update 1030 models

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:a16635bad922d2cf2eedc97088c6269934d3fe38b185e2791663432d0d307325
+size 4941082400

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d62a0369c05e4081e0d938fcf240ff8c781f549ddc685236dd24bde0671da85
+size 4947390768

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd50a3bdd97f74279fe736cafd4b008c7623671c645ca248aeae425958e92862
+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 +1,3133 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9974842767295597,
+  "eval_steps": 20,
+  "global_step": 794,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005031446540880503,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0,
+      "loss": 0.8316,
+      "step": 2
+    },
+    {
+      "epoch": 0.010062893081761006,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0,
+      "loss": 0.8423,
+      "step": 4
+    },
+    {
+      "epoch": 0.01509433962264151,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0,
+      "loss": 0.8389,
+      "step": 6
+    },
+    {
+      "epoch": 0.02012578616352201,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0,
+      "loss": 0.8302,
+      "step": 8
+    },
+    {
+      "epoch": 0.025157232704402517,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0,
+      "loss": 0.8634,
+      "step": 10
+    },
+    {
+      "epoch": 0.03018867924528302,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0,
+      "loss": 0.8553,
+      "step": 12
+    },
+    {
+      "epoch": 0.03522012578616352,
+      "grad_norm": 0.7739448547363281,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 0.8423,
+      "step": 14
+    },
+    {
+      "epoch": 0.04025157232704402,
+      "grad_norm": 0.7387983202934265,
+      "learning_rate": 5e-06,
+      "loss": 0.8385,
+      "step": 16
+    },
+    {
+      "epoch": 0.045283018867924525,
+      "grad_norm": 0.34386318922042847,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.8163,
+      "step": 18
+    },
+    {
+      "epoch": 0.050314465408805034,
+      "grad_norm": 0.32477569580078125,
+      "learning_rate": 1e-05,
+      "loss": 0.7541,
+      "step": 20
+    },
+    {
+      "epoch": 0.050314465408805034,
+      "eval_loss": 0.7434237599372864,
+      "eval_runtime": 512.9045,
+      "eval_samples_per_second": 20.873,
+      "eval_steps_per_second": 0.164,
+      "step": 20
+    },
+    {
+      "epoch": 0.055345911949685536,
+      "grad_norm": 0.3248128294944763,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.7494,
+      "step": 22
+    },
+    {
+      "epoch": 0.06037735849056604,
+      "grad_norm": 0.25117382407188416,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.7204,
+      "step": 24
+    },
+    {
+      "epoch": 0.06540880503144654,
+      "grad_norm": 0.23494713008403778,
+      "learning_rate": 2e-05,
+      "loss": 0.6902,
+      "step": 26
+    },
+    {
+      "epoch": 0.07044025157232704,
+      "grad_norm": 0.19120900332927704,
+      "learning_rate": 2.3333333333333336e-05,
+      "loss": 0.6971,
+      "step": 28
+    },
+    {
+      "epoch": 0.07547169811320754,
+      "grad_norm": 0.16960154473781586,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 0.677,
+      "step": 30
+    },
+    {
+      "epoch": 0.08050314465408805,
+      "grad_norm": 0.16359932720661163,
+      "learning_rate": 3e-05,
+      "loss": 0.6863,
+      "step": 32
+    },
+    {
+      "epoch": 0.08553459119496855,
+      "grad_norm": 0.1389608234167099,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.6786,
+      "step": 34
+    },
+    {
+      "epoch": 0.09056603773584905,
+      "grad_norm": 0.14994372427463531,
+      "learning_rate": 3.6666666666666666e-05,
+      "loss": 0.6692,
+      "step": 36
+    },
+    {
+      "epoch": 0.09559748427672957,
+      "grad_norm": 0.13334757089614868,
+      "learning_rate": 4e-05,
+      "loss": 0.666,
+      "step": 38
+    },
+    {
+      "epoch": 0.10062893081761007,
+      "grad_norm": 0.14932414889335632,
+      "learning_rate": 4.3333333333333334e-05,
+      "loss": 0.6771,
+      "step": 40
+    },
+    {
+      "epoch": 0.10062893081761007,
+      "eval_loss": 0.6487388610839844,
+      "eval_runtime": 477.079,
+      "eval_samples_per_second": 22.441,
+      "eval_steps_per_second": 0.176,
+      "step": 40
+    },
+    {
+      "epoch": 0.10566037735849057,
+      "grad_norm": 0.1352750062942505,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 0.668,
+      "step": 42
+    },
+    {
+      "epoch": 0.11069182389937107,
+      "grad_norm": 0.11694569140672684,
+      "learning_rate": 5e-05,
+      "loss": 0.6517,
+      "step": 44
+    },
+    {
+      "epoch": 0.11572327044025157,
+      "grad_norm": 0.12432057410478592,
+      "learning_rate": 4.9999239107866414e-05,
+      "loss": 0.6353,
+      "step": 46
+    },
+    {
+      "epoch": 0.12075471698113208,
+      "grad_norm": 0.121449314057827,
+      "learning_rate": 4.9996956482928485e-05,
+      "loss": 0.6348,
+      "step": 48
+    },
+    {
+      "epoch": 0.12578616352201258,
+      "grad_norm": 0.119928739964962,
+      "learning_rate": 4.999315227957123e-05,
+      "loss": 0.6402,
+      "step": 50
+    },
+    {
+      "epoch": 0.13081761006289308,
+      "grad_norm": 0.12270842492580414,
+      "learning_rate": 4.998782675509138e-05,
+      "loss": 0.6294,
+      "step": 52
+    },
+    {
+      "epoch": 0.13584905660377358,
+      "grad_norm": 0.1132158562541008,
+      "learning_rate": 4.998098026968003e-05,
+      "loss": 0.6417,
+      "step": 54
+    },
+    {
+      "epoch": 0.14088050314465408,
+      "grad_norm": 0.13522745668888092,
+      "learning_rate": 4.997261328639824e-05,
+      "loss": 0.6366,
+      "step": 56
+    },
+    {
+      "epoch": 0.1459119496855346,
+      "grad_norm": 0.11879543960094452,
+      "learning_rate": 4.996272637114571e-05,
+      "loss": 0.6335,
+      "step": 58
+    },
+    {
+      "epoch": 0.1509433962264151,
+      "grad_norm": 0.1235610768198967,
+      "learning_rate": 4.995132019262254e-05,
+      "loss": 0.6483,
+      "step": 60
+    },
+    {
+      "epoch": 0.1509433962264151,
+      "eval_loss": 0.6241472363471985,
+      "eval_runtime": 445.3592,
+      "eval_samples_per_second": 24.039,
+      "eval_steps_per_second": 0.189,
+      "step": 60
+    },
+    {
+      "epoch": 0.1559748427672956,
+      "grad_norm": 0.11320329457521439,
+      "learning_rate": 4.993839552228398e-05,
+      "loss": 0.6242,
+      "step": 62
+    },
+    {
+      "epoch": 0.1610062893081761,
+      "grad_norm": 0.12192777544260025,
+      "learning_rate": 4.992395323428824e-05,
+      "loss": 0.6214,
+      "step": 64
+    },
+    {
+      "epoch": 0.1660377358490566,
+      "grad_norm": 0.12313053756952286,
+      "learning_rate": 4.9907994305437405e-05,
+      "loss": 0.6331,
+      "step": 66
+    },
+    {
+      "epoch": 0.1710691823899371,
+      "grad_norm": 0.12243402749300003,
+      "learning_rate": 4.989051981511133e-05,
+      "loss": 0.6222,
+      "step": 68
+    },
+    {
+      "epoch": 0.1761006289308176,
+      "grad_norm": 0.12040385603904724,
+      "learning_rate": 4.9871530945194654e-05,
+      "loss": 0.6394,
+      "step": 70
+    },
+    {
+      "epoch": 0.1811320754716981,
+      "grad_norm": 0.11485008895397186,
+      "learning_rate": 4.985102897999687e-05,
+      "loss": 0.5755,
+      "step": 72
+    },
+    {
+      "epoch": 0.1861635220125786,
+      "grad_norm": 0.1206885501742363,
+      "learning_rate": 4.982901530616545e-05,
+      "loss": 0.6354,
+      "step": 74
+    },
+    {
+      "epoch": 0.19119496855345913,
+      "grad_norm": 0.12174931168556213,
+      "learning_rate": 4.980549141259205e-05,
+      "loss": 0.6362,
+      "step": 76
+    },
+    {
+      "epoch": 0.19622641509433963,
+      "grad_norm": 0.13587461411952972,
+      "learning_rate": 4.9780458890311846e-05,
+      "loss": 0.616,
+      "step": 78
+    },
+    {
+      "epoch": 0.20125786163522014,
+      "grad_norm": 0.12933531403541565,
+      "learning_rate": 4.9753919432395876e-05,
+      "loss": 0.6363,
+      "step": 80
+    },
+    {
+      "epoch": 0.20125786163522014,
+      "eval_loss": 0.6132378578186035,
+      "eval_runtime": 463.9686,
+      "eval_samples_per_second": 23.075,
+      "eval_steps_per_second": 0.181,
+      "step": 80
+    },
+    {
+      "epoch": 0.20628930817610064,
+      "grad_norm": 0.11656603217124939,
+      "learning_rate": 4.9725874833836574e-05,
+      "loss": 0.62,
+      "step": 82
+    },
+    {
+      "epoch": 0.21132075471698114,
+      "grad_norm": 0.11784744262695312,
+      "learning_rate": 4.969632699142632e-05,
+      "loss": 0.6094,
+      "step": 84
+    },
+    {
+      "epoch": 0.21635220125786164,
+      "grad_norm": 0.11344680190086365,
+      "learning_rate": 4.966527790362919e-05,
+      "loss": 0.5968,
+      "step": 86
+    },
+    {
+      "epoch": 0.22138364779874214,
+      "grad_norm": 0.11833988130092621,
+      "learning_rate": 4.963272967044579e-05,
+      "loss": 0.6306,
+      "step": 88
+    },
+    {
+      "epoch": 0.22641509433962265,
+      "grad_norm": 0.11473698914051056,
+      "learning_rate": 4.959868449327119e-05,
+      "loss": 0.6152,
+      "step": 90
+    },
+    {
+      "epoch": 0.23144654088050315,
+      "grad_norm": 0.10996667295694351,
+      "learning_rate": 4.9563144674746046e-05,
+      "loss": 0.595,
+      "step": 92
+    },
+    {
+      "epoch": 0.23647798742138365,
+      "grad_norm": 0.11677283048629761,
+      "learning_rate": 4.952611261860089e-05,
+      "loss": 0.5967,
+      "step": 94
+    },
+    {
+      "epoch": 0.24150943396226415,
+      "grad_norm": 0.1206679567694664,
+      "learning_rate": 4.9487590829493514e-05,
+      "loss": 0.604,
+      "step": 96
+    },
+    {
+      "epoch": 0.24654088050314465,
+      "grad_norm": 0.12233300507068634,
+      "learning_rate": 4.944758191283959e-05,
+      "loss": 0.6043,
+      "step": 98
+    },
+    {
+      "epoch": 0.25157232704402516,
+      "grad_norm": 0.11701351404190063,
+      "learning_rate": 4.940608857463644e-05,
+      "loss": 0.6,
+      "step": 100
+    },
+    {
+      "epoch": 0.25157232704402516,
+      "eval_loss": 0.6065506339073181,
+      "eval_runtime": 422.5948,
+      "eval_samples_per_second": 25.334,
+      "eval_steps_per_second": 0.199,
+      "step": 100
+    },
+    {
+      "epoch": 0.25660377358490566,
+      "grad_norm": 0.1179809644818306,
+      "learning_rate": 4.9363113621280036e-05,
+      "loss": 0.6406,
+      "step": 102
+    },
+    {
+      "epoch": 0.26163522012578616,
+      "grad_norm": 0.12534746527671814,
+      "learning_rate": 4.931865995937519e-05,
+      "loss": 0.6227,
+      "step": 104
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.12294790893793106,
+      "learning_rate": 4.927273059553892e-05,
+      "loss": 0.5957,
+      "step": 106
+    },
+    {
+      "epoch": 0.27169811320754716,
+      "grad_norm": 0.12756744027137756,
+      "learning_rate": 4.9225328636197144e-05,
+      "loss": 0.6226,
+      "step": 108
+    },
+    {
+      "epoch": 0.27672955974842767,
+      "grad_norm": 0.12662391364574432,
+      "learning_rate": 4.9176457287374584e-05,
+      "loss": 0.5899,
+      "step": 110
+    },
+    {
+      "epoch": 0.28176100628930817,
+      "grad_norm": 0.12516862154006958,
+      "learning_rate": 4.912611985447789e-05,
+      "loss": 0.6238,
+      "step": 112
+    },
+    {
+      "epoch": 0.28679245283018867,
+      "grad_norm": 0.116559699177742,
+      "learning_rate": 4.907431974207211e-05,
+      "loss": 0.6112,
+      "step": 114
+    },
+    {
+      "epoch": 0.2918238993710692,
+      "grad_norm": 0.11833405494689941,
+      "learning_rate": 4.90210604536504e-05,
+      "loss": 0.6087,
+      "step": 116
+    },
+    {
+      "epoch": 0.2968553459119497,
+      "grad_norm": 0.1188972070813179,
+      "learning_rate": 4.896634559139707e-05,
+      "loss": 0.594,
+      "step": 118
+    },
+    {
+      "epoch": 0.3018867924528302,
+      "grad_norm": 0.11520268023014069,
+      "learning_rate": 4.891017885594399e-05,
+      "loss": 0.6059,
+      "step": 120
+    },
+    {
+      "epoch": 0.3018867924528302,
+      "eval_loss": 0.6016330718994141,
+      "eval_runtime": 415.9012,
+      "eval_samples_per_second": 25.742,
+      "eval_steps_per_second": 0.202,
+      "step": 120
+    },
+    {
+      "epoch": 0.3069182389937107,
+      "grad_norm": 0.11097536981105804,
+      "learning_rate": 4.885256404612022e-05,
+      "loss": 0.5963,
+      "step": 122
+    },
+    {
+      "epoch": 0.3119496855345912,
+      "grad_norm": 0.1210559606552124,
+      "learning_rate": 4.8793505058695155e-05,
+      "loss": 0.6367,
+      "step": 124
+    },
+    {
+      "epoch": 0.3169811320754717,
+      "grad_norm": 0.12011069059371948,
+      "learning_rate": 4.8733005888114915e-05,
+      "loss": 0.5889,
+      "step": 126
+    },
+    {
+      "epoch": 0.3220125786163522,
+      "grad_norm": 0.12133902311325073,
+      "learning_rate": 4.867107062623223e-05,
+      "loss": 0.5812,
+      "step": 128
+    },
+    {
+      "epoch": 0.3270440251572327,
+      "grad_norm": 0.11452817916870117,
+      "learning_rate": 4.860770346202962e-05,
+      "loss": 0.607,
+      "step": 130
+    },
+    {
+      "epoch": 0.3320754716981132,
+      "grad_norm": 0.1322205364704132,
+      "learning_rate": 4.854290868133614e-05,
+      "loss": 0.5789,
+      "step": 132
+    },
+    {
+      "epoch": 0.3371069182389937,
+      "grad_norm": 0.1177845150232315,
+      "learning_rate": 4.847669066653746e-05,
+      "loss": 0.5834,
+      "step": 134
+    },
+    {
+      "epoch": 0.3421383647798742,
+      "grad_norm": 0.12132906913757324,
+      "learning_rate": 4.840905389627951e-05,
+      "loss": 0.6178,
+      "step": 136
+    },
+    {
+      "epoch": 0.3471698113207547,
+      "grad_norm": 0.11665117740631104,
+      "learning_rate": 4.834000294516552e-05,
+      "loss": 0.5999,
+      "step": 138
+    },
+    {
+      "epoch": 0.3522012578616352,
+      "grad_norm": 0.12204349786043167,
+      "learning_rate": 4.8269542483446654e-05,
+      "loss": 0.602,
+      "step": 140
+    },
+    {
+      "epoch": 0.3522012578616352,
+      "eval_loss": 0.5978492498397827,
+      "eval_runtime": 462.6047,
+      "eval_samples_per_second": 23.143,
+      "eval_steps_per_second": 0.182,
+      "step": 140
+    },
+    {
+      "epoch": 0.3572327044025157,
+      "grad_norm": 0.1177980899810791,
+      "learning_rate": 4.819767727670612e-05,
+      "loss": 0.6035,
+      "step": 142
+    },
+    {
+      "epoch": 0.3622641509433962,
+      "grad_norm": 0.12166167795658112,
+      "learning_rate": 4.812441218553683e-05,
+      "loss": 0.5909,
+      "step": 144
+    },
+    {
+      "epoch": 0.3672955974842767,
+      "grad_norm": 0.13141223788261414,
+      "learning_rate": 4.804975216521272e-05,
+      "loss": 0.5985,
+      "step": 146
+    },
+    {
+      "epoch": 0.3723270440251572,
+      "grad_norm": 0.12138612568378448,
+      "learning_rate": 4.797370226535353e-05,
+      "loss": 0.5866,
+      "step": 148
+    },
+    {
+      "epoch": 0.37735849056603776,
+      "grad_norm": 0.12571364641189575,
+      "learning_rate": 4.789626762958331e-05,
+      "loss": 0.5789,
+      "step": 150
+    },
+    {
+      "epoch": 0.38238993710691827,
+      "grad_norm": 0.1183118149638176,
+      "learning_rate": 4.781745349518252e-05,
+      "loss": 0.5958,
+      "step": 152
+    },
+    {
+      "epoch": 0.38742138364779877,
+      "grad_norm": 0.11182838678359985,
+      "learning_rate": 4.7737265192733815e-05,
+      "loss": 0.5768,
+      "step": 154
+    },
+    {
+      "epoch": 0.39245283018867927,
+      "grad_norm": 0.12711752951145172,
+      "learning_rate": 4.765570814576153e-05,
+      "loss": 0.5951,
+      "step": 156
+    },
+    {
+      "epoch": 0.39748427672955977,
+      "grad_norm": 0.12628626823425293,
+      "learning_rate": 4.757278787036479e-05,
+      "loss": 0.5907,
+      "step": 158
+    },
+    {
+      "epoch": 0.4025157232704403,
+      "grad_norm": 0.11637621372938156,
+      "learning_rate": 4.748850997484452e-05,
+      "loss": 0.6115,
+      "step": 160
+    },
+    {
+      "epoch": 0.4025157232704403,
+      "eval_loss": 0.5944415926933289,
+      "eval_runtime": 416.2458,
+      "eval_samples_per_second": 25.72,
+      "eval_steps_per_second": 0.202,
+      "step": 160
+    },
+    {
+      "epoch": 0.4075471698113208,
+      "grad_norm": 0.11336452513933182,
+      "learning_rate": 4.7402880159324084e-05,
+      "loss": 0.5685,
+      "step": 162
+    },
+    {
+      "epoch": 0.4125786163522013,
+      "grad_norm": 0.12172479182481766,
+      "learning_rate": 4.7315904215363734e-05,
+      "loss": 0.5765,
+      "step": 164
+    },
+    {
+      "epoch": 0.4176100628930818,
+      "grad_norm": 0.11980731040239334,
+      "learning_rate": 4.722758802556896e-05,
+      "loss": 0.5948,
+      "step": 166
+    },
+    {
+      "epoch": 0.4226415094339623,
+      "grad_norm": 0.11705721169710159,
+      "learning_rate": 4.7137937563192555e-05,
+      "loss": 0.5749,
+      "step": 168
+    },
+    {
+      "epoch": 0.4276729559748428,
+      "grad_norm": 0.1204642727971077,
+      "learning_rate": 4.704695889173066e-05,
+      "loss": 0.6069,
+      "step": 170
+    },
+    {
+      "epoch": 0.4327044025157233,
+      "grad_norm": 0.11957567930221558,
+      "learning_rate": 4.695465816451266e-05,
+      "loss": 0.5724,
+      "step": 172
+    },
+    {
+      "epoch": 0.4377358490566038,
+      "grad_norm": 0.12370068579912186,
+      "learning_rate": 4.686104162428497e-05,
+      "loss": 0.6164,
+      "step": 174
+    },
+    {
+      "epoch": 0.4427672955974843,
+      "grad_norm": 0.14216069877147675,
+      "learning_rate": 4.676611560278884e-05,
+      "loss": 0.6018,
+      "step": 176
+    },
+    {
+      "epoch": 0.4477987421383648,
+      "grad_norm": 0.12077496945858002,
+      "learning_rate": 4.66698865203321e-05,
+      "loss": 0.5919,
+      "step": 178
+    },
+    {
+      "epoch": 0.4528301886792453,
+      "grad_norm": 0.12382370233535767,
+      "learning_rate": 4.6572360885354905e-05,
+      "loss": 0.6304,
+      "step": 180
+    },
+    {
+      "epoch": 0.4528301886792453,
+      "eval_loss": 0.5917236804962158,
+      "eval_runtime": 416.6125,
+      "eval_samples_per_second": 25.698,
+      "eval_steps_per_second": 0.202,
+      "step": 180
+    },
+    {
+      "epoch": 0.4578616352201258,
+      "grad_norm": 0.11310654878616333,
+      "learning_rate": 4.647354529398957e-05,
+      "loss": 0.5984,
+      "step": 182
+    },
+    {
+      "epoch": 0.4628930817610063,
+      "grad_norm": 0.11125874519348145,
+      "learning_rate": 4.637344642961442e-05,
+      "loss": 0.5993,
+      "step": 184
+    },
+    {
+      "epoch": 0.4679245283018868,
+      "grad_norm": 0.10250482708215714,
+      "learning_rate": 4.627207106240176e-05,
+      "loss": 0.5958,
+      "step": 186
+    },
+    {
+      "epoch": 0.4729559748427673,
+      "grad_norm": 0.10660769045352936,
+      "learning_rate": 4.6169426048859994e-05,
+      "loss": 0.5602,
+      "step": 188
+    },
+    {
+      "epoch": 0.4779874213836478,
+      "grad_norm": 0.10431323200464249,
+      "learning_rate": 4.606551833136985e-05,
+      "loss": 0.5903,
+      "step": 190
+    },
+    {
+      "epoch": 0.4830188679245283,
+      "grad_norm": 0.11766020953655243,
+      "learning_rate": 4.596035493771488e-05,
+      "loss": 0.6004,
+      "step": 192
+    },
+    {
+      "epoch": 0.4880503144654088,
+      "grad_norm": 0.1166047751903534,
+      "learning_rate": 4.585394298060611e-05,
+      "loss": 0.5977,
+      "step": 194
+    },
+    {
+      "epoch": 0.4930817610062893,
+      "grad_norm": 0.1147083193063736,
+      "learning_rate": 4.574628965720097e-05,
+      "loss": 0.5897,
+      "step": 196
+    },
+    {
+      "epoch": 0.4981132075471698,
+      "grad_norm": 0.10733990371227264,
+      "learning_rate": 4.5637402248616506e-05,
+      "loss": 0.5978,
+      "step": 198
+    },
+    {
+      "epoch": 0.5031446540880503,
+      "grad_norm": 0.10964643210172653,
+      "learning_rate": 4.552728811943696e-05,
+      "loss": 0.602,
+      "step": 200
+    },
+    {
+      "epoch": 0.5031446540880503,
+      "eval_loss": 0.5892359018325806,
+      "eval_runtime": 416.8902,
+      "eval_samples_per_second": 25.681,
+      "eval_steps_per_second": 0.201,
+      "step": 200
+    },
+    {
+      "epoch": 0.5081761006289308,
+      "grad_norm": 0.11032500118017197,
+      "learning_rate": 4.54717733587572e-05,
+      "loss": 0.5817,
+      "step": 202
+    },
+    {
+      "epoch": 0.5132075471698113,
+      "grad_norm": 0.1092258021235466,
+      "learning_rate": 4.5359833138637734e-05,
+      "loss": 0.5982,
+      "step": 204
+    },
+    {
+      "epoch": 0.5182389937106918,
+      "grad_norm": 0.10684628039598465,
+      "learning_rate": 4.524668497127006e-05,
+      "loss": 0.5923,
+      "step": 206
+    },
+    {
+      "epoch": 0.5232704402515723,
+      "grad_norm": 0.11228887736797333,
+      "learning_rate": 4.513233650941422e-05,
+      "loss": 0.5742,
+      "step": 208
+    },
+    {
+      "epoch": 0.5283018867924528,
+      "grad_norm": 0.1152106523513794,
+      "learning_rate": 4.501679548701201e-05,
+      "loss": 0.5955,
+      "step": 210
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.11588042229413986,
+      "learning_rate": 4.490006971866385e-05,
+      "loss": 0.5936,
+      "step": 212
+    },
+    {
+      "epoch": 0.5383647798742138,
+      "grad_norm": 0.11394830793142319,
+      "learning_rate": 4.478216709910035e-05,
+      "loss": 0.5937,
+      "step": 214
+    },
+    {
+      "epoch": 0.5433962264150943,
+      "grad_norm": 0.11031538993120193,
+      "learning_rate": 4.466309560264822e-05,
+      "loss": 0.5973,
+      "step": 216
+    },
+    {
+      "epoch": 0.5484276729559748,
+      "grad_norm": 0.11161042749881744,
+      "learning_rate": 4.4542863282691014e-05,
+      "loss": 0.5701,
+      "step": 218
+    },
+    {
+      "epoch": 0.5534591194968553,
+      "grad_norm": 0.11783146113157272,
+      "learning_rate": 4.4421478271124426e-05,
+      "loss": 0.603,
+      "step": 220
+    },
+    {
+      "epoch": 0.5534591194968553,
+      "eval_loss": 0.5872239470481873,
+      "eval_runtime": 412.7815,
+      "eval_samples_per_second": 25.936,
+      "eval_steps_per_second": 0.203,
+      "step": 220
+    },
+    {
+      "epoch": 0.5584905660377358,
+      "grad_norm": 0.10747622698545456,
+      "learning_rate": 4.429894877780627e-05,
+      "loss": 0.6089,
+      "step": 222
+    },
+    {
+      "epoch": 0.5635220125786163,
+      "grad_norm": 0.1075616180896759,
+      "learning_rate": 4.4175283090001225e-05,
+      "loss": 0.6042,
+      "step": 224
+    },
+    {
+      "epoch": 0.5685534591194968,
+      "grad_norm": 0.11763885617256165,
+      "learning_rate": 4.4050489571820306e-05,
+      "loss": 0.5854,
+      "step": 226
+    },
+    {
+      "epoch": 0.5735849056603773,
+      "grad_norm": 0.1110839769244194,
+      "learning_rate": 4.392457666365519e-05,
+      "loss": 0.5731,
+      "step": 228
+    },
+    {
+      "epoch": 0.5786163522012578,
+      "grad_norm": 0.1211901530623436,
+      "learning_rate": 4.379755288160733e-05,
+      "loss": 0.5571,
+      "step": 230
+    },
+    {
+      "epoch": 0.5836477987421383,
+      "grad_norm": 0.10990186035633087,
+      "learning_rate": 4.3669426816911985e-05,
+      "loss": 0.5919,
+      "step": 232
+    },
+    {
+      "epoch": 0.5886792452830188,
+      "grad_norm": 0.1129634901881218,
+      "learning_rate": 4.354020713535711e-05,
+      "loss": 0.5853,
+      "step": 234
+    },
+    {
+      "epoch": 0.5937106918238994,
+      "grad_norm": 0.11691266298294067,
+      "learning_rate": 4.340990257669732e-05,
+      "loss": 0.5878,
+      "step": 236
+    },
+    {
+      "epoch": 0.5987421383647799,
+      "grad_norm": 0.11645273119211197,
+      "learning_rate": 4.327852195406271e-05,
+      "loss": 0.5946,
+      "step": 238
+    },
+    {
+      "epoch": 0.6037735849056604,
+      "grad_norm": 0.1155095249414444,
+      "learning_rate": 4.314607415336281e-05,
+      "loss": 0.6004,
+      "step": 240
+    },
+    {
+      "epoch": 0.6037735849056604,
+      "eval_loss": 0.5851526856422424,
+      "eval_runtime": 413.8117,
+      "eval_samples_per_second": 25.872,
+      "eval_steps_per_second": 0.203,
+      "step": 240
+    },
+    {
+      "epoch": 0.6088050314465409,
+      "grad_norm": 0.11004958301782608,
+      "learning_rate": 4.301256813268559e-05,
+      "loss": 0.5846,
+      "step": 242
+    },
+    {
+      "epoch": 0.6138364779874214,
+      "grad_norm": 0.10904593765735626,
+      "learning_rate": 4.287801292169159e-05,
+      "loss": 0.5871,
+      "step": 244
+    },
+    {
+      "epoch": 0.6188679245283019,
+      "grad_norm": 0.11857830733060837,
+      "learning_rate": 4.274241762100315e-05,
+      "loss": 0.5826,
+      "step": 246
+    },
+    {
+      "epoch": 0.6238993710691824,
+      "grad_norm": 0.11342642456293106,
+      "learning_rate": 4.260579140158898e-05,
+      "loss": 0.5807,
+      "step": 248
+    },
+    {
+      "epoch": 0.6289308176100629,
+      "grad_norm": 0.10923154652118683,
+      "learning_rate": 4.246814350414377e-05,
+      "loss": 0.5732,
+      "step": 250
+    },
+    {
+      "epoch": 0.6339622641509434,
+      "grad_norm": 0.11175252497196198,
+      "learning_rate": 4.2329483238463304e-05,
+      "loss": 0.5649,
+      "step": 252
+    },
+    {
+      "epoch": 0.6389937106918239,
+      "grad_norm": 0.10550232976675034,
+      "learning_rate": 4.218981998281471e-05,
+      "loss": 0.5853,
+      "step": 254
+    },
+    {
+      "epoch": 0.6440251572327044,
+      "grad_norm": 0.10999017208814621,
+      "learning_rate": 4.204916318330225e-05,
+      "loss": 0.5864,
+      "step": 256
+    },
+    {
+      "epoch": 0.6490566037735849,
+      "grad_norm": 0.13525208830833435,
+      "learning_rate": 4.190752235322832e-05,
+      "loss": 0.5842,
+      "step": 258
+    },
+    {
+      "epoch": 0.6540880503144654,
+      "grad_norm": 0.11547064781188965,
+      "learning_rate": 4.176490707245011e-05,
+      "loss": 0.5891,
+      "step": 260
+    },
+    {
+      "epoch": 0.6540880503144654,
+      "eval_loss": 0.5836161971092224,
+      "eval_runtime": 414.2177,
+      "eval_samples_per_second": 25.846,
+      "eval_steps_per_second": 0.203,
+      "step": 260
+    },
+    {
+      "epoch": 0.6591194968553459,
+      "grad_norm": 0.10233239829540253,
+      "learning_rate": 4.162132698673167e-05,
+      "loss": 0.5708,
+      "step": 262
+    },
+    {
+      "epoch": 0.6641509433962264,
+      "grad_norm": 0.11854418367147446,
+      "learning_rate": 4.1476791807091445e-05,
+      "loss": 0.6074,
+      "step": 264
+    },
+    {
+      "epoch": 0.6691823899371069,
+      "grad_norm": 0.13011477887630463,
+      "learning_rate": 4.133131130914555e-05,
+      "loss": 0.597,
+      "step": 266
+    },
+    {
+      "epoch": 0.6742138364779874,
+      "grad_norm": 0.11256586760282516,
+      "learning_rate": 4.118489533244655e-05,
+      "loss": 0.5895,
+      "step": 268
+    },
+    {
+      "epoch": 0.6792452830188679,
+      "grad_norm": 0.10651887208223343,
+      "learning_rate": 4.1037553779818016e-05,
+      "loss": 0.5934,
+      "step": 270
+    },
+    {
+      "epoch": 0.6842767295597484,
+      "grad_norm": 0.11151424050331116,
+      "learning_rate": 4.088929661668468e-05,
+      "loss": 0.6028,
+      "step": 272
+    },
+    {
+      "epoch": 0.6893081761006289,
+      "grad_norm": 0.10524857044219971,
+      "learning_rate": 4.0740133870398456e-05,
+      "loss": 0.608,
+      "step": 274
+    },
+    {
+      "epoch": 0.6943396226415094,
+      "grad_norm": 0.12080366164445877,
+      "learning_rate": 4.059007562956027e-05,
+      "loss": 0.6175,
+      "step": 276
+    },
+    {
+      "epoch": 0.6993710691823899,
+      "grad_norm": 0.1079036071896553,
+      "learning_rate": 4.0439132043337666e-05,
+      "loss": 0.5938,
+      "step": 278
+    },
+    {
+      "epoch": 0.7044025157232704,
+      "grad_norm": 0.11142345517873764,
+      "learning_rate": 4.028731332077843e-05,
+      "loss": 0.5752,
+      "step": 280
+    },
+    {
+      "epoch": 0.7044025157232704,
+      "eval_loss": 0.5814208984375,
+      "eval_runtime": 413.672,
+      "eval_samples_per_second": 25.88,
+      "eval_steps_per_second": 0.203,
+      "step": 280
+    },
+    {
+      "epoch": 0.7094339622641509,
+      "grad_norm": 0.11195844411849976,
+      "learning_rate": 4.0134629730120045e-05,
+      "loss": 0.583,
+      "step": 282
+    },
+    {
+      "epoch": 0.7144654088050314,
+      "grad_norm": 0.10488727688789368,
+      "learning_rate": 3.9981091598095213e-05,
+      "loss": 0.5593,
+      "step": 284
+    },
+    {
+      "epoch": 0.7194968553459119,
+      "grad_norm": 0.10145172476768494,
+      "learning_rate": 3.9826709309233454e-05,
+      "loss": 0.5839,
+      "step": 286
+    },
+    {
+      "epoch": 0.7245283018867924,
+      "grad_norm": 0.1036810651421547,
+      "learning_rate": 3.967149330515867e-05,
+      "loss": 0.5796,
+      "step": 288
+    },
+    {
+      "epoch": 0.7295597484276729,
+      "grad_norm": 0.1167021244764328,
+      "learning_rate": 3.951545408388301e-05,
+      "loss": 0.6006,
+      "step": 290
+    },
+    {
+      "epoch": 0.7345911949685534,
+      "grad_norm": 0.10975436121225357,
+      "learning_rate": 3.935860219909679e-05,
+      "loss": 0.5802,
+      "step": 292
+    },
+    {
+      "epoch": 0.7396226415094339,
+      "grad_norm": 0.11112164705991745,
+      "learning_rate": 3.920094825945468e-05,
+      "loss": 0.5851,
+      "step": 294
+    },
+    {
+      "epoch": 0.7446540880503144,
+      "grad_norm": 0.10697871446609497,
+      "learning_rate": 3.904250292785825e-05,
+      "loss": 0.5855,
+      "step": 296
+    },
+    {
+      "epoch": 0.7496855345911949,
+      "grad_norm": 0.10061946511268616,
+      "learning_rate": 3.8883276920734736e-05,
+      "loss": 0.5941,
+      "step": 298
+    },
+    {
+      "epoch": 0.7547169811320755,
+      "grad_norm": 0.102944515645504,
+      "learning_rate": 3.8723281007312256e-05,
+      "loss": 0.5732,
+      "step": 300
+    },
+    {
+      "epoch": 0.7547169811320755,
+      "eval_loss": 0.5801501870155334,
+      "eval_runtime": 412.1928,
+      "eval_samples_per_second": 25.973,
+      "eval_steps_per_second": 0.204,
+      "step": 300
+    },
+    {
+      "epoch": 0.759748427672956,
+      "grad_norm": 0.10275246948003769,
+      "learning_rate": 3.856252600889143e-05,
+      "loss": 0.5803,
+      "step": 302
+    },
+    {
+      "epoch": 0.7647798742138365,
+      "grad_norm": 0.10686468333005905,
+      "learning_rate": 3.840102279811345e-05,
+      "loss": 0.585,
+      "step": 304
+    },
+    {
+      "epoch": 0.769811320754717,
+      "grad_norm": 0.11284485459327698,
+      "learning_rate": 3.82387822982248e-05,
+      "loss": 0.5937,
+      "step": 306
+    },
+    {
+      "epoch": 0.7748427672955975,
+      "grad_norm": 0.10271965712308884,
+      "learning_rate": 3.807581548233837e-05,
+      "loss": 0.5777,
+      "step": 308
+    },
+    {
+      "epoch": 0.779874213836478,
+      "grad_norm": 0.10338881611824036,
+      "learning_rate": 3.791213337269134e-05,
+      "loss": 0.5888,
+      "step": 310
+    },
+    {
+      "epoch": 0.7849056603773585,
+      "grad_norm": 0.11098296195268631,
+      "learning_rate": 3.7747747039899676e-05,
+      "loss": 0.5764,
+      "step": 312
+    },
+    {
+      "epoch": 0.789937106918239,
+      "grad_norm": 0.10431266576051712,
+      "learning_rate": 3.758266760220937e-05,
+      "loss": 0.5985,
+      "step": 314
+    },
+    {
+      "epoch": 0.7949685534591195,
+      "grad_norm": 0.10191661864519119,
+      "learning_rate": 3.741690622474449e-05,
+      "loss": 0.5626,
+      "step": 316
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.11264406889677048,
+      "learning_rate": 3.7250474118751974e-05,
+      "loss": 0.6094,
+      "step": 318
+    },
+    {
+      "epoch": 0.8050314465408805,
+      "grad_norm": 0.10798995941877365,
+      "learning_rate": 3.708338254084339e-05,
+      "loss": 0.5714,
+      "step": 320
+    },
+    {
+      "epoch": 0.8050314465408805,
+      "eval_loss": 0.5783895254135132,
+      "eval_runtime": 411.3396,
+      "eval_samples_per_second": 26.027,
+      "eval_steps_per_second": 0.204,
+      "step": 320
+    },
+    {
+      "epoch": 0.810062893081761,
+      "grad_norm": 0.10546964406967163,
+      "learning_rate": 3.69156427922336e-05,
+      "loss": 0.5682,
+      "step": 322
+    },
+    {
+      "epoch": 0.8150943396226416,
+      "grad_norm": 0.11086619645357132,
+      "learning_rate": 3.6747266217976414e-05,
+      "loss": 0.5682,
+      "step": 324
+    },
+    {
+      "epoch": 0.820125786163522,
+      "grad_norm": 0.11166223883628845,
+      "learning_rate": 3.6578264206197245e-05,
+      "loss": 0.5798,
+      "step": 326
+    },
+    {
+      "epoch": 0.8251572327044026,
+      "grad_norm": 0.1012871265411377,
+      "learning_rate": 3.6408648187322854e-05,
+      "loss": 0.5694,
+      "step": 328
+    },
+    {
+      "epoch": 0.8301886792452831,
+      "grad_norm": 0.11129719018936157,
+      "learning_rate": 3.623842963330832e-05,
+      "loss": 0.5827,
+      "step": 330
+    },
+    {
+      "epoch": 0.8352201257861636,
+      "grad_norm": 0.10445208847522736,
+      "learning_rate": 3.6067620056861086e-05,
+      "loss": 0.5684,
+      "step": 332
+    },
+    {
+      "epoch": 0.8402515723270441,
+      "grad_norm": 0.09836594015359879,
+      "learning_rate": 3.589623101066232e-05,
+      "loss": 0.5755,
+      "step": 334
+    },
+    {
+      "epoch": 0.8452830188679246,
+      "grad_norm": 0.10354923456907272,
+      "learning_rate": 3.572427408658552e-05,
+      "loss": 0.5782,
+      "step": 336
+    },
+    {
+      "epoch": 0.8503144654088051,
+      "grad_norm": 0.10813874751329422,
+      "learning_rate": 3.5551760914912546e-05,
+      "loss": 0.5939,
+      "step": 338
+    },
+    {
+      "epoch": 0.8553459119496856,
+      "grad_norm": 0.10268381237983704,
+      "learning_rate": 3.537870316354699e-05,
+      "loss": 0.5697,
+      "step": 340
+    },
+    {
+      "epoch": 0.8553459119496856,
+      "eval_loss": 0.5766698122024536,
+      "eval_runtime": 412.4072,
+      "eval_samples_per_second": 25.96,
+      "eval_steps_per_second": 0.204,
+      "step": 340
+    },
+    {
+      "epoch": 0.8603773584905661,
+      "grad_norm": 0.10261879861354828,
+      "learning_rate": 3.5205112537224974e-05,
+      "loss": 0.5694,
+      "step": 342
+    },
+    {
+      "epoch": 0.8654088050314466,
+      "grad_norm": 0.10596223920583725,
+      "learning_rate": 3.50310007767236e-05,
+      "loss": 0.6091,
+      "step": 344
+    },
+    {
+      "epoch": 0.8704402515723271,
+      "grad_norm": 0.09846257418394089,
+      "learning_rate": 3.485637965806674e-05,
+      "loss": 0.5808,
+      "step": 346
+    },
+    {
+      "epoch": 0.8754716981132076,
+      "grad_norm": 0.10605087131261826,
+      "learning_rate": 3.4681260991728685e-05,
+      "loss": 0.5737,
+      "step": 348
+    },
+    {
+      "epoch": 0.8805031446540881,
+      "grad_norm": 0.11082804203033447,
+      "learning_rate": 3.450565662183527e-05,
+      "loss": 0.5826,
+      "step": 350
+    },
+    {
+      "epoch": 0.8855345911949686,
+      "grad_norm": 0.10169358551502228,
+      "learning_rate": 3.432957842536282e-05,
+      "loss": 0.5724,
+      "step": 352
+    },
+    {
+      "epoch": 0.8905660377358491,
+      "grad_norm": 0.10837408900260925,
+      "learning_rate": 3.415303831133485e-05,
+      "loss": 0.5736,
+      "step": 354
+    },
+    {
+      "epoch": 0.8955974842767296,
+      "grad_norm": 0.11302381008863449,
+      "learning_rate": 3.3976048220016604e-05,
+      "loss": 0.589,
+      "step": 356
+    },
+    {
+      "epoch": 0.9006289308176101,
+      "grad_norm": 0.10759381949901581,
+      "learning_rate": 3.37986201221075e-05,
+      "loss": 0.5769,
+      "step": 358
+    },
+    {
+      "epoch": 0.9056603773584906,
+      "grad_norm": 0.11644274741411209,
+      "learning_rate": 3.362076601793142e-05,
+      "loss": 0.5603,
+      "step": 360
+    },
+    {
+      "epoch": 0.9056603773584906,
+      "eval_loss": 0.5751825571060181,
+      "eval_runtime": 411.2176,
+      "eval_samples_per_second": 26.035,
+      "eval_steps_per_second": 0.204,
+      "step": 360
+    },
+    {
+      "epoch": 0.9106918238993711,
+      "grad_norm": 0.10910682380199432,
+      "learning_rate": 3.344249793662514e-05,
+      "loss": 0.5632,
+      "step": 362
+    },
+    {
+      "epoch": 0.9157232704402516,
+      "grad_norm": 0.10915949195623398,
+      "learning_rate": 3.326382793532476e-05,
+      "loss": 0.5903,
+      "step": 364
+    },
+    {
+      "epoch": 0.9207547169811321,
+      "grad_norm": 0.11586213856935501,
+      "learning_rate": 3.308476809835013e-05,
+      "loss": 0.594,
+      "step": 366
+    },
+    {
+      "epoch": 0.9257861635220126,
+      "grad_norm": 0.11010655015707016,
+      "learning_rate": 3.290533053638759e-05,
+      "loss": 0.5723,
+      "step": 368
+    },
+    {
+      "epoch": 0.9308176100628931,
+      "grad_norm": 0.11362364888191223,
+      "learning_rate": 3.272552738567086e-05,
+      "loss": 0.5825,
+      "step": 370
+    },
+    {
+      "epoch": 0.9358490566037736,
+      "grad_norm": 0.10686285048723221,
+      "learning_rate": 3.254537080716021e-05,
+      "loss": 0.586,
+      "step": 372
+    },
+    {
+      "epoch": 0.9408805031446541,
+      "grad_norm": 0.11016613245010376,
+      "learning_rate": 3.236487298571996e-05,
+      "loss": 0.5813,
+      "step": 374
+    },
+    {
+      "epoch": 0.9459119496855346,
+      "grad_norm": 0.10999295115470886,
+      "learning_rate": 3.2184046129294295e-05,
+      "loss": 0.5716,
+      "step": 376
+    },
+    {
+      "epoch": 0.9509433962264151,
+      "grad_norm": 0.1100740134716034,
+      "learning_rate": 3.20029024680817e-05,
+      "loss": 0.5424,
+      "step": 378
+    },
+    {
+      "epoch": 0.9559748427672956,
+      "grad_norm": 0.105403371155262,
+      "learning_rate": 3.1821454253707646e-05,
+      "loss": 0.5963,
+      "step": 380
+    },
+    {
+      "epoch": 0.9559748427672956,
+      "eval_loss": 0.5737633109092712,
+      "eval_runtime": 412.702,
+      "eval_samples_per_second": 25.941,
+      "eval_steps_per_second": 0.204,
+      "step": 380
+    },
+    {
+      "epoch": 0.9610062893081761,
+      "grad_norm": 0.10489460825920105,
+      "learning_rate": 3.1639713758396055e-05,
+      "loss": 0.567,
+      "step": 382
+    },
+    {
+      "epoch": 0.9660377358490566,
+      "grad_norm": 0.10349351167678833,
+      "learning_rate": 3.145769327413922e-05,
+      "loss": 0.5721,
+      "step": 384
+    },
+    {
+      "epoch": 0.9710691823899371,
+      "grad_norm": 0.10395889729261398,
+      "learning_rate": 3.127540511186643e-05,
+      "loss": 0.569,
+      "step": 386
+    },
+    {
+      "epoch": 0.9761006289308176,
+      "grad_norm": 0.10146255046129227,
+      "learning_rate": 3.109286160061136e-05,
+      "loss": 0.5699,
+      "step": 388
+    },
+    {
+      "epoch": 0.9811320754716981,
+      "grad_norm": 0.10547154396772385,
+      "learning_rate": 3.091007508667814e-05,
+      "loss": 0.5686,
+      "step": 390
+    },
+    {
+      "epoch": 0.9861635220125786,
+      "grad_norm": 0.10124453902244568,
+      "learning_rate": 3.072705793280642e-05,
+      "loss": 0.5983,
+      "step": 392
+    },
+    {
+      "epoch": 0.9911949685534591,
+      "grad_norm": 0.10909611731767654,
+      "learning_rate": 3.054382251733507e-05,
+      "loss": 0.5881,
+      "step": 394
+    },
+    {
+      "epoch": 0.9962264150943396,
+      "grad_norm": 0.10168620944023132,
+      "learning_rate": 3.0360381233365105e-05,
+      "loss": 0.5978,
+      "step": 396
+    },
+    {
+      "epoch": 1.0012578616352201,
+      "grad_norm": 0.1318611353635788,
+      "learning_rate": 3.0176746487921404e-05,
+      "loss": 0.5694,
+      "step": 398
+    },
+    {
+      "epoch": 1.0062893081761006,
+      "grad_norm": 0.12533968687057495,
+      "learning_rate": 2.9992930701113586e-05,
+      "loss": 0.5082,
+      "step": 400
+    },
+    {
+      "epoch": 1.0062893081761006,
+      "eval_loss": 0.5776596665382385,
+      "eval_runtime": 410.8135,
+      "eval_samples_per_second": 26.06,
+      "eval_steps_per_second": 0.204,
+      "step": 400
+    },
+    {
+      "epoch": 1.0113207547169811,
+      "grad_norm": 0.12798835337162018,
+      "learning_rate": 2.9808946305295988e-05,
+      "loss": 0.4912,
+      "step": 402
+    },
+    {
+      "epoch": 1.0163522012578616,
+      "grad_norm": 0.13782812654972076,
+      "learning_rate": 2.962480574422678e-05,
+      "loss": 0.5288,
+      "step": 404
+    },
+    {
+      "epoch": 1.0213836477987421,
+      "grad_norm": 0.11341769248247147,
+      "learning_rate": 2.9440521472226368e-05,
+      "loss": 0.5032,
+      "step": 406
+    },
+    {
+      "epoch": 1.0264150943396226,
+      "grad_norm": 0.1318856179714203,
+      "learning_rate": 2.9256105953334982e-05,
+      "loss": 0.5038,
+      "step": 408
+    },
+    {
+      "epoch": 1.0314465408805031,
+      "grad_norm": 0.11981856822967529,
+      "learning_rate": 2.9071571660469775e-05,
+      "loss": 0.4965,
+      "step": 410
+    },
+    {
+      "epoch": 1.0364779874213836,
+      "grad_norm": 0.11475057154893875,
+      "learning_rate": 2.888693107458111e-05,
+      "loss": 0.4912,
+      "step": 412
+    },
+    {
+      "epoch": 1.0415094339622641,
+      "grad_norm": 0.13232818245887756,
+      "learning_rate": 2.8702196683808496e-05,
+      "loss": 0.5065,
+      "step": 414
+    },
+    {
+      "epoch": 1.0465408805031446,
+      "grad_norm": 0.1348014920949936,
+      "learning_rate": 2.8517380982635906e-05,
+      "loss": 0.5293,
+      "step": 416
+    },
+    {
+      "epoch": 1.0515723270440251,
+      "grad_norm": 0.11755809187889099,
+      "learning_rate": 2.8332496471046737e-05,
+      "loss": 0.486,
+      "step": 418
+    },
+    {
+      "epoch": 1.0566037735849056,
+      "grad_norm": 0.1252366006374359,
+      "learning_rate": 2.8147555653678353e-05,
+      "loss": 0.4975,
+      "step": 420
+    },
+    {
+      "epoch": 1.0566037735849056,
+      "eval_loss": 0.5800932049751282,
+      "eval_runtime": 411.2332,
+      "eval_samples_per_second": 26.034,
+      "eval_steps_per_second": 0.204,
+      "step": 420
+    },
+    {
+      "epoch": 1.0616352201257861,
+      "grad_norm": 0.11638514697551727,
+      "learning_rate": 2.7962571038976376e-05,
+      "loss": 0.5021,
+      "step": 422
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 0.11196921765804291,
+      "learning_rate": 2.777755513834865e-05,
+      "loss": 0.5081,
+      "step": 424
+    },
+    {
+      "epoch": 1.0716981132075472,
+      "grad_norm": 0.12703673541545868,
+      "learning_rate": 2.7592520465319012e-05,
+      "loss": 0.5186,
+      "step": 426
+    },
+    {
+      "epoch": 1.0767295597484277,
+      "grad_norm": 0.12006295472383499,
+      "learning_rate": 2.7407479534680997e-05,
+      "loss": 0.5123,
+      "step": 428
+    },
+    {
+      "epoch": 1.0817610062893082,
+      "grad_norm": 0.11968886107206345,
+      "learning_rate": 2.722244486165136e-05,
+      "loss": 0.5135,
+      "step": 430
+    },
+    {
+      "epoch": 1.0867924528301887,
+      "grad_norm": 0.11439641565084457,
+      "learning_rate": 2.7037428961023632e-05,
+      "loss": 0.4964,
+      "step": 432
+    },
+    {
+      "epoch": 1.0918238993710692,
+      "grad_norm": 0.12513814866542816,
+      "learning_rate": 2.685244434632166e-05,
+      "loss": 0.5103,
+      "step": 434
+    },
+    {
+      "epoch": 1.0968553459119497,
+      "grad_norm": 0.11105407029390335,
+      "learning_rate": 2.6667503528953275e-05,
+      "loss": 0.4915,
+      "step": 436
+    },
+    {
+      "epoch": 1.1018867924528302,
+      "grad_norm": 0.1270296275615692,
+      "learning_rate": 2.6482619017364096e-05,
+      "loss": 0.5197,
+      "step": 438
+    },
+    {
+      "epoch": 1.1069182389937107,
+      "grad_norm": 0.12292016297578812,
+      "learning_rate": 2.629780331619151e-05,
+      "loss": 0.5131,
+      "step": 440
+    },
+    {
+      "epoch": 1.1069182389937107,
+      "eval_loss": 0.5787190198898315,
+      "eval_runtime": 410.8629,
+      "eval_samples_per_second": 26.057,
+      "eval_steps_per_second": 0.204,
+      "step": 440
+    },
+    {
+      "epoch": 1.1119496855345912,
+      "grad_norm": 0.10833011567592621,
+      "learning_rate": 2.6113068925418892e-05,
+      "loss": 0.4747,
+      "step": 442
+    },
+    {
+      "epoch": 1.1169811320754717,
+      "grad_norm": 0.11480649560689926,
+      "learning_rate": 2.592842833953023e-05,
+      "loss": 0.5033,
+      "step": 444
+    },
+    {
+      "epoch": 1.1220125786163522,
+      "grad_norm": 0.11621647328138351,
+      "learning_rate": 2.5743894046665013e-05,
+      "loss": 0.5041,
+      "step": 446
+    },
+    {
+      "epoch": 1.1270440251572327,
+      "grad_norm": 0.11848396062850952,
+      "learning_rate": 2.555947852777364e-05,
+      "loss": 0.4868,
+      "step": 448
+    },
+    {
+      "epoch": 1.1320754716981132,
+      "grad_norm": 0.11532817780971527,
+      "learning_rate": 2.537519425577322e-05,
+      "loss": 0.485,
+      "step": 450
+    },
+    {
+      "epoch": 1.1371069182389937,
+      "grad_norm": 0.11470374464988708,
+      "learning_rate": 2.519105369470402e-05,
+      "loss": 0.5009,
+      "step": 452
+    },
+    {
+      "epoch": 1.1421383647798742,
+      "grad_norm": 0.11918400973081589,
+      "learning_rate": 2.5007069298886416e-05,
+      "loss": 0.492,
+      "step": 454
+    },
+    {
+      "epoch": 1.1471698113207547,
+      "grad_norm": 0.11399897933006287,
+      "learning_rate": 2.4823253512078605e-05,
+      "loss": 0.5227,
+      "step": 456
+    },
+    {
+      "epoch": 1.1522012578616352,
+      "grad_norm": 0.1135721504688263,
+      "learning_rate": 2.4639618766634904e-05,
+      "loss": 0.4948,
+      "step": 458
+    },
+    {
+      "epoch": 1.1572327044025157,
+      "grad_norm": 0.11768464744091034,
+      "learning_rate": 2.4456177482664932e-05,
+      "loss": 0.5069,
+      "step": 460
+    },
+    {
+      "epoch": 1.1572327044025157,
+      "eval_loss": 0.5783973932266235,
+      "eval_runtime": 410.9352,
+      "eval_samples_per_second": 26.053,
+      "eval_steps_per_second": 0.204,
+      "step": 460
+    },
+    {
+      "epoch": 1.1622641509433962,
+      "grad_norm": 0.11413212865591049,
+      "learning_rate": 2.4272942067193593e-05,
+      "loss": 0.4919,
+      "step": 462
+    },
+    {
+      "epoch": 1.1672955974842767,
+      "grad_norm": 0.11099102348089218,
+      "learning_rate": 2.4089924913321854e-05,
+      "loss": 0.5131,
+      "step": 464
+    },
+    {
+      "epoch": 1.1723270440251572,
+      "grad_norm": 0.12233982235193253,
+      "learning_rate": 2.3907138399388656e-05,
+      "loss": 0.5152,
+      "step": 466
+    },
+    {
+      "epoch": 1.1773584905660377,
+      "grad_norm": 0.109150230884552,
+      "learning_rate": 2.3724594888133578e-05,
+      "loss": 0.4942,
+      "step": 468
+    },
+    {
+      "epoch": 1.1823899371069182,
+      "grad_norm": 0.11547227948904037,
+      "learning_rate": 2.354230672586079e-05,
+      "loss": 0.5087,
+      "step": 470
+    },
+    {
+      "epoch": 1.1874213836477987,
+      "grad_norm": 0.11096334457397461,
+      "learning_rate": 2.3360286241603947e-05,
+      "loss": 0.528,
+      "step": 472
+    },
+    {
+      "epoch": 1.1924528301886792,
+      "grad_norm": 0.11583118885755539,
+      "learning_rate": 2.3178545746292363e-05,
+      "loss": 0.5053,
+      "step": 474
+    },
+    {
+      "epoch": 1.1974842767295597,
+      "grad_norm": 0.12394651025533676,
+      "learning_rate": 2.299709753191831e-05,
+      "loss": 0.519,
+      "step": 476
+    },
+    {
+      "epoch": 1.2025157232704402,
+      "grad_norm": 0.10962869971990585,
+      "learning_rate": 2.281595387070571e-05,
+      "loss": 0.5119,
+      "step": 478
+    },
+    {
+      "epoch": 1.2075471698113207,
+      "grad_norm": 0.11548969149589539,
+      "learning_rate": 2.263512701428005e-05,
+      "loss": 0.5053,
+      "step": 480
+    },
+    {
+      "epoch": 1.2075471698113207,
+      "eval_loss": 0.5777500867843628,
+      "eval_runtime": 410.7907,
+      "eval_samples_per_second": 26.062,
+      "eval_steps_per_second": 0.204,
+      "step": 480
+    },
+    {
+      "epoch": 1.2125786163522012,
+      "grad_norm": 0.11964194476604462,
+      "learning_rate": 2.2454629192839782e-05,
+      "loss": 0.5067,
+      "step": 482
+    },
+    {
+      "epoch": 1.2176100628930817,
+      "grad_norm": 0.11280932277441025,
+      "learning_rate": 2.2274472614329146e-05,
+      "loss": 0.5097,
+      "step": 484
+    },
+    {
+      "epoch": 1.2226415094339622,
+      "grad_norm": 0.11903873831033707,
+      "learning_rate": 2.2094669463612417e-05,
+      "loss": 0.4973,
+      "step": 486
+    },
+    {
+      "epoch": 1.2276729559748427,
+      "grad_norm": 0.11274790018796921,
+      "learning_rate": 2.191523190164988e-05,
+      "loss": 0.4802,
+      "step": 488
+    },
+    {
+      "epoch": 1.2327044025157232,
+      "grad_norm": 0.12155181169509888,
+      "learning_rate": 2.1736172064675242e-05,
+      "loss": 0.5039,
+      "step": 490
+    },
+    {
+      "epoch": 1.2377358490566037,
+      "grad_norm": 0.1149788573384285,
+      "learning_rate": 2.1557502063374863e-05,
+      "loss": 0.5018,
+      "step": 492
+    },
+    {
+      "epoch": 1.2427672955974842,
+      "grad_norm": 0.11619096249341965,
+      "learning_rate": 2.1379233982068597e-05,
+      "loss": 0.5001,
+      "step": 494
+    },
+    {
+      "epoch": 1.2477987421383647,
+      "grad_norm": 0.11911306530237198,
+      "learning_rate": 2.120137987789252e-05,
+      "loss": 0.5257,
+      "step": 496
+    },
+    {
+      "epoch": 1.2528301886792452,
+      "grad_norm": 0.11577396094799042,
+      "learning_rate": 2.1023951779983408e-05,
+      "loss": 0.5156,
+      "step": 498
+    },
+    {
+      "epoch": 1.2578616352201257,
+      "grad_norm": 0.11911614239215851,
+      "learning_rate": 2.0846961688665158e-05,
+      "loss": 0.5189,
+      "step": 500
+    },
+    {
+      "epoch": 1.2578616352201257,
+      "eval_loss": 0.5771186947822571,
+      "eval_runtime": 410.8096,
+      "eval_samples_per_second": 26.061,
+      "eval_steps_per_second": 0.204,
+      "step": 500
+    },
+    {
+      "epoch": 1.2628930817610062,
+      "grad_norm": 0.12026111036539078,
+      "learning_rate": 2.0670421574637182e-05,
+      "loss": 0.4965,
+      "step": 502
+    },
+    {
+      "epoch": 1.2679245283018867,
+      "grad_norm": 0.11090611666440964,
+      "learning_rate": 2.0494343378164736e-05,
+      "loss": 0.4924,
+      "step": 504
+    },
+    {
+      "epoch": 1.2729559748427672,
+      "grad_norm": 0.11498820036649704,
+      "learning_rate": 2.0318739008271327e-05,
+      "loss": 0.5069,
+      "step": 506
+    },
+    {
+      "epoch": 1.2779874213836477,
+      "grad_norm": 0.11681642383337021,
+      "learning_rate": 2.014362034193326e-05,
+      "loss": 0.5208,
+      "step": 508
+    },
+    {
+      "epoch": 1.2830188679245282,
+      "grad_norm": 0.11289618164300919,
+      "learning_rate": 1.9968999223276406e-05,
+      "loss": 0.497,
+      "step": 510
+    },
+    {
+      "epoch": 1.2880503144654087,
+      "grad_norm": 0.11700893938541412,
+      "learning_rate": 1.979488746277503e-05,
+      "loss": 0.4872,
+      "step": 512
+    },
+    {
+      "epoch": 1.2930817610062892,
+      "grad_norm": 0.11669134348630905,
+      "learning_rate": 1.9621296836453025e-05,
+      "loss": 0.5117,
+      "step": 514
+    },
+    {
+      "epoch": 1.2981132075471697,
+      "grad_norm": 0.11578242480754852,
+      "learning_rate": 1.944823908508745e-05,
+      "loss": 0.5046,
+      "step": 516
+    },
+    {
+      "epoch": 1.3031446540880502,
+      "grad_norm": 0.11336881667375565,
+      "learning_rate": 1.9275725913414483e-05,
+      "loss": 0.4828,
+      "step": 518
+    },
+    {
+      "epoch": 1.3081761006289307,
+      "grad_norm": 0.1218356043100357,
+      "learning_rate": 1.910376898933769e-05,
+      "loss": 0.5173,
+      "step": 520
+    },
+    {
+      "epoch": 1.3081761006289307,
+      "eval_loss": 0.5762000679969788,
+      "eval_runtime": 410.9091,
+      "eval_samples_per_second": 26.054,
+      "eval_steps_per_second": 0.204,
+      "step": 520
+    },
+    {
+      "epoch": 1.3132075471698113,
+      "grad_norm": 0.11644181609153748,
+      "learning_rate": 1.8932379943138916e-05,
+      "loss": 0.5002,
+      "step": 522
+    },
+    {
+      "epoch": 1.3182389937106918,
+      "grad_norm": 0.11215106397867203,
+      "learning_rate": 1.8761570366691684e-05,
+      "loss": 0.4808,
+      "step": 524
+    },
+    {
+      "epoch": 1.3232704402515723,
+      "grad_norm": 0.11506900936365128,
+      "learning_rate": 1.8591351812677144e-05,
+      "loss": 0.4915,
+      "step": 526
+    },
+    {
+      "epoch": 1.3283018867924528,
+      "grad_norm": 0.11646901071071625,
+      "learning_rate": 1.8421735793802763e-05,
+      "loss": 0.5067,
+      "step": 528
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.1217241957783699,
+      "learning_rate": 1.8252733782023584e-05,
+      "loss": 0.5105,
+      "step": 530
+    },
+    {
+      "epoch": 1.3383647798742138,
+      "grad_norm": 0.12330880761146545,
+      "learning_rate": 1.8084357207766406e-05,
+      "loss": 0.5107,
+      "step": 532
+    },
+    {
+      "epoch": 1.3433962264150943,
+      "grad_norm": 0.10948923975229263,
+      "learning_rate": 1.7916617459156615e-05,
+      "loss": 0.4929,
+      "step": 534
+    },
+    {
+      "epoch": 1.3484276729559748,
+      "grad_norm": 0.11415420472621918,
+      "learning_rate": 1.7749525881248035e-05,
+      "loss": 0.5123,
+      "step": 536
+    },
+    {
+      "epoch": 1.3534591194968553,
+      "grad_norm": 0.11750365048646927,
+      "learning_rate": 1.7583093775255516e-05,
+      "loss": 0.5082,
+      "step": 538
+    },
+    {
+      "epoch": 1.3584905660377358,
+      "grad_norm": 0.11664094030857086,
+      "learning_rate": 1.741733239779063e-05,
+      "loss": 0.5048,
+      "step": 540
+    },
+    {
+      "epoch": 1.3584905660377358,
+      "eval_loss": 0.5755621194839478,
+      "eval_runtime": 410.7838,
+      "eval_samples_per_second": 26.062,
+      "eval_steps_per_second": 0.204,
+      "step": 540
+    },
+    {
+      "epoch": 1.3635220125786163,
+      "grad_norm": 0.11655986309051514,
+      "learning_rate": 1.725225296010034e-05,
+      "loss": 0.4923,
+      "step": 542
+    },
+    {
+      "epoch": 1.3685534591194968,
+      "grad_norm": 0.11432712525129318,
+      "learning_rate": 1.7087866627308664e-05,
+      "loss": 0.4976,
+      "step": 544
+    },
+    {
+      "epoch": 1.3735849056603773,
+      "grad_norm": 0.11400482058525085,
+      "learning_rate": 1.692418451766163e-05,
+      "loss": 0.5026,
+      "step": 546
+    },
+    {
+      "epoch": 1.378616352201258,
+      "grad_norm": 0.11588790267705917,
+      "learning_rate": 1.6761217701775207e-05,
+      "loss": 0.5031,
+      "step": 548
+    },
+    {
+      "epoch": 1.3836477987421385,
+      "grad_norm": 0.11426915228366852,
+      "learning_rate": 1.6598977201886558e-05,
+      "loss": 0.5001,
+      "step": 550
+    },
+    {
+      "epoch": 1.388679245283019,
+      "grad_norm": 0.11552328616380692,
+      "learning_rate": 1.6437473991108585e-05,
+      "loss": 0.4928,
+      "step": 552
+    },
+    {
+      "epoch": 1.3937106918238995,
+      "grad_norm": 0.11312104761600494,
+      "learning_rate": 1.6276718992687746e-05,
+      "loss": 0.4977,
+      "step": 554
+    },
+    {
+      "epoch": 1.39874213836478,
+      "grad_norm": 0.11197475343942642,
+      "learning_rate": 1.6116723079265263e-05,
+      "loss": 0.489,
+      "step": 556
+    },
+    {
+      "epoch": 1.4037735849056605,
+      "grad_norm": 0.11652438342571259,
+      "learning_rate": 1.5957497072141758e-05,
+      "loss": 0.4971,
+      "step": 558
+    },
+    {
+      "epoch": 1.408805031446541,
+      "grad_norm": 0.1163628101348877,
+      "learning_rate": 1.579905174054533e-05,
+      "loss": 0.4986,
+      "step": 560
+    },
+    {
+      "epoch": 1.408805031446541,
+      "eval_loss": 0.5742356777191162,
+      "eval_runtime": 410.5998,
+      "eval_samples_per_second": 26.074,
+      "eval_steps_per_second": 0.205,
+      "step": 560
+    },
+    {
+      "epoch": 1.4138364779874215,
+      "grad_norm": 0.1128329187631607,
+      "learning_rate": 1.5641397800903222e-05,
+      "loss": 0.5068,
+      "step": 562
+    },
+    {
+      "epoch": 1.418867924528302,
+      "grad_norm": 0.11648018658161163,
+      "learning_rate": 1.5484545916116995e-05,
+      "loss": 0.4958,
+      "step": 564
+    },
+    {
+      "epoch": 1.4238993710691825,
+      "grad_norm": 0.1150885596871376,
+      "learning_rate": 1.5328506694841334e-05,
+      "loss": 0.4855,
+      "step": 566
+    },
+    {
+      "epoch": 1.428930817610063,
+      "grad_norm": 0.11181043833494186,
+      "learning_rate": 1.5173290690766553e-05,
+      "loss": 0.5114,
+      "step": 568
+    },
+    {
+      "epoch": 1.4339622641509435,
+      "grad_norm": 0.11899517476558685,
+      "learning_rate": 1.5018908401904785e-05,
+      "loss": 0.5048,
+      "step": 570
+    },
+    {
+      "epoch": 1.438993710691824,
+      "grad_norm": 0.11897191405296326,
+      "learning_rate": 1.4865370269879955e-05,
+      "loss": 0.5308,
+      "step": 572
+    },
+    {
+      "epoch": 1.4440251572327045,
+      "grad_norm": 0.11142674088478088,
+      "learning_rate": 1.471268667922157e-05,
+      "loss": 0.4958,
+      "step": 574
+    },
+    {
+      "epoch": 1.449056603773585,
+      "grad_norm": 0.1150866225361824,
+      "learning_rate": 1.4560867956662336e-05,
+      "loss": 0.4939,
+      "step": 576
+    },
+    {
+      "epoch": 1.4540880503144655,
+      "grad_norm": 0.11816877871751785,
+      "learning_rate": 1.4409924370439737e-05,
+      "loss": 0.4913,
+      "step": 578
+    },
+    {
+      "epoch": 1.459119496855346,
+      "grad_norm": 0.11381349712610245,
+      "learning_rate": 1.425986612960155e-05,
+      "loss": 0.5039,
+      "step": 580
+    },
+    {
+      "epoch": 1.459119496855346,
+      "eval_loss": 0.573836624622345,
+      "eval_runtime": 410.5985,
+      "eval_samples_per_second": 26.074,
+      "eval_steps_per_second": 0.205,
+      "step": 580
+    },
+    {
+      "epoch": 1.4641509433962265,
+      "grad_norm": 0.1094905436038971,
+      "learning_rate": 1.4110703383315326e-05,
+      "loss": 0.4901,
+      "step": 582
+    },
+    {
+      "epoch": 1.469182389937107,
+      "grad_norm": 0.11396130174398422,
+      "learning_rate": 1.396244622018199e-05,
+      "loss": 0.5081,
+      "step": 584
+    },
+    {
+      "epoch": 1.4742138364779875,
+      "grad_norm": 0.1160426139831543,
+      "learning_rate": 1.3815104667553452e-05,
+      "loss": 0.4869,
+      "step": 586
+    },
+    {
+      "epoch": 1.479245283018868,
+      "grad_norm": 0.11492225527763367,
+      "learning_rate": 1.3668688690854453e-05,
+      "loss": 0.4888,
+      "step": 588
+    },
+    {
+      "epoch": 1.4842767295597485,
+      "grad_norm": 0.11282163113355637,
+      "learning_rate": 1.3523208192908562e-05,
+      "loss": 0.4983,
+      "step": 590
+    },
+    {
+      "epoch": 1.489308176100629,
+      "grad_norm": 0.11276757717132568,
+      "learning_rate": 1.3378673013268336e-05,
+      "loss": 0.517,
+      "step": 592
+    },
+    {
+      "epoch": 1.4943396226415095,
+      "grad_norm": 0.11005326360464096,
+      "learning_rate": 1.3235092927549888e-05,
+      "loss": 0.4933,
+      "step": 594
+    },
+    {
+      "epoch": 1.49937106918239,
+      "grad_norm": 0.11391846090555191,
+      "learning_rate": 1.3092477646771686e-05,
+      "loss": 0.5047,
+      "step": 596
+    },
+    {
+      "epoch": 1.5044025157232706,
+      "grad_norm": 0.112746462225914,
+      "learning_rate": 1.2950836816697753e-05,
+      "loss": 0.4933,
+      "step": 598
+    },
+    {
+      "epoch": 1.509433962264151,
+      "grad_norm": 0.11274772882461548,
+      "learning_rate": 1.2810180017185286e-05,
+      "loss": 0.4928,
+      "step": 600
+    },
+    {
+      "epoch": 1.509433962264151,
+      "eval_loss": 0.5733875632286072,
+      "eval_runtime": 410.9812,
+      "eval_samples_per_second": 26.05,
+      "eval_steps_per_second": 0.204,
+      "step": 600
+    },
+    {
+      "epoch": 1.5144654088050316,
+      "grad_norm": 0.11344069242477417,
+      "learning_rate": 1.2670516761536705e-05,
+      "loss": 0.5083,
+      "step": 602
+    },
+    {
+      "epoch": 1.519496855345912,
+      "grad_norm": 0.1206919476389885,
+      "learning_rate": 1.2531856495856234e-05,
+      "loss": 0.4931,
+      "step": 604
+    },
+    {
+      "epoch": 1.5245283018867926,
+      "grad_norm": 0.11568621546030045,
+      "learning_rate": 1.2394208598411026e-05,
+      "loss": 0.4961,
+      "step": 606
+    },
+    {
+      "epoch": 1.529559748427673,
+      "grad_norm": 0.11288320273160934,
+      "learning_rate": 1.2257582378996846e-05,
+      "loss": 0.493,
+      "step": 608
+    },
+    {
+      "epoch": 1.5345911949685536,
+      "grad_norm": 0.11447000503540039,
+      "learning_rate": 1.2121987078308414e-05,
+      "loss": 0.487,
+      "step": 610
+    },
+    {
+      "epoch": 1.539622641509434,
+      "grad_norm": 0.1167483702301979,
+      "learning_rate": 1.1987431867314417e-05,
+      "loss": 0.5078,
+      "step": 612
+    },
+    {
+      "epoch": 1.5446540880503146,
+      "grad_norm": 0.11339499801397324,
+      "learning_rate": 1.1853925846637192e-05,
+      "loss": 0.5101,
+      "step": 614
+    },
+    {
+      "epoch": 1.549685534591195,
+      "grad_norm": 0.11238376796245575,
+      "learning_rate": 1.1721478045937298e-05,
+      "loss": 0.5075,
+      "step": 616
+    },
+    {
+      "epoch": 1.5547169811320756,
+      "grad_norm": 0.11750028282403946,
+      "learning_rate": 1.1590097423302684e-05,
+      "loss": 0.5223,
+      "step": 618
+    },
+    {
+      "epoch": 1.559748427672956,
+      "grad_norm": 0.11243315786123276,
+      "learning_rate": 1.1459792864642889e-05,
+      "loss": 0.5014,
+      "step": 620
+    },
+    {
+      "epoch": 1.559748427672956,
+      "eval_loss": 0.5725140571594238,
+      "eval_runtime": 411.304,
+      "eval_samples_per_second": 26.029,
+      "eval_steps_per_second": 0.204,
+      "step": 620
+    },
+    {
+      "epoch": 1.5647798742138366,
+      "grad_norm": 0.10880452394485474,
+      "learning_rate": 1.1330573183088027e-05,
+      "loss": 0.4946,
+      "step": 622
+    },
+    {
+      "epoch": 1.569811320754717,
+      "grad_norm": 0.11715767532587051,
+      "learning_rate": 1.1202447118392666e-05,
+      "loss": 0.4934,
+      "step": 624
+    },
+    {
+      "epoch": 1.5748427672955976,
+      "grad_norm": 0.1085837110877037,
+      "learning_rate": 1.1075423336344815e-05,
+      "loss": 0.4918,
+      "step": 626
+    },
+    {
+      "epoch": 1.579874213836478,
+      "grad_norm": 0.11400571465492249,
+      "learning_rate": 1.0949510428179703e-05,
+      "loss": 0.4907,
+      "step": 628
+    },
+    {
+      "epoch": 1.5849056603773586,
+      "grad_norm": 0.11114535480737686,
+      "learning_rate": 1.0824716909998783e-05,
+      "loss": 0.504,
+      "step": 630
+    },
+    {
+      "epoch": 1.589937106918239,
+      "grad_norm": 0.10678807646036148,
+      "learning_rate": 1.0701051222193734e-05,
+      "loss": 0.4757,
+      "step": 632
+    },
+    {
+      "epoch": 1.5949685534591196,
+      "grad_norm": 0.11523126810789108,
+      "learning_rate": 1.0578521728875578e-05,
+      "loss": 0.5019,
+      "step": 634
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.11389489471912384,
+      "learning_rate": 1.0457136717308988e-05,
+      "loss": 0.5162,
+      "step": 636
+    },
+    {
+      "epoch": 1.6050314465408806,
+      "grad_norm": 0.11754269152879715,
+      "learning_rate": 1.0336904397351794e-05,
+      "loss": 0.4991,
+      "step": 638
+    },
+    {
+      "epoch": 1.610062893081761,
+      "grad_norm": 0.11521238088607788,
+      "learning_rate": 1.021783290089966e-05,
+      "loss": 0.5041,
+      "step": 640
+    },
+    {
+      "epoch": 1.610062893081761,
+      "eval_loss": 0.57233065366745,
+      "eval_runtime": 417.7875,
+      "eval_samples_per_second": 25.625,
+      "eval_steps_per_second": 0.201,
+      "step": 640
+    },
+    {
+      "epoch": 1.6150943396226416,
+      "grad_norm": 0.1117156520485878,
+      "learning_rate": 1.009993028133615e-05,
+      "loss": 0.4919,
+      "step": 642
+    },
+    {
+      "epoch": 1.620125786163522,
+      "grad_norm": 0.11549975723028183,
+      "learning_rate": 9.983204512988004e-06,
+      "loss": 0.4988,
+      "step": 644
+    },
+    {
+      "epoch": 1.6251572327044026,
+      "grad_norm": 0.11243242025375366,
+      "learning_rate": 9.867663490585783e-06,
+      "loss": 0.5128,
+      "step": 646
+    },
+    {
+      "epoch": 1.630188679245283,
+      "grad_norm": 0.11129079759120941,
+      "learning_rate": 9.753315028729948e-06,
+      "loss": 0.4893,
+      "step": 648
+    },
+    {
+      "epoch": 1.6352201257861636,
+      "grad_norm": 0.11360695213079453,
+      "learning_rate": 9.640166861362268e-06,
+      "loss": 0.503,
+      "step": 650
+    },
+    {
+      "epoch": 1.640251572327044,
+      "grad_norm": 0.11027677357196808,
+      "learning_rate": 9.528226641242804e-06,
+      "loss": 0.4933,
+      "step": 652
+    },
+    {
+      "epoch": 1.6452830188679246,
+      "grad_norm": 0.11328162252902985,
+      "learning_rate": 9.417501939432257e-06,
+      "loss": 0.4969,
+      "step": 654
+    },
+    {
+      "epoch": 1.650314465408805,
+      "grad_norm": 0.111870676279068,
+      "learning_rate": 9.308000244779918e-06,
+      "loss": 0.5009,
+      "step": 656
+    },
+    {
+      "epoch": 1.6553459119496856,
+      "grad_norm": 0.11578749120235443,
+      "learning_rate": 9.19972896341717e-06,
+      "loss": 0.5226,
+      "step": 658
+    },
+    {
+      "epoch": 1.6603773584905661,
+      "grad_norm": 0.11840783059597015,
+      "learning_rate": 9.09269541825658e-06,
+      "loss": 0.4876,
+      "step": 660
+    },
+    {
+      "epoch": 1.6603773584905661,
+      "eval_loss": 0.5716937184333801,
+      "eval_runtime": 411.8982,
+      "eval_samples_per_second": 25.992,
+      "eval_steps_per_second": 0.204,
+      "step": 660
+    },
+    {
+      "epoch": 1.6654088050314466,
+      "grad_norm": 0.10933776944875717,
+      "learning_rate": 8.98690684849659e-06,
+      "loss": 0.5217,
+      "step": 662
+    },
+    {
+      "epoch": 1.6704402515723271,
+      "grad_norm": 0.11809239536523819,
+      "learning_rate": 8.882370409131924e-06,
+      "loss": 0.5182,
+      "step": 664
+    },
+    {
+      "epoch": 1.6754716981132076,
+      "grad_norm": 0.1144753098487854,
+      "learning_rate": 8.779093170469629e-06,
+      "loss": 0.4999,
+      "step": 666
+    },
+    {
+      "epoch": 1.6805031446540881,
+      "grad_norm": 0.11396916210651398,
+      "learning_rate": 8.677082117650906e-06,
+      "loss": 0.507,
+      "step": 668
+    },
+    {
+      "epoch": 1.6855345911949686,
+      "grad_norm": 0.11068397760391235,
+      "learning_rate": 8.576344150178653e-06,
+      "loss": 0.5136,
+      "step": 670
+    },
+    {
+      "epoch": 1.6905660377358491,
+      "grad_norm": 0.1053067147731781,
+      "learning_rate": 8.47688608145083e-06,
+      "loss": 0.4907,
+      "step": 672
+    },
+    {
+      "epoch": 1.6955974842767296,
+      "grad_norm": 0.1102994978427887,
+      "learning_rate": 8.378714638299628e-06,
+      "loss": 0.4881,
+      "step": 674
+    },
+    {
+      "epoch": 1.7006289308176101,
+      "grad_norm": 0.10971739888191223,
+      "learning_rate": 8.28183646053649e-06,
+      "loss": 0.5176,
+      "step": 676
+    },
+    {
+      "epoch": 1.7056603773584906,
+      "grad_norm": 0.11169516295194626,
+      "learning_rate": 8.186258100503058e-06,
+      "loss": 0.5102,
+      "step": 678
+    },
+    {
+      "epoch": 1.7106918238993711,
+      "grad_norm": 0.1112278550863266,
+      "learning_rate": 8.091986022627978e-06,
+      "loss": 0.5272,
+      "step": 680
+    },
+    {
+      "epoch": 1.7106918238993711,
+      "eval_loss": 0.5712010860443115,
+      "eval_runtime": 411.4247,
+      "eval_samples_per_second": 26.022,
+      "eval_steps_per_second": 0.204,
+      "step": 680
+    },
+    {
+      "epoch": 1.7157232704402516,
+      "grad_norm": 0.11466188728809357,
+      "learning_rate": 7.999026602989687e-06,
+      "loss": 0.4974,
+      "step": 682
+    },
+    {
+      "epoch": 1.7207547169811321,
+      "grad_norm": 0.12257977575063705,
+      "learning_rate": 7.907386128885182e-06,
+      "loss": 0.4946,
+      "step": 684
+    },
+    {
+      "epoch": 1.7257861635220126,
+      "grad_norm": 0.12135323882102966,
+      "learning_rate": 7.817070798404755e-06,
+      "loss": 0.5374,
+      "step": 686
+    },
+    {
+      "epoch": 1.7308176100628931,
+      "grad_norm": 0.11566798388957977,
+      "learning_rate": 7.728086720012813e-06,
+      "loss": 0.5048,
+      "step": 688
+    },
+    {
+      "epoch": 1.7358490566037736,
+      "grad_norm": 0.11244137585163116,
+      "learning_rate": 7.640439912134711e-06,
+      "loss": 0.5169,
+      "step": 690
+    },
+    {
+      "epoch": 1.7408805031446541,
+      "grad_norm": 0.1125202625989914,
+      "learning_rate": 7.554136302749705e-06,
+      "loss": 0.5076,
+      "step": 692
+    },
+    {
+      "epoch": 1.7459119496855346,
+      "grad_norm": 0.1143079325556755,
+      "learning_rate": 7.469181728990013e-06,
+      "loss": 0.4961,
+      "step": 694
+    },
+    {
+      "epoch": 1.7509433962264151,
+      "grad_norm": 0.11676593869924545,
+      "learning_rate": 7.385581936746035e-06,
+      "loss": 0.5003,
+      "step": 696
+    },
+    {
+      "epoch": 1.7559748427672957,
+      "grad_norm": 0.1095028892159462,
+      "learning_rate": 7.303342580277696e-06,
+      "loss": 0.4755,
+      "step": 698
+    },
+    {
+      "epoch": 1.7610062893081762,
+      "grad_norm": 0.11439331620931625,
+      "learning_rate": 7.222469221832061e-06,
+      "loss": 0.5057,
+      "step": 700
+    },
+    {
+      "epoch": 1.7610062893081762,
+      "eval_loss": 0.5707039833068848,
+      "eval_runtime": 411.7854,
+      "eval_samples_per_second": 25.999,
+      "eval_steps_per_second": 0.204,
+      "step": 700
+    },
+    {
+      "epoch": 1.7660377358490567,
+      "grad_norm": 0.11388733237981796,
+      "learning_rate": 7.142967331267113e-06,
+      "loss": 0.4748,
+      "step": 702
+    },
+    {
+      "epoch": 1.7710691823899372,
+      "grad_norm": 0.11583738774061203,
+      "learning_rate": 7.064842285681781e-06,
+      "loss": 0.494,
+      "step": 704
+    },
+    {
+      "epoch": 1.7761006289308177,
+      "grad_norm": 0.11597929149866104,
+      "learning_rate": 6.988099369052318e-06,
+      "loss": 0.5106,
+      "step": 706
+    },
+    {
+      "epoch": 1.7811320754716982,
+      "grad_norm": 0.1117326021194458,
+      "learning_rate": 6.9127437718748465e-06,
+      "loss": 0.4844,
+      "step": 708
+    },
+    {
+      "epoch": 1.7861635220125787,
+      "grad_norm": 0.11276806890964508,
+      "learning_rate": 6.838780590814366e-06,
+      "loss": 0.5221,
+      "step": 710
+    },
+    {
+      "epoch": 1.7911949685534592,
+      "grad_norm": 0.11557289958000183,
+      "learning_rate": 6.7662148283599955e-06,
+      "loss": 0.5021,
+      "step": 712
+    },
+    {
+      "epoch": 1.7962264150943397,
+      "grad_norm": 0.11254438757896423,
+      "learning_rate": 6.695051392486652e-06,
+      "loss": 0.4999,
+      "step": 714
+    },
+    {
+      "epoch": 1.8012578616352202,
+      "grad_norm": 0.11114822328090668,
+      "learning_rate": 6.625295096323097e-06,
+      "loss": 0.4849,
+      "step": 716
+    },
+    {
+      "epoch": 1.8062893081761007,
+      "grad_norm": 0.11419788002967834,
+      "learning_rate": 6.556950657826405e-06,
+      "loss": 0.5227,
+      "step": 718
+    },
+    {
+      "epoch": 1.8113207547169812,
+      "grad_norm": 0.11834213882684708,
+      "learning_rate": 6.490022699462844e-06,
+      "loss": 0.5043,
+      "step": 720
+    },
+    {
+      "epoch": 1.8113207547169812,
+      "eval_loss": 0.5703166723251343,
+      "eval_runtime": 411.34,
+      "eval_samples_per_second": 26.027,
+      "eval_steps_per_second": 0.204,
+      "step": 720
+    },
+    {
+      "epoch": 1.8163522012578617,
+      "grad_norm": 0.11034736037254333,
+      "learning_rate": 6.424515747895265e-06,
+      "loss": 0.48,
+      "step": 722
+    },
+    {
+      "epoch": 1.8213836477987422,
+      "grad_norm": 0.11254922300577164,
+      "learning_rate": 6.360434233676926e-06,
+      "loss": 0.4864,
+      "step": 724
+    },
+    {
+      "epoch": 1.8264150943396227,
+      "grad_norm": 0.10830461978912354,
+      "learning_rate": 6.297782490951833e-06,
+      "loss": 0.4943,
+      "step": 726
+    },
+    {
+      "epoch": 1.8314465408805032,
+      "grad_norm": 0.1077997013926506,
+      "learning_rate": 6.236564757161608e-06,
+      "loss": 0.4865,
+      "step": 728
+    },
+    {
+      "epoch": 1.8364779874213837,
+      "grad_norm": 0.11505385488271713,
+      "learning_rate": 6.176785172758871e-06,
+      "loss": 0.5039,
+      "step": 730
+    },
+    {
+      "epoch": 1.8415094339622642,
+      "grad_norm": 0.12043328583240509,
+      "learning_rate": 6.118447780927233e-06,
+      "loss": 0.4909,
+      "step": 732
+    },
+    {
+      "epoch": 1.8465408805031447,
+      "grad_norm": 0.11934798955917358,
+      "learning_rate": 6.0615565273078025e-06,
+      "loss": 0.4978,
+      "step": 734
+    },
+    {
+      "epoch": 1.8515723270440252,
+      "grad_norm": 0.11153744161128998,
+      "learning_rate": 6.006115259732345e-06,
+      "loss": 0.4924,
+      "step": 736
+    },
+    {
+      "epoch": 1.8566037735849057,
+      "grad_norm": 0.11369643360376358,
+      "learning_rate": 5.952127727963029e-06,
+      "loss": 0.4938,
+      "step": 738
+    },
+    {
+      "epoch": 1.8616352201257862,
+      "grad_norm": 0.1063813716173172,
+      "learning_rate": 5.899597583438808e-06,
+      "loss": 0.5059,
+      "step": 740
+    },
+    {
+      "epoch": 1.8616352201257862,
+      "eval_loss": 0.5707431435585022,
+      "eval_runtime": 411.3909,
+      "eval_samples_per_second": 26.024,
+      "eval_steps_per_second": 0.204,
+      "step": 740
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "grad_norm": 0.12777185440063477,
+      "learning_rate": 5.848528379028456e-06,
+      "loss": 0.5138,
+      "step": 742
+    },
+    {
+      "epoch": 1.8716981132075472,
+      "grad_norm": 0.11385183781385422,
+      "learning_rate": 5.798923568790283e-06,
+      "loss": 0.5101,
+      "step": 744
+    },
+    {
+      "epoch": 1.8767295597484277,
+      "grad_norm": 0.11212068051099777,
+      "learning_rate": 5.750786507738497e-06,
+      "loss": 0.4845,
+      "step": 746
+    },
+    {
+      "epoch": 1.8817610062893082,
+      "grad_norm": 0.11255759000778198,
+      "learning_rate": 5.704120451616305e-06,
+      "loss": 0.5019,
+      "step": 748
+    },
+    {
+      "epoch": 1.8867924528301887,
+      "grad_norm": 0.11542278528213501,
+      "learning_rate": 5.6589285566757095e-06,
+      "loss": 0.5014,
+      "step": 750
+    },
+    {
+      "epoch": 1.8918238993710692,
+      "grad_norm": 0.11562332510948181,
+      "learning_rate": 5.61521387946403e-06,
+      "loss": 0.5077,
+      "step": 752
+    },
+    {
+      "epoch": 1.8968553459119497,
+      "grad_norm": 0.10956519842147827,
+      "learning_rate": 5.572979376617183e-06,
+      "loss": 0.4842,
+      "step": 754
+    },
+    {
+      "epoch": 1.9018867924528302,
+      "grad_norm": 0.11526080965995789,
+      "learning_rate": 5.532227904659695e-06,
+      "loss": 0.488,
+      "step": 756
+    },
+    {
+      "epoch": 1.9069182389937107,
+      "grad_norm": 0.11320438235998154,
+      "learning_rate": 5.49296221981152e-06,
+      "loss": 0.5021,
+      "step": 758
+    },
+    {
+      "epoch": 1.9119496855345912,
+      "grad_norm": 0.11186771839857101,
+      "learning_rate": 5.455184977801612e-06,
+      "loss": 0.4996,
+      "step": 760
+    },
+    {
+      "epoch": 1.9119496855345912,
+      "eval_loss": 0.5699969530105591,
+      "eval_runtime": 411.4136,
+      "eval_samples_per_second": 26.022,
+      "eval_steps_per_second": 0.204,
+      "step": 760
+    },
+    {
+      "epoch": 1.9169811320754717,
+      "grad_norm": 0.1088699921965599,
+      "learning_rate": 5.418898733688302e-06,
+      "loss": 0.4933,
+      "step": 762
+    },
+    {
+      "epoch": 1.9220125786163522,
+      "grad_norm": 0.11521943658590317,
+      "learning_rate": 5.384105941686499e-06,
+      "loss": 0.5018,
+      "step": 764
+    },
+    {
+      "epoch": 1.9270440251572327,
+      "grad_norm": 0.1104261726140976,
+      "learning_rate": 5.350808955001693e-06,
+      "loss": 0.4945,
+      "step": 766
+    },
+    {
+      "epoch": 1.9320754716981132,
+      "grad_norm": 0.11762084811925888,
+      "learning_rate": 5.3190100256707905e-06,
+      "loss": 0.4892,
+      "step": 768
+    },
+    {
+      "epoch": 1.9371069182389937,
+      "grad_norm": 0.1136779636144638,
+      "learning_rate": 5.288711304409814e-06,
+      "loss": 0.5075,
+      "step": 770
+    },
+    {
+      "epoch": 1.9421383647798742,
+      "grad_norm": 0.11609724909067154,
+      "learning_rate": 5.259914840468416e-06,
+      "loss": 0.5052,
+      "step": 772
+    },
+    {
+      "epoch": 1.9471698113207547,
+      "grad_norm": 0.11565674096345901,
+      "learning_rate": 5.2326225814913e-06,
+      "loss": 0.5054,
+      "step": 774
+    },
+    {
+      "epoch": 1.9522012578616352,
+      "grad_norm": 0.10971004515886307,
+      "learning_rate": 5.206836373386482e-06,
+      "loss": 0.4711,
+      "step": 776
+    },
+    {
+      "epoch": 1.9572327044025157,
+      "grad_norm": 0.11187240481376648,
+      "learning_rate": 5.182557960200441e-06,
+      "loss": 0.4946,
+      "step": 778
+    },
+    {
+      "epoch": 1.9622641509433962,
+      "grad_norm": 0.11195476353168488,
+      "learning_rate": 5.1597889840001635e-06,
+      "loss": 0.4975,
+      "step": 780
+    },
+    {
+      "epoch": 1.9622641509433962,
+      "eval_loss": 0.5697274208068848,
+      "eval_runtime": 411.2337,
+      "eval_samples_per_second": 26.034,
+      "eval_steps_per_second": 0.204,
+      "step": 780
+    },
+    {
+      "epoch": 1.9672955974842767,
+      "grad_norm": 0.11138684302568436,
+      "learning_rate": 5.138530984762087e-06,
+      "loss": 0.4915,
+      "step": 782
+    },
+    {
+      "epoch": 1.9723270440251572,
+      "grad_norm": 0.10923836380243301,
+      "learning_rate": 5.118785400267929e-06,
+      "loss": 0.4855,
+      "step": 784
+    },
+    {
+      "epoch": 1.9773584905660377,
+      "grad_norm": 0.10922150313854218,
+      "learning_rate": 5.100553566007467e-06,
+      "loss": 0.4794,
+      "step": 786
+    },
+    {
+      "epoch": 1.9823899371069182,
+      "grad_norm": 0.10965920239686966,
+      "learning_rate": 5.083836715088188e-06,
+      "loss": 0.4836,
+      "step": 788
+    },
+    {
+      "epoch": 1.9874213836477987,
+      "grad_norm": 0.11357378959655762,
+      "learning_rate": 5.068635978151901e-06,
+      "loss": 0.4942,
+      "step": 790
+    },
+    {
+      "epoch": 1.9924528301886792,
+      "grad_norm": 0.11112317442893982,
+      "learning_rate": 5.0549523832982645e-06,
+      "loss": 0.4939,
+      "step": 792
+    },
+    {
+      "epoch": 1.9974842767295597,
+      "grad_norm": 0.11381904780864716,
+      "learning_rate": 5.042786856015253e-06,
+      "loss": 0.5013,
+      "step": 794
+    },
+    {
+      "epoch": 1.9974842767295597,
+      "step": 794,
+      "total_flos": 946984181301248.0,
+      "train_loss": 0.5561736259862818,
+      "train_runtime": 112418.4712,
+      "train_samples_per_second": 3.619,
+      "train_steps_per_second": 0.007
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 794,
+  "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": 946984181301248.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}