Training in progress, step 2000, checkpoint

checkpoint-2000/config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "microsoft/phi-2",
+  "architectures": [
+    "PhiForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 50256,
+  "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,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.3",
+  "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": "4.48.3"
+}

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ff2a4f162e6ba9077782270dee700c9634c3bfad67c885e44e809195fee98b7
+size 4995584848

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5cad4a755a5e51fb4b82a8754377020861b60411f6ba5a584ffd18e61dae3a2
+size 563833008

checkpoint-2000/model.safetensors.index.json

@@ -0,0 +1,460 @@
+{
+  "metadata": {
+    "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 sha256:0a7828475c1ca30e84d8b327f95b54c143feaf386c2f57bf0008bce7feb1f190
+size 10470622

checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af9efeb2a6b512ea76ffe6ceec2cae66d80b2b6882eb6af19b5dcff348dbfaa0
+size 14244

checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe6b601f8c77d93a0e053b92ea127a17aea5c5021426dfd754395ac532bf9532
+size 1064

checkpoint-2000/trainer_state.json

@@ -0,0 +1,1433 @@
+{
+  "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": 99.5,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 1.3438,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 110.5,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.3195,
+      "step": 20
+    },
+    {
+      "epoch": 0.015,
+      "grad_norm": 101.5,
+      "learning_rate": 3e-06,
+      "loss": 1.3234,
+      "step": 30
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 117.0,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.332,
+      "step": 40
+    },
+    {
+      "epoch": 0.025,
+      "grad_norm": 182.0,
+      "learning_rate": 5e-06,
+      "loss": 1.2867,
+      "step": 50
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 133.0,
+      "learning_rate": 6e-06,
+      "loss": 1.1648,
+      "step": 60
+    },
+    {
+      "epoch": 0.035,
+      "grad_norm": 45.75,
+      "learning_rate": 7e-06,
+      "loss": 0.991,
+      "step": 70
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 135.0,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.8773,
+      "step": 80
+    },
+    {
+      "epoch": 0.045,
+      "grad_norm": 34.25,
+      "learning_rate": 9e-06,
+      "loss": 0.8332,
+      "step": 90
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 43.25,
+      "learning_rate": 1e-05,
+      "loss": 0.7129,
+      "step": 100
+    },
+    {
+      "epoch": 0.055,
+      "grad_norm": 20.5,
+      "learning_rate": 1.1000000000000001e-05,
+      "loss": 0.6535,
+      "step": 110
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 26.75,
+      "learning_rate": 1.2e-05,
+      "loss": 0.5713,
+      "step": 120
+    },
+    {
+      "epoch": 0.065,
+      "grad_norm": 37.75,
+      "learning_rate": 1.3000000000000001e-05,
+      "loss": 0.5668,
+      "step": 130
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 39.25,
+      "learning_rate": 1.4e-05,
+      "loss": 0.535,
+      "step": 140
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 139.0,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.5762,
+      "step": 150
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 20.5,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.51,
+      "step": 160
+    },
+    {
+      "epoch": 0.085,
+      "grad_norm": 61.0,
+      "learning_rate": 1.7e-05,
+      "loss": 0.4625,
+      "step": 170
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 3.796875,
+      "learning_rate": 1.8e-05,
+      "loss": 0.4006,
+      "step": 180
+    },
+    {
+      "epoch": 0.095,
+      "grad_norm": 7.59375,
+      "learning_rate": 1.9e-05,
+      "loss": 0.4035,
+      "step": 190
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 4.90625,
+      "learning_rate": 2e-05,
+      "loss": 0.3875,
+      "step": 200
+    },
+    {
+      "epoch": 0.105,
+      "grad_norm": 4.5625,
+      "learning_rate": 1.9998476951563914e-05,
+      "loss": 0.351,
+      "step": 210
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 3.609375,
+      "learning_rate": 1.999390827019096e-05,
+      "loss": 0.3271,
+      "step": 220
+    },
+    {
+      "epoch": 0.115,
+      "grad_norm": 3.578125,
+      "learning_rate": 1.9986295347545738e-05,
+      "loss": 0.301,
+      "step": 230
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 12.9375,
+      "learning_rate": 1.9975640502598243e-05,
+      "loss": 0.2996,
+      "step": 240
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 4.84375,
+      "learning_rate": 1.9961946980917457e-05,
+      "loss": 0.2951,
+      "step": 250
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 3.59375,
+      "learning_rate": 1.9945218953682736e-05,
+      "loss": 0.2805,
+      "step": 260
+    },
+    {
+      "epoch": 0.135,
+      "grad_norm": 2.84375,
+      "learning_rate": 1.9925461516413224e-05,
+      "loss": 0.2726,
+      "step": 270
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 2.109375,
+      "learning_rate": 1.9902680687415704e-05,
+      "loss": 0.2619,
+      "step": 280
+    },
+    {
+      "epoch": 0.145,
+      "grad_norm": 3.734375,
+      "learning_rate": 1.9876883405951378e-05,
+      "loss": 0.2633,
+      "step": 290
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 2.875,
+      "learning_rate": 1.9848077530122083e-05,
+      "loss": 0.2517,
+      "step": 300
+    },
+    {
+      "epoch": 0.155,
+      "grad_norm": 3.796875,
+      "learning_rate": 1.9816271834476642e-05,
+      "loss": 0.2622,
+      "step": 310
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 3.703125,
+      "learning_rate": 1.9781476007338058e-05,
+      "loss": 0.2524,
+      "step": 320
+    },
+    {
+      "epoch": 0.165,
+      "grad_norm": 3.109375,
+      "learning_rate": 1.9743700647852356e-05,
+      "loss": 0.2375,
+      "step": 330
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 4.65625,
+      "learning_rate": 1.9702957262759964e-05,
+      "loss": 0.2414,
+      "step": 340
+    },
+    {
+      "epoch": 0.175,
+      "grad_norm": 2.203125,
+      "learning_rate": 1.9659258262890683e-05,
+      "loss": 0.2405,
+      "step": 350
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 2.734375,
+      "learning_rate": 1.961261695938319e-05,
+      "loss": 0.2604,
+      "step": 360
+    },
+    {
+      "epoch": 0.185,
+      "grad_norm": 2.625,
+      "learning_rate": 1.9563047559630356e-05,
+      "loss": 0.2386,
+      "step": 370
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 2.65625,
+      "learning_rate": 1.9510565162951538e-05,
+      "loss": 0.2479,
+      "step": 380
+    },
+    {
+      "epoch": 0.195,
+      "grad_norm": 4.0625,
+      "learning_rate": 1.945518575599317e-05,
+      "loss": 0.2427,
+      "step": 390
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 3.84375,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 0.2357,
+      "step": 400
+    },
+    {
+      "epoch": 0.205,
+      "grad_norm": 3.28125,
+      "learning_rate": 1.9335804264972018e-05,
+      "loss": 0.2371,
+      "step": 410
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 2.8125,
+      "learning_rate": 1.9271838545667876e-05,
+      "loss": 0.2343,
+      "step": 420
+    },
+    {
+      "epoch": 0.215,
+      "grad_norm": 3.75,
+      "learning_rate": 1.9205048534524405e-05,
+      "loss": 0.2278,
+      "step": 430
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 2.15625,
+      "learning_rate": 1.913545457642601e-05,
+      "loss": 0.2275,
+      "step": 440
+    },
+    {
+      "epoch": 0.225,
+      "grad_norm": 1.859375,
+      "learning_rate": 1.9063077870366504e-05,
+      "loss": 0.2349,
+      "step": 450
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 2.28125,
+      "learning_rate": 1.8987940462991673e-05,
+      "loss": 0.2354,
+      "step": 460
+    },
+    {
+      "epoch": 0.235,
+      "grad_norm": 3.078125,
+      "learning_rate": 1.891006524188368e-05,
+      "loss": 0.2296,
+      "step": 470
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.921875,
+      "learning_rate": 1.8829475928589272e-05,
+      "loss": 0.2383,
+      "step": 480
+    },
+    {
+      "epoch": 0.245,
+      "grad_norm": 1.9375,
+      "learning_rate": 1.874619707139396e-05,
+      "loss": 0.2272,
+      "step": 490
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 2.421875,
+      "learning_rate": 1.866025403784439e-05,
+      "loss": 0.2134,
+      "step": 500
+    },
+    {
+      "epoch": 0.255,
+      "grad_norm": 2.484375,
+      "learning_rate": 1.8571673007021124e-05,
+      "loss": 0.2243,
+      "step": 510
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 2.109375,
+      "learning_rate": 1.848048096156426e-05,
+      "loss": 0.2193,
+      "step": 520
+    },
+    {
+      "epoch": 0.265,
+      "grad_norm": 3.9375,
+      "learning_rate": 1.8386705679454243e-05,
+      "loss": 0.2273,
+      "step": 530
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 2.21875,
+      "learning_rate": 1.8290375725550417e-05,
+      "loss": 0.2113,
+      "step": 540
+    },
+    {
+      "epoch": 0.275,
+      "grad_norm": 2.1875,
+      "learning_rate": 1.819152044288992e-05,
+      "loss": 0.218,
+      "step": 550
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 1.65625,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 0.2086,
+      "step": 560
+    },
+    {
+      "epoch": 0.285,
+      "grad_norm": 1.65625,
+      "learning_rate": 1.798635510047293e-05,
+      "loss": 0.2122,
+      "step": 570
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 3.203125,
+      "learning_rate": 1.788010753606722e-05,
+      "loss": 0.2165,
+      "step": 580
+    },
+    {
+      "epoch": 0.295,
+      "grad_norm": 1.5,
+      "learning_rate": 1.777145961456971e-05,
+      "loss": 0.2059,
+      "step": 590
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 2.34375,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 0.2121,
+      "step": 600
+    },
+    {
+      "epoch": 0.305,
+      "grad_norm": 2.34375,
+      "learning_rate": 1.7547095802227723e-05,
+      "loss": 0.2029,
+      "step": 610
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 2.140625,
+      "learning_rate": 1.7431448254773943e-05,
+      "loss": 0.2092,
+      "step": 620
+    },
+    {
+      "epoch": 0.315,
+      "grad_norm": 2.65625,
+      "learning_rate": 1.7313537016191706e-05,
+      "loss": 0.2082,
+      "step": 630
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 2.265625,
+      "learning_rate": 1.7193398003386514e-05,
+      "loss": 0.2084,
+      "step": 640
+    },
+    {
+      "epoch": 0.325,
+      "grad_norm": 1.75,
+      "learning_rate": 1.7071067811865477e-05,
+      "loss": 0.2109,
+      "step": 650
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 1.9140625,
+      "learning_rate": 1.6946583704589973e-05,
+      "loss": 0.2124,
+      "step": 660
+    },
+    {
+      "epoch": 0.335,
+      "grad_norm": 1.9375,
+      "learning_rate": 1.6819983600624986e-05,
+      "loss": 0.2048,
+      "step": 670
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 2.578125,
+      "learning_rate": 1.6691306063588583e-05,
+      "loss": 0.2036,
+      "step": 680
+    },
+    {
+      "epoch": 0.345,
+      "grad_norm": 1.8359375,
+      "learning_rate": 1.6560590289905074e-05,
+      "loss": 0.2068,
+      "step": 690
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 2.8125,
+      "learning_rate": 1.6427876096865394e-05,
+      "loss": 0.2078,
+      "step": 700
+    },
+    {
+      "epoch": 0.355,
+      "grad_norm": 1.5703125,
+      "learning_rate": 1.6293203910498375e-05,
+      "loss": 0.202,
+      "step": 710
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.9375,
+      "learning_rate": 1.6156614753256583e-05,
+      "loss": 0.2026,
+      "step": 720
+    },
+    {
+      "epoch": 0.365,
+      "grad_norm": 3.53125,
+      "learning_rate": 1.6018150231520486e-05,
+      "loss": 0.2104,
+      "step": 730
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 1.890625,
+      "learning_rate": 1.5877852522924733e-05,
+      "loss": 0.2106,
+      "step": 740
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 1.9296875,
+      "learning_rate": 1.573576436351046e-05,
+      "loss": 0.1996,
+      "step": 750
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 4.5625,
+      "learning_rate": 1.5591929034707468e-05,
+      "loss": 0.1965,
+      "step": 760
+    },
+    {
+      "epoch": 0.385,
+      "grad_norm": 1.703125,
+      "learning_rate": 1.5446390350150272e-05,
+      "loss": 0.1935,
+      "step": 770
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 2.140625,
+      "learning_rate": 1.529919264233205e-05,
+      "loss": 0.1954,
+      "step": 780
+    },
+    {
+      "epoch": 0.395,
+      "grad_norm": 4.1875,
+      "learning_rate": 1.5150380749100545e-05,
+      "loss": 0.2036,
+      "step": 790
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 3.328125,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.2004,
+      "step": 800
+    },
+    {
+      "epoch": 0.405,
+      "grad_norm": 2.03125,
+      "learning_rate": 1.4848096202463373e-05,
+      "loss": 0.1983,
+      "step": 810
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 3.15625,
+      "learning_rate": 1.469471562785891e-05,
+      "loss": 0.1967,
+      "step": 820
+    },
+    {
+      "epoch": 0.415,
+      "grad_norm": 2.296875,
+      "learning_rate": 1.4539904997395468e-05,
+      "loss": 0.1923,
+      "step": 830
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 1.71875,
+      "learning_rate": 1.4383711467890776e-05,
+      "loss": 0.1982,
+      "step": 840
+    },
+    {
+      "epoch": 0.425,
+      "grad_norm": 3.09375,
+      "learning_rate": 1.4226182617406996e-05,
+      "loss": 0.1933,
+      "step": 850
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 2.328125,
+      "learning_rate": 1.4067366430758004e-05,
+      "loss": 0.1886,
+      "step": 860
+    },
+    {
+      "epoch": 0.435,
+      "grad_norm": 2.0625,
+      "learning_rate": 1.3907311284892737e-05,
+      "loss": 0.1909,
+      "step": 870
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 2.140625,
+      "learning_rate": 1.3746065934159123e-05,
+      "loss": 0.1916,
+      "step": 880
+    },
+    {
+      "epoch": 0.445,
+      "grad_norm": 1.8359375,
+      "learning_rate": 1.3583679495453e-05,
+      "loss": 0.1938,
+      "step": 890
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 4.625,
+      "learning_rate": 1.342020143325669e-05,
+      "loss": 0.1959,
+      "step": 900
+    },
+    {
+      "epoch": 0.455,
+      "grad_norm": 1.7734375,
+      "learning_rate": 1.3255681544571568e-05,
+      "loss": 0.1952,
+      "step": 910
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 2.671875,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 0.1925,
+      "step": 920
+    },
+    {
+      "epoch": 0.465,
+      "grad_norm": 2.390625,
+      "learning_rate": 1.2923717047227368e-05,
+      "loss": 0.191,
+      "step": 930
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 2.265625,
+      "learning_rate": 1.2756373558169992e-05,
+      "loss": 0.1938,
+      "step": 940
+    },
+    {
+      "epoch": 0.475,
+      "grad_norm": 4.65625,
+      "learning_rate": 1.2588190451025209e-05,
+      "loss": 0.189,
+      "step": 950
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.9375,
+      "learning_rate": 1.2419218955996677e-05,
+      "loss": 0.1918,
+      "step": 960
+    },
+    {
+      "epoch": 0.485,
+      "grad_norm": 8.4375,
+      "learning_rate": 1.2249510543438652e-05,
+      "loss": 0.1886,
+      "step": 970
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 1.8125,
+      "learning_rate": 1.2079116908177592e-05,
+      "loss": 0.1876,
+      "step": 980
+    },
+    {
+      "epoch": 0.495,
+      "grad_norm": 2.78125,
+      "learning_rate": 1.190808995376545e-05,
+      "loss": 0.1943,
+      "step": 990
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.90625,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 0.1953,
+      "step": 1000
+    },
+    {
+      "epoch": 0.505,
+      "grad_norm": 2.921875,
+      "learning_rate": 1.156434465040231e-05,
+      "loss": 0.1946,
+      "step": 1010
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 2.3125,
+      "learning_rate": 1.1391731009600655e-05,
+      "loss": 0.1862,
+      "step": 1020
+    },
+    {
+      "epoch": 0.515,
+      "grad_norm": 1.59375,
+      "learning_rate": 1.1218693434051475e-05,
+      "loss": 0.1854,
+      "step": 1030
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.8125,
+      "learning_rate": 1.1045284632676535e-05,
+      "loss": 0.1918,
+      "step": 1040
+    },
+    {
+      "epoch": 0.525,
+      "grad_norm": 2.046875,
+      "learning_rate": 1.0871557427476585e-05,
+      "loss": 0.1848,
+      "step": 1050
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 1.4765625,
+      "learning_rate": 1.0697564737441254e-05,
+      "loss": 0.1855,
+      "step": 1060
+    },
+    {
+      "epoch": 0.535,
+      "grad_norm": 2.484375,
+      "learning_rate": 1.0523359562429441e-05,
+      "loss": 0.1846,
+      "step": 1070
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 2.46875,
+      "learning_rate": 1.0348994967025012e-05,
+      "loss": 0.1818,
+      "step": 1080
+    },
+    {
+      "epoch": 0.545,
+      "grad_norm": 1.7734375,
+      "learning_rate": 1.0174524064372837e-05,
+      "loss": 0.1812,
+      "step": 1090
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 2.203125,
+      "learning_rate": 1e-05,
+      "loss": 0.1866,
+      "step": 1100
+    },
+    {
+      "epoch": 0.555,
+      "grad_norm": 2.078125,
+      "learning_rate": 9.825475935627165e-06,
+      "loss": 0.1901,
+      "step": 1110
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.9296875,
+      "learning_rate": 9.651005032974994e-06,
+      "loss": 0.1753,
+      "step": 1120
+    },
+    {
+      "epoch": 0.565,
+      "grad_norm": 1.6875,
+      "learning_rate": 9.476640437570562e-06,
+      "loss": 0.1809,
+      "step": 1130
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 1.8671875,
+      "learning_rate": 9.302435262558748e-06,
+      "loss": 0.1819,
+      "step": 1140
+    },
+    {
+      "epoch": 0.575,
+      "grad_norm": 1.7890625,
+      "learning_rate": 9.128442572523418e-06,
+      "loss": 0.1832,
+      "step": 1150
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 3.25,
+      "learning_rate": 8.954715367323468e-06,
+      "loss": 0.1906,
+      "step": 1160
+    },
+    {
+      "epoch": 0.585,
+      "grad_norm": 2.109375,
+      "learning_rate": 8.781306565948528e-06,
+      "loss": 0.1863,
+      "step": 1170
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 4.96875,
+      "learning_rate": 8.60826899039935e-06,
+      "loss": 0.1851,
+      "step": 1180
+    },
+    {
+      "epoch": 0.595,
+      "grad_norm": 1.6328125,
+      "learning_rate": 8.43565534959769e-06,
+      "loss": 0.1855,
+      "step": 1190
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 2.078125,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 0.1856,
+      "step": 1200
+    },
+    {
+      "epoch": 0.605,
+      "grad_norm": 2.203125,
+      "learning_rate": 8.091910046234552e-06,
+      "loss": 0.1859,
+      "step": 1210
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 1.640625,
+      "learning_rate": 7.92088309182241e-06,
+      "loss": 0.1792,
+      "step": 1220
+    },
+    {
+      "epoch": 0.615,
+      "grad_norm": 2.53125,
+      "learning_rate": 7.750489456561351e-06,
+      "loss": 0.1798,
+      "step": 1230
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.875,
+      "learning_rate": 7.580781044003324e-06,
+      "loss": 0.1848,
+      "step": 1240
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 2.65625,
+      "learning_rate": 7.411809548974792e-06,
+      "loss": 0.1843,
+      "step": 1250
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 1.953125,
+      "learning_rate": 7.243626441830009e-06,
+      "loss": 0.1804,
+      "step": 1260
+    },
+    {
+      "epoch": 0.635,
+      "grad_norm": 5.96875,
+      "learning_rate": 7.076282952772634e-06,
+      "loss": 0.189,
+      "step": 1270
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.671875,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 0.1835,
+      "step": 1280
+    },
+    {
+      "epoch": 0.645,
+      "grad_norm": 2.03125,
+      "learning_rate": 6.744318455428436e-06,
+      "loss": 0.179,
+      "step": 1290
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 1.84375,
+      "learning_rate": 6.579798566743314e-06,
+      "loss": 0.1777,
+      "step": 1300
+    },
+    {
+      "epoch": 0.655,
+      "grad_norm": 2.15625,
+      "learning_rate": 6.4163205045469975e-06,
+      "loss": 0.1791,
+      "step": 1310
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.78125,
+      "learning_rate": 6.25393406584088e-06,
+      "loss": 0.1857,
+      "step": 1320
+    },
+    {
+      "epoch": 0.665,
+      "grad_norm": 3.1875,
+      "learning_rate": 6.092688715107265e-06,
+      "loss": 0.1775,
+      "step": 1330
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 2.484375,
+      "learning_rate": 5.932633569242e-06,
+      "loss": 0.1835,
+      "step": 1340
+    },
+    {
+      "epoch": 0.675,
+      "grad_norm": 2.625,
+      "learning_rate": 5.773817382593008e-06,
+      "loss": 0.1746,
+      "step": 1350
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.8671875,
+      "learning_rate": 5.616288532109225e-06,
+      "loss": 0.1795,
+      "step": 1360
+    },
+    {
+      "epoch": 0.685,
+      "grad_norm": 2.0,
+      "learning_rate": 5.460095002604533e-06,
+      "loss": 0.1795,
+      "step": 1370
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 1.421875,
+      "learning_rate": 5.305284372141095e-06,
+      "loss": 0.1729,
+      "step": 1380
+    },
+    {
+      "epoch": 0.695,
+      "grad_norm": 1.2578125,
+      "learning_rate": 5.151903797536631e-06,
+      "loss": 0.1793,
+      "step": 1390
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.4140625,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.174,
+      "step": 1400
+    },
+    {
+      "epoch": 0.705,
+      "grad_norm": 2.25,
+      "learning_rate": 4.849619250899458e-06,
+      "loss": 0.1799,
+      "step": 1410
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 2.765625,
+      "learning_rate": 4.700807357667953e-06,
+      "loss": 0.1791,
+      "step": 1420
+    },
+    {
+      "epoch": 0.715,
+      "grad_norm": 4.5625,
+      "learning_rate": 4.5536096498497295e-06,
+      "loss": 0.1832,
+      "step": 1430
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.6640625,
+      "learning_rate": 4.408070965292534e-06,
+      "loss": 0.1762,
+      "step": 1440
+    },
+    {
+      "epoch": 0.725,
+      "grad_norm": 3.59375,
+      "learning_rate": 4.264235636489542e-06,
+      "loss": 0.1845,
+      "step": 1450
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 2.0625,
+      "learning_rate": 4.12214747707527e-06,
+      "loss": 0.1778,
+      "step": 1460
+    },
+    {
+      "epoch": 0.735,
+      "grad_norm": 2.25,
+      "learning_rate": 3.981849768479516e-06,
+      "loss": 0.1869,
+      "step": 1470
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.5703125,
+      "learning_rate": 3.8433852467434175e-06,
+      "loss": 0.1803,
+      "step": 1480
+    },
+    {
+      "epoch": 0.745,
+      "grad_norm": 2.078125,
+      "learning_rate": 3.7067960895016277e-06,
+      "loss": 0.1775,
+      "step": 1490
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 1.796875,
+      "learning_rate": 3.5721239031346067e-06,
+      "loss": 0.1783,
+      "step": 1500
+    },
+    {
+      "epoch": 0.755,
+      "grad_norm": 2.40625,
+      "learning_rate": 3.4394097100949286e-06,
+      "loss": 0.1835,
+      "step": 1510
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 2.015625,
+      "learning_rate": 3.308693936411421e-06,
+      "loss": 0.1815,
+      "step": 1520
+    },
+    {
+      "epoch": 0.765,
+      "grad_norm": 3.0625,
+      "learning_rate": 3.1800163993750166e-06,
+      "loss": 0.184,
+      "step": 1530
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 1.859375,
+      "learning_rate": 3.0534162954100264e-06,
+      "loss": 0.179,
+      "step": 1540
+    },
+    {
+      "epoch": 0.775,
+      "grad_norm": 2.09375,
+      "learning_rate": 2.9289321881345257e-06,
+      "loss": 0.174,
+      "step": 1550
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 2.03125,
+      "learning_rate": 2.8066019966134907e-06,
+      "loss": 0.1794,
+      "step": 1560
+    },
+    {
+      "epoch": 0.785,
+      "grad_norm": 2.328125,
+      "learning_rate": 2.6864629838082957e-06,
+      "loss": 0.1722,
+      "step": 1570
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 1.8984375,
+      "learning_rate": 2.5685517452260566e-06,
+      "loss": 0.1778,
+      "step": 1580
+    },
+    {
+      "epoch": 0.795,
+      "grad_norm": 1.40625,
+      "learning_rate": 2.45290419777228e-06,
+      "loss": 0.1736,
+      "step": 1590
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 2.15625,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 0.1803,
+      "step": 1600
+    },
+    {
+      "epoch": 0.805,
+      "grad_norm": 1.921875,
+      "learning_rate": 2.2285403854302912e-06,
+      "loss": 0.1735,
+      "step": 1610
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 2.78125,
+      "learning_rate": 2.119892463932781e-06,
+      "loss": 0.1791,
+      "step": 1620
+    },
+    {
+      "epoch": 0.815,
+      "grad_norm": 1.796875,
+      "learning_rate": 2.013644899527074e-06,
+      "loss": 0.1762,
+      "step": 1630
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 2.03125,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 0.1729,
+      "step": 1640
+    },
+    {
+      "epoch": 0.825,
+      "grad_norm": 1.890625,
+      "learning_rate": 1.808479557110081e-06,
+      "loss": 0.1741,
+      "step": 1650
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 1.859375,
+      "learning_rate": 1.709624274449584e-06,
+      "loss": 0.1695,
+      "step": 1660
+    },
+    {
+      "epoch": 0.835,
+      "grad_norm": 1.9765625,
+      "learning_rate": 1.6132943205457607e-06,
+      "loss": 0.1768,
+      "step": 1670
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.34375,
+      "learning_rate": 1.5195190384357405e-06,
+      "loss": 0.1798,
+      "step": 1680
+    },
+    {
+      "epoch": 0.845,
+      "grad_norm": 1.984375,
+      "learning_rate": 1.4283269929788779e-06,
+      "loss": 0.1839,
+      "step": 1690
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 1.5859375,
+      "learning_rate": 1.339745962155613e-06,
+      "loss": 0.1776,
+      "step": 1700
+    },
+    {
+      "epoch": 0.855,
+      "grad_norm": 2.109375,
+      "learning_rate": 1.2538029286060428e-06,
+      "loss": 0.1751,
+      "step": 1710
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.8671875,
+      "learning_rate": 1.1705240714107301e-06,
+      "loss": 0.1745,
+      "step": 1720
+    },
+    {
+      "epoch": 0.865,
+      "grad_norm": 1.421875,
+      "learning_rate": 1.0899347581163222e-06,
+      "loss": 0.1792,
+      "step": 1730
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 1.859375,
+      "learning_rate": 1.012059537008332e-06,
+      "loss": 0.1764,
+      "step": 1740
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 1.9453125,
+      "learning_rate": 9.369221296335007e-07,
+      "loss": 0.1745,
+      "step": 1750
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.765625,
+      "learning_rate": 8.645454235739903e-07,
+      "loss": 0.1772,
+      "step": 1760
+    },
+    {
+      "epoch": 0.885,
+      "grad_norm": 2.453125,
+      "learning_rate": 7.949514654755963e-07,
+      "loss": 0.1753,
+      "step": 1770
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 1.6171875,
+      "learning_rate": 7.281614543321269e-07,
+      "loss": 0.1791,
+      "step": 1780
+    },
+    {
+      "epoch": 0.895,
+      "grad_norm": 1.9921875,
+      "learning_rate": 6.641957350279838e-07,
+      "loss": 0.184,
+      "step": 1790
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 2.296875,
+      "learning_rate": 6.030737921409169e-07,
+      "loss": 0.1765,
+      "step": 1800
+    },
+    {
+      "epoch": 0.905,
+      "grad_norm": 1.640625,
+      "learning_rate": 5.448142440068316e-07,
+      "loss": 0.176,
+      "step": 1810
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 2.96875,
+      "learning_rate": 4.894348370484648e-07,
+      "loss": 0.1694,
+      "step": 1820
+    },
+    {
+      "epoch": 0.915,
+      "grad_norm": 8.3125,
+      "learning_rate": 4.3695244036964567e-07,
+      "loss": 0.1781,
+      "step": 1830
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.953125,
+      "learning_rate": 3.8738304061681107e-07,
+      "loss": 0.1757,
+      "step": 1840
+    },
+    {
+      "epoch": 0.925,
+      "grad_norm": 3.859375,
+      "learning_rate": 3.4074173710931804e-07,
+      "loss": 0.1762,
+      "step": 1850
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 4.03125,
+      "learning_rate": 2.970427372400353e-07,
+      "loss": 0.1789,
+      "step": 1860
+    },
+    {
+      "epoch": 0.935,
+      "grad_norm": 3.296875,
+      "learning_rate": 2.5629935214764866e-07,
+      "loss": 0.1734,
+      "step": 1870
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.953125,
+      "learning_rate": 2.1852399266194312e-07,
+      "loss": 0.1754,
+      "step": 1880
+    },
+    {
+      "epoch": 0.945,
+      "grad_norm": 1.90625,
+      "learning_rate": 1.8372816552336025e-07,
+      "loss": 0.1871,
+      "step": 1890
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 1.8671875,
+      "learning_rate": 1.519224698779198e-07,
+      "loss": 0.176,
+      "step": 1900
+    },
+    {
+      "epoch": 0.955,
+      "grad_norm": 1.421875,
+      "learning_rate": 1.231165940486234e-07,
+      "loss": 0.1753,
+      "step": 1910
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.46875,
+      "learning_rate": 9.731931258429638e-08,
+      "loss": 0.1765,
+      "step": 1920
+    },
+    {
+      "epoch": 0.965,
+      "grad_norm": 2.03125,
+      "learning_rate": 7.453848358678018e-08,
+      "loss": 0.1723,
+      "step": 1930
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 1.953125,
+      "learning_rate": 5.4781046317267103e-08,
+      "loss": 0.1775,
+      "step": 1940
+    },
+    {
+      "epoch": 0.975,
+      "grad_norm": 2.0,
+      "learning_rate": 3.805301908254455e-08,
+      "loss": 0.1854,
+      "step": 1950
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.6171875,
+      "learning_rate": 2.4359497401758026e-08,
+      "loss": 0.1794,
+      "step": 1960
+    },
+    {
+      "epoch": 0.985,
+      "grad_norm": 2.109375,
+      "learning_rate": 1.370465245426167e-08,
+      "loss": 0.1818,
+      "step": 1970
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 1.9921875,
+      "learning_rate": 6.091729809042379e-09,
+      "loss": 0.1856,
+      "step": 1980
+    },
+    {
+      "epoch": 0.995,
+      "grad_norm": 1.9375,
+      "learning_rate": 1.5230484360873043e-09,
+      "loss": 0.1736,
+      "step": 1990
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.65625,
+      "learning_rate": 0.0,
+      "loss": 0.1816,
+      "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 sha256:206b03b520d0fa785a6ebb9c079f0187074a80da5b453ad2cb8f03a9db0abe07
+size 5368