1030 model updates

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "deepseek-ai/deepseek-coder-6.7b-base",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 32013,
+  "eos_token_id": 32014,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 16384,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "factor": 4.0,
+    "rope_type": "linear",
+    "type": "linear"
+  },
+  "rope_theta": 100000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "vocab_size": 32256
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 32013,
+  "eos_token_id": 32014,
+  "transformers_version": "4.44.2"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5d3643e8ff84e64e72aeafc6c2a85badcfdff7d2d121884b7a41d95785039f1
+size 4941082400

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c2ffafe48100c2899ffa336650cd329644f8976d45f930a6e076ec3453d5bc8
+size 4947390768

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ff11cc143b9be57c1a708b5745b87e9febf0a2fc964466be8101fe23fa37e78
+size 3592585888

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 13481025536
+  },
+  "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-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-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-00001-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-00001-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-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-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-00002-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-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-00002-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-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"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,193 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "32000": {
+      "content": "õ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32001": {
+      "content": "÷",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32002": {
+      "content": "Á",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32003": {
+      "content": "ý",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32004": {
+      "content": "À",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32005": {
+      "content": "ÿ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32006": {
+      "content": "ø",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32007": {
+      "content": "ú",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32008": {
+      "content": "þ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32009": {
+      "content": "ü",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32010": {
+      "content": "ù",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32011": {
+      "content": "ö",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32012": {
+      "content": "û",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32013": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<｜fim▁hole｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32016": {
+      "content": "<｜fim▁begin｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32017": {
+      "content": "<｜fim▁end｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32018": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32019": {
+      "content": "<|User|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32020": {
+      "content": "<|Assistant|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32021": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,1389 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.994236311239193,
+  "eval_steps": 20,
+  "global_step": 346,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.011527377521613832,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0,
+      "loss": 0.7662,
+      "step": 2
+    },
+    {
+      "epoch": 0.023054755043227664,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0,
+      "loss": 0.7773,
+      "step": 4
+    },
+    {
+      "epoch": 0.0345821325648415,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0,
+      "loss": 0.7593,
+      "step": 6
+    },
+    {
+      "epoch": 0.04610951008645533,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0,
+      "loss": 0.795,
+      "step": 8
+    },
+    {
+      "epoch": 0.05763688760806916,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0,
+      "loss": 0.7765,
+      "step": 10
+    },
+    {
+      "epoch": 0.069164265129683,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0,
+      "loss": 0.7819,
+      "step": 12
+    },
+    {
+      "epoch": 0.08069164265129683,
+      "grad_norm": 1.0932377576828003,
+      "learning_rate": 2.5e-06,
+      "loss": 0.7426,
+      "step": 14
+    },
+    {
+      "epoch": 0.09221902017291066,
+      "grad_norm": 1.0143316984176636,
+      "learning_rate": 7.5e-06,
+      "loss": 0.7667,
+      "step": 16
+    },
+    {
+      "epoch": 0.1037463976945245,
+      "grad_norm": 0.5817523002624512,
+      "learning_rate": 1.25e-05,
+      "loss": 0.6819,
+      "step": 18
+    },
+    {
+      "epoch": 0.11527377521613832,
+      "grad_norm": 0.7819337248802185,
+      "learning_rate": 1.5e-05,
+      "loss": 0.6171,
+      "step": 20
+    },
+    {
+      "epoch": 0.11527377521613832,
+      "eval_loss": 0.5882565379142761,
+      "eval_runtime": 219.1309,
+      "eval_samples_per_second": 21.325,
+      "eval_steps_per_second": 0.169,
+      "step": 20
+    },
+    {
+      "epoch": 0.12680115273775217,
+      "grad_norm": 0.4540252089500427,
+      "learning_rate": 2e-05,
+      "loss": 0.5573,
+      "step": 22
+    },
+    {
+      "epoch": 0.138328530259366,
+      "grad_norm": 0.31643402576446533,
+      "learning_rate": 2.5e-05,
+      "loss": 0.5615,
+      "step": 24
+    },
+    {
+      "epoch": 0.14985590778097982,
+      "grad_norm": 0.2575995922088623,
+      "learning_rate": 3e-05,
+      "loss": 0.5225,
+      "step": 26
+    },
+    {
+      "epoch": 0.16138328530259366,
+      "grad_norm": 0.1953422576189041,
+      "learning_rate": 3.5e-05,
+      "loss": 0.5141,
+      "step": 28
+    },
+    {
+      "epoch": 0.1729106628242075,
+      "grad_norm": 0.17974254488945007,
+      "learning_rate": 4e-05,
+      "loss": 0.508,
+      "step": 30
+    },
+    {
+      "epoch": 0.1844380403458213,
+      "grad_norm": 0.16816851496696472,
+      "learning_rate": 4.5e-05,
+      "loss": 0.4763,
+      "step": 32
+    },
+    {
+      "epoch": 0.19596541786743515,
+      "grad_norm": 0.16267944872379303,
+      "learning_rate": 5e-05,
+      "loss": 0.4757,
+      "step": 34
+    },
+    {
+      "epoch": 0.207492795389049,
+      "grad_norm": 0.1356152594089508,
+      "learning_rate": 4.9995821084255035e-05,
+      "loss": 0.4714,
+      "step": 36
+    },
+    {
+      "epoch": 0.21902017291066284,
+      "grad_norm": 0.12293241173028946,
+      "learning_rate": 4.998328588931674e-05,
+      "loss": 0.4777,
+      "step": 38
+    },
+    {
+      "epoch": 0.23054755043227665,
+      "grad_norm": 0.12494528293609619,
+      "learning_rate": 4.996239907149833e-05,
+      "loss": 0.4649,
+      "step": 40
+    },
+    {
+      "epoch": 0.23054755043227665,
+      "eval_loss": 0.45945191383361816,
+      "eval_runtime": 163.1604,
+      "eval_samples_per_second": 28.641,
+      "eval_steps_per_second": 0.227,
+      "step": 40
+    },
+    {
+      "epoch": 0.2420749279538905,
+      "grad_norm": 0.11425463855266571,
+      "learning_rate": 4.993316838939995e-05,
+      "loss": 0.4508,
+      "step": 42
+    },
+    {
+      "epoch": 0.25360230547550433,
+      "grad_norm": 0.11498431116342545,
+      "learning_rate": 4.9895604701026735e-05,
+      "loss": 0.4433,
+      "step": 44
+    },
+    {
+      "epoch": 0.26512968299711814,
+      "grad_norm": 0.12802694737911224,
+      "learning_rate": 4.9849721959755464e-05,
+      "loss": 0.451,
+      "step": 46
+    },
+    {
+      "epoch": 0.276657060518732,
+      "grad_norm": 0.11723160743713379,
+      "learning_rate": 4.979553720915145e-05,
+      "loss": 0.4344,
+      "step": 48
+    },
+    {
+      "epoch": 0.2881844380403458,
+      "grad_norm": 0.11519418656826019,
+      "learning_rate": 4.9733070576637606e-05,
+      "loss": 0.4464,
+      "step": 50
+    },
+    {
+      "epoch": 0.29971181556195964,
+      "grad_norm": 0.1040327250957489,
+      "learning_rate": 4.9662345266017836e-05,
+      "loss": 0.4367,
+      "step": 52
+    },
+    {
+      "epoch": 0.3112391930835735,
+      "grad_norm": 0.10918751358985901,
+      "learning_rate": 4.9583387548857836e-05,
+      "loss": 0.4411,
+      "step": 54
+    },
+    {
+      "epoch": 0.3227665706051873,
+      "grad_norm": 0.11520207673311234,
+      "learning_rate": 4.949622675472627e-05,
+      "loss": 0.4119,
+      "step": 56
+    },
+    {
+      "epoch": 0.33429394812680113,
+      "grad_norm": 0.11275804787874222,
+      "learning_rate": 4.940089526030003e-05,
+      "loss": 0.4387,
+      "step": 58
+    },
+    {
+      "epoch": 0.345821325648415,
+      "grad_norm": 0.11030508577823639,
+      "learning_rate": 4.92974284773376e-05,
+      "loss": 0.4265,
+      "step": 60
+    },
+    {
+      "epoch": 0.345821325648415,
+      "eval_loss": 0.4273378252983093,
+      "eval_runtime": 163.6226,
+      "eval_samples_per_second": 28.56,
+      "eval_steps_per_second": 0.226,
+      "step": 60
+    },
+    {
+      "epoch": 0.3573487031700288,
+      "grad_norm": 0.1050853505730629,
+      "learning_rate": 4.9185864839525065e-05,
+      "loss": 0.4217,
+      "step": 62
+    },
+    {
+      "epoch": 0.3688760806916426,
+      "grad_norm": 0.1106187105178833,
+      "learning_rate": 4.906624578819954e-05,
+      "loss": 0.4244,
+      "step": 64
+    },
+    {
+      "epoch": 0.3804034582132565,
+      "grad_norm": 0.1203250139951706,
+      "learning_rate": 4.893861575695544e-05,
+      "loss": 0.4161,
+      "step": 66
+    },
+    {
+      "epoch": 0.3919308357348703,
+      "grad_norm": 0.13240748643875122,
+      "learning_rate": 4.880302215513915e-05,
+      "loss": 0.4205,
+      "step": 68
+    },
+    {
+      "epoch": 0.4034582132564842,
+      "grad_norm": 0.11961999535560608,
+      "learning_rate": 4.865951535023847e-05,
+      "loss": 0.4152,
+      "step": 70
+    },
+    {
+      "epoch": 0.414985590778098,
+      "grad_norm": 0.10617737472057343,
+      "learning_rate": 4.850814864917309e-05,
+      "loss": 0.4151,
+      "step": 72
+    },
+    {
+      "epoch": 0.4265129682997118,
+      "grad_norm": 0.1053657978773117,
+      "learning_rate": 4.834897827849325e-05,
+      "loss": 0.4286,
+      "step": 74
+    },
+    {
+      "epoch": 0.43804034582132567,
+      "grad_norm": 0.1263289898633957,
+      "learning_rate": 4.818206336349391e-05,
+      "loss": 0.4206,
+      "step": 76
+    },
+    {
+      "epoch": 0.4495677233429395,
+      "grad_norm": 0.11088111996650696,
+      "learning_rate": 4.8007465906252065e-05,
+      "loss": 0.4127,
+      "step": 78
+    },
+    {
+      "epoch": 0.4610951008645533,
+      "grad_norm": 0.10416624695062637,
+      "learning_rate": 4.782525076259556e-05,
+      "loss": 0.3924,
+      "step": 80
+    },
+    {
+      "epoch": 0.4610951008645533,
+      "eval_loss": 0.41243475675582886,
+      "eval_runtime": 163.0434,
+      "eval_samples_per_second": 28.661,
+      "eval_steps_per_second": 0.227,
+      "step": 80
+    },
+    {
+      "epoch": 0.47262247838616717,
+      "grad_norm": 0.109275221824646,
+      "learning_rate": 4.763548561801175e-05,
+      "loss": 0.418,
+      "step": 82
+    },
+    {
+      "epoch": 0.484149855907781,
+      "grad_norm": 0.11440867185592651,
+      "learning_rate": 4.743824096250513e-05,
+      "loss": 0.4054,
+      "step": 84
+    },
+    {
+      "epoch": 0.4956772334293948,
+      "grad_norm": 0.11359245330095291,
+      "learning_rate": 4.723359006441316e-05,
+      "loss": 0.3969,
+      "step": 86
+    },
+    {
+      "epoch": 0.5072046109510087,
+      "grad_norm": 0.11708330363035202,
+      "learning_rate": 4.7021608943190105e-05,
+      "loss": 0.4052,
+      "step": 88
+    },
+    {
+      "epoch": 0.5187319884726225,
+      "grad_norm": 0.1086309477686882,
+      "learning_rate": 4.680237634116884e-05,
+      "loss": 0.4055,
+      "step": 90
+    },
+    {
+      "epoch": 0.5302593659942363,
+      "grad_norm": 0.1133558601140976,
+      "learning_rate": 4.6575973694311364e-05,
+      "loss": 0.4016,
+      "step": 92
+    },
+    {
+      "epoch": 0.5417867435158501,
+      "grad_norm": 0.11118675768375397,
+      "learning_rate": 4.6342485101958634e-05,
+      "loss": 0.4137,
+      "step": 94
+    },
+    {
+      "epoch": 0.553314121037464,
+      "grad_norm": 0.1130242571234703,
+      "learning_rate": 4.610199729559106e-05,
+      "loss": 0.4125,
+      "step": 96
+    },
+    {
+      "epoch": 0.5648414985590778,
+      "grad_norm": 0.10623504966497421,
+      "learning_rate": 4.585459960661137e-05,
+      "loss": 0.3989,
+      "step": 98
+    },
+    {
+      "epoch": 0.5763688760806917,
+      "grad_norm": 0.10171157866716385,
+      "learning_rate": 4.5600383933161586e-05,
+      "loss": 0.4099,
+      "step": 100
+    },
+    {
+      "epoch": 0.5763688760806917,
+      "eval_loss": 0.40298977494239807,
+      "eval_runtime": 163.0144,
+      "eval_samples_per_second": 28.666,
+      "eval_steps_per_second": 0.227,
+      "step": 100
+    },
+    {
+      "epoch": 0.5878962536023055,
+      "grad_norm": 0.1252756267786026,
+      "learning_rate": 4.5339444705986636e-05,
+      "loss": 0.4047,
+      "step": 102
+    },
+    {
+      "epoch": 0.5994236311239193,
+      "grad_norm": 0.12425834685564041,
+      "learning_rate": 4.507187885335716e-05,
+      "loss": 0.4044,
+      "step": 104
+    },
+    {
+      "epoch": 0.6109510086455331,
+      "grad_norm": 0.12188662588596344,
+      "learning_rate": 4.479778576506467e-05,
+      "loss": 0.3985,
+      "step": 106
+    },
+    {
+      "epoch": 0.622478386167147,
+      "grad_norm": 0.1297188252210617,
+      "learning_rate": 4.451726725550226e-05,
+      "loss": 0.4105,
+      "step": 108
+    },
+    {
+      "epoch": 0.6340057636887608,
+      "grad_norm": 0.1405544877052307,
+      "learning_rate": 4.423042752584471e-05,
+      "loss": 0.3943,
+      "step": 110
+    },
+    {
+      "epoch": 0.6455331412103746,
+      "grad_norm": 0.1427697390317917,
+      "learning_rate": 4.393737312534203e-05,
+      "loss": 0.3929,
+      "step": 112
+    },
+    {
+      "epoch": 0.6570605187319885,
+      "grad_norm": 0.12234554439783096,
+      "learning_rate": 4.363821291174073e-05,
+      "loss": 0.385,
+      "step": 114
+    },
+    {
+      "epoch": 0.6685878962536023,
+      "grad_norm": 0.11913135647773743,
+      "learning_rate": 4.3333058010847665e-05,
+      "loss": 0.3944,
+      "step": 116
+    },
+    {
+      "epoch": 0.6801152737752162,
+      "grad_norm": 0.10236409306526184,
+      "learning_rate": 4.302202177525126e-05,
+      "loss": 0.4088,
+      "step": 118
+    },
+    {
+      "epoch": 0.69164265129683,
+      "grad_norm": 0.1148187592625618,
+      "learning_rate": 4.270521974221572e-05,
+      "loss": 0.3925,
+      "step": 120
+    },
+    {
+      "epoch": 0.69164265129683,
+      "eval_loss": 0.39593446254730225,
+      "eval_runtime": 163.197,
+      "eval_samples_per_second": 28.634,
+      "eval_steps_per_second": 0.227,
+      "step": 120
+    },
+    {
+      "epoch": 0.7031700288184438,
+      "grad_norm": 0.1020105630159378,
+      "learning_rate": 4.238276959076362e-05,
+      "loss": 0.3959,
+      "step": 122
+    },
+    {
+      "epoch": 0.7146974063400576,
+      "grad_norm": 0.09900052100419998,
+      "learning_rate": 4.205479109796293e-05,
+      "loss": 0.3938,
+      "step": 124
+    },
+    {
+      "epoch": 0.7262247838616714,
+      "grad_norm": 0.11457400768995285,
+      "learning_rate": 4.172140609443478e-05,
+      "loss": 0.3941,
+      "step": 126
+    },
+    {
+      "epoch": 0.7377521613832853,
+      "grad_norm": 0.12308034300804138,
+      "learning_rate": 4.138273841909831e-05,
+      "loss": 0.3773,
+      "step": 128
+    },
+    {
+      "epoch": 0.7492795389048992,
+      "grad_norm": 0.11765991151332855,
+      "learning_rate": 4.1038913873169606e-05,
+      "loss": 0.3908,
+      "step": 130
+    },
+    {
+      "epoch": 0.760806916426513,
+      "grad_norm": 0.11604655534029007,
+      "learning_rate": 4.069006017343161e-05,
+      "loss": 0.4024,
+      "step": 132
+    },
+    {
+      "epoch": 0.7723342939481268,
+      "grad_norm": 0.10507753491401672,
+      "learning_rate": 4.033630690479266e-05,
+      "loss": 0.3874,
+      "step": 134
+    },
+    {
+      "epoch": 0.7838616714697406,
+      "grad_norm": 0.11194345355033875,
+      "learning_rate": 3.99777854721509e-05,
+      "loss": 0.3902,
+      "step": 136
+    },
+    {
+      "epoch": 0.7953890489913544,
+      "grad_norm": 0.10498375445604324,
+      "learning_rate": 3.961462905158275e-05,
+      "loss": 0.3922,
+      "step": 138
+    },
+    {
+      "epoch": 0.8069164265129684,
+      "grad_norm": 0.10028143227100372,
+      "learning_rate": 3.924697254087344e-05,
+      "loss": 0.3884,
+      "step": 140
+    },
+    {
+      "epoch": 0.8069164265129684,
+      "eval_loss": 0.3904818892478943,
+      "eval_runtime": 165.7335,
+      "eval_samples_per_second": 28.196,
+      "eval_steps_per_second": 0.223,
+      "step": 140
+    },
+    {
+      "epoch": 0.8184438040345822,
+      "grad_norm": 0.10579356551170349,
+      "learning_rate": 3.887495250940798e-05,
+      "loss": 0.3945,
+      "step": 142
+    },
+    {
+      "epoch": 0.829971181556196,
+      "grad_norm": 0.10865680873394012,
+      "learning_rate": 3.8498707147441186e-05,
+      "loss": 0.396,
+      "step": 144
+    },
+    {
+      "epoch": 0.8414985590778098,
+      "grad_norm": 0.10962694138288498,
+      "learning_rate": 3.8118376214765724e-05,
+      "loss": 0.3925,
+      "step": 146
+    },
+    {
+      "epoch": 0.8530259365994236,
+      "grad_norm": 0.14297883212566376,
+      "learning_rate": 3.773410098879694e-05,
+      "loss": 0.3862,
+      "step": 148
+    },
+    {
+      "epoch": 0.8645533141210374,
+      "grad_norm": 0.12033689022064209,
+      "learning_rate": 3.734602421209414e-05,
+      "loss": 0.3923,
+      "step": 150
+    },
+    {
+      "epoch": 0.8760806916426513,
+      "grad_norm": 0.11992188543081284,
+      "learning_rate": 3.6954290039337544e-05,
+      "loss": 0.3864,
+      "step": 152
+    },
+    {
+      "epoch": 0.8876080691642652,
+      "grad_norm": 0.1202910915017128,
+      "learning_rate": 3.6559043983780695e-05,
+      "loss": 0.3965,
+      "step": 154
+    },
+    {
+      "epoch": 0.899135446685879,
+      "grad_norm": 0.1139882281422615,
+      "learning_rate": 3.6160432863198227e-05,
+      "loss": 0.3867,
+      "step": 156
+    },
+    {
+      "epoch": 0.9106628242074928,
+      "grad_norm": 0.10837512463331223,
+      "learning_rate": 3.575860474534907e-05,
+      "loss": 0.3734,
+      "step": 158
+    },
+    {
+      "epoch": 0.9221902017291066,
+      "grad_norm": 0.11608846485614777,
+      "learning_rate": 3.535370889297532e-05,
+      "loss": 0.3856,
+      "step": 160
+    },
+    {
+      "epoch": 0.9221902017291066,
+      "eval_loss": 0.3864249289035797,
+      "eval_runtime": 162.9187,
+      "eval_samples_per_second": 28.683,
+      "eval_steps_per_second": 0.227,
+      "step": 160
+    },
+    {
+      "epoch": 0.9337175792507204,
+      "grad_norm": 0.11061898618936539,
+      "learning_rate": 3.494589570835719e-05,
+      "loss": 0.3874,
+      "step": 162
+    },
+    {
+      "epoch": 0.9452449567723343,
+      "grad_norm": 0.10494677722454071,
+      "learning_rate": 3.4535316677444745e-05,
+      "loss": 0.3862,
+      "step": 164
+    },
+    {
+      "epoch": 0.9567723342939481,
+      "grad_norm": 0.11414439976215363,
+      "learning_rate": 3.412212431358704e-05,
+      "loss": 0.382,
+      "step": 166
+    },
+    {
+      "epoch": 0.968299711815562,
+      "grad_norm": 0.12404631823301315,
+      "learning_rate": 3.3706472100879635e-05,
+      "loss": 0.3893,
+      "step": 168
+    },
+    {
+      "epoch": 0.9798270893371758,
+      "grad_norm": 0.11317316442728043,
+      "learning_rate": 3.3288514437151505e-05,
+      "loss": 0.379,
+      "step": 170
+    },
+    {
+      "epoch": 0.9913544668587896,
+      "grad_norm": 0.11200971901416779,
+      "learning_rate": 3.286840657661259e-05,
+      "loss": 0.3829,
+      "step": 172
+    },
+    {
+      "epoch": 1.0028818443804035,
+      "grad_norm": 0.11575999855995178,
+      "learning_rate": 3.2446304572183155e-05,
+      "loss": 0.3757,
+      "step": 174
+    },
+    {
+      "epoch": 1.0144092219020173,
+      "grad_norm": 0.1118895411491394,
+      "learning_rate": 3.2022365217526515e-05,
+      "loss": 0.3487,
+      "step": 176
+    },
+    {
+      "epoch": 1.0259365994236311,
+      "grad_norm": 0.11941341310739517,
+      "learning_rate": 3.159674598880658e-05,
+      "loss": 0.3611,
+      "step": 178
+    },
+    {
+      "epoch": 1.037463976945245,
+      "grad_norm": 0.12434028834104538,
+      "learning_rate": 3.116960498619191e-05,
+      "loss": 0.3527,
+      "step": 180
+    },
+    {
+      "epoch": 1.037463976945245,
+      "eval_loss": 0.38433459401130676,
+      "eval_runtime": 167.462,
+      "eval_samples_per_second": 27.905,
+      "eval_steps_per_second": 0.221,
+      "step": 180
+    },
+    {
+      "epoch": 1.0489913544668588,
+      "grad_norm": 0.1257391721010208,
+      "learning_rate": 3.0741100875127956e-05,
+      "loss": 0.346,
+      "step": 182
+    },
+    {
+      "epoch": 1.0605187319884726,
+      "grad_norm": 0.1072888970375061,
+      "learning_rate": 3.0311392827399266e-05,
+      "loss": 0.351,
+      "step": 184
+    },
+    {
+      "epoch": 1.0720461095100864,
+      "grad_norm": 0.11550486832857132,
+      "learning_rate": 2.9880640462003766e-05,
+      "loss": 0.3584,
+      "step": 186
+    },
+    {
+      "epoch": 1.0835734870317002,
+      "grad_norm": 0.11017844080924988,
+      "learning_rate": 2.944900378586073e-05,
+      "loss": 0.3528,
+      "step": 188
+    },
+    {
+      "epoch": 1.0951008645533142,
+      "grad_norm": 0.11351864784955978,
+      "learning_rate": 2.901664313437478e-05,
+      "loss": 0.3548,
+      "step": 190
+    },
+    {
+      "epoch": 1.106628242074928,
+      "grad_norm": 0.11179786920547485,
+      "learning_rate": 2.8583719111877844e-05,
+      "loss": 0.3433,
+      "step": 192
+    },
+    {
+      "epoch": 1.1181556195965419,
+      "grad_norm": 0.10140883177518845,
+      "learning_rate": 2.8150392531971137e-05,
+      "loss": 0.3524,
+      "step": 194
+    },
+    {
+      "epoch": 1.1296829971181557,
+      "grad_norm": 0.10281901806592941,
+      "learning_rate": 2.7716824357789567e-05,
+      "loss": 0.3527,
+      "step": 196
+    },
+    {
+      "epoch": 1.1412103746397695,
+      "grad_norm": 0.09435153007507324,
+      "learning_rate": 2.728317564221044e-05,
+      "loss": 0.3521,
+      "step": 198
+    },
+    {
+      "epoch": 1.1527377521613833,
+      "grad_norm": 0.10692735016345978,
+      "learning_rate": 2.684960746802887e-05,
+      "loss": 0.3635,
+      "step": 200
+    },
+    {
+      "epoch": 1.1527377521613833,
+      "eval_loss": 0.3818141520023346,
+      "eval_runtime": 163.2711,
+      "eval_samples_per_second": 28.621,
+      "eval_steps_per_second": 0.227,
+      "step": 200
+    },
+    {
+      "epoch": 1.1642651296829971,
+      "grad_norm": 0.10303134471178055,
+      "learning_rate": 2.6416280888122165e-05,
+      "loss": 0.341,
+      "step": 202
+    },
+    {
+      "epoch": 1.175792507204611,
+      "grad_norm": 0.1047578901052475,
+      "learning_rate": 2.5983356865625224e-05,
+      "loss": 0.3483,
+      "step": 204
+    },
+    {
+      "epoch": 1.1873198847262247,
+      "grad_norm": 0.09823092073202133,
+      "learning_rate": 2.5550996214139283e-05,
+      "loss": 0.3469,
+      "step": 206
+    },
+    {
+      "epoch": 1.1988472622478386,
+      "grad_norm": 0.10456107556819916,
+      "learning_rate": 2.511935953799624e-05,
+      "loss": 0.3498,
+      "step": 208
+    },
+    {
+      "epoch": 1.2103746397694524,
+      "grad_norm": 0.10154879838228226,
+      "learning_rate": 2.4688607172600742e-05,
+      "loss": 0.3494,
+      "step": 210
+    },
+    {
+      "epoch": 1.2219020172910664,
+      "grad_norm": 0.10301995277404785,
+      "learning_rate": 2.4258899124872063e-05,
+      "loss": 0.344,
+      "step": 212
+    },
+    {
+      "epoch": 1.23342939481268,
+      "grad_norm": 0.10198619216680527,
+      "learning_rate": 2.3830395013808088e-05,
+      "loss": 0.3453,
+      "step": 214
+    },
+    {
+      "epoch": 1.244956772334294,
+      "grad_norm": 0.10618147999048233,
+      "learning_rate": 2.3403254011193433e-05,
+      "loss": 0.3492,
+      "step": 216
+    },
+    {
+      "epoch": 1.2564841498559078,
+      "grad_norm": 0.10644455999135971,
+      "learning_rate": 2.2977634782473493e-05,
+      "loss": 0.3365,
+      "step": 218
+    },
+    {
+      "epoch": 1.2680115273775217,
+      "grad_norm": 0.10750509053468704,
+      "learning_rate": 2.2553695427816847e-05,
+      "loss": 0.3527,
+      "step": 220
+    },
+    {
+      "epoch": 1.2680115273775217,
+      "eval_loss": 0.37958407402038574,
+      "eval_runtime": 162.0488,
+      "eval_samples_per_second": 28.837,
+      "eval_steps_per_second": 0.228,
+      "step": 220
+    },
+    {
+      "epoch": 1.2795389048991355,
+      "grad_norm": 0.10969573259353638,
+      "learning_rate": 2.2131593423387414e-05,
+      "loss": 0.3388,
+      "step": 222
+    },
+    {
+      "epoch": 1.2910662824207493,
+      "grad_norm": 0.11101813614368439,
+      "learning_rate": 2.1711485562848504e-05,
+      "loss": 0.3417,
+      "step": 224
+    },
+    {
+      "epoch": 1.302593659942363,
+      "grad_norm": 0.10727708041667938,
+      "learning_rate": 2.1293527899120374e-05,
+      "loss": 0.3478,
+      "step": 226
+    },
+    {
+      "epoch": 1.314121037463977,
+      "grad_norm": 0.11611964553594589,
+      "learning_rate": 2.0877875686412966e-05,
+      "loss": 0.34,
+      "step": 228
+    },
+    {
+      "epoch": 1.3256484149855907,
+      "grad_norm": 0.11851979792118073,
+      "learning_rate": 2.0464683322555267e-05,
+      "loss": 0.3413,
+      "step": 230
+    },
+    {
+      "epoch": 1.3371757925072045,
+      "grad_norm": 0.11880774050951004,
+      "learning_rate": 2.0054104291642818e-05,
+      "loss": 0.3479,
+      "step": 232
+    },
+    {
+      "epoch": 1.3487031700288186,
+      "grad_norm": 0.10287457704544067,
+      "learning_rate": 1.964629110702469e-05,
+      "loss": 0.3434,
+      "step": 234
+    },
+    {
+      "epoch": 1.3602305475504322,
+      "grad_norm": 0.10474801808595657,
+      "learning_rate": 1.924139525465093e-05,
+      "loss": 0.338,
+      "step": 236
+    },
+    {
+      "epoch": 1.3717579250720462,
+      "grad_norm": 0.10204192996025085,
+      "learning_rate": 1.8839567136801772e-05,
+      "loss": 0.3369,
+      "step": 238
+    },
+    {
+      "epoch": 1.38328530259366,
+      "grad_norm": 0.1050105094909668,
+      "learning_rate": 1.8440956016219314e-05,
+      "loss": 0.3407,
+      "step": 240
+    },
+    {
+      "epoch": 1.38328530259366,
+      "eval_loss": 0.3772360384464264,
+      "eval_runtime": 161.7846,
+      "eval_samples_per_second": 28.884,
+      "eval_steps_per_second": 0.229,
+      "step": 240
+    },
+    {
+      "epoch": 1.3948126801152738,
+      "grad_norm": 0.10698170959949493,
+      "learning_rate": 1.8045709960662465e-05,
+      "loss": 0.355,
+      "step": 242
+    },
+    {
+      "epoch": 1.4063400576368876,
+      "grad_norm": 0.09979532659053802,
+      "learning_rate": 1.765397578790587e-05,
+      "loss": 0.3419,
+      "step": 244
+    },
+    {
+      "epoch": 1.4178674351585014,
+      "grad_norm": 0.09883076697587967,
+      "learning_rate": 1.7265899011203065e-05,
+      "loss": 0.3415,
+      "step": 246
+    },
+    {
+      "epoch": 1.4293948126801153,
+      "grad_norm": 0.10558874905109406,
+      "learning_rate": 1.6881623785234285e-05,
+      "loss": 0.353,
+      "step": 248
+    },
+    {
+      "epoch": 1.440922190201729,
+      "grad_norm": 0.1028595045208931,
+      "learning_rate": 1.650129285255882e-05,
+      "loss": 0.3537,
+      "step": 250
+    },
+    {
+      "epoch": 1.4524495677233429,
+      "grad_norm": 0.10255461186170578,
+      "learning_rate": 1.6125047490592034e-05,
+      "loss": 0.3393,
+      "step": 252
+    },
+    {
+      "epoch": 1.4639769452449567,
+      "grad_norm": 0.10520190000534058,
+      "learning_rate": 1.5753027459126566e-05,
+      "loss": 0.3469,
+      "step": 254
+    },
+    {
+      "epoch": 1.4755043227665707,
+      "grad_norm": 0.10457232594490051,
+      "learning_rate": 1.5385370948417256e-05,
+      "loss": 0.3548,
+      "step": 256
+    },
+    {
+      "epoch": 1.4870317002881843,
+      "grad_norm": 0.10024940967559814,
+      "learning_rate": 1.5022214527849105e-05,
+      "loss": 0.3403,
+      "step": 258
+    },
+    {
+      "epoch": 1.4985590778097984,
+      "grad_norm": 0.09729419648647308,
+      "learning_rate": 1.4663693095207343e-05,
+      "loss": 0.3372,
+      "step": 260
+    },
+    {
+      "epoch": 1.4985590778097984,
+      "eval_loss": 0.3750576674938202,
+      "eval_runtime": 161.7883,
+      "eval_samples_per_second": 28.883,
+      "eval_steps_per_second": 0.229,
+      "step": 260
+    },
+    {
+      "epoch": 1.510086455331412,
+      "grad_norm": 0.09922486543655396,
+      "learning_rate": 1.43099398265684e-05,
+      "loss": 0.329,
+      "step": 262
+    },
+    {
+      "epoch": 1.521613832853026,
+      "grad_norm": 0.10505367070436478,
+      "learning_rate": 1.3961086126830403e-05,
+      "loss": 0.3404,
+      "step": 264
+    },
+    {
+      "epoch": 1.5331412103746398,
+      "grad_norm": 0.10513550788164139,
+      "learning_rate": 1.3617261580901691e-05,
+      "loss": 0.3436,
+      "step": 266
+    },
+    {
+      "epoch": 1.5446685878962536,
+      "grad_norm": 0.10580945760011673,
+      "learning_rate": 1.3278593905565224e-05,
+      "loss": 0.3448,
+      "step": 268
+    },
+    {
+      "epoch": 1.5561959654178674,
+      "grad_norm": 0.0965629443526268,
+      "learning_rate": 1.2945208902037071e-05,
+      "loss": 0.3323,
+      "step": 270
+    },
+    {
+      "epoch": 1.5677233429394812,
+      "grad_norm": 0.1028643250465393,
+      "learning_rate": 1.261723040923638e-05,
+      "loss": 0.341,
+      "step": 272
+    },
+    {
+      "epoch": 1.579250720461095,
+      "grad_norm": 0.10219055414199829,
+      "learning_rate": 1.2294780257784277e-05,
+      "loss": 0.3337,
+      "step": 274
+    },
+    {
+      "epoch": 1.5907780979827089,
+      "grad_norm": 0.10359715670347214,
+      "learning_rate": 1.1977978224748735e-05,
+      "loss": 0.3388,
+      "step": 276
+    },
+    {
+      "epoch": 1.602305475504323,
+      "grad_norm": 0.09491585195064545,
+      "learning_rate": 1.166694198915234e-05,
+      "loss": 0.3404,
+      "step": 278
+    },
+    {
+      "epoch": 1.6138328530259365,
+      "grad_norm": 0.10194993764162064,
+      "learning_rate": 1.1361787088259273e-05,
+      "loss": 0.3453,
+      "step": 280
+    },
+    {
+      "epoch": 1.6138328530259365,
+      "eval_loss": 0.3727053105831146,
+      "eval_runtime": 161.5061,
+      "eval_samples_per_second": 28.934,
+      "eval_steps_per_second": 0.229,
+      "step": 280
+    },
+    {
+      "epoch": 1.6253602305475505,
+      "grad_norm": 0.09746123105287552,
+      "learning_rate": 1.1062626874657977e-05,
+      "loss": 0.3372,
+      "step": 282
+    },
+    {
+      "epoch": 1.6368876080691641,
+      "grad_norm": 0.1048843190073967,
+      "learning_rate": 1.0769572474155296e-05,
+      "loss": 0.3415,
+      "step": 284
+    },
+    {
+      "epoch": 1.6484149855907781,
+      "grad_norm": 0.10008594393730164,
+      "learning_rate": 1.0482732744497742e-05,
+      "loss": 0.3332,
+      "step": 286
+    },
+    {
+      "epoch": 1.659942363112392,
+      "grad_norm": 0.09605535864830017,
+      "learning_rate": 1.020221423493533e-05,
+      "loss": 0.3355,
+      "step": 288
+    },
+    {
+      "epoch": 1.6714697406340058,
+      "grad_norm": 0.0957765281200409,
+      "learning_rate": 9.928121146642841e-06,
+      "loss": 0.3511,
+      "step": 290
+    },
+    {
+      "epoch": 1.6829971181556196,
+      "grad_norm": 0.10064635425806046,
+      "learning_rate": 9.660555294013373e-06,
+      "loss": 0.3462,
+      "step": 292
+    },
+    {
+      "epoch": 1.6945244956772334,
+      "grad_norm": 0.09759914875030518,
+      "learning_rate": 9.399616066838415e-06,
+      "loss": 0.3476,
+      "step": 294
+    },
+    {
+      "epoch": 1.7060518731988472,
+      "grad_norm": 0.1018439456820488,
+      "learning_rate": 9.145400393388629e-06,
+      "loss": 0.3542,
+      "step": 296
+    },
+    {
+      "epoch": 1.717579250720461,
+      "grad_norm": 0.10098982602357864,
+      "learning_rate": 8.898002704408944e-06,
+      "loss": 0.3474,
+      "step": 298
+    },
+    {
+      "epoch": 1.729106628242075,
+      "grad_norm": 0.09507515281438828,
+      "learning_rate": 8.657514898041381e-06,
+      "loss": 0.3408,
+      "step": 300
+    },
+    {
+      "epoch": 1.729106628242075,
+      "eval_loss": 0.37131258845329285,
+      "eval_runtime": 161.848,
+      "eval_samples_per_second": 28.873,
+      "eval_steps_per_second": 0.229,
+      "step": 300
+    },
+    {
+      "epoch": 1.7406340057636887,
+      "grad_norm": 0.09314768761396408,
+      "learning_rate": 8.424026305688643e-06,
+      "loss": 0.341,
+      "step": 302
+    },
+    {
+      "epoch": 1.7521613832853027,
+      "grad_norm": 0.09930098056793213,
+      "learning_rate": 8.197623658831165e-06,
+      "loss": 0.3397,
+      "step": 304
+    },
+    {
+      "epoch": 1.7636887608069163,
+      "grad_norm": 0.10165336728096008,
+      "learning_rate": 7.978391056809904e-06,
+      "loss": 0.3419,
+      "step": 306
+    },
+    {
+      "epoch": 1.7752161383285303,
+      "grad_norm": 0.09817034006118774,
+      "learning_rate": 7.766409935586837e-06,
+      "loss": 0.3456,
+      "step": 308
+    },
+    {
+      "epoch": 1.7867435158501441,
+      "grad_norm": 0.10100841522216797,
+      "learning_rate": 7.5617590374948745e-06,
+      "loss": 0.3464,
+      "step": 310
+    },
+    {
+      "epoch": 1.798270893371758,
+      "grad_norm": 0.10015368461608887,
+      "learning_rate": 7.364514381988254e-06,
+      "loss": 0.3402,
+      "step": 312
+    },
+    {
+      "epoch": 1.8097982708933718,
+      "grad_norm": 0.10384070128202438,
+      "learning_rate": 7.174749237404444e-06,
+      "loss": 0.3312,
+      "step": 314
+    },
+    {
+      "epoch": 1.8213256484149856,
+      "grad_norm": 0.10439052432775497,
+      "learning_rate": 6.992534093747942e-06,
+      "loss": 0.3333,
+      "step": 316
+    },
+    {
+      "epoch": 1.8328530259365994,
+      "grad_norm": 0.09687253832817078,
+      "learning_rate": 6.8179366365061e-06,
+      "loss": 0.3358,
+      "step": 318
+    },
+    {
+      "epoch": 1.8443804034582132,
+      "grad_norm": 0.10308189690113068,
+      "learning_rate": 6.651021721506756e-06,
+      "loss": 0.3342,
+      "step": 320
+    },
+    {
+      "epoch": 1.8443804034582132,
+      "eval_loss": 0.3700437545776367,
+      "eval_runtime": 161.117,
+      "eval_samples_per_second": 29.004,
+      "eval_steps_per_second": 0.23,
+      "step": 320
+    },
+    {
+      "epoch": 1.8559077809798272,
+      "grad_norm": 0.09917671233415604,
+      "learning_rate": 6.491851350826915e-06,
+      "loss": 0.35,
+      "step": 322
+    },
+    {
+      "epoch": 1.8674351585014408,
+      "grad_norm": 0.09794910252094269,
+      "learning_rate": 6.340484649761529e-06,
+      "loss": 0.3382,
+      "step": 324
+    },
+    {
+      "epoch": 1.8789625360230549,
+      "grad_norm": 0.10062103718519211,
+      "learning_rate": 6.196977844860848e-06,
+      "loss": 0.3313,
+      "step": 326
+    },
+    {
+      "epoch": 1.8904899135446684,
+      "grad_norm": 0.09653456509113312,
+      "learning_rate": 6.061384243044564e-06,
+      "loss": 0.3364,
+      "step": 328
+    },
+    {
+      "epoch": 1.9020172910662825,
+      "grad_norm": 0.09764689952135086,
+      "learning_rate": 5.933754211800459e-06,
+      "loss": 0.332,
+      "step": 330
+    },
+    {
+      "epoch": 1.9135446685878963,
+      "grad_norm": 0.09577332437038422,
+      "learning_rate": 5.814135160474937e-06,
+      "loss": 0.339,
+      "step": 332
+    },
+    {
+      "epoch": 1.92507204610951,
+      "grad_norm": 0.0969650149345398,
+      "learning_rate": 5.7025715226624036e-06,
+      "loss": 0.3301,
+      "step": 334
+    },
+    {
+      "epoch": 1.936599423631124,
+      "grad_norm": 0.09393922984600067,
+      "learning_rate": 5.5991047396999735e-06,
+      "loss": 0.3374,
+      "step": 336
+    },
+    {
+      "epoch": 1.9481268011527377,
+      "grad_norm": 0.11683030426502228,
+      "learning_rate": 5.503773245273734e-06,
+      "loss": 0.3424,
+      "step": 338
+    },
+    {
+      "epoch": 1.9596541786743515,
+      "grad_norm": 0.09428226202726364,
+      "learning_rate": 5.41661245114217e-06,
+      "loss": 0.332,
+      "step": 340
+    },
+    {
+      "epoch": 1.9596541786743515,
+      "eval_loss": 0.36898180842399597,
+      "eval_runtime": 161.0051,
+      "eval_samples_per_second": 29.024,
+      "eval_steps_per_second": 0.23,
+      "step": 340
+    },
+    {
+      "epoch": 1.9711815561959654,
+      "grad_norm": 0.09828232228755951,
+      "learning_rate": 5.337654733982173e-06,
+      "loss": 0.3386,
+      "step": 342
+    },
+    {
+      "epoch": 1.9827089337175794,
+      "grad_norm": 0.09727545082569122,
+      "learning_rate": 5.2669294233624e-06,
+      "loss": 0.331,
+      "step": 344
+    },
+    {
+      "epoch": 1.994236311239193,
+      "grad_norm": 0.09713173657655716,
+      "learning_rate": 5.204462790848549e-06,
+      "loss": 0.3478,
+      "step": 346
+    },
+    {
+      "epoch": 1.994236311239193,
+      "step": 346,
+      "total_flos": 388981471576064.0,
+      "train_loss": 0.3994986457976303,
+      "train_runtime": 42730.5756,
+      "train_samples_per_second": 4.155,
+      "train_steps_per_second": 0.008
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 346,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 388981471576064.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}