189
+    },
+    {
+      "epoch": 0.15710594315245477,
+      "grad_norm": 1.6953125,
+      "learning_rate": 9.501278772378517e-06,
+      "loss": 0.5482,
+      "step": 190
+    },
+    {
+      "epoch": 0.1579328165374677,
+      "grad_norm": 1.546875,
+      "learning_rate": 9.497016197783462e-06,
+      "loss": 0.5702,
+      "step": 191
+    },
+    {
+      "epoch": 0.15875968992248063,
+      "grad_norm": 1.640625,
+      "learning_rate": 9.492753623188407e-06,
+      "loss": 0.5684,
+      "step": 192
+    },
+    {
+      "epoch": 0.15958656330749355,
+      "grad_norm": 1.625,
+      "learning_rate": 9.488491048593351e-06,
+      "loss": 0.5742,
+      "step": 193
+    },
+    {
+      "epoch": 0.16041343669250646,
+      "grad_norm": 1.671875,
+      "learning_rate": 9.484228473998295e-06,
+      "loss": 0.5751,
+      "step": 194
+    },
+    {
+      "epoch": 0.16124031007751938,
+      "grad_norm": 1.6015625,
+      "learning_rate": 9.479965899403241e-06,
+      "loss": 0.5678,
+      "step": 195
+    },
+    {
+      "epoch": 0.1620671834625323,
+      "grad_norm": 1.453125,
+      "learning_rate": 9.475703324808185e-06,
+      "loss": 0.5053,
+      "step": 196
+    },
+    {
+      "epoch": 0.1628940568475452,
+      "grad_norm": 1.609375,
+      "learning_rate": 9.47144075021313e-06,
+      "loss": 0.5837,
+      "step": 197
+    },
+    {
+      "epoch": 0.16372093023255813,
+      "grad_norm": 1.5078125,
+      "learning_rate": 9.467178175618073e-06,
+      "loss": 0.5579,
+      "step": 198
+    },
+    {
+      "epoch": 0.16454780361757107,
+      "grad_norm": 1.4453125,
+      "learning_rate": 9.462915601023019e-06,
+      "loss": 0.571,
+      "step": 199
+    },
+    {
+      "epoch": 0.165374677002584,
+      "grad_norm": 1.5078125,
+      "learning_rate": 9.458653026427963e-06,
+      "loss": 0.5302,
+      "step": 200
+    },
+    {
+      "epoch": 0.1662015503875969,
+      "grad_norm": 1.5859375,
+      "learning_rate": 9.454390451832909e-06,
+      "loss": 0.5409,
+      "step": 201
+    },
+    {
+      "epoch": 0.16702842377260982,
+      "grad_norm": 1.6796875,
+      "learning_rate": 9.450127877237853e-06,
+      "loss": 0.6042,
+      "step": 202
+    },
+    {
+      "epoch": 0.16785529715762273,
+      "grad_norm": 1.4375,
+      "learning_rate": 9.445865302642797e-06,
+      "loss": 0.5902,
+      "step": 203
+    },
+    {
+      "epoch": 0.16868217054263565,
+      "grad_norm": 1.515625,
+      "learning_rate": 9.441602728047742e-06,
+      "loss": 0.5542,
+      "step": 204
+    },
+    {
+      "epoch": 0.16950904392764857,
+      "grad_norm": 1.453125,
+      "learning_rate": 9.437340153452686e-06,
+      "loss": 0.5515,
+      "step": 205
+    },
+    {
+      "epoch": 0.1703359173126615,
+      "grad_norm": 1.53125,
+      "learning_rate": 9.433077578857632e-06,
+      "loss": 0.6025,
+      "step": 206
+    },
+    {
+      "epoch": 0.17116279069767443,
+      "grad_norm": 1.625,
+      "learning_rate": 9.428815004262576e-06,
+      "loss": 0.5495,
+      "step": 207
+    },
+    {
+      "epoch": 0.17198966408268734,
+      "grad_norm": 1.40625,
+      "learning_rate": 9.42455242966752e-06,
+      "loss": 0.5598,
+      "step": 208
+    },
+    {
+      "epoch": 0.17281653746770026,
+      "grad_norm": 1.4765625,
+      "learning_rate": 9.420289855072464e-06,
+      "loss": 0.5368,
+      "step": 209
+    },
+    {
+      "epoch": 0.17364341085271318,
+      "grad_norm": 1.59375,
+      "learning_rate": 9.416027280477408e-06,
+      "loss": 0.5879,
+      "step": 210
+    },
+    {
+      "epoch": 0.1744702842377261,
+      "grad_norm": 1.5546875,
+      "learning_rate": 9.411764705882354e-06,
+      "loss": 0.632,
+      "step": 211
+    },
+    {
+      "epoch": 0.175297157622739,
+      "grad_norm": 1.59375,
+      "learning_rate": 9.407502131287298e-06,
+      "loss": 0.577,
+      "step": 212
+    },
+    {
+      "epoch": 0.17612403100775192,
+      "grad_norm": 1.46875,
+      "learning_rate": 9.403239556692244e-06,
+      "loss": 0.5793,
+      "step": 213
+    },
+    {
+      "epoch": 0.17695090439276487,
+      "grad_norm": 1.578125,
+      "learning_rate": 9.398976982097188e-06,
+      "loss": 0.5671,
+      "step": 214
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 1.5078125,
+      "learning_rate": 9.394714407502132e-06,
+      "loss": 0.5092,
+      "step": 215
+    },
+    {
+      "epoch": 0.1786046511627907,
+      "grad_norm": 1.4375,
+      "learning_rate": 9.390451832907077e-06,
+      "loss": 0.5474,
+      "step": 216
+    },
+    {
+      "epoch": 0.17943152454780362,
+      "grad_norm": 1.4765625,
+      "learning_rate": 9.386189258312021e-06,
+      "loss": 0.5455,
+      "step": 217
+    },
+    {
+      "epoch": 0.18025839793281653,
+      "grad_norm": 1.4765625,
+      "learning_rate": 9.381926683716965e-06,
+      "loss": 0.5659,
+      "step": 218
+    },
+    {
+      "epoch": 0.18108527131782945,
+      "grad_norm": 1.46875,
+      "learning_rate": 9.37766410912191e-06,
+      "loss": 0.542,
+      "step": 219
+    },
+    {
+      "epoch": 0.18191214470284237,
+      "grad_norm": 1.4375,
+      "learning_rate": 9.373401534526855e-06,
+      "loss": 0.4909,
+      "step": 220
+    },
+    {
+      "epoch": 0.1827390180878553,
+      "grad_norm": 1.453125,
+      "learning_rate": 9.369138959931799e-06,
+      "loss": 0.5891,
+      "step": 221
+    },
+    {
+      "epoch": 0.18356589147286823,
+      "grad_norm": 1.5,
+      "learning_rate": 9.364876385336745e-06,
+      "loss": 0.5387,
+      "step": 222
+    },
+    {
+      "epoch": 0.18439276485788114,
+      "grad_norm": 1.3984375,
+      "learning_rate": 9.360613810741689e-06,
+      "loss": 0.5262,
+      "step": 223
+    },
+    {
+      "epoch": 0.18521963824289406,
+      "grad_norm": 1.5859375,
+      "learning_rate": 9.356351236146633e-06,
+      "loss": 0.572,
+      "step": 224
+    },
+    {
+      "epoch": 0.18604651162790697,
+      "grad_norm": 1.421875,
+      "learning_rate": 9.352088661551579e-06,
+      "loss": 0.5528,
+      "step": 225
+    },
+    {
+      "epoch": 0.1868733850129199,
+      "grad_norm": 1.6640625,
+      "learning_rate": 9.347826086956523e-06,
+      "loss": 0.5928,
+      "step": 226
+    },
+    {
+      "epoch": 0.1877002583979328,
+      "grad_norm": 1.4609375,
+      "learning_rate": 9.343563512361468e-06,
+      "loss": 0.5656,
+      "step": 227
+    },
+    {
+      "epoch": 0.18852713178294572,
+      "grad_norm": 1.6640625,
+      "learning_rate": 9.33930093776641e-06,
+      "loss": 0.5646,
+      "step": 228
+    },
+    {
+      "epoch": 0.18935400516795867,
+      "grad_norm": 1.5390625,
+      "learning_rate": 9.335038363171356e-06,
+      "loss": 0.525,
+      "step": 229
+    },
+    {
+      "epoch": 0.19018087855297158,
+      "grad_norm": 1.609375,
+      "learning_rate": 9.3307757885763e-06,
+      "loss": 0.547,
+      "step": 230
+    },
+    {
+      "epoch": 0.1910077519379845,
+      "grad_norm": 1.65625,
+      "learning_rate": 9.326513213981246e-06,
+      "loss": 0.5762,
+      "step": 231
+    },
+    {
+      "epoch": 0.19183462532299742,
+      "grad_norm": 1.609375,
+      "learning_rate": 9.32225063938619e-06,
+      "loss": 0.5248,
+      "step": 232
+    },
+    {
+      "epoch": 0.19266149870801033,
+      "grad_norm": 2.4375,
+      "learning_rate": 9.317988064791134e-06,
+      "loss": 0.5127,
+      "step": 233
+    },
+    {
+      "epoch": 0.19348837209302325,
+      "grad_norm": 1.609375,
+      "learning_rate": 9.31372549019608e-06,
+      "loss": 0.508,
+      "step": 234
+    },
+    {
+      "epoch": 0.19431524547803616,
+      "grad_norm": 1.4453125,
+      "learning_rate": 9.309462915601024e-06,
+      "loss": 0.5567,
+      "step": 235
+    },
+    {
+      "epoch": 0.1951421188630491,
+      "grad_norm": 1.5546875,
+      "learning_rate": 9.30520034100597e-06,
+      "loss": 0.6026,
+      "step": 236
+    },
+    {
+      "epoch": 0.19596899224806202,
+      "grad_norm": 1.5234375,
+      "learning_rate": 9.300937766410914e-06,
+      "loss": 0.5514,
+      "step": 237
+    },
+    {
+      "epoch": 0.19679586563307494,
+      "grad_norm": 1.453125,
+      "learning_rate": 9.296675191815858e-06,
+      "loss": 0.5806,
+      "step": 238
+    },
+    {
+      "epoch": 0.19762273901808786,
+      "grad_norm": 1.75,
+      "learning_rate": 9.292412617220802e-06,
+      "loss": 0.592,
+      "step": 239
+    },
+    {
+      "epoch": 0.19844961240310077,
+      "grad_norm": 1.4453125,
+      "learning_rate": 9.288150042625746e-06,
+      "loss": 0.5198,
+      "step": 240
+    },
+    {
+      "epoch": 0.1992764857881137,
+      "grad_norm": 1.4296875,
+      "learning_rate": 9.283887468030691e-06,
+      "loss": 0.5488,
+      "step": 241
+    },
+    {
+      "epoch": 0.2001033591731266,
+      "grad_norm": 1.5390625,
+      "learning_rate": 9.279624893435635e-06,
+      "loss": 0.5306,
+      "step": 242
+    },
+    {
+      "epoch": 0.20093023255813955,
+      "grad_norm": 1.546875,
+      "learning_rate": 9.275362318840581e-06,
+      "loss": 0.5467,
+      "step": 243
+    },
+    {
+      "epoch": 0.20175710594315246,
+      "grad_norm": 1.3984375,
+      "learning_rate": 9.271099744245525e-06,
+      "loss": 0.5444,
+      "step": 244
+    },
+    {
+      "epoch": 0.20258397932816538,
+      "grad_norm": 1.53125,
+      "learning_rate": 9.26683716965047e-06,
+      "loss": 0.5286,
+      "step": 245
+    },
+    {
+      "epoch": 0.2034108527131783,
+      "grad_norm": 1.5,
+      "learning_rate": 9.262574595055415e-06,
+      "loss": 0.5965,
+      "step": 246
+    },
+    {
+      "epoch": 0.2042377260981912,
+      "grad_norm": 1.453125,
+      "learning_rate": 9.258312020460359e-06,
+      "loss": 0.532,
+      "step": 247
+    },
+    {
+      "epoch": 0.20506459948320413,
+      "grad_norm": 1.4375,
+      "learning_rate": 9.254049445865303e-06,
+      "loss": 0.5107,
+      "step": 248
+    },
+    {
+      "epoch": 0.20589147286821705,
+      "grad_norm": 1.3828125,
+      "learning_rate": 9.249786871270247e-06,
+      "loss": 0.5696,
+      "step": 249
+    },
+    {
+      "epoch": 0.20671834625322996,
+      "grad_norm": 1.5078125,
+      "learning_rate": 9.245524296675193e-06,
+      "loss": 0.5902,
+      "step": 250
+    },
+    {
+      "epoch": 0.2075452196382429,
+      "grad_norm": 1.4375,
+      "learning_rate": 9.241261722080137e-06,
+      "loss": 0.5349,
+      "step": 251
+    },
+    {
+      "epoch": 0.20837209302325582,
+      "grad_norm": 1.5078125,
+      "learning_rate": 9.236999147485082e-06,
+      "loss": 0.5458,
+      "step": 252
+    },
+    {
+      "epoch": 0.20919896640826874,
+      "grad_norm": 1.5390625,
+      "learning_rate": 9.232736572890026e-06,
+      "loss": 0.5239,
+      "step": 253
+    },
+    {
+      "epoch": 0.21002583979328165,
+      "grad_norm": 1.4609375,
+      "learning_rate": 9.22847399829497e-06,
+      "loss": 0.5634,
+      "step": 254
+    },
+    {
+      "epoch": 0.21085271317829457,
+      "grad_norm": 1.5,
+      "learning_rate": 9.224211423699916e-06,
+      "loss": 0.5557,
+      "step": 255
+    },
+    {
+      "epoch": 0.2116795865633075,
+      "grad_norm": 1.4765625,
+      "learning_rate": 9.21994884910486e-06,
+      "loss": 0.5513,
+      "step": 256
+    },
+    {
+      "epoch": 0.2125064599483204,
+      "grad_norm": 1.4296875,
+      "learning_rate": 9.215686274509804e-06,
+      "loss": 0.5685,
+      "step": 257
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 1.5,
+      "learning_rate": 9.211423699914748e-06,
+      "loss": 0.5946,
+      "step": 258
+    },
+    {
+      "epoch": 0.21416020671834626,
+      "grad_norm": 1.484375,
+      "learning_rate": 9.207161125319694e-06,
+      "loss": 0.5498,
+      "step": 259
+    },
+    {
+      "epoch": 0.21498708010335918,
+      "grad_norm": 1.5234375,
+      "learning_rate": 9.202898550724638e-06,
+      "loss": 0.5409,
+      "step": 260
+    },
+    {
+      "epoch": 0.2158139534883721,
+      "grad_norm": 1.3671875,
+      "learning_rate": 9.198635976129584e-06,
+      "loss": 0.549,
+      "step": 261
+    },
+    {
+      "epoch": 0.216640826873385,
+      "grad_norm": 1.890625,
+      "learning_rate": 9.194373401534528e-06,
+      "loss": 0.6063,
+      "step": 262
+    },
+    {
+      "epoch": 0.21746770025839793,
+      "grad_norm": 1.5234375,
+      "learning_rate": 9.190110826939472e-06,
+      "loss": 0.5595,
+      "step": 263
+    },
+    {
+      "epoch": 0.21829457364341084,
+      "grad_norm": 1.4375,
+      "learning_rate": 9.185848252344417e-06,
+      "loss": 0.5713,
+      "step": 264
+    },
+    {
+      "epoch": 0.21912144702842376,
+      "grad_norm": 1.6015625,
+      "learning_rate": 9.181585677749362e-06,
+      "loss": 0.5665,
+      "step": 265
+    },
+    {
+      "epoch": 0.2199483204134367,
+      "grad_norm": 1.4453125,
+      "learning_rate": 9.177323103154307e-06,
+      "loss": 0.5006,
+      "step": 266
+    },
+    {
+      "epoch": 0.22077519379844962,
+      "grad_norm": 1.5234375,
+      "learning_rate": 9.17306052855925e-06,
+      "loss": 0.5815,
+      "step": 267
+    },
+    {
+      "epoch": 0.22160206718346254,
+      "grad_norm": 1.75,
+      "learning_rate": 9.168797953964195e-06,
+      "loss": 0.567,
+      "step": 268
+    },
+    {
+      "epoch": 0.22242894056847545,
+      "grad_norm": 1.4140625,
+      "learning_rate": 9.16453537936914e-06,
+      "loss": 0.5538,
+      "step": 269
+    },
+    {
+      "epoch": 0.22325581395348837,
+      "grad_norm": 1.5859375,
+      "learning_rate": 9.160272804774083e-06,
+      "loss": 0.5602,
+      "step": 270
+    },
+    {
+      "epoch": 0.22408268733850129,
+      "grad_norm": 1.5078125,
+      "learning_rate": 9.156010230179029e-06,
+      "loss": 0.556,
+      "step": 271
+    },
+    {
+      "epoch": 0.2249095607235142,
+      "grad_norm": 1.3984375,
+      "learning_rate": 9.151747655583973e-06,
+      "loss": 0.5395,
+      "step": 272
+    },
+    {
+      "epoch": 0.22573643410852715,
+      "grad_norm": 1.59375,
+      "learning_rate": 9.147485080988919e-06,
+      "loss": 0.5405,
+      "step": 273
+    },
+    {
+      "epoch": 0.22656330749354006,
+      "grad_norm": 1.453125,
+      "learning_rate": 9.143222506393863e-06,
+      "loss": 0.5249,
+      "step": 274
+    },
+    {
+      "epoch": 0.22739018087855298,
+      "grad_norm": 1.4765625,
+      "learning_rate": 9.138959931798807e-06,
+      "loss": 0.5361,
+      "step": 275
+    },
+    {
+      "epoch": 0.2282170542635659,
+      "grad_norm": 1.4453125,
+      "learning_rate": 9.134697357203753e-06,
+      "loss": 0.5761,
+      "step": 276
+    },
+    {
+      "epoch": 0.2290439276485788,
+      "grad_norm": 1.46875,
+      "learning_rate": 9.130434782608697e-06,
+      "loss": 0.5722,
+      "step": 277
+    },
+    {
+      "epoch": 0.22987080103359173,
+      "grad_norm": 1.390625,
+      "learning_rate": 9.12617220801364e-06,
+      "loss": 0.5481,
+      "step": 278
+    },
+    {
+      "epoch": 0.23069767441860464,
+      "grad_norm": 1.5546875,
+      "learning_rate": 9.121909633418585e-06,
+      "loss": 0.5455,
+      "step": 279
+    },
+    {
+      "epoch": 0.23152454780361756,
+      "grad_norm": 1.3515625,
+      "learning_rate": 9.11764705882353e-06,
+      "loss": 0.5168,
+      "step": 280
+    },
+    {
+      "epoch": 0.2323514211886305,
+      "grad_norm": 1.328125,
+      "learning_rate": 9.113384484228474e-06,
+      "loss": 0.564,
+      "step": 281
+    },
+    {
+      "epoch": 0.23317829457364342,
+      "grad_norm": 1.390625,
+      "learning_rate": 9.10912190963342e-06,
+      "loss": 0.5747,
+      "step": 282
+    },
+    {
+      "epoch": 0.23400516795865633,
+      "grad_norm": 1.3984375,
+      "learning_rate": 9.104859335038364e-06,
+      "loss": 0.5543,
+      "step": 283
+    },
+    {
+      "epoch": 0.23483204134366925,
+      "grad_norm": 1.484375,
+      "learning_rate": 9.100596760443308e-06,
+      "loss": 0.5222,
+      "step": 284
+    },
+    {
+      "epoch": 0.23565891472868217,
+      "grad_norm": 1.921875,
+      "learning_rate": 9.096334185848254e-06,
+      "loss": 0.5809,
+      "step": 285
+    },
+    {
+      "epoch": 0.23648578811369508,
+      "grad_norm": 1.4375,
+      "learning_rate": 9.092071611253198e-06,
+      "loss": 0.5408,
+      "step": 286
+    },
+    {
+      "epoch": 0.237312661498708,
+      "grad_norm": 1.4453125,
+      "learning_rate": 9.087809036658142e-06,
+      "loss": 0.5426,
+      "step": 287
+    },
+    {
+      "epoch": 0.23813953488372094,
+      "grad_norm": 1.390625,
+      "learning_rate": 9.083546462063086e-06,
+      "loss": 0.5592,
+      "step": 288
+    },
+    {
+      "epoch": 0.23896640826873386,
+      "grad_norm": 1.46875,
+      "learning_rate": 9.079283887468032e-06,
+      "loss": 0.5664,
+      "step": 289
+    },
+    {
+      "epoch": 0.23979328165374678,
+      "grad_norm": 1.4375,
+      "learning_rate": 9.075021312872976e-06,
+      "loss": 0.5509,
+      "step": 290
+    },
+    {
+      "epoch": 0.2406201550387597,
+      "grad_norm": 1.4296875,
+      "learning_rate": 9.070758738277921e-06,
+      "loss": 0.5863,
+      "step": 291
+    },
+    {
+      "epoch": 0.2414470284237726,
+      "grad_norm": 1.46875,
+      "learning_rate": 9.066496163682865e-06,
+      "loss": 0.5757,
+      "step": 292
+    },
+    {
+      "epoch": 0.24227390180878552,
+      "grad_norm": 1.4140625,
+      "learning_rate": 9.06223358908781e-06,
+      "loss": 0.5344,
+      "step": 293
+    },
+    {
+      "epoch": 0.24310077519379844,
+      "grad_norm": 1.625,
+      "learning_rate": 9.057971014492755e-06,
+      "loss": 0.5545,
+      "step": 294
+    },
+    {
+      "epoch": 0.24392764857881136,
+      "grad_norm": 1.4921875,
+      "learning_rate": 9.053708439897699e-06,
+      "loss": 0.568,
+      "step": 295
+    },
+    {
+      "epoch": 0.2447545219638243,
+      "grad_norm": 1.3984375,
+      "learning_rate": 9.049445865302645e-06,
+      "loss": 0.5555,
+      "step": 296
+    },
+    {
+      "epoch": 0.24558139534883722,
+      "grad_norm": 1.375,
+      "learning_rate": 9.045183290707587e-06,
+      "loss": 0.551,
+      "step": 297
+    },
+    {
+      "epoch": 0.24640826873385013,
+      "grad_norm": 1.5078125,
+      "learning_rate": 9.040920716112533e-06,
+      "loss": 0.5729,
+      "step": 298
+    },
+    {
+      "epoch": 0.24723514211886305,
+      "grad_norm": 1.4296875,
+      "learning_rate": 9.036658141517477e-06,
+      "loss": 0.5513,
+      "step": 299
+    },
+    {
+      "epoch": 0.24806201550387597,
+      "grad_norm": 1.484375,
+      "learning_rate": 9.032395566922421e-06,
+      "loss": 0.5587,
+      "step": 300
+    },
+    {
+      "epoch": 0.24888888888888888,
+      "grad_norm": 1.4375,
+      "learning_rate": 9.028132992327367e-06,
+      "loss": 0.5753,
+      "step": 301
+    },
+    {
+      "epoch": 0.2497157622739018,
+      "grad_norm": 1.4296875,
+      "learning_rate": 9.02387041773231e-06,
+      "loss": 0.5658,
+      "step": 302
+    },
+    {
+      "epoch": 0.2505426356589147,
+      "grad_norm": 1.4609375,
+      "learning_rate": 9.019607843137256e-06,
+      "loss": 0.4941,
+      "step": 303
+    },
+    {
+      "epoch": 0.25136950904392763,
+      "grad_norm": 1.5078125,
+      "learning_rate": 9.0153452685422e-06,
+      "loss": 0.5505,
+      "step": 304
+    },
+    {
+      "epoch": 0.25219638242894055,
+      "grad_norm": 1.3046875,
+      "learning_rate": 9.011082693947144e-06,
+      "loss": 0.502,
+      "step": 305
+    },
+    {
+      "epoch": 0.25302325581395346,
+      "grad_norm": 1.59375,
+      "learning_rate": 9.00682011935209e-06,
+      "loss": 0.5908,
+      "step": 306
+    },
+    {
+      "epoch": 0.25385012919896643,
+      "grad_norm": 1.4296875,
+      "learning_rate": 9.002557544757034e-06,
+      "loss": 0.4948,
+      "step": 307
+    },
+    {
+      "epoch": 0.25467700258397935,
+      "grad_norm": 1.6484375,
+      "learning_rate": 8.998294970161978e-06,
+      "loss": 0.5696,
+      "step": 308
+    },
+    {
+      "epoch": 0.25550387596899227,
+      "grad_norm": 1.4375,
+      "learning_rate": 8.994032395566922e-06,
+      "loss": 0.5292,
+      "step": 309
+    },
+    {
+      "epoch": 0.2563307493540052,
+      "grad_norm": 1.5078125,
+      "learning_rate": 8.989769820971868e-06,
+      "loss": 0.5214,
+      "step": 310
+    },
+    {
+      "epoch": 0.2571576227390181,
+      "grad_norm": 1.328125,
+      "learning_rate": 8.985507246376812e-06,
+      "loss": 0.5,
+      "step": 311
+    },
+    {
+      "epoch": 0.257984496124031,
+      "grad_norm": 1.46875,
+      "learning_rate": 8.981244671781758e-06,
+      "loss": 0.5398,
+      "step": 312
+    },
+    {
+      "epoch": 0.25881136950904393,
+      "grad_norm": 1.390625,
+      "learning_rate": 8.976982097186702e-06,
+      "loss": 0.5366,
+      "step": 313
+    },
+    {
+      "epoch": 0.25963824289405685,
+      "grad_norm": 1.5703125,
+      "learning_rate": 8.972719522591646e-06,
+      "loss": 0.5952,
+      "step": 314
+    },
+    {
+      "epoch": 0.26046511627906976,
+      "grad_norm": 1.390625,
+      "learning_rate": 8.968456947996591e-06,
+      "loss": 0.5442,
+      "step": 315
+    },
+    {
+      "epoch": 0.2612919896640827,
+      "grad_norm": 1.4296875,
+      "learning_rate": 8.964194373401535e-06,
+      "loss": 0.5722,
+      "step": 316
+    },
+    {
+      "epoch": 0.2621188630490956,
+      "grad_norm": 1.5,
+      "learning_rate": 8.95993179880648e-06,
+      "loss": 0.5415,
+      "step": 317
+    },
+    {
+      "epoch": 0.2629457364341085,
+      "grad_norm": 1.5234375,
+      "learning_rate": 8.955669224211423e-06,
+      "loss": 0.5508,
+      "step": 318
+    },
+    {
+      "epoch": 0.26377260981912143,
+      "grad_norm": 1.3828125,
+      "learning_rate": 8.95140664961637e-06,
+      "loss": 0.546,
+      "step": 319
+    },
+    {
+      "epoch": 0.26459948320413434,
+      "grad_norm": 1.5234375,
+      "learning_rate": 8.947144075021313e-06,
+      "loss": 0.5803,
+      "step": 320
+    },
+    {
+      "epoch": 0.26542635658914726,
+      "grad_norm": 1.3671875,
+      "learning_rate": 8.942881500426259e-06,
+      "loss": 0.4805,
+      "step": 321
+    },
+    {
+      "epoch": 0.26625322997416023,
+      "grad_norm": 1.4296875,
+      "learning_rate": 8.938618925831203e-06,
+      "loss": 0.5396,
+      "step": 322
+    },
+    {
+      "epoch": 0.26708010335917315,
+      "grad_norm": 1.34375,
+      "learning_rate": 8.934356351236147e-06,
+      "loss": 0.5116,
+      "step": 323
+    },
+    {
+      "epoch": 0.26790697674418606,
+      "grad_norm": 1.53125,
+      "learning_rate": 8.930093776641093e-06,
+      "loss": 0.5334,
+      "step": 324
+    },
+    {
+      "epoch": 0.268733850129199,
+      "grad_norm": 1.328125,
+      "learning_rate": 8.925831202046037e-06,
+      "loss": 0.5089,
+      "step": 325
+    },
+    {
+      "epoch": 0.2695607235142119,
+      "grad_norm": 1.421875,
+      "learning_rate": 8.921568627450982e-06,
+      "loss": 0.538,
+      "step": 326
+    },
+    {
+      "epoch": 0.2703875968992248,
+      "grad_norm": 1.4609375,
+      "learning_rate": 8.917306052855925e-06,
+      "loss": 0.5415,
+      "step": 327
+    },
+    {
+      "epoch": 0.27121447028423773,
+      "grad_norm": 1.3671875,
+      "learning_rate": 8.91304347826087e-06,
+      "loss": 0.5222,
+      "step": 328
+    },
+    {
+      "epoch": 0.27204134366925065,
+      "grad_norm": 1.3984375,
+      "learning_rate": 8.908780903665815e-06,
+      "loss": 0.5499,
+      "step": 329
+    },
+    {
+      "epoch": 0.27286821705426356,
+      "grad_norm": 1.4296875,
+      "learning_rate": 8.904518329070759e-06,
+      "loss": 0.5752,
+      "step": 330
+    },
+    {
+      "epoch": 0.2736950904392765,
+      "grad_norm": 1.375,
+      "learning_rate": 8.900255754475704e-06,
+      "loss": 0.5626,
+      "step": 331
+    },
+    {
+      "epoch": 0.2745219638242894,
+      "grad_norm": 1.390625,
+      "learning_rate": 8.895993179880648e-06,
+      "loss": 0.5555,
+      "step": 332
+    },
+    {
+      "epoch": 0.2753488372093023,
+      "grad_norm": 1.3359375,
+      "learning_rate": 8.891730605285594e-06,
+      "loss": 0.5089,
+      "step": 333
+    },
+    {
+      "epoch": 0.2761757105943152,
+      "grad_norm": 1.4296875,
+      "learning_rate": 8.887468030690538e-06,
+      "loss": 0.524,
+      "step": 334
+    },
+    {
+      "epoch": 0.27700258397932814,
+      "grad_norm": 1.3046875,
+      "learning_rate": 8.883205456095482e-06,
+      "loss": 0.5237,
+      "step": 335
+    },
+    {
+      "epoch": 0.27782945736434106,
+      "grad_norm": 1.3125,
+      "learning_rate": 8.878942881500428e-06,
+      "loss": 0.5164,
+      "step": 336
+    },
+    {
+      "epoch": 0.27865633074935403,
+      "grad_norm": 1.359375,
+      "learning_rate": 8.874680306905372e-06,
+      "loss": 0.541,
+      "step": 337
+    },
+    {
+      "epoch": 0.27948320413436695,
+      "grad_norm": 1.3359375,
+      "learning_rate": 8.870417732310316e-06,
+      "loss": 0.55,
+      "step": 338
+    },
+    {
+      "epoch": 0.28031007751937986,
+      "grad_norm": 1.3984375,
+      "learning_rate": 8.86615515771526e-06,
+      "loss": 0.5185,
+      "step": 339
+    },
+    {
+      "epoch": 0.2811369509043928,
+      "grad_norm": 1.3515625,
+      "learning_rate": 8.861892583120206e-06,
+      "loss": 0.5298,
+      "step": 340
+    },
+    {
+      "epoch": 0.2819638242894057,
+      "grad_norm": 1.3828125,
+      "learning_rate": 8.85763000852515e-06,
+      "loss": 0.529,
+      "step": 341
+    },
+    {
+      "epoch": 0.2827906976744186,
+      "grad_norm": 1.3359375,
+      "learning_rate": 8.853367433930095e-06,
+      "loss": 0.5416,
+      "step": 342
+    },
+    {
+      "epoch": 0.28361757105943153,
+      "grad_norm": 1.359375,
+      "learning_rate": 8.84910485933504e-06,
+      "loss": 0.5272,
+      "step": 343
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 1.40625,
+      "learning_rate": 8.844842284739983e-06,
+      "loss": 0.5242,
+      "step": 344
+    },
+    {
+      "epoch": 0.28527131782945736,
+      "grad_norm": 1.6015625,
+      "learning_rate": 8.840579710144929e-06,
+      "loss": 0.5575,
+      "step": 345
+    },
+    {
+      "epoch": 0.2860981912144703,
+      "grad_norm": 1.46875,
+      "learning_rate": 8.836317135549873e-06,
+      "loss": 0.5506,
+      "step": 346
+    },
+    {
+      "epoch": 0.2869250645994832,
+      "grad_norm": 1.484375,
+      "learning_rate": 8.832054560954817e-06,
+      "loss": 0.5472,
+      "step": 347
+    },
+    {
+      "epoch": 0.2877519379844961,
+      "grad_norm": 1.578125,
+      "learning_rate": 8.827791986359761e-06,
+      "loss": 0.5494,
+      "step": 348
+    },
+    {
+      "epoch": 0.288578811369509,
+      "grad_norm": 1.421875,
+      "learning_rate": 8.823529411764707e-06,
+      "loss": 0.5172,
+      "step": 349
+    },
+    {
+      "epoch": 0.28940568475452194,
+      "grad_norm": 1.53125,
+      "learning_rate": 8.81926683716965e-06,
+      "loss": 0.562,
+      "step": 350
+    },
+    {
+      "epoch": 0.29023255813953486,
+      "grad_norm": 1.4765625,
+      "learning_rate": 8.815004262574597e-06,
+      "loss": 0.5714,
+      "step": 351
+    },
+    {
+      "epoch": 0.29105943152454783,
+      "grad_norm": 1.6640625,
+      "learning_rate": 8.81074168797954e-06,
+      "loss": 0.5154,
+      "step": 352
+    },
+    {
+      "epoch": 0.29188630490956075,
+      "grad_norm": 1.96875,
+      "learning_rate": 8.806479113384485e-06,
+      "loss": 0.5346,
+      "step": 353
+    },
+    {
+      "epoch": 0.29271317829457366,
+      "grad_norm": 1.5859375,
+      "learning_rate": 8.80221653878943e-06,
+      "loss": 0.541,
+      "step": 354
+    },
+    {
+      "epoch": 0.2935400516795866,
+      "grad_norm": 1.390625,
+      "learning_rate": 8.797953964194374e-06,
+      "loss": 0.5115,
+      "step": 355
+    },
+    {
+      "epoch": 0.2943669250645995,
+      "grad_norm": 1.3984375,
+      "learning_rate": 8.79369138959932e-06,
+      "loss": 0.5598,
+      "step": 356
+    },
+    {
+      "epoch": 0.2951937984496124,
+      "grad_norm": 1.40625,
+      "learning_rate": 8.789428815004262e-06,
+      "loss": 0.5382,
+      "step": 357
+    },
+    {
+      "epoch": 0.2960206718346253,
+      "grad_norm": 1.3671875,
+      "learning_rate": 8.785166240409208e-06,
+      "loss": 0.5305,
+      "step": 358
+    },
+    {
+      "epoch": 0.29684754521963824,
+      "grad_norm": 1.390625,
+      "learning_rate": 8.780903665814152e-06,
+      "loss": 0.5208,
+      "step": 359
+    },
+    {
+      "epoch": 0.29767441860465116,
+      "grad_norm": 1.421875,
+      "learning_rate": 8.776641091219096e-06,
+      "loss": 0.5524,
+      "step": 360
+    },
+    {
+      "epoch": 0.2985012919896641,
+      "grad_norm": 1.359375,
+      "learning_rate": 8.772378516624042e-06,
+      "loss": 0.5516,
+      "step": 361
+    },
+    {
+      "epoch": 0.299328165374677,
+      "grad_norm": 1.4453125,
+      "learning_rate": 8.768115942028986e-06,
+      "loss": 0.5724,
+      "step": 362
+    },
+    {
+      "epoch": 0.3001550387596899,
+      "grad_norm": 1.4921875,
+      "learning_rate": 8.763853367433932e-06,
+      "loss": 0.5821,
+      "step": 363
+    },
+    {
+      "epoch": 0.3009819121447028,
+      "grad_norm": 1.4453125,
+      "learning_rate": 8.759590792838876e-06,
+      "loss": 0.5687,
+      "step": 364
+    },
+    {
+      "epoch": 0.30180878552971574,
+      "grad_norm": 1.3359375,
+      "learning_rate": 8.75532821824382e-06,
+      "loss": 0.5271,
+      "step": 365
+    },
+    {
+      "epoch": 0.30263565891472866,
+      "grad_norm": 1.5,
+      "learning_rate": 8.751065643648765e-06,
+      "loss": 0.535,
+      "step": 366
+    },
+    {
+      "epoch": 0.3034625322997416,
+      "grad_norm": 1.375,
+      "learning_rate": 8.74680306905371e-06,
+      "loss": 0.538,
+      "step": 367
+    },
+    {
+      "epoch": 0.30428940568475454,
+      "grad_norm": 1.46875,
+      "learning_rate": 8.742540494458653e-06,
+      "loss": 0.545,
+      "step": 368
+    },
+    {
+      "epoch": 0.30511627906976746,
+      "grad_norm": 1.375,
+      "learning_rate": 8.738277919863597e-06,
+      "loss": 0.5746,
+      "step": 369
+    },
+    {
+      "epoch": 0.3059431524547804,
+      "grad_norm": 1.5,
+      "learning_rate": 8.734015345268543e-06,
+      "loss": 0.5912,
+      "step": 370
+    },
+    {
+      "epoch": 0.3067700258397933,
+      "grad_norm": 1.6328125,
+      "learning_rate": 8.729752770673487e-06,
+      "loss": 0.5714,
+      "step": 371
+    },
+    {
+      "epoch": 0.3075968992248062,
+      "grad_norm": 1.3984375,
+      "learning_rate": 8.725490196078433e-06,
+      "loss": 0.5431,
+      "step": 372
+    },
+    {
+      "epoch": 0.3084237726098191,
+      "grad_norm": 1.453125,
+      "learning_rate": 8.721227621483377e-06,
+      "loss": 0.5373,
+      "step": 373
+    },
+    {
+      "epoch": 0.30925064599483204,
+      "grad_norm": 1.4375,
+      "learning_rate": 8.716965046888321e-06,
+      "loss": 0.5799,
+      "step": 374
+    },
+    {
+      "epoch": 0.31007751937984496,
+      "grad_norm": 1.4609375,
+      "learning_rate": 8.712702472293267e-06,
+      "loss": 0.5062,
+      "step": 375
+    },
+    {
+      "epoch": 0.3109043927648579,
+      "grad_norm": 1.3515625,
+      "learning_rate": 8.70843989769821e-06,
+      "loss": 0.5134,
+      "step": 376
+    },
+    {
+      "epoch": 0.3117312661498708,
+      "grad_norm": 1.5625,
+      "learning_rate": 8.704177323103155e-06,
+      "loss": 0.5668,
+      "step": 377
+    },
+    {
+      "epoch": 0.3125581395348837,
+      "grad_norm": 1.40625,
+      "learning_rate": 8.699914748508099e-06,
+      "loss": 0.5645,
+      "step": 378
+    },
+    {
+      "epoch": 0.3133850129198966,
+      "grad_norm": 1.4765625,
+      "learning_rate": 8.695652173913044e-06,
+      "loss": 0.5874,
+      "step": 379
+    },
+    {
+      "epoch": 0.31421188630490954,
+      "grad_norm": 1.421875,
+      "learning_rate": 8.691389599317988e-06,
+      "loss": 0.5218,
+      "step": 380
+    },
+    {
+      "epoch": 0.31503875968992245,
+      "grad_norm": 1.3984375,
+      "learning_rate": 8.687127024722934e-06,
+      "loss": 0.551,
+      "step": 381
+    },
+    {
+      "epoch": 0.3158656330749354,
+      "grad_norm": 1.453125,
+      "learning_rate": 8.682864450127878e-06,
+      "loss": 0.561,
+      "step": 382
+    },
+    {
+      "epoch": 0.31669250645994834,
+      "grad_norm": 1.328125,
+      "learning_rate": 8.678601875532822e-06,
+      "loss": 0.5168,
+      "step": 383
+    },
+    {
+      "epoch": 0.31751937984496126,
+      "grad_norm": 1.359375,
+      "learning_rate": 8.674339300937768e-06,
+      "loss": 0.5225,
+      "step": 384
+    },
+    {
+      "epoch": 0.3183462532299742,
+      "grad_norm": 1.359375,
+      "learning_rate": 8.670076726342712e-06,
+      "loss": 0.5415,
+      "step": 385
+    },
+    {
+      "epoch": 0.3191731266149871,
+      "grad_norm": 1.3984375,
+      "learning_rate": 8.665814151747658e-06,
+      "loss": 0.5761,
+      "step": 386
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.3671875,
+      "learning_rate": 8.6615515771526e-06,
+      "loss": 0.5399,
+      "step": 387
+    },
+    {
+      "epoch": 0.3208268733850129,
+      "grad_norm": 1.4765625,
+      "learning_rate": 8.657289002557546e-06,
+      "loss": 0.5813,
+      "step": 388
+    },
+    {
+      "epoch": 0.32165374677002584,
+      "grad_norm": 1.3984375,
+      "learning_rate": 8.65302642796249e-06,
+      "loss": 0.5352,
+      "step": 389
+    },
+    {
+      "epoch": 0.32248062015503876,
+      "grad_norm": 1.5,
+      "learning_rate": 8.648763853367434e-06,
+      "loss": 0.557,
+      "step": 390
+    },
+    {
+      "epoch": 0.32330749354005167,
+      "grad_norm": 1.359375,
+      "learning_rate": 8.64450127877238e-06,
+      "loss": 0.5463,
+      "step": 391
+    },
+    {
+      "epoch": 0.3241343669250646,
+      "grad_norm": 1.546875,
+      "learning_rate": 8.640238704177323e-06,
+      "loss": 0.5588,
+      "step": 392
+    },
+    {
+      "epoch": 0.3249612403100775,
+      "grad_norm": 1.3828125,
+      "learning_rate": 8.63597612958227e-06,
+      "loss": 0.5253,
+      "step": 393
+    },
+    {
+      "epoch": 0.3257881136950904,
+      "grad_norm": 1.5546875,
+      "learning_rate": 8.631713554987213e-06,
+      "loss": 0.5296,
+      "step": 394
+    },
+    {
+      "epoch": 0.32661498708010334,
+      "grad_norm": 1.5,
+      "learning_rate": 8.627450980392157e-06,
+      "loss": 0.5896,
+      "step": 395
+    },
+    {
+      "epoch": 0.32744186046511625,
+      "grad_norm": 1.375,
+      "learning_rate": 8.623188405797103e-06,
+      "loss": 0.4987,
+      "step": 396
+    },
+    {
+      "epoch": 0.3282687338501292,
+      "grad_norm": 1.609375,
+      "learning_rate": 8.618925831202047e-06,
+      "loss": 0.5512,
+      "step": 397
+    },
+    {
+      "epoch": 0.32909560723514214,
+      "grad_norm": 1.3515625,
+      "learning_rate": 8.614663256606991e-06,
+      "loss": 0.5419,
+      "step": 398
+    },
+    {
+      "epoch": 0.32992248062015506,
+      "grad_norm": 1.4921875,
+      "learning_rate": 8.610400682011935e-06,
+      "loss": 0.512,
+      "step": 399
+    },
+    {
+      "epoch": 0.330749354005168,
+      "grad_norm": 1.4609375,
+      "learning_rate": 8.60613810741688e-06,
+      "loss": 0.5138,
+      "step": 400
+    },
+    {
+      "epoch": 0.3315762273901809,
+      "grad_norm": 1.390625,
+      "learning_rate": 8.601875532821825e-06,
+      "loss": 0.5786,
+      "step": 401
+    },
+    {
+      "epoch": 0.3324031007751938,
+      "grad_norm": 1.5703125,
+      "learning_rate": 8.59761295822677e-06,
+      "loss": 0.4939,
+      "step": 402
+    },
+    {
+      "epoch": 0.3332299741602067,
+      "grad_norm": 1.3359375,
+      "learning_rate": 8.593350383631714e-06,
+      "loss": 0.5249,
+      "step": 403
+    },
+    {
+      "epoch": 0.33405684754521964,
+      "grad_norm": 1.4921875,
+      "learning_rate": 8.589087809036659e-06,
+      "loss": 0.5522,
+      "step": 404
+    },
+    {
+      "epoch": 0.33488372093023255,
+      "grad_norm": 1.515625,
+      "learning_rate": 8.584825234441604e-06,
+      "loss": 0.4874,
+      "step": 405
+    },
+    {
+      "epoch": 0.33571059431524547,
+      "grad_norm": 1.5390625,
+      "learning_rate": 8.580562659846548e-06,
+      "loss": 0.5813,
+      "step": 406
+    },
+    {
+      "epoch": 0.3365374677002584,
+      "grad_norm": 1.453125,
+      "learning_rate": 8.576300085251492e-06,
+      "loss": 0.5856,
+      "step": 407
+    },
+    {
+      "epoch": 0.3373643410852713,
+      "grad_norm": 1.4609375,
+      "learning_rate": 8.572037510656436e-06,
+      "loss": 0.5478,
+      "step": 408
+    },
+    {
+      "epoch": 0.3381912144702842,
+      "grad_norm": 1.453125,
+      "learning_rate": 8.567774936061382e-06,
+      "loss": 0.5272,
+      "step": 409
+    },
+    {
+      "epoch": 0.33901808785529713,
+      "grad_norm": 1.4140625,
+      "learning_rate": 8.563512361466326e-06,
+      "loss": 0.5151,
+      "step": 410
+    },
+    {
+      "epoch": 0.33984496124031005,
+      "grad_norm": 1.421875,
+      "learning_rate": 8.559249786871272e-06,
+      "loss": 0.5219,
+      "step": 411
+    },
+    {
+      "epoch": 0.340671834625323,
+      "grad_norm": 1.5390625,
+      "learning_rate": 8.554987212276216e-06,
+      "loss": 0.5277,
+      "step": 412
+    },
+    {
+      "epoch": 0.34149870801033594,
+      "grad_norm": 1.375,
+      "learning_rate": 8.55072463768116e-06,
+      "loss": 0.5577,
+      "step": 413
+    },
+    {
+      "epoch": 0.34232558139534885,
+      "grad_norm": 1.40625,
+      "learning_rate": 8.546462063086106e-06,
+      "loss": 0.5317,
+      "step": 414
+    },
+    {
+      "epoch": 0.34315245478036177,
+      "grad_norm": 1.4296875,
+      "learning_rate": 8.54219948849105e-06,
+      "loss": 0.5449,
+      "step": 415
+    },
+    {
+      "epoch": 0.3439793281653747,
+      "grad_norm": 1.5,
+      "learning_rate": 8.537936913895994e-06,
+      "loss": 0.5239,
+      "step": 416
+    },
+    {
+      "epoch": 0.3448062015503876,
+      "grad_norm": 1.3203125,
+      "learning_rate": 8.533674339300938e-06,
+      "loss": 0.5108,
+      "step": 417
+    },
+    {
+      "epoch": 0.3456330749354005,
+      "grad_norm": 1.453125,
+      "learning_rate": 8.529411764705883e-06,
+      "loss": 0.531,
+      "step": 418
+    },
+    {
+      "epoch": 0.34645994832041344,
+      "grad_norm": 1.359375,
+      "learning_rate": 8.525149190110827e-06,
+      "loss": 0.5228,
+      "step": 419
+    },
+    {
+      "epoch": 0.34728682170542635,
+      "grad_norm": 1.375,
+      "learning_rate": 8.520886615515771e-06,
+      "loss": 0.5578,
+      "step": 420
+    },
+    {
+      "epoch": 0.34811369509043927,
+      "grad_norm": 1.4296875,
+      "learning_rate": 8.516624040920717e-06,
+      "loss": 0.5662,
+      "step": 421
+    },
+    {
+      "epoch": 0.3489405684754522,
+      "grad_norm": 1.3671875,
+      "learning_rate": 8.512361466325661e-06,
+      "loss": 0.5242,
+      "step": 422
+    },
+    {
+      "epoch": 0.3497674418604651,
+      "grad_norm": 1.4140625,
+      "learning_rate": 8.508098891730607e-06,
+      "loss": 0.561,
+      "step": 423
+    },
+    {
+      "epoch": 0.350594315245478,
+      "grad_norm": 1.3984375,
+      "learning_rate": 8.50383631713555e-06,
+      "loss": 0.5288,
+      "step": 424
+    },
+    {
+      "epoch": 0.35142118863049093,
+      "grad_norm": 1.3203125,
+      "learning_rate": 8.499573742540495e-06,
+      "loss": 0.5674,
+      "step": 425
+    },
+    {
+      "epoch": 0.35224806201550385,
+      "grad_norm": 1.40625,
+      "learning_rate": 8.495311167945439e-06,
+      "loss": 0.5498,
+      "step": 426
+    },
+    {
+      "epoch": 0.3530749354005168,
+      "grad_norm": 1.3125,
+      "learning_rate": 8.491048593350385e-06,
+      "loss": 0.5596,
+      "step": 427
+    },
+    {
+      "epoch": 0.35390180878552974,
+      "grad_norm": 1.421875,
+      "learning_rate": 8.486786018755329e-06,
+      "loss": 0.5644,
+      "step": 428
+    },
+    {
+      "epoch": 0.35472868217054265,
+      "grad_norm": 1.453125,
+      "learning_rate": 8.482523444160273e-06,
+      "loss": 0.5438,
+      "step": 429
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 1.390625,
+      "learning_rate": 8.478260869565218e-06,
+      "loss": 0.5453,
+      "step": 430
+    },
+    {
+      "epoch": 0.3563824289405685,
+      "grad_norm": 1.3828125,
+      "learning_rate": 8.473998294970162e-06,
+      "loss": 0.5225,
+      "step": 431
+    },
+    {
+      "epoch": 0.3572093023255814,
+      "grad_norm": 1.34375,
+      "learning_rate": 8.469735720375108e-06,
+      "loss": 0.5388,
+      "step": 432
+    },
+    {
+      "epoch": 0.3580361757105943,
+      "grad_norm": 1.4140625,
+      "learning_rate": 8.465473145780052e-06,
+      "loss": 0.5856,
+      "step": 433
+    },
+    {
+      "epoch": 0.35886304909560723,
+      "grad_norm": 1.359375,
+      "learning_rate": 8.461210571184996e-06,
+      "loss": 0.5072,
+      "step": 434
+    },
+    {
+      "epoch": 0.35968992248062015,
+      "grad_norm": 1.4375,
+      "learning_rate": 8.456947996589942e-06,
+      "loss": 0.5303,
+      "step": 435
+    },
+    {
+      "epoch": 0.36051679586563307,
+      "grad_norm": 1.28125,
+      "learning_rate": 8.452685421994886e-06,
+      "loss": 0.5313,
+      "step": 436
+    },
+    {
+      "epoch": 0.361343669250646,
+      "grad_norm": 1.3671875,
+      "learning_rate": 8.44842284739983e-06,
+      "loss": 0.5301,
+      "step": 437
+    },
+    {
+      "epoch": 0.3621705426356589,
+      "grad_norm": 1.34375,
+      "learning_rate": 8.444160272804774e-06,
+      "loss": 0.5223,
+      "step": 438
+    },
+    {
+      "epoch": 0.3629974160206718,
+      "grad_norm": 1.359375,
+      "learning_rate": 8.43989769820972e-06,
+      "loss": 0.5389,
+      "step": 439
+    },
+    {
+      "epoch": 0.36382428940568473,
+      "grad_norm": 1.390625,
+      "learning_rate": 8.435635123614664e-06,
+      "loss": 0.538,
+      "step": 440
+    },
+    {
+      "epoch": 0.36465116279069765,
+      "grad_norm": 1.265625,
+      "learning_rate": 8.43137254901961e-06,
+      "loss": 0.5157,
+      "step": 441
+    },
+    {
+      "epoch": 0.3654780361757106,
+      "grad_norm": 1.4375,
+      "learning_rate": 8.427109974424553e-06,
+      "loss": 0.5694,
+      "step": 442
+    },
+    {
+      "epoch": 0.36630490956072354,
+      "grad_norm": 1.3671875,
+      "learning_rate": 8.422847399829497e-06,
+      "loss": 0.5588,
+      "step": 443
+    },
+    {
+      "epoch": 0.36713178294573645,
+      "grad_norm": 1.296875,
+      "learning_rate": 8.418584825234443e-06,
+      "loss": 0.5218,
+      "step": 444
+    },
+    {
+      "epoch": 0.36795865633074937,
+      "grad_norm": 1.375,
+      "learning_rate": 8.414322250639387e-06,
+      "loss": 0.5072,
+      "step": 445
+    },
+    {
+      "epoch": 0.3687855297157623,
+      "grad_norm": 1.390625,
+      "learning_rate": 8.410059676044331e-06,
+      "loss": 0.5609,
+      "step": 446
+    },
+    {
+      "epoch": 0.3696124031007752,
+      "grad_norm": 1.3984375,
+      "learning_rate": 8.405797101449275e-06,
+      "loss": 0.506,
+      "step": 447
+    },
+    {
+      "epoch": 0.3704392764857881,
+      "grad_norm": 1.375,
+      "learning_rate": 8.401534526854221e-06,
+      "loss": 0.583,
+      "step": 448
+    },
+    {
+      "epoch": 0.37126614987080103,
+      "grad_norm": 1.4609375,
+      "learning_rate": 8.397271952259165e-06,
+      "loss": 0.5959,
+      "step": 449
+    },
+    {
+      "epoch": 0.37209302325581395,
+      "grad_norm": 1.3515625,
+      "learning_rate": 8.393009377664109e-06,
+      "loss": 0.5341,
+      "step": 450
+    },
+    {
+      "epoch": 0.37291989664082686,
+      "grad_norm": 1.5390625,
+      "learning_rate": 8.388746803069055e-06,
+      "loss": 0.5695,
+      "step": 451
+    },
+    {
+      "epoch": 0.3737467700258398,
+      "grad_norm": 1.453125,
+      "learning_rate": 8.384484228473999e-06,
+      "loss": 0.5309,
+      "step": 452
+    },
+    {
+      "epoch": 0.3745736434108527,
+      "grad_norm": 1.40625,
+      "learning_rate": 8.380221653878944e-06,
+      "loss": 0.511,
+      "step": 453
+    },
+    {
+      "epoch": 0.3754005167958656,
+      "grad_norm": 1.3046875,
+      "learning_rate": 8.375959079283888e-06,
+      "loss": 0.5633,
+      "step": 454
+    },
+    {
+      "epoch": 0.37622739018087853,
+      "grad_norm": 1.4375,
+      "learning_rate": 8.371696504688832e-06,
+      "loss": 0.5362,
+      "step": 455
+    },
+    {
+      "epoch": 0.37705426356589145,
+      "grad_norm": 1.3359375,
+      "learning_rate": 8.367433930093776e-06,
+      "loss": 0.4971,
+      "step": 456
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 2418,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 152,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.198203633149149e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-456/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b8b70bdd6844cbc575a210bfbaeeb5f4c70cbdff738b68a67f3400f40348d0c
+size 7096

checkpoint-608/config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 11,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 770,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "unsloth_version": "2024.9",
+  "use_cache": false,
+  "vocab_size": 32768
+}

checkpoint-608/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 11,
+  "max_length": 32768,
+  "pad_token_id": 770,
+  "transformers_version": "4.51.3"
+}

checkpoint-608/model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2342956a0c7d82ce1e0f984284c9c1b7947ef9004c24bc9ea1016ad6be5f891c
+size 4949453792

checkpoint-608/model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be1f900e798a8f2efec8639c43f8a78dcea0a7ca38105c6ec13d2e69cc585554
+size 4999819336

checkpoint-608/model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fec27ec457ab85c91a850c1cc2ec9fcf69af67fb0610ffde4b1ecbcf3f119e9d
+size 4546807800

checkpoint-608/model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 14496047104
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

checkpoint-608/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64013f519b50226f97b3caca87e8c163895d511fdade8c7876f462a7e7037864
+size 28992288510

checkpoint-608/pytorch_model_fsdp.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbca23dedb85e1f799ef533006c2db638685b29e472eec133845b29c619c39e4
+size 14496203157

checkpoint-608/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad792af33c7cfa8b15298ecc9d976ebdcdeb444ca0e704c7b0657f41ee6547eb
+size 14512

checkpoint-608/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:722c924fceffd85f8ab1a5445f1ea1e6c502644b6a42e2ff6b5a9a76ea26e1fe
+size 14512

checkpoint-608/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4efc49c85307316a3f2a47c48ea34efeb9ea75897e06451437f4b9174a81da06
+size 1064

checkpoint-608/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[control_768]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-608/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93e01cb5f215abfe797344a3b7bf0e874b49708177a8b115bbdde722983e3948
+size 587414

checkpoint-608/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b8b70bdd6844cbc575a210bfbaeeb5f4c70cbdff738b68a67f3400f40348d0c
+size 7096

config.json

@@ -0,0 +1,29 @@
+{
+  "_attn_implementation_autoset": true,
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 11,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 770,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "unsloth_version": "2024.9",
+  "use_cache": false,
+  "vocab_size": 32768
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 11,
+  "max_length": 32768,
+  "pad_token_id": 770,
+  "transformers_version": "4.51.3"
+}