add weights

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "deepseek-ai/deepseek-coder-1.3b-instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 32013,
+  "eos_token_id": 32021,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5504,
+  "max_position_embeddings": 16384,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "factor": 4.0,
+    "type": "linear"
+  },
+  "rope_theta": 100000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 32256
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 32013,
+  "eos_token_id": 32021,
+  "transformers_version": "4.38.2"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:367920bd8acaddfe49c0068b7c0c7f29fa77349cfb5ed005ee5d9293bb7e637a
+size 4986380064

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ca3220441ce821288bab339da81fa4b0f8c148e4639d87a84ed3ddaccf246f0
+size 399532808

model.safetensors.index.json

@@ -0,0 +1,226 @@
+{
+  "metadata": {
+    "total_size": 5385887744
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e80cac6b83b0cd0fdc5758ea86bdc1d2e2e533768654c1ac6c8571e0e18682e
+size 2699039674

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a98b5eeda36641dd33e456332c9b6689766261f6ca2e072a3944dc0409056a9
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac561d5bae52f045ad741f583876902fae946798abbad291a974460e1c9c0b6f
+size 1064

trainer_state.json

@@ -0,0 +1,1741 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 20000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 5.078273773193359,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.8583,
+      "step": 100
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 6.52927303314209,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.7022,
+      "step": 200
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 4.726405620574951,
+      "learning_rate": 1.2e-05,
+      "loss": 1.7109,
+      "step": 300
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 6.379272937774658,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 1.6689,
+      "step": 400
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 3.252293109893799,
+      "learning_rate": 2e-05,
+      "loss": 1.6766,
+      "step": 500
+    },
+    {
+      "epoch": 0.1,
+      "eval_loss": 1.6459439992904663,
+      "eval_runtime": 21.8542,
+      "eval_samples_per_second": 45.758,
+      "eval_steps_per_second": 5.72,
+      "step": 500
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 3.9442427158355713,
+      "learning_rate": 1.9932203389830512e-05,
+      "loss": 1.6865,
+      "step": 600
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 2.5662379264831543,
+      "learning_rate": 1.986440677966102e-05,
+      "loss": 1.6535,
+      "step": 700
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.087454795837402,
+      "learning_rate": 1.9796610169491527e-05,
+      "loss": 1.6463,
+      "step": 800
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 3.5358777046203613,
+      "learning_rate": 1.9728813559322034e-05,
+      "loss": 1.6238,
+      "step": 900
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 4.294543743133545,
+      "learning_rate": 1.9661016949152545e-05,
+      "loss": 1.614,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 1.587148666381836,
+      "eval_runtime": 21.7559,
+      "eval_samples_per_second": 45.965,
+      "eval_steps_per_second": 5.746,
+      "step": 1000
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 4.340688705444336,
+      "learning_rate": 1.9593220338983052e-05,
+      "loss": 1.5889,
+      "step": 1100
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 3.321453094482422,
+      "learning_rate": 1.9525423728813562e-05,
+      "loss": 1.5936,
+      "step": 1200
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 2.8375635147094727,
+      "learning_rate": 1.945762711864407e-05,
+      "loss": 1.5839,
+      "step": 1300
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 4.362390518188477,
+      "learning_rate": 1.938983050847458e-05,
+      "loss": 1.5912,
+      "step": 1400
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 2.9954068660736084,
+      "learning_rate": 1.9322033898305087e-05,
+      "loss": 1.5593,
+      "step": 1500
+    },
+    {
+      "epoch": 0.3,
+      "eval_loss": 1.5585581064224243,
+      "eval_runtime": 21.6908,
+      "eval_samples_per_second": 46.102,
+      "eval_steps_per_second": 5.763,
+      "step": 1500
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 3.2162888050079346,
+      "learning_rate": 1.9254237288135595e-05,
+      "loss": 1.5627,
+      "step": 1600
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 4.054400444030762,
+      "learning_rate": 1.9186440677966102e-05,
+      "loss": 1.5486,
+      "step": 1700
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 3.2316372394561768,
+      "learning_rate": 1.9118644067796613e-05,
+      "loss": 1.536,
+      "step": 1800
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 3.4788625240325928,
+      "learning_rate": 1.905084745762712e-05,
+      "loss": 1.5398,
+      "step": 1900
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.387064218521118,
+      "learning_rate": 1.898305084745763e-05,
+      "loss": 1.5452,
+      "step": 2000
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 1.5381073951721191,
+      "eval_runtime": 21.6995,
+      "eval_samples_per_second": 46.084,
+      "eval_steps_per_second": 5.761,
+      "step": 2000
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 3.577282428741455,
+      "learning_rate": 1.8915254237288138e-05,
+      "loss": 1.5287,
+      "step": 2100
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 2.2378621101379395,
+      "learning_rate": 1.8847457627118645e-05,
+      "loss": 1.5211,
+      "step": 2200
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 3.0354368686676025,
+      "learning_rate": 1.878033898305085e-05,
+      "loss": 1.5209,
+      "step": 2300
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.8990373611450195,
+      "learning_rate": 1.8712542372881358e-05,
+      "loss": 1.5072,
+      "step": 2400
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 2.9740238189697266,
+      "learning_rate": 1.8644745762711865e-05,
+      "loss": 1.496,
+      "step": 2500
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 1.5467579364776611,
+      "eval_runtime": 21.7136,
+      "eval_samples_per_second": 46.054,
+      "eval_steps_per_second": 5.757,
+      "step": 2500
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 2.4562160968780518,
+      "learning_rate": 1.8576949152542373e-05,
+      "loss": 1.5311,
+      "step": 2600
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 2.0434107780456543,
+      "learning_rate": 1.8509152542372883e-05,
+      "loss": 1.5107,
+      "step": 2700
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 3.7302677631378174,
+      "learning_rate": 1.844135593220339e-05,
+      "loss": 1.4883,
+      "step": 2800
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 2.7409582138061523,
+      "learning_rate": 1.83735593220339e-05,
+      "loss": 1.4936,
+      "step": 2900
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 3.0569841861724854,
+      "learning_rate": 1.8305762711864408e-05,
+      "loss": 1.4633,
+      "step": 3000
+    },
+    {
+      "epoch": 0.6,
+      "eval_loss": 1.4889390468597412,
+      "eval_runtime": 21.6749,
+      "eval_samples_per_second": 46.136,
+      "eval_steps_per_second": 5.767,
+      "step": 3000
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 3.209660768508911,
+      "learning_rate": 1.823796610169492e-05,
+      "loss": 1.468,
+      "step": 3100
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 2.617828130722046,
+      "learning_rate": 1.8170169491525426e-05,
+      "loss": 1.4635,
+      "step": 3200
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 3.617861747741699,
+      "learning_rate": 1.8102372881355933e-05,
+      "loss": 1.4716,
+      "step": 3300
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 3.5618486404418945,
+      "learning_rate": 1.803457627118644e-05,
+      "loss": 1.4736,
+      "step": 3400
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 3.6922543048858643,
+      "learning_rate": 1.796677966101695e-05,
+      "loss": 1.4669,
+      "step": 3500
+    },
+    {
+      "epoch": 0.7,
+      "eval_loss": 1.4697989225387573,
+      "eval_runtime": 21.6816,
+      "eval_samples_per_second": 46.122,
+      "eval_steps_per_second": 5.765,
+      "step": 3500
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 2.977830171585083,
+      "learning_rate": 1.789898305084746e-05,
+      "loss": 1.4782,
+      "step": 3600
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 2.5865039825439453,
+      "learning_rate": 1.783118644067797e-05,
+      "loss": 1.4519,
+      "step": 3700
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 2.9079766273498535,
+      "learning_rate": 1.7763389830508476e-05,
+      "loss": 1.4447,
+      "step": 3800
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 2.9517862796783447,
+      "learning_rate": 1.7695593220338983e-05,
+      "loss": 1.4631,
+      "step": 3900
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.2457385063171387,
+      "learning_rate": 1.762779661016949e-05,
+      "loss": 1.4366,
+      "step": 4000
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 1.4445842504501343,
+      "eval_runtime": 21.6792,
+      "eval_samples_per_second": 46.127,
+      "eval_steps_per_second": 5.766,
+      "step": 4000
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 3.206425189971924,
+      "learning_rate": 1.756e-05,
+      "loss": 1.4466,
+      "step": 4100
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 2.559532403945923,
+      "learning_rate": 1.749220338983051e-05,
+      "loss": 1.433,
+      "step": 4200
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 3.243443012237549,
+      "learning_rate": 1.742440677966102e-05,
+      "loss": 1.437,
+      "step": 4300
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 3.06264066696167,
+      "learning_rate": 1.7357288135593222e-05,
+      "loss": 1.4512,
+      "step": 4400
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 3.4852590560913086,
+      "learning_rate": 1.728949152542373e-05,
+      "loss": 1.4121,
+      "step": 4500
+    },
+    {
+      "epoch": 0.9,
+      "eval_loss": 1.4205034971237183,
+      "eval_runtime": 21.6783,
+      "eval_samples_per_second": 46.129,
+      "eval_steps_per_second": 5.766,
+      "step": 4500
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 3.3655240535736084,
+      "learning_rate": 1.722169491525424e-05,
+      "loss": 1.4101,
+      "step": 4600
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 2.9424891471862793,
+      "learning_rate": 1.7154576271186442e-05,
+      "loss": 1.4278,
+      "step": 4700
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 2.7033684253692627,
+      "learning_rate": 1.708677966101695e-05,
+      "loss": 1.4321,
+      "step": 4800
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 2.4086625576019287,
+      "learning_rate": 1.701898305084746e-05,
+      "loss": 1.4152,
+      "step": 4900
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.7739360332489014,
+      "learning_rate": 1.6951186440677967e-05,
+      "loss": 1.3941,
+      "step": 5000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.4043042659759521,
+      "eval_runtime": 21.6957,
+      "eval_samples_per_second": 46.092,
+      "eval_steps_per_second": 5.762,
+      "step": 5000
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 2.722904682159424,
+      "learning_rate": 1.6883389830508478e-05,
+      "loss": 1.3979,
+      "step": 5100
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 2.617483615875244,
+      "learning_rate": 1.6815593220338985e-05,
+      "loss": 1.3741,
+      "step": 5200
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 4.135140419006348,
+      "learning_rate": 1.6747796610169492e-05,
+      "loss": 1.3929,
+      "step": 5300
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 2.5010900497436523,
+      "learning_rate": 1.668e-05,
+      "loss": 1.3895,
+      "step": 5400
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 2.8484292030334473,
+      "learning_rate": 1.661220338983051e-05,
+      "loss": 1.4055,
+      "step": 5500
+    },
+    {
+      "epoch": 1.1,
+      "eval_loss": 1.4005763530731201,
+      "eval_runtime": 21.7476,
+      "eval_samples_per_second": 45.982,
+      "eval_steps_per_second": 5.748,
+      "step": 5500
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 3.469156503677368,
+      "learning_rate": 1.6544406779661017e-05,
+      "loss": 1.3843,
+      "step": 5600
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 2.569080352783203,
+      "learning_rate": 1.6476610169491528e-05,
+      "loss": 1.3812,
+      "step": 5700
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 2.751028299331665,
+      "learning_rate": 1.6408813559322035e-05,
+      "loss": 1.3811,
+      "step": 5800
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 3.277967691421509,
+      "learning_rate": 1.6341016949152542e-05,
+      "loss": 1.3601,
+      "step": 5900
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 2.5392448902130127,
+      "learning_rate": 1.627322033898305e-05,
+      "loss": 1.359,
+      "step": 6000
+    },
+    {
+      "epoch": 1.2,
+      "eval_loss": 1.3665966987609863,
+      "eval_runtime": 21.7115,
+      "eval_samples_per_second": 46.059,
+      "eval_steps_per_second": 5.757,
+      "step": 6000
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 2.700984477996826,
+      "learning_rate": 1.620542372881356e-05,
+      "loss": 1.3541,
+      "step": 6100
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 1.9332221746444702,
+      "learning_rate": 1.6137627118644068e-05,
+      "loss": 1.3674,
+      "step": 6200
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 2.326171636581421,
+      "learning_rate": 1.6069830508474578e-05,
+      "loss": 1.3703,
+      "step": 6300
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 2.8028652667999268,
+      "learning_rate": 1.600203389830509e-05,
+      "loss": 1.3662,
+      "step": 6400
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 3.253483295440674,
+      "learning_rate": 1.5934237288135596e-05,
+      "loss": 1.348,
+      "step": 6500
+    },
+    {
+      "epoch": 1.3,
+      "eval_loss": 1.388239860534668,
+      "eval_runtime": 21.7372,
+      "eval_samples_per_second": 46.004,
+      "eval_steps_per_second": 5.751,
+      "step": 6500
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 2.5033419132232666,
+      "learning_rate": 1.5866440677966103e-05,
+      "loss": 1.3552,
+      "step": 6600
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 3.955854892730713,
+      "learning_rate": 1.579864406779661e-05,
+      "loss": 1.364,
+      "step": 6700
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 6.7678422927856445,
+      "learning_rate": 1.573084745762712e-05,
+      "loss": 1.3657,
+      "step": 6800
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 3.65767502784729,
+      "learning_rate": 1.5663050847457628e-05,
+      "loss": 1.37,
+      "step": 6900
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 3.6031250953674316,
+      "learning_rate": 1.559525423728814e-05,
+      "loss": 1.3703,
+      "step": 7000
+    },
+    {
+      "epoch": 1.4,
+      "eval_loss": 1.40153169631958,
+      "eval_runtime": 21.6996,
+      "eval_samples_per_second": 46.084,
+      "eval_steps_per_second": 5.76,
+      "step": 7000
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 3.184861421585083,
+      "learning_rate": 1.5527457627118646e-05,
+      "loss": 1.3393,
+      "step": 7100
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 2.626770496368408,
+      "learning_rate": 1.546033898305085e-05,
+      "loss": 1.3341,
+      "step": 7200
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 3.0047240257263184,
+      "learning_rate": 1.5392542372881356e-05,
+      "loss": 1.3362,
+      "step": 7300
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 2.881134033203125,
+      "learning_rate": 1.5324745762711867e-05,
+      "loss": 1.3449,
+      "step": 7400
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 3.289036512374878,
+      "learning_rate": 1.5256949152542376e-05,
+      "loss": 1.3317,
+      "step": 7500
+    },
+    {
+      "epoch": 1.5,
+      "eval_loss": 1.372812271118164,
+      "eval_runtime": 21.7039,
+      "eval_samples_per_second": 46.075,
+      "eval_steps_per_second": 5.759,
+      "step": 7500
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 2.3777339458465576,
+      "learning_rate": 1.5189152542372883e-05,
+      "loss": 1.3556,
+      "step": 7600
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 2.7420947551727295,
+      "learning_rate": 1.5121355932203392e-05,
+      "loss": 1.3268,
+      "step": 7700
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 4.065169334411621,
+      "learning_rate": 1.5053559322033899e-05,
+      "loss": 1.3289,
+      "step": 7800
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 2.720052719116211,
+      "learning_rate": 1.498576271186441e-05,
+      "loss": 1.324,
+      "step": 7900
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 2.457838773727417,
+      "learning_rate": 1.4917966101694917e-05,
+      "loss": 1.3361,
+      "step": 8000
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 1.298282265663147,
+      "eval_runtime": 21.7632,
+      "eval_samples_per_second": 45.949,
+      "eval_steps_per_second": 5.744,
+      "step": 8000
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 3.103018045425415,
+      "learning_rate": 1.4850169491525426e-05,
+      "loss": 1.3192,
+      "step": 8100
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 2.3513784408569336,
+      "learning_rate": 1.4782372881355933e-05,
+      "loss": 1.3202,
+      "step": 8200
+    },
+    {
+      "epoch": 1.66,
+      "grad_norm": 2.4736735820770264,
+      "learning_rate": 1.4714576271186442e-05,
+      "loss": 1.3378,
+      "step": 8300
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 2.902289628982544,
+      "learning_rate": 1.464677966101695e-05,
+      "loss": 1.3158,
+      "step": 8400
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 4.001801490783691,
+      "learning_rate": 1.457898305084746e-05,
+      "loss": 1.317,
+      "step": 8500
+    },
+    {
+      "epoch": 1.7,
+      "eval_loss": 1.3023865222930908,
+      "eval_runtime": 21.713,
+      "eval_samples_per_second": 46.055,
+      "eval_steps_per_second": 5.757,
+      "step": 8500
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 3.5500471591949463,
+      "learning_rate": 1.4511186440677967e-05,
+      "loss": 1.3322,
+      "step": 8600
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 5.206698894500732,
+      "learning_rate": 1.4443389830508476e-05,
+      "loss": 1.3038,
+      "step": 8700
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 3.068844795227051,
+      "learning_rate": 1.4375593220338983e-05,
+      "loss": 1.3209,
+      "step": 8800
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 2.7392385005950928,
+      "learning_rate": 1.4307796610169494e-05,
+      "loss": 1.3151,
+      "step": 8900
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 2.984192132949829,
+      "learning_rate": 1.4240000000000001e-05,
+      "loss": 1.3201,
+      "step": 9000
+    },
+    {
+      "epoch": 1.8,
+      "eval_loss": 1.2849023342132568,
+      "eval_runtime": 21.7137,
+      "eval_samples_per_second": 46.054,
+      "eval_steps_per_second": 5.757,
+      "step": 9000
+    },
+    {
+      "epoch": 1.82,
+      "grad_norm": 2.816089630126953,
+      "learning_rate": 1.417220338983051e-05,
+      "loss": 1.3105,
+      "step": 9100
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 2.776275634765625,
+      "learning_rate": 1.4104406779661017e-05,
+      "loss": 1.3145,
+      "step": 9200
+    },
+    {
+      "epoch": 1.86,
+      "grad_norm": 3.164463758468628,
+      "learning_rate": 1.4036610169491528e-05,
+      "loss": 1.3104,
+      "step": 9300
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 4.110715866088867,
+      "learning_rate": 1.3968813559322035e-05,
+      "loss": 1.2873,
+      "step": 9400
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 3.3705735206604004,
+      "learning_rate": 1.3901016949152544e-05,
+      "loss": 1.2955,
+      "step": 9500
+    },
+    {
+      "epoch": 1.9,
+      "eval_loss": 1.317952275276184,
+      "eval_runtime": 21.6894,
+      "eval_samples_per_second": 46.105,
+      "eval_steps_per_second": 5.763,
+      "step": 9500
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 2.7719411849975586,
+      "learning_rate": 1.3833220338983051e-05,
+      "loss": 1.2867,
+      "step": 9600
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 3.694045305252075,
+      "learning_rate": 1.376542372881356e-05,
+      "loss": 1.3052,
+      "step": 9700
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 3.4335978031158447,
+      "learning_rate": 1.3697627118644067e-05,
+      "loss": 1.2788,
+      "step": 9800
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 2.300137758255005,
+      "learning_rate": 1.3629830508474578e-05,
+      "loss": 1.2964,
+      "step": 9900
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.1676926612854004,
+      "learning_rate": 1.3562033898305085e-05,
+      "loss": 1.2852,
+      "step": 10000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.3348548412322998,
+      "eval_runtime": 21.6828,
+      "eval_samples_per_second": 46.12,
+      "eval_steps_per_second": 5.765,
+      "step": 10000
+    },
+    {
+      "epoch": 2.02,
+      "grad_norm": 2.558415651321411,
+      "learning_rate": 1.3494237288135594e-05,
+      "loss": 1.2674,
+      "step": 10100
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 2.86045241355896,
+      "learning_rate": 1.3426440677966105e-05,
+      "loss": 1.2711,
+      "step": 10200
+    },
+    {
+      "epoch": 2.06,
+      "grad_norm": 4.301458358764648,
+      "learning_rate": 1.3358644067796612e-05,
+      "loss": 1.2672,
+      "step": 10300
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 2.699399709701538,
+      "learning_rate": 1.329084745762712e-05,
+      "loss": 1.2781,
+      "step": 10400
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 2.920149087905884,
+      "learning_rate": 1.3223050847457628e-05,
+      "loss": 1.2323,
+      "step": 10500
+    },
+    {
+      "epoch": 2.1,
+      "eval_loss": 1.2642160654067993,
+      "eval_runtime": 21.6839,
+      "eval_samples_per_second": 46.117,
+      "eval_steps_per_second": 5.765,
+      "step": 10500
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 3.0505363941192627,
+      "learning_rate": 1.3155254237288137e-05,
+      "loss": 1.2486,
+      "step": 10600
+    },
+    {
+      "epoch": 2.14,
+      "grad_norm": 3.141021490097046,
+      "learning_rate": 1.3087457627118644e-05,
+      "loss": 1.2725,
+      "step": 10700
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 2.433058977127075,
+      "learning_rate": 1.3019661016949155e-05,
+      "loss": 1.2387,
+      "step": 10800
+    },
+    {
+      "epoch": 2.18,
+      "grad_norm": 2.907503366470337,
+      "learning_rate": 1.2951864406779662e-05,
+      "loss": 1.2391,
+      "step": 10900
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 2.7510807514190674,
+      "learning_rate": 1.2884067796610171e-05,
+      "loss": 1.2601,
+      "step": 11000
+    },
+    {
+      "epoch": 2.2,
+      "eval_loss": 1.3154401779174805,
+      "eval_runtime": 21.6833,
+      "eval_samples_per_second": 46.119,
+      "eval_steps_per_second": 5.765,
+      "step": 11000
+    },
+    {
+      "epoch": 2.22,
+      "grad_norm": 4.341352462768555,
+      "learning_rate": 1.2816949152542375e-05,
+      "loss": 1.2722,
+      "step": 11100
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 3.5941874980926514,
+      "learning_rate": 1.2749152542372882e-05,
+      "loss": 1.2785,
+      "step": 11200
+    },
+    {
+      "epoch": 2.26,
+      "grad_norm": 2.437255382537842,
+      "learning_rate": 1.2681355932203391e-05,
+      "loss": 1.224,
+      "step": 11300
+    },
+    {
+      "epoch": 2.28,
+      "grad_norm": 2.8359203338623047,
+      "learning_rate": 1.2613559322033899e-05,
+      "loss": 1.2363,
+      "step": 11400
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 2.7164149284362793,
+      "learning_rate": 1.2545762711864409e-05,
+      "loss": 1.2596,
+      "step": 11500
+    },
+    {
+      "epoch": 2.3,
+      "eval_loss": 1.3095141649246216,
+      "eval_runtime": 21.6842,
+      "eval_samples_per_second": 46.117,
+      "eval_steps_per_second": 5.765,
+      "step": 11500
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 3.826754570007324,
+      "learning_rate": 1.2477966101694916e-05,
+      "loss": 1.2449,
+      "step": 11600
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 3.325650691986084,
+      "learning_rate": 1.2410169491525425e-05,
+      "loss": 1.2449,
+      "step": 11700
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 3.709676504135132,
+      "learning_rate": 1.2342372881355933e-05,
+      "loss": 1.2362,
+      "step": 11800
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 3.0213212966918945,
+      "learning_rate": 1.2274576271186443e-05,
+      "loss": 1.2403,
+      "step": 11900
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 3.0036745071411133,
+      "learning_rate": 1.220677966101695e-05,
+      "loss": 1.2504,
+      "step": 12000
+    },
+    {
+      "epoch": 2.4,
+      "eval_loss": 1.2542531490325928,
+      "eval_runtime": 21.677,
+      "eval_samples_per_second": 46.132,
+      "eval_steps_per_second": 5.766,
+      "step": 12000
+    },
+    {
+      "epoch": 2.42,
+      "grad_norm": 3.031303882598877,
+      "learning_rate": 1.213898305084746e-05,
+      "loss": 1.2479,
+      "step": 12100
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 2.805032968521118,
+      "learning_rate": 1.2071864406779664e-05,
+      "loss": 1.2266,
+      "step": 12200
+    },
+    {
+      "epoch": 2.46,
+      "grad_norm": 3.027392625808716,
+      "learning_rate": 1.200406779661017e-05,
+      "loss": 1.2298,
+      "step": 12300
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 3.9545884132385254,
+      "learning_rate": 1.193627118644068e-05,
+      "loss": 1.2506,
+      "step": 12400
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 2.7534937858581543,
+      "learning_rate": 1.1868474576271187e-05,
+      "loss": 1.2424,
+      "step": 12500
+    },
+    {
+      "epoch": 2.5,
+      "eval_loss": 1.274129867553711,
+      "eval_runtime": 21.6835,
+      "eval_samples_per_second": 46.118,
+      "eval_steps_per_second": 5.765,
+      "step": 12500
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 3.8661746978759766,
+      "learning_rate": 1.1800677966101698e-05,
+      "loss": 1.2244,
+      "step": 12600
+    },
+    {
+      "epoch": 2.54,
+      "grad_norm": 3.3711798191070557,
+      "learning_rate": 1.1732881355932205e-05,
+      "loss": 1.218,
+      "step": 12700
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 2.4355905055999756,
+      "learning_rate": 1.1665084745762714e-05,
+      "loss": 1.2145,
+      "step": 12800
+    },
+    {
+      "epoch": 2.58,
+      "grad_norm": 3.467618942260742,
+      "learning_rate": 1.1597288135593221e-05,
+      "loss": 1.2331,
+      "step": 12900
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 2.9236645698547363,
+      "learning_rate": 1.152949152542373e-05,
+      "loss": 1.2457,
+      "step": 13000
+    },
+    {
+      "epoch": 2.6,
+      "eval_loss": 1.278497576713562,
+      "eval_runtime": 21.6894,
+      "eval_samples_per_second": 46.105,
+      "eval_steps_per_second": 5.763,
+      "step": 13000
+    },
+    {
+      "epoch": 2.62,
+      "grad_norm": 2.343590259552002,
+      "learning_rate": 1.1461694915254237e-05,
+      "loss": 1.227,
+      "step": 13100
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 3.2813720703125,
+      "learning_rate": 1.1393898305084748e-05,
+      "loss": 1.2429,
+      "step": 13200
+    },
+    {
+      "epoch": 2.66,
+      "grad_norm": 3.157639503479004,
+      "learning_rate": 1.1326101694915255e-05,
+      "loss": 1.2018,
+      "step": 13300
+    },
+    {
+      "epoch": 2.68,
+      "grad_norm": 3.017834424972534,
+      "learning_rate": 1.1258305084745764e-05,
+      "loss": 1.2358,
+      "step": 13400
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 2.672147274017334,
+      "learning_rate": 1.1190508474576271e-05,
+      "loss": 1.2224,
+      "step": 13500
+    },
+    {
+      "epoch": 2.7,
+      "eval_loss": 1.2449040412902832,
+      "eval_runtime": 21.7033,
+      "eval_samples_per_second": 46.076,
+      "eval_steps_per_second": 5.759,
+      "step": 13500
+    },
+    {
+      "epoch": 2.72,
+      "grad_norm": 3.6956965923309326,
+      "learning_rate": 1.1122711864406782e-05,
+      "loss": 1.2373,
+      "step": 13600
+    },
+    {
+      "epoch": 2.74,
+      "grad_norm": 3.9109997749328613,
+      "learning_rate": 1.1054915254237289e-05,
+      "loss": 1.2181,
+      "step": 13700
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 2.4544878005981445,
+      "learning_rate": 1.0987118644067798e-05,
+      "loss": 1.2264,
+      "step": 13800
+    },
+    {
+      "epoch": 2.78,
+      "grad_norm": 3.372176170349121,
+      "learning_rate": 1.0919322033898305e-05,
+      "loss": 1.2231,
+      "step": 13900
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 2.1014392375946045,
+      "learning_rate": 1.0851525423728814e-05,
+      "loss": 1.2189,
+      "step": 14000
+    },
+    {
+      "epoch": 2.8,
+      "eval_loss": 1.2467758655548096,
+      "eval_runtime": 21.68,
+      "eval_samples_per_second": 46.125,
+      "eval_steps_per_second": 5.766,
+      "step": 14000
+    },
+    {
+      "epoch": 2.82,
+      "grad_norm": 3.0673794746398926,
+      "learning_rate": 1.0783728813559321e-05,
+      "loss": 1.2277,
+      "step": 14100
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 3.052077531814575,
+      "learning_rate": 1.0715932203389832e-05,
+      "loss": 1.2175,
+      "step": 14200
+    },
+    {
+      "epoch": 2.86,
+      "grad_norm": 3.2878353595733643,
+      "learning_rate": 1.0648135593220339e-05,
+      "loss": 1.1976,
+      "step": 14300
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 3.1332175731658936,
+      "learning_rate": 1.0580338983050848e-05,
+      "loss": 1.2191,
+      "step": 14400
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 3.573296308517456,
+      "learning_rate": 1.0512542372881355e-05,
+      "loss": 1.2118,
+      "step": 14500
+    },
+    {
+      "epoch": 2.9,
+      "eval_loss": 1.2437331676483154,
+      "eval_runtime": 21.7028,
+      "eval_samples_per_second": 46.077,
+      "eval_steps_per_second": 5.76,
+      "step": 14500
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 2.835487127304077,
+      "learning_rate": 1.0444745762711866e-05,
+      "loss": 1.2057,
+      "step": 14600
+    },
+    {
+      "epoch": 2.94,
+      "grad_norm": 3.7973036766052246,
+      "learning_rate": 1.0376949152542373e-05,
+      "loss": 1.2043,
+      "step": 14700
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 3.0734457969665527,
+      "learning_rate": 1.0309152542372882e-05,
+      "loss": 1.1986,
+      "step": 14800
+    },
+    {
+      "epoch": 2.98,
+      "grad_norm": 2.8893818855285645,
+      "learning_rate": 1.0241355932203391e-05,
+      "loss": 1.2152,
+      "step": 14900
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.576925039291382,
+      "learning_rate": 1.01735593220339e-05,
+      "loss": 1.2324,
+      "step": 15000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.2094933986663818,
+      "eval_runtime": 21.6901,
+      "eval_samples_per_second": 46.104,
+      "eval_steps_per_second": 5.763,
+      "step": 15000
+    },
+    {
+      "epoch": 3.02,
+      "grad_norm": 2.6094210147857666,
+      "learning_rate": 1.0105762711864409e-05,
+      "loss": 1.1757,
+      "step": 15100
+    },
+    {
+      "epoch": 3.04,
+      "grad_norm": 3.7070980072021484,
+      "learning_rate": 1.0037966101694916e-05,
+      "loss": 1.1799,
+      "step": 15200
+    },
+    {
+      "epoch": 3.06,
+      "grad_norm": 3.4685747623443604,
+      "learning_rate": 9.970169491525425e-06,
+      "loss": 1.1715,
+      "step": 15300
+    },
+    {
+      "epoch": 3.08,
+      "grad_norm": 2.8845009803771973,
+      "learning_rate": 9.902372881355932e-06,
+      "loss": 1.1536,
+      "step": 15400
+    },
+    {
+      "epoch": 3.1,
+      "grad_norm": 3.583442211151123,
+      "learning_rate": 9.834576271186441e-06,
+      "loss": 1.1663,
+      "step": 15500
+    },
+    {
+      "epoch": 3.1,
+      "eval_loss": 1.2352399826049805,
+      "eval_runtime": 21.7081,
+      "eval_samples_per_second": 46.066,
+      "eval_steps_per_second": 5.758,
+      "step": 15500
+    },
+    {
+      "epoch": 3.12,
+      "grad_norm": 3.343341827392578,
+      "learning_rate": 9.76677966101695e-06,
+      "loss": 1.169,
+      "step": 15600
+    },
+    {
+      "epoch": 3.14,
+      "grad_norm": 3.7276506423950195,
+      "learning_rate": 9.698983050847457e-06,
+      "loss": 1.16,
+      "step": 15700
+    },
+    {
+      "epoch": 3.16,
+      "grad_norm": 2.9194743633270264,
+      "learning_rate": 9.631864406779662e-06,
+      "loss": 1.1731,
+      "step": 15800
+    },
+    {
+      "epoch": 3.18,
+      "grad_norm": 3.365588426589966,
+      "learning_rate": 9.56406779661017e-06,
+      "loss": 1.1727,
+      "step": 15900
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 4.017807483673096,
+      "learning_rate": 9.49627118644068e-06,
+      "loss": 1.153,
+      "step": 16000
+    },
+    {
+      "epoch": 3.2,
+      "eval_loss": 1.2391220331192017,
+      "eval_runtime": 21.7087,
+      "eval_samples_per_second": 46.064,
+      "eval_steps_per_second": 5.758,
+      "step": 16000
+    },
+    {
+      "epoch": 3.22,
+      "grad_norm": 3.4895777702331543,
+      "learning_rate": 9.428474576271187e-06,
+      "loss": 1.1423,
+      "step": 16100
+    },
+    {
+      "epoch": 3.24,
+      "grad_norm": 3.7175400257110596,
+      "learning_rate": 9.360677966101696e-06,
+      "loss": 1.1687,
+      "step": 16200
+    },
+    {
+      "epoch": 3.26,
+      "grad_norm": 4.337020397186279,
+      "learning_rate": 9.292881355932204e-06,
+      "loss": 1.1395,
+      "step": 16300
+    },
+    {
+      "epoch": 3.28,
+      "grad_norm": 2.255091905593872,
+      "learning_rate": 9.225084745762712e-06,
+      "loss": 1.1648,
+      "step": 16400
+    },
+    {
+      "epoch": 3.3,
+      "grad_norm": 2.8030898571014404,
+      "learning_rate": 9.15728813559322e-06,
+      "loss": 1.1507,
+      "step": 16500
+    },
+    {
+      "epoch": 3.3,
+      "eval_loss": 1.2618576288223267,
+      "eval_runtime": 21.7474,
+      "eval_samples_per_second": 45.982,
+      "eval_steps_per_second": 5.748,
+      "step": 16500
+    },
+    {
+      "epoch": 3.32,
+      "grad_norm": 3.8894705772399902,
+      "learning_rate": 9.08949152542373e-06,
+      "loss": 1.1533,
+      "step": 16600
+    },
+    {
+      "epoch": 3.34,
+      "grad_norm": 3.553032398223877,
+      "learning_rate": 9.021694915254238e-06,
+      "loss": 1.1472,
+      "step": 16700
+    },
+    {
+      "epoch": 3.36,
+      "grad_norm": 4.201476097106934,
+      "learning_rate": 8.953898305084746e-06,
+      "loss": 1.1577,
+      "step": 16800
+    },
+    {
+      "epoch": 3.38,
+      "grad_norm": 3.702571153640747,
+      "learning_rate": 8.886101694915255e-06,
+      "loss": 1.1598,
+      "step": 16900
+    },
+    {
+      "epoch": 3.4,
+      "grad_norm": 4.799776077270508,
+      "learning_rate": 8.818305084745764e-06,
+      "loss": 1.1653,
+      "step": 17000
+    },
+    {
+      "epoch": 3.4,
+      "eval_loss": 1.236145257949829,
+      "eval_runtime": 21.7006,
+      "eval_samples_per_second": 46.082,
+      "eval_steps_per_second": 5.76,
+      "step": 17000
+    },
+    {
+      "epoch": 3.42,
+      "grad_norm": 3.39278244972229,
+      "learning_rate": 8.75050847457627e-06,
+      "loss": 1.1573,
+      "step": 17100
+    },
+    {
+      "epoch": 3.44,
+      "grad_norm": 3.210745334625244,
+      "learning_rate": 8.68271186440678e-06,
+      "loss": 1.1597,
+      "step": 17200
+    },
+    {
+      "epoch": 3.46,
+      "grad_norm": 3.6098508834838867,
+      "learning_rate": 8.614915254237289e-06,
+      "loss": 1.1487,
+      "step": 17300
+    },
+    {
+      "epoch": 3.48,
+      "grad_norm": 2.9269042015075684,
+      "learning_rate": 8.547118644067798e-06,
+      "loss": 1.1511,
+      "step": 17400
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 2.969214677810669,
+      "learning_rate": 8.479322033898306e-06,
+      "loss": 1.1619,
+      "step": 17500
+    },
+    {
+      "epoch": 3.5,
+      "eval_loss": 1.2679368257522583,
+      "eval_runtime": 21.6891,
+      "eval_samples_per_second": 46.106,
+      "eval_steps_per_second": 5.763,
+      "step": 17500
+    },
+    {
+      "epoch": 3.52,
+      "grad_norm": 3.1029062271118164,
+      "learning_rate": 8.411525423728815e-06,
+      "loss": 1.1475,
+      "step": 17600
+    },
+    {
+      "epoch": 3.54,
+      "grad_norm": 3.8454771041870117,
+      "learning_rate": 8.343728813559323e-06,
+      "loss": 1.1606,
+      "step": 17700
+    },
+    {
+      "epoch": 3.56,
+      "grad_norm": 3.526176929473877,
+      "learning_rate": 8.275932203389832e-06,
+      "loss": 1.1378,
+      "step": 17800
+    },
+    {
+      "epoch": 3.58,
+      "grad_norm": 3.3350830078125,
+      "learning_rate": 8.20813559322034e-06,
+      "loss": 1.1394,
+      "step": 17900
+    },
+    {
+      "epoch": 3.6,
+      "grad_norm": 3.0847814083099365,
+      "learning_rate": 8.140338983050848e-06,
+      "loss": 1.1326,
+      "step": 18000
+    },
+    {
+      "epoch": 3.6,
+      "eval_loss": 1.1844274997711182,
+      "eval_runtime": 21.679,
+      "eval_samples_per_second": 46.128,
+      "eval_steps_per_second": 5.766,
+      "step": 18000
+    },
+    {
+      "epoch": 3.62,
+      "grad_norm": 3.5144150257110596,
+      "learning_rate": 8.072542372881357e-06,
+      "loss": 1.1651,
+      "step": 18100
+    },
+    {
+      "epoch": 3.64,
+      "grad_norm": 3.8517796993255615,
+      "learning_rate": 8.004745762711866e-06,
+      "loss": 1.141,
+      "step": 18200
+    },
+    {
+      "epoch": 3.66,
+      "grad_norm": 3.909298896789551,
+      "learning_rate": 7.936949152542374e-06,
+      "loss": 1.1452,
+      "step": 18300
+    },
+    {
+      "epoch": 3.68,
+      "grad_norm": 4.035452365875244,
+      "learning_rate": 7.869152542372882e-06,
+      "loss": 1.1231,
+      "step": 18400
+    },
+    {
+      "epoch": 3.7,
+      "grad_norm": 4.456254005432129,
+      "learning_rate": 7.80135593220339e-06,
+      "loss": 1.1399,
+      "step": 18500
+    },
+    {
+      "epoch": 3.7,
+      "eval_loss": 1.1855617761611938,
+      "eval_runtime": 21.7513,
+      "eval_samples_per_second": 45.974,
+      "eval_steps_per_second": 5.747,
+      "step": 18500
+    },
+    {
+      "epoch": 3.72,
+      "grad_norm": 3.6256027221679688,
+      "learning_rate": 7.7335593220339e-06,
+      "loss": 1.1358,
+      "step": 18600
+    },
+    {
+      "epoch": 3.74,
+      "grad_norm": 3.213271379470825,
+      "learning_rate": 7.665762711864407e-06,
+      "loss": 1.1656,
+      "step": 18700
+    },
+    {
+      "epoch": 3.76,
+      "grad_norm": 3.707228660583496,
+      "learning_rate": 7.597966101694916e-06,
+      "loss": 1.1242,
+      "step": 18800
+    },
+    {
+      "epoch": 3.78,
+      "grad_norm": 4.290109634399414,
+      "learning_rate": 7.530169491525425e-06,
+      "loss": 1.1259,
+      "step": 18900
+    },
+    {
+      "epoch": 3.8,
+      "grad_norm": 3.573901653289795,
+      "learning_rate": 7.462372881355933e-06,
+      "loss": 1.1479,
+      "step": 19000
+    },
+    {
+      "epoch": 3.8,
+      "eval_loss": 1.2305423021316528,
+      "eval_runtime": 21.7032,
+      "eval_samples_per_second": 46.076,
+      "eval_steps_per_second": 5.76,
+      "step": 19000
+    },
+    {
+      "epoch": 3.82,
+      "grad_norm": 2.7192249298095703,
+      "learning_rate": 7.394576271186441e-06,
+      "loss": 1.1305,
+      "step": 19100
+    },
+    {
+      "epoch": 3.84,
+      "grad_norm": 3.500718355178833,
+      "learning_rate": 7.32677966101695e-06,
+      "loss": 1.1393,
+      "step": 19200
+    },
+    {
+      "epoch": 3.86,
+      "grad_norm": 3.137812852859497,
+      "learning_rate": 7.258983050847458e-06,
+      "loss": 1.1469,
+      "step": 19300
+    },
+    {
+      "epoch": 3.88,
+      "grad_norm": 3.7159972190856934,
+      "learning_rate": 7.191186440677967e-06,
+      "loss": 1.1334,
+      "step": 19400
+    },
+    {
+      "epoch": 3.9,
+      "grad_norm": 3.60858416557312,
+      "learning_rate": 7.123389830508475e-06,
+      "loss": 1.1508,
+      "step": 19500
+    },
+    {
+      "epoch": 3.9,
+      "eval_loss": 1.2171376943588257,
+      "eval_runtime": 21.677,
+      "eval_samples_per_second": 46.132,
+      "eval_steps_per_second": 5.766,
+      "step": 19500
+    },
+    {
+      "epoch": 3.92,
+      "grad_norm": 3.1851789951324463,
+      "learning_rate": 7.055593220338983e-06,
+      "loss": 1.1485,
+      "step": 19600
+    },
+    {
+      "epoch": 3.94,
+      "grad_norm": 4.118582248687744,
+      "learning_rate": 6.987796610169492e-06,
+      "loss": 1.1243,
+      "step": 19700
+    },
+    {
+      "epoch": 3.96,
+      "grad_norm": 2.8532917499542236,
+      "learning_rate": 6.92e-06,
+      "loss": 1.1052,
+      "step": 19800
+    },
+    {
+      "epoch": 3.98,
+      "grad_norm": 4.4881815910339355,
+      "learning_rate": 6.852881355932204e-06,
+      "loss": 1.1387,
+      "step": 19900
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.3558459281921387,
+      "learning_rate": 6.785084745762712e-06,
+      "loss": 1.1294,
+      "step": 20000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.1705737113952637,
+      "eval_runtime": 21.6721,
+      "eval_samples_per_second": 46.142,
+      "eval_steps_per_second": 5.768,
+      "step": 20000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 30000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 9.4402189983744e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecc8826a21247a9b8aa24df86ce4655638c6fd92f1a6a4209e083f8899dbc7e7
+size 4920