Training in progress, step 2000, checkpoint

checkpoint-2000/config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "PhiForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 50256,
+  "dtype": "bfloat16",
+  "embd_pdrop": 0.0,
+  "eos_token_id": 50256,
+  "hidden_act": "gelu_new",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 10240,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "phi",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "partial_rotary_factor": 0.4,
+  "qk_layernorm": false,
+  "resid_pdrop": 0.1,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
+  "use_cache": true,
+  "vocab_size": 51200
+}

checkpoint-2000/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.57.1"
+}

checkpoint-2000/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8350f0e048044517070d401a44342453b83d01d030a7b62289bbbbb836134939
+size 4995584848

checkpoint-2000/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e559dcc3a611d557420b7e14eab25ab7febee9f46c61f3d493f6031bfdb0c00
+size 563833008

checkpoint-2000/model.safetensors.index.json

@@ -0,0 +1,461 @@
+{
+  "metadata": {
+    "total_parameters": 2779683840,
+    "total_size": 5559367680
+  },
+  "weight_map": {
+    "lm_head.bias": "model-00002-of-00002.safetensors",
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.final_layernorm.bias": "model-00002-of-00002.safetensors",
+    "model.final_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.dense.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.dense.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.dense.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.dense.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors"
+  }
+}

checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2ec1f60142f46b3cab2c6de1de478355d438d7e8cdc9e7da07bbd6dac52731e
+size 10471087

checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f8a0a178f9ed8b76d0f7e29b0405fe2a4345ae9a508a794d1ecd9e4047f52af
+size 14645

checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:197cfcfbf9a36f4f36efb39330b481554a65e22895ce4f427a55d7698d737749
+size 1465

checkpoint-2000/trainer_state.json

@@ -0,0 +1,1434 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005,
+      "grad_norm": 348.0,
+      "learning_rate": 9.000000000000001e-07,
+      "loss": 2.5297,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 552.0,
+      "learning_rate": 1.9000000000000002e-06,
+      "loss": 2.4797,
+      "step": 20
+    },
+    {
+      "epoch": 0.015,
+      "grad_norm": 260.0,
+      "learning_rate": 2.9e-06,
+      "loss": 2.4797,
+      "step": 30
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 266.0,
+      "learning_rate": 3.900000000000001e-06,
+      "loss": 2.4797,
+      "step": 40
+    },
+    {
+      "epoch": 0.025,
+      "grad_norm": 292.0,
+      "learning_rate": 4.9000000000000005e-06,
+      "loss": 2.3375,
+      "step": 50
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 234.0,
+      "learning_rate": 5.9e-06,
+      "loss": 2.2234,
+      "step": 60
+    },
+    {
+      "epoch": 0.035,
+      "grad_norm": 149.0,
+      "learning_rate": 6.9e-06,
+      "loss": 1.943,
+      "step": 70
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 120.0,
+      "learning_rate": 7.9e-06,
+      "loss": 1.7836,
+      "step": 80
+    },
+    {
+      "epoch": 0.045,
+      "grad_norm": 191.0,
+      "learning_rate": 8.900000000000001e-06,
+      "loss": 1.607,
+      "step": 90
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 131.0,
+      "learning_rate": 9.9e-06,
+      "loss": 1.4055,
+      "step": 100
+    },
+    {
+      "epoch": 0.055,
+      "grad_norm": 213.0,
+      "learning_rate": 1.0900000000000002e-05,
+      "loss": 1.3477,
+      "step": 110
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 104.5,
+      "learning_rate": 1.1900000000000001e-05,
+      "loss": 1.225,
+      "step": 120
+    },
+    {
+      "epoch": 0.065,
+      "grad_norm": 160.0,
+      "learning_rate": 1.2900000000000002e-05,
+      "loss": 1.1309,
+      "step": 130
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 73.0,
+      "learning_rate": 1.39e-05,
+      "loss": 1.0074,
+      "step": 140
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 44.0,
+      "learning_rate": 1.4900000000000001e-05,
+      "loss": 0.977,
+      "step": 150
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 36.75,
+      "learning_rate": 1.5900000000000004e-05,
+      "loss": 0.8699,
+      "step": 160
+    },
+    {
+      "epoch": 0.085,
+      "grad_norm": 20.5,
+      "learning_rate": 1.69e-05,
+      "loss": 0.773,
+      "step": 170
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 20.25,
+      "learning_rate": 1.79e-05,
+      "loss": 0.6977,
+      "step": 180
+    },
+    {
+      "epoch": 0.095,
+      "grad_norm": 64.5,
+      "learning_rate": 1.8900000000000002e-05,
+      "loss": 0.7164,
+      "step": 190
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 25.625,
+      "learning_rate": 1.9900000000000003e-05,
+      "loss": 0.6656,
+      "step": 200
+    },
+    {
+      "epoch": 0.105,
+      "grad_norm": 15.375,
+      "learning_rate": 1.9998766324816606e-05,
+      "loss": 0.5887,
+      "step": 210
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 19.625,
+      "learning_rate": 1.9994502159417576e-05,
+      "loss": 0.5699,
+      "step": 220
+    },
+    {
+      "epoch": 0.115,
+      "grad_norm": 28.125,
+      "learning_rate": 1.9987193571841865e-05,
+      "loss": 0.5387,
+      "step": 230
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 21.25,
+      "learning_rate": 1.9976842788356054e-05,
+      "loss": 0.5301,
+      "step": 240
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 12.8125,
+      "learning_rate": 1.9963452961909065e-05,
+      "loss": 0.541,
+      "step": 250
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 12.25,
+      "learning_rate": 1.9947028171171742e-05,
+      "loss": 0.5219,
+      "step": 260
+    },
+    {
+      "epoch": 0.135,
+      "grad_norm": 10.25,
+      "learning_rate": 1.9927573419294456e-05,
+      "loss": 0.5066,
+      "step": 270
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 10.625,
+      "learning_rate": 1.990509463238309e-05,
+      "loss": 0.4719,
+      "step": 280
+    },
+    {
+      "epoch": 0.145,
+      "grad_norm": 23.25,
+      "learning_rate": 1.9879598657693894e-05,
+      "loss": 0.474,
+      "step": 290
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 8.8125,
+      "learning_rate": 1.985109326154774e-05,
+      "loss": 0.485,
+      "step": 300
+    },
+    {
+      "epoch": 0.155,
+      "grad_norm": 12.9375,
+      "learning_rate": 1.981958712696444e-05,
+      "loss": 0.4543,
+      "step": 310
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 14.0625,
+      "learning_rate": 1.9785089851017788e-05,
+      "loss": 0.434,
+      "step": 320
+    },
+    {
+      "epoch": 0.165,
+      "grad_norm": 20.375,
+      "learning_rate": 1.974761194191222e-05,
+      "loss": 0.4443,
+      "step": 330
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 12.875,
+      "learning_rate": 1.970716481578191e-05,
+      "loss": 0.4527,
+      "step": 340
+    },
+    {
+      "epoch": 0.175,
+      "grad_norm": 10.8125,
+      "learning_rate": 1.9663760793213297e-05,
+      "loss": 0.4523,
+      "step": 350
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 10.3125,
+      "learning_rate": 1.9617413095492114e-05,
+      "loss": 0.4791,
+      "step": 360
+    },
+    {
+      "epoch": 0.185,
+      "grad_norm": 8.8125,
+      "learning_rate": 1.956813584057608e-05,
+      "loss": 0.4262,
+      "step": 370
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 18.375,
+      "learning_rate": 1.9515944038794384e-05,
+      "loss": 0.4195,
+      "step": 380
+    },
+    {
+      "epoch": 0.195,
+      "grad_norm": 5.375,
+      "learning_rate": 1.9460853588275454e-05,
+      "loss": 0.4141,
+      "step": 390
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 9.75,
+      "learning_rate": 1.940288127010419e-05,
+      "loss": 0.4182,
+      "step": 400
+    },
+    {
+      "epoch": 0.205,
+      "grad_norm": 15.375,
+      "learning_rate": 1.9342044743210295e-05,
+      "loss": 0.3795,
+      "step": 410
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 10.4375,
+      "learning_rate": 1.92783625389892e-05,
+      "loss": 0.4021,
+      "step": 420
+    },
+    {
+      "epoch": 0.215,
+      "grad_norm": 10.9375,
+      "learning_rate": 1.9211854055657216e-05,
+      "loss": 0.4043,
+      "step": 430
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 6.125,
+      "learning_rate": 1.9142539552342638e-05,
+      "loss": 0.3889,
+      "step": 440
+    },
+    {
+      "epoch": 0.225,
+      "grad_norm": 6.3125,
+      "learning_rate": 1.907044014291465e-05,
+      "loss": 0.3758,
+      "step": 450
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 12.5625,
+      "learning_rate": 1.8995577789551806e-05,
+      "loss": 0.3789,
+      "step": 460
+    },
+    {
+      "epoch": 0.235,
+      "grad_norm": 62.0,
+      "learning_rate": 1.8917975296052143e-05,
+      "loss": 0.3867,
+      "step": 470
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 6.09375,
+      "learning_rate": 1.8837656300886937e-05,
+      "loss": 0.3713,
+      "step": 480
+    },
+    {
+      "epoch": 0.245,
+      "grad_norm": 7.40625,
+      "learning_rate": 1.875464527000018e-05,
+      "loss": 0.3877,
+      "step": 490
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 6.65625,
+      "learning_rate": 1.866896748935603e-05,
+      "loss": 0.3906,
+      "step": 500
+    },
+    {
+      "epoch": 0.255,
+      "grad_norm": 9.875,
+      "learning_rate": 1.858064905723645e-05,
+      "loss": 0.3668,
+      "step": 510
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 6.8125,
+      "learning_rate": 1.8489716876291417e-05,
+      "loss": 0.3834,
+      "step": 520
+    },
+    {
+      "epoch": 0.265,
+      "grad_norm": 5.875,
+      "learning_rate": 1.8396198645344133e-05,
+      "loss": 0.3752,
+      "step": 530
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 9.625,
+      "learning_rate": 1.8300122850953678e-05,
+      "loss": 0.3721,
+      "step": 540
+    },
+    {
+      "epoch": 0.275,
+      "grad_norm": 12.75,
+      "learning_rate": 1.8201518758737726e-05,
+      "loss": 0.3787,
+      "step": 550
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 6.0625,
+      "learning_rate": 1.8100416404457962e-05,
+      "loss": 0.3529,
+      "step": 560
+    },
+    {
+      "epoch": 0.285,
+      "grad_norm": 7.375,
+      "learning_rate": 1.799684658487091e-05,
+      "loss": 0.3484,
+      "step": 570
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 7.8125,
+      "learning_rate": 1.789084084834691e-05,
+      "loss": 0.3557,
+      "step": 580
+    },
+    {
+      "epoch": 0.295,
+      "grad_norm": 3.796875,
+      "learning_rate": 1.778243148526021e-05,
+      "loss": 0.3709,
+      "step": 590
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 7.0625,
+      "learning_rate": 1.7671651518153e-05,
+      "loss": 0.3416,
+      "step": 600
+    },
+    {
+      "epoch": 0.305,
+      "grad_norm": 5.28125,
+      "learning_rate": 1.7558534691676396e-05,
+      "loss": 0.3631,
+      "step": 610
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 5.34375,
+      "learning_rate": 1.744311546231154e-05,
+      "loss": 0.3668,
+      "step": 620
+    },
+    {
+      "epoch": 0.315,
+      "grad_norm": 4.96875,
+      "learning_rate": 1.732542898787379e-05,
+      "loss": 0.3611,
+      "step": 630
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 8.0625,
+      "learning_rate": 1.7205511116803306e-05,
+      "loss": 0.3678,
+      "step": 640
+    },
+    {
+      "epoch": 0.325,
+      "grad_norm": 4.5625,
+      "learning_rate": 1.708339837724529e-05,
+      "loss": 0.3568,
+      "step": 650
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 14.75,
+      "learning_rate": 1.6959127965923144e-05,
+      "loss": 0.341,
+      "step": 660
+    },
+    {
+      "epoch": 0.335,
+      "grad_norm": 10.625,
+      "learning_rate": 1.6832737736807994e-05,
+      "loss": 0.3336,
+      "step": 670
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 10.0625,
+      "learning_rate": 1.6704266189587992e-05,
+      "loss": 0.3453,
+      "step": 680
+    },
+    {
+      "epoch": 0.345,
+      "grad_norm": 3.765625,
+      "learning_rate": 1.657375245794096e-05,
+      "loss": 0.3361,
+      "step": 690
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 12.25,
+      "learning_rate": 1.644123629761387e-05,
+      "loss": 0.348,
+      "step": 700
+    },
+    {
+      "epoch": 0.355,
+      "grad_norm": 4.375,
+      "learning_rate": 1.6306758074312866e-05,
+      "loss": 0.3488,
+      "step": 710
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 6.25,
+      "learning_rate": 1.617035875140749e-05,
+      "loss": 0.341,
+      "step": 720
+    },
+    {
+      "epoch": 0.365,
+      "grad_norm": 7.8125,
+      "learning_rate": 1.6032079877452825e-05,
+      "loss": 0.3486,
+      "step": 730
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 17.875,
+      "learning_rate": 1.5891963573533424e-05,
+      "loss": 0.3406,
+      "step": 740
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 9.0625,
+      "learning_rate": 1.575005252043279e-05,
+      "loss": 0.3365,
+      "step": 750
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 5.8125,
+      "learning_rate": 1.560638994563242e-05,
+      "loss": 0.3482,
+      "step": 760
+    },
+    {
+      "epoch": 0.385,
+      "grad_norm": 7.96875,
+      "learning_rate": 1.5461019610144292e-05,
+      "loss": 0.3309,
+      "step": 770
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 9.9375,
+      "learning_rate": 1.531398579518083e-05,
+      "loss": 0.3396,
+      "step": 780
+    },
+    {
+      "epoch": 0.395,
+      "grad_norm": 4.84375,
+      "learning_rate": 1.516533328866642e-05,
+      "loss": 0.3254,
+      "step": 790
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 7.84375,
+      "learning_rate": 1.5015107371594576e-05,
+      "loss": 0.3182,
+      "step": 800
+    },
+    {
+      "epoch": 0.405,
+      "grad_norm": 6.15625,
+      "learning_rate": 1.4863353804234906e-05,
+      "loss": 0.3289,
+      "step": 810
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 7.4375,
+      "learning_rate": 1.47101188121941e-05,
+      "loss": 0.3455,
+      "step": 820
+    },
+    {
+      "epoch": 0.415,
+      "grad_norm": 7.875,
+      "learning_rate": 1.4555449072335157e-05,
+      "loss": 0.3252,
+      "step": 830
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 5.4375,
+      "learning_rate": 1.4399391698559153e-05,
+      "loss": 0.316,
+      "step": 840
+    },
+    {
+      "epoch": 0.425,
+      "grad_norm": 9.5,
+      "learning_rate": 1.4241994227453902e-05,
+      "loss": 0.3293,
+      "step": 850
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 5.375,
+      "learning_rate": 1.408330460381385e-05,
+      "loss": 0.318,
+      "step": 860
+    },
+    {
+      "epoch": 0.435,
+      "grad_norm": 5.71875,
+      "learning_rate": 1.3923371166035615e-05,
+      "loss": 0.3258,
+      "step": 870
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 6.53125,
+      "learning_rate": 1.3762242631393656e-05,
+      "loss": 0.3264,
+      "step": 880
+    },
+    {
+      "epoch": 0.445,
+      "grad_norm": 5.625,
+      "learning_rate": 1.3599968081200515e-05,
+      "loss": 0.3359,
+      "step": 890
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 3.171875,
+      "learning_rate": 1.3436596945856164e-05,
+      "loss": 0.3068,
+      "step": 900
+    },
+    {
+      "epoch": 0.455,
+      "grad_norm": 7.125,
+      "learning_rate": 1.327217898979104e-05,
+      "loss": 0.3197,
+      "step": 910
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 6.96875,
+      "learning_rate": 1.310676429630732e-05,
+      "loss": 0.3266,
+      "step": 920
+    },
+    {
+      "epoch": 0.465,
+      "grad_norm": 6.46875,
+      "learning_rate": 1.294040325232304e-05,
+      "loss": 0.3088,
+      "step": 930
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 6.3125,
+      "learning_rate": 1.2773146533023782e-05,
+      "loss": 0.3041,
+      "step": 940
+    },
+    {
+      "epoch": 0.475,
+      "grad_norm": 5.46875,
+      "learning_rate": 1.2605045086426487e-05,
+      "loss": 0.3256,
+      "step": 950
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 8.125,
+      "learning_rate": 1.2436150117860226e-05,
+      "loss": 0.3264,
+      "step": 960
+    },
+    {
+      "epoch": 0.485,
+      "grad_norm": 4.25,
+      "learning_rate": 1.2266513074368552e-05,
+      "loss": 0.3037,
+      "step": 970
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 7.34375,
+      "learning_rate": 1.2096185629038219e-05,
+      "loss": 0.3102,
+      "step": 980
+    },
+    {
+      "epoch": 0.495,
+      "grad_norm": 3.6875,
+      "learning_rate": 1.1925219665259076e-05,
+      "loss": 0.3121,
+      "step": 990
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 7.28125,
+      "learning_rate": 1.1753667260919872e-05,
+      "loss": 0.3248,
+      "step": 1000
+    },
+    {
+      "epoch": 0.505,
+      "grad_norm": 5.5,
+      "learning_rate": 1.1581580672544839e-05,
+      "loss": 0.315,
+      "step": 1010
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 5.75,
+      "learning_rate": 1.1409012319375828e-05,
+      "loss": 0.3207,
+      "step": 1020
+    },
+    {
+      "epoch": 0.515,
+      "grad_norm": 7.09375,
+      "learning_rate": 1.1236014767404929e-05,
+      "loss": 0.3053,
+      "step": 1030
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 6.0,
+      "learning_rate": 1.1062640713362333e-05,
+      "loss": 0.3014,
+      "step": 1040
+    },
+    {
+      "epoch": 0.525,
+      "grad_norm": 4.59375,
+      "learning_rate": 1.0888942968664417e-05,
+      "loss": 0.3018,
+      "step": 1050
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 4.84375,
+      "learning_rate": 1.071497444332686e-05,
+      "loss": 0.3029,
+      "step": 1060
+    },
+    {
+      "epoch": 0.535,
+      "grad_norm": 4.53125,
+      "learning_rate": 1.0540788129847757e-05,
+      "loss": 0.3014,
+      "step": 1070
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 6.625,
+      "learning_rate": 1.0366437087065564e-05,
+      "loss": 0.3023,
+      "step": 1080
+    },
+    {
+      "epoch": 0.545,
+      "grad_norm": 5.34375,
+      "learning_rate": 1.01919744239969e-05,
+      "loss": 0.2912,
+      "step": 1090
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 5.5625,
+      "learning_rate": 1.0017453283658984e-05,
+      "loss": 0.3121,
+      "step": 1100
+    },
+    {
+      "epoch": 0.555,
+      "grad_norm": 4.25,
+      "learning_rate": 9.842926826881796e-06,
+      "loss": 0.3027,
+      "step": 1110
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 5.40625,
+      "learning_rate": 9.668448216114739e-06,
+      "loss": 0.298,
+      "step": 1120
+    },
+    {
+      "epoch": 0.565,
+      "grad_norm": 5.25,
+      "learning_rate": 9.494070599232868e-06,
+      "loss": 0.3061,
+      "step": 1130
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 5.4375,
+      "learning_rate": 9.319847093347522e-06,
+      "loss": 0.3053,
+      "step": 1140
+    },
+    {
+      "epoch": 0.575,
+      "grad_norm": 4.09375,
+      "learning_rate": 9.145830768626326e-06,
+      "loss": 0.2938,
+      "step": 1150
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 5.71875,
+      "learning_rate": 8.972074632127533e-06,
+      "loss": 0.3043,
+      "step": 1160
+    },
+    {
+      "epoch": 0.585,
+      "grad_norm": 5.75,
+      "learning_rate": 8.79863161165353e-06,
+      "loss": 0.2947,
+      "step": 1170
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 6.71875,
+      "learning_rate": 8.625554539628536e-06,
+      "loss": 0.3041,
+      "step": 1180
+    },
+    {
+      "epoch": 0.595,
+      "grad_norm": 4.21875,
+      "learning_rate": 8.452896137005322e-06,
+      "loss": 0.292,
+      "step": 1190
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 3.75,
+      "learning_rate": 8.280708997205904e-06,
+      "loss": 0.2797,
+      "step": 1200
+    },
+    {
+      "epoch": 0.605,
+      "grad_norm": 5.09375,
+      "learning_rate": 8.109045570101086e-06,
+      "loss": 0.2932,
+      "step": 1210
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 4.59375,
+      "learning_rate": 7.937958146033706e-06,
+      "loss": 0.293,
+      "step": 1220
+    },
+    {
+      "epoch": 0.615,
+      "grad_norm": 5.15625,
+      "learning_rate": 7.767498839890489e-06,
+      "loss": 0.3025,
+      "step": 1230
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 4.90625,
+      "learning_rate": 7.597719575227364e-06,
+      "loss": 0.2916,
+      "step": 1240
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 7.25,
+      "learning_rate": 7.428672068453041e-06,
+      "loss": 0.2949,
+      "step": 1250
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 9.3125,
+      "learning_rate": 7.260407813075676e-06,
+      "loss": 0.2924,
+      "step": 1260
+    },
+    {
+      "epoch": 0.635,
+      "grad_norm": 6.0,
+      "learning_rate": 7.092978064017475e-06,
+      "loss": 0.2924,
+      "step": 1270
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 5.1875,
+      "learning_rate": 6.92643382200193e-06,
+      "loss": 0.2902,
+      "step": 1280
+    },
+    {
+      "epoch": 0.645,
+      "grad_norm": 3.5625,
+      "learning_rate": 6.7608258180185085e-06,
+      "loss": 0.2848,
+      "step": 1290
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 7.46875,
+      "learning_rate": 6.596204497869501e-06,
+      "loss": 0.2859,
+      "step": 1300
+    },
+    {
+      "epoch": 0.655,
+      "grad_norm": 3.96875,
+      "learning_rate": 6.432620006803747e-06,
+      "loss": 0.2811,
+      "step": 1310
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 4.0625,
+      "learning_rate": 6.2701221742419106e-06,
+      "loss": 0.2941,
+      "step": 1320
+    },
+    {
+      "epoch": 0.665,
+      "grad_norm": 3.75,
+      "learning_rate": 6.108760498597939e-06,
+      "loss": 0.2949,
+      "step": 1330
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 4.5625,
+      "learning_rate": 5.948584132201376e-06,
+      "loss": 0.2787,
+      "step": 1340
+    },
+    {
+      "epoch": 0.675,
+      "grad_norm": 5.8125,
+      "learning_rate": 5.789641866325091e-06,
+      "loss": 0.2895,
+      "step": 1350
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 5.84375,
+      "learning_rate": 5.631982116322981e-06,
+      "loss": 0.2844,
+      "step": 1360
+    },
+    {
+      "epoch": 0.685,
+      "grad_norm": 4.96875,
+      "learning_rate": 5.475652906882173e-06,
+      "loss": 0.2824,
+      "step": 1370
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 5.46875,
+      "learning_rate": 5.3207018573942684e-06,
+      "loss": 0.2939,
+      "step": 1380
+    },
+    {
+      "epoch": 0.695,
+      "grad_norm": 4.09375,
+      "learning_rate": 5.167176167449977e-06,
+      "loss": 0.2808,
+      "step": 1390
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 8.375,
+      "learning_rate": 5.015122602461698e-06,
+      "loss": 0.2844,
+      "step": 1400
+    },
+    {
+      "epoch": 0.705,
+      "grad_norm": 6.9375,
+      "learning_rate": 4.864587479418302e-06,
+      "loss": 0.2842,
+      "step": 1410
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 5.84375,
+      "learning_rate": 4.71561665277653e-06,
+      "loss": 0.2975,
+      "step": 1420
+    },
+    {
+      "epoch": 0.715,
+      "grad_norm": 6.21875,
+      "learning_rate": 4.568255500493292e-06,
+      "loss": 0.2819,
+      "step": 1430
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 4.78125,
+      "learning_rate": 4.422548910203099e-06,
+      "loss": 0.2885,
+      "step": 1440
+    },
+    {
+      "epoch": 0.725,
+      "grad_norm": 5.46875,
+      "learning_rate": 4.27854126554484e-06,
+      "loss": 0.299,
+      "step": 1450
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 4.3125,
+      "learning_rate": 4.136276432642107e-06,
+      "loss": 0.2834,
+      "step": 1460
+    },
+    {
+      "epoch": 0.735,
+      "grad_norm": 5.71875,
+      "learning_rate": 3.9957977467411615e-06,
+      "loss": 0.2872,
+      "step": 1470
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 15.5625,
+      "learning_rate": 3.857147999010568e-06,
+      "loss": 0.2795,
+      "step": 1480
+    },
+    {
+      "epoch": 0.745,
+      "grad_norm": 5.03125,
+      "learning_rate": 3.7203694235066224e-06,
+      "loss": 0.3002,
+      "step": 1490
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 3.703125,
+      "learning_rate": 3.5855036843084213e-06,
+      "loss": 0.2896,
+      "step": 1500
+    },
+    {
+      "epoch": 0.755,
+      "grad_norm": 7.53125,
+      "learning_rate": 3.452591862826603e-06,
+      "loss": 0.2881,
+      "step": 1510
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 4.375,
+      "learning_rate": 3.3216744452895356e-06,
+      "loss": 0.283,
+      "step": 1520
+    },
+    {
+      "epoch": 0.765,
+      "grad_norm": 4.15625,
+      "learning_rate": 3.192791310410822e-06,
+      "loss": 0.2826,
+      "step": 1530
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 5.15625,
+      "learning_rate": 3.0659817172418694e-06,
+      "loss": 0.2912,
+      "step": 1540
+    },
+    {
+      "epoch": 0.775,
+      "grad_norm": 3.171875,
+      "learning_rate": 2.9412842932131904e-06,
+      "loss": 0.2869,
+      "step": 1550
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 5.15625,
+      "learning_rate": 2.8187370223681134e-06,
+      "loss": 0.2842,
+      "step": 1560
+    },
+    {
+      "epoch": 0.785,
+      "grad_norm": 5.15625,
+      "learning_rate": 2.698377233792476e-06,
+      "loss": 0.285,
+      "step": 1570
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 5.875,
+      "learning_rate": 2.5802415902438373e-06,
+      "loss": 0.2809,
+      "step": 1580
+    },
+    {
+      "epoch": 0.795,
+      "grad_norm": 4.28125,
+      "learning_rate": 2.464366076983623e-06,
+      "loss": 0.2807,
+      "step": 1590
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 6.75,
+      "learning_rate": 2.3507859908156828e-06,
+      "loss": 0.2911,
+      "step": 1600
+    },
+    {
+      "epoch": 0.805,
+      "grad_norm": 5.5,
+      "learning_rate": 2.2395359293345396e-06,
+      "loss": 0.2812,
+      "step": 1610
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 8.25,
+      "learning_rate": 2.130649780386628e-06,
+      "loss": 0.282,
+      "step": 1620
+    },
+    {
+      "epoch": 0.815,
+      "grad_norm": 4.8125,
+      "learning_rate": 2.024160711747717e-06,
+      "loss": 0.2686,
+      "step": 1630
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 9.375,
+      "learning_rate": 1.9201011610196972e-06,
+      "loss": 0.2863,
+      "step": 1640
+    },
+    {
+      "epoch": 0.825,
+      "grad_norm": 4.59375,
+      "learning_rate": 1.818502825749764e-06,
+      "loss": 0.2812,
+      "step": 1650
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 5.0625,
+      "learning_rate": 1.7193966537750561e-06,
+      "loss": 0.2982,
+      "step": 1660
+    },
+    {
+      "epoch": 0.835,
+      "grad_norm": 4.6875,
+      "learning_rate": 1.6228128337956128e-06,
+      "loss": 0.2963,
+      "step": 1670
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 4.4375,
+      "learning_rate": 1.5287807861786308e-06,
+      "loss": 0.2902,
+      "step": 1680
+    },
+    {
+      "epoch": 0.845,
+      "grad_norm": 4.8125,
+      "learning_rate": 1.4373291539967182e-06,
+      "loss": 0.29,
+      "step": 1690
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 3.75,
+      "learning_rate": 1.3484857943029572e-06,
+      "loss": 0.2791,
+      "step": 1700
+    },
+    {
+      "epoch": 0.855,
+      "grad_norm": 4.5625,
+      "learning_rate": 1.2622777696453482e-06,
+      "loss": 0.2938,
+      "step": 1710
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 4.53125,
+      "learning_rate": 1.1787313398233235e-06,
+      "loss": 0.2672,
+      "step": 1720
+    },
+    {
+      "epoch": 0.865,
+      "grad_norm": 3.359375,
+      "learning_rate": 1.097871953888735e-06,
+      "loss": 0.2744,
+      "step": 1730
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 3.9375,
+      "learning_rate": 1.0197242423938447e-06,
+      "loss": 0.2792,
+      "step": 1740
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 5.15625,
+      "learning_rate": 9.44312009888606e-07,
+      "loss": 0.28,
+      "step": 1750
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 5.25,
+      "learning_rate": 8.716582276695729e-07,
+      "loss": 0.2836,
+      "step": 1760
+    },
+    {
+      "epoch": 0.885,
+      "grad_norm": 4.6875,
+      "learning_rate": 8.017850267826233e-07,
+      "loss": 0.2854,
+      "step": 1770
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 5.625,
+      "learning_rate": 7.347136912816277e-07,
+      "loss": 0.2898,
+      "step": 1780
+    },
+    {
+      "epoch": 0.895,
+      "grad_norm": 3.171875,
+      "learning_rate": 6.704646517451108e-07,
+      "loss": 0.2803,
+      "step": 1790
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 5.21875,
+      "learning_rate": 6.090574790529091e-07,
+      "loss": 0.2742,
+      "step": 1800
+    },
+    {
+      "epoch": 0.905,
+      "grad_norm": 6.65625,
+      "learning_rate": 5.505108784246926e-07,
+      "loss": 0.2847,
+      "step": 1810
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 4.84375,
+      "learning_rate": 4.948426837221632e-07,
+      "loss": 0.2766,
+      "step": 1820
+    },
+    {
+      "epoch": 0.915,
+      "grad_norm": 5.125,
+      "learning_rate": 4.420698520166988e-07,
+      "loss": 0.2826,
+      "step": 1830
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 5.625,
+      "learning_rate": 3.922084584240582e-07,
+      "loss": 0.2926,
+      "step": 1840
+    },
+    {
+      "epoch": 0.925,
+      "grad_norm": 8.3125,
+      "learning_rate": 3.4527369120775036e-07,
+      "loss": 0.276,
+      "step": 1850
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 5.0,
+      "learning_rate": 3.0127984715253246e-07,
+      "loss": 0.2975,
+      "step": 1860
+    },
+    {
+      "epoch": 0.935,
+      "grad_norm": 7.03125,
+      "learning_rate": 2.6024032720948446e-07,
+      "loss": 0.2904,
+      "step": 1870
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 3.890625,
+      "learning_rate": 2.221676324139377e-07,
+      "loss": 0.2789,
+      "step": 1880
+    },
+    {
+      "epoch": 0.945,
+      "grad_norm": 6.375,
+      "learning_rate": 1.8707336007754873e-07,
+      "loss": 0.276,
+      "step": 1890
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 4.6875,
+      "learning_rate": 1.549682002556341e-07,
+      "loss": 0.2869,
+      "step": 1900
+    },
+    {
+      "epoch": 0.955,
+      "grad_norm": 4.03125,
+      "learning_rate": 1.2586193249088607e-07,
+      "loss": 0.2855,
+      "step": 1910
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 6.125,
+      "learning_rate": 9.976342283442464e-08,
+      "loss": 0.2846,
+      "step": 1920
+    },
+    {
+      "epoch": 0.965,
+      "grad_norm": 5.40625,
+      "learning_rate": 7.66806211451132e-08,
+      "loss": 0.2861,
+      "step": 1930
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 4.0625,
+      "learning_rate": 5.662055866795357e-08,
+      "loss": 0.2776,
+      "step": 1940
+    },
+    {
+      "epoch": 0.975,
+      "grad_norm": 5.40625,
+      "learning_rate": 3.9589345892304673e-08,
+      "loss": 0.2809,
+      "step": 1950
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 7.15625,
+      "learning_rate": 2.5592170690560415e-08,
+      "loss": 0.2867,
+      "step": 1960
+    },
+    {
+      "epoch": 0.985,
+      "grad_norm": 4.75,
+      "learning_rate": 1.4633296737882607e-08,
+      "loss": 0.2891,
+      "step": 1970
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 4.84375,
+      "learning_rate": 6.716062213437679e-09,
+      "loss": 0.2842,
+      "step": 1980
+    },
+    {
+      "epoch": 0.995,
+      "grad_norm": 3.625,
+      "learning_rate": 1.8428787835578222e-09,
+      "loss": 0.2832,
+      "step": 1990
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 5.03125,
+      "learning_rate": 1.5230867123072757e-11,
+      "loss": 0.2829,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9223372036854775807,
+  "save_steps": 2000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.2073827663872e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f91eab69be20627a6920bf3258ba24308da76607427dab55f0b1d55feafb9ce3
+size 5777