Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,40 @@
+{
+  "\t\t": 50294,
+  "\t\t\t": 50293,
+  "\t\t\t\t": 50292,
+  "\t\t\t\t\t": 50291,
+  "\t\t\t\t\t\t": 50290,
+  "\t\t\t\t\t\t\t": 50289,
+  "\t\t\t\t\t\t\t\t": 50288,
+  "\t\t\t\t\t\t\t\t\t": 50287,
+  "  ": 50286,
+  "   ": 50285,
+  "    ": 50284,
+  "     ": 50283,
+  "      ": 50282,
+  "       ": 50281,
+  "        ": 50280,
+  "         ": 50279,
+  "          ": 50278,
+  "           ": 50277,
+  "            ": 50276,
+  "             ": 50275,
+  "              ": 50274,
+  "               ": 50273,
+  "                ": 50272,
+  "                 ": 50271,
+  "                  ": 50270,
+  "                   ": 50269,
+  "                    ": 50268,
+  "                     ": 50267,
+  "                      ": 50266,
+  "                       ": 50265,
+  "                        ": 50264,
+  "                         ": 50263,
+  "                          ": 50262,
+  "                           ": 50261,
+  "                            ": 50260,
+  "                             ": 50259,
+  "                              ": 50258,
+  "                               ": 50257
+}

config.json

@@ -0,0 +1,50 @@
+{
+  "_name_or_path": "microsoft/phi-1",
+  "architectures": [
+    "PhiForSequenceClassification"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "microsoft/phi-1--configuration_phi.PhiConfig",
+    "AutoModelForCausalLM": "microsoft/phi-1--modeling_phi.PhiForCausalLM"
+  },
+  "bos_token_id": null,
+  "embd_pdrop": 0.0,
+  "eos_token_id": null,
+  "hidden_act": "gelu_new",
+  "hidden_size": 2048,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "phi",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 32,
+  "pad_token_id": 50256,
+  "partial_rotary_factor": 0.5,
+  "problem_type": "single_label_classification",
+  "qk_layernorm": false,
+  "resid_pdrop": 0.0,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 50295
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a3d09d9cb13a238a936f56851901998e11f4c8607d9f8df4315dc69e3415c9a
+size 4977502392

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaa860ec47d0d2a341bc1c14dca3b002a21f5db8f6770326e7b3c02f4f58fa60
+size 268609688

model.safetensors.index.json

@@ -0,0 +1,347 @@
+{
+  "metadata": {
+    "total_size": 5246074880
+  },
+  "weight_map": {
+    "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-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-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-00002-of-00002.safetensors",
+    "model.layers.22.mlp.fc2.weight": "model-00002-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-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.dense.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.dense.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-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.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",
+    "score.weight": "model-00002-of-00002.safetensors"
+  }
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7df2890f80c5aa96e710152eb537de15df7afab5ff894947d5a36ff9a98bb5f
+size 10492444053

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2278a87cdf86c3f9219223c847f6b27f6b7f15b8226b617f38936e8ff2cbcde
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cb3c4a3b46289636891768e1330232ee327d2c0d3ba3003cc04e21e2b95cf97
+size 627

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,324 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "                               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "                         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50277": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50278": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50279": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50280": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50281": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50282": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50283": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50284": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50285": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50286": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50287": {
+      "content": "\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50288": {
+      "content": "\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50289": {
+      "content": "\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50290": {
+      "content": "\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50291": {
+      "content": "\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50292": {
+      "content": "\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50293": {
+      "content": "\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50294": {
+      "content": "\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "CodeGenTokenizer",
+  "unk_token": "<|endoftext|>"
+}

trainer_state.json

@@ -0,0 +1,1164 @@
+{
+  "best_metric": 0.7210479974746704,
+  "best_model_checkpoint": "sean_test_out/checkpoint-81250",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 81250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "grad_norm": 143092.3125,
+      "learning_rate": 5.9630769230769234e-05,
+      "loss": 1.284,
+      "step": 500
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 220955.625,
+      "learning_rate": 5.926153846153846e-05,
+      "loss": 1.0569,
+      "step": 1000
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 195870.921875,
+      "learning_rate": 5.88923076923077e-05,
+      "loss": 1.02,
+      "step": 1500
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 375734.96875,
+      "learning_rate": 5.8523076923076926e-05,
+      "loss": 0.9793,
+      "step": 2000
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 294788.75,
+      "learning_rate": 5.815384615384616e-05,
+      "loss": 0.9703,
+      "step": 2500
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 185062.484375,
+      "learning_rate": 5.7784615384615384e-05,
+      "loss": 0.9628,
+      "step": 3000
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 91022.734375,
+      "learning_rate": 5.741538461538462e-05,
+      "loss": 0.9524,
+      "step": 3500
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 262511.375,
+      "learning_rate": 5.704615384615385e-05,
+      "loss": 0.9158,
+      "step": 4000
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 205652.171875,
+      "learning_rate": 5.667692307692308e-05,
+      "loss": 0.9065,
+      "step": 4500
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 133203.75,
+      "learning_rate": 5.630769230769231e-05,
+      "loss": 0.9291,
+      "step": 5000
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 287849.9375,
+      "learning_rate": 5.593846153846154e-05,
+      "loss": 0.8981,
+      "step": 5500
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 295450.40625,
+      "learning_rate": 5.556923076923077e-05,
+      "loss": 0.8868,
+      "step": 6000
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 229412.40625,
+      "learning_rate": 5.520000000000001e-05,
+      "loss": 0.9001,
+      "step": 6500
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 362417.71875,
+      "learning_rate": 5.483076923076923e-05,
+      "loss": 0.8748,
+      "step": 7000
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 232139.9375,
+      "learning_rate": 5.4461538461538466e-05,
+      "loss": 0.8565,
+      "step": 7500
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 439068.125,
+      "learning_rate": 5.409230769230769e-05,
+      "loss": 0.8653,
+      "step": 8000
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 176573.96875,
+      "learning_rate": 5.3723076923076924e-05,
+      "loss": 0.8592,
+      "step": 8500
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 122979.9140625,
+      "learning_rate": 5.335384615384616e-05,
+      "loss": 0.8881,
+      "step": 9000
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 163604.125,
+      "learning_rate": 5.298461538461539e-05,
+      "loss": 0.8512,
+      "step": 9500
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 265370.75,
+      "learning_rate": 5.2615384615384616e-05,
+      "loss": 0.8654,
+      "step": 10000
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 308622.75,
+      "learning_rate": 5.224615384615385e-05,
+      "loss": 0.849,
+      "step": 10500
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 121160.9609375,
+      "learning_rate": 5.1876923076923074e-05,
+      "loss": 0.8561,
+      "step": 11000
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 172874.421875,
+      "learning_rate": 5.1507692307692314e-05,
+      "loss": 0.8487,
+      "step": 11500
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 227611.28125,
+      "learning_rate": 5.113846153846154e-05,
+      "loss": 0.8266,
+      "step": 12000
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 61996.62890625,
+      "learning_rate": 5.076923076923077e-05,
+      "loss": 0.8243,
+      "step": 12500
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 157856.609375,
+      "learning_rate": 5.04e-05,
+      "loss": 0.8127,
+      "step": 13000
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 308874.09375,
+      "learning_rate": 5.003076923076923e-05,
+      "loss": 0.8439,
+      "step": 13500
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 234965.546875,
+      "learning_rate": 4.9661538461538464e-05,
+      "loss": 0.8501,
+      "step": 14000
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 146659.5,
+      "learning_rate": 4.92923076923077e-05,
+      "loss": 0.8142,
+      "step": 14500
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 330394.90625,
+      "learning_rate": 4.892307692307692e-05,
+      "loss": 0.8347,
+      "step": 15000
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 134570.78125,
+      "learning_rate": 4.8553846153846155e-05,
+      "loss": 0.8189,
+      "step": 15500
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 231298.65625,
+      "learning_rate": 4.818461538461538e-05,
+      "loss": 0.8235,
+      "step": 16000
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 180303.484375,
+      "learning_rate": 4.781538461538462e-05,
+      "loss": 0.8131,
+      "step": 16500
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 326101.53125,
+      "learning_rate": 4.744615384615385e-05,
+      "loss": 0.8432,
+      "step": 17000
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 184914.640625,
+      "learning_rate": 4.707692307692308e-05,
+      "loss": 0.8138,
+      "step": 17500
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 159594.78125,
+      "learning_rate": 4.6707692307692306e-05,
+      "loss": 0.8243,
+      "step": 18000
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 282742.4375,
+      "learning_rate": 4.6338461538461545e-05,
+      "loss": 0.827,
+      "step": 18500
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 203088.765625,
+      "learning_rate": 4.596923076923077e-05,
+      "loss": 0.8547,
+      "step": 19000
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 220744.96875,
+      "learning_rate": 4.5600000000000004e-05,
+      "loss": 0.8126,
+      "step": 19500
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 244869.15625,
+      "learning_rate": 4.523076923076923e-05,
+      "loss": 0.8038,
+      "step": 20000
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 168005.03125,
+      "learning_rate": 4.486153846153846e-05,
+      "loss": 0.8196,
+      "step": 20500
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 201658.421875,
+      "learning_rate": 4.4492307692307695e-05,
+      "loss": 0.8087,
+      "step": 21000
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 149320.546875,
+      "learning_rate": 4.412307692307693e-05,
+      "loss": 0.8014,
+      "step": 21500
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 174892.421875,
+      "learning_rate": 4.3753846153846154e-05,
+      "loss": 0.8044,
+      "step": 22000
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 91686.6953125,
+      "learning_rate": 4.338461538461539e-05,
+      "loss": 0.8066,
+      "step": 22500
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 159807.546875,
+      "learning_rate": 4.301538461538461e-05,
+      "loss": 0.7999,
+      "step": 23000
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 74645.9609375,
+      "learning_rate": 4.264615384615385e-05,
+      "loss": 0.8069,
+      "step": 23500
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 150263.703125,
+      "learning_rate": 4.227692307692308e-05,
+      "loss": 0.8012,
+      "step": 24000
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 128120.828125,
+      "learning_rate": 4.190769230769231e-05,
+      "loss": 0.8068,
+      "step": 24500
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 179413.015625,
+      "learning_rate": 4.153846153846154e-05,
+      "loss": 0.7907,
+      "step": 25000
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 185550.65625,
+      "learning_rate": 4.116923076923077e-05,
+      "loss": 0.8009,
+      "step": 25500
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 188985.90625,
+      "learning_rate": 4.08e-05,
+      "loss": 0.7801,
+      "step": 26000
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 144887.1875,
+      "learning_rate": 4.0430769230769235e-05,
+      "loss": 0.8008,
+      "step": 26500
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 127779.3515625,
+      "learning_rate": 4.006153846153846e-05,
+      "loss": 0.8072,
+      "step": 27000
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 170718.90625,
+      "learning_rate": 3.9692307692307694e-05,
+      "loss": 0.7795,
+      "step": 27500
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 144447.703125,
+      "learning_rate": 3.932307692307692e-05,
+      "loss": 0.7961,
+      "step": 28000
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 214981.546875,
+      "learning_rate": 3.895384615384616e-05,
+      "loss": 0.8085,
+      "step": 28500
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 152927.65625,
+      "learning_rate": 3.8584615384615385e-05,
+      "loss": 0.8134,
+      "step": 29000
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 139227.46875,
+      "learning_rate": 3.821538461538462e-05,
+      "loss": 0.7859,
+      "step": 29500
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 180853.71875,
+      "learning_rate": 3.7846153846153844e-05,
+      "loss": 0.7803,
+      "step": 30000
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 223101.5625,
+      "learning_rate": 3.747692307692308e-05,
+      "loss": 0.7783,
+      "step": 30500
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 135408.609375,
+      "learning_rate": 3.710769230769231e-05,
+      "loss": 0.7729,
+      "step": 31000
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 162892.96875,
+      "learning_rate": 3.673846153846154e-05,
+      "loss": 0.7834,
+      "step": 31500
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 100030.2265625,
+      "learning_rate": 3.636923076923077e-05,
+      "loss": 0.7979,
+      "step": 32000
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 139896.234375,
+      "learning_rate": 3.6e-05,
+      "loss": 0.8103,
+      "step": 32500
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 252651.6875,
+      "learning_rate": 3.563076923076923e-05,
+      "loss": 0.7809,
+      "step": 33000
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 203613.046875,
+      "learning_rate": 3.5261538461538466e-05,
+      "loss": 0.7929,
+      "step": 33500
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 242859.828125,
+      "learning_rate": 3.489230769230769e-05,
+      "loss": 0.7644,
+      "step": 34000
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 119250.8203125,
+      "learning_rate": 3.4523076923076925e-05,
+      "loss": 0.783,
+      "step": 34500
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 242804.640625,
+      "learning_rate": 3.415384615384615e-05,
+      "loss": 0.7716,
+      "step": 35000
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 190967.953125,
+      "learning_rate": 3.3784615384615384e-05,
+      "loss": 0.7651,
+      "step": 35500
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 94749.5390625,
+      "learning_rate": 3.3415384615384617e-05,
+      "loss": 0.776,
+      "step": 36000
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 207242.640625,
+      "learning_rate": 3.304615384615385e-05,
+      "loss": 0.7691,
+      "step": 36500
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 168760.109375,
+      "learning_rate": 3.2676923076923075e-05,
+      "loss": 0.7726,
+      "step": 37000
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 118607.4921875,
+      "learning_rate": 3.230769230769231e-05,
+      "loss": 0.7882,
+      "step": 37500
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 273119.8125,
+      "learning_rate": 3.1938461538461534e-05,
+      "loss": 0.7551,
+      "step": 38000
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 146971.109375,
+      "learning_rate": 3.1569230769230773e-05,
+      "loss": 0.7744,
+      "step": 38500
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 137494.625,
+      "learning_rate": 3.12e-05,
+      "loss": 0.7544,
+      "step": 39000
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 157850.96875,
+      "learning_rate": 3.083076923076923e-05,
+      "loss": 0.7666,
+      "step": 39500
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 121842.53125,
+      "learning_rate": 3.046153846153846e-05,
+      "loss": 0.779,
+      "step": 40000
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 238816.578125,
+      "learning_rate": 3.009230769230769e-05,
+      "loss": 0.7595,
+      "step": 40500
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 202905.109375,
+      "learning_rate": 2.9723076923076924e-05,
+      "loss": 0.7742,
+      "step": 41000
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 118714.484375,
+      "learning_rate": 2.9353846153846156e-05,
+      "loss": 0.7616,
+      "step": 41500
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 78076.921875,
+      "learning_rate": 2.8984615384615386e-05,
+      "loss": 0.7365,
+      "step": 42000
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 185485.65625,
+      "learning_rate": 2.861538461538462e-05,
+      "loss": 0.7758,
+      "step": 42500
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 281552.0625,
+      "learning_rate": 2.8246153846153848e-05,
+      "loss": 0.7684,
+      "step": 43000
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 158893.921875,
+      "learning_rate": 2.7876923076923077e-05,
+      "loss": 0.7746,
+      "step": 43500
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 107463.6015625,
+      "learning_rate": 2.750769230769231e-05,
+      "loss": 0.7434,
+      "step": 44000
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 167811.15625,
+      "learning_rate": 2.713846153846154e-05,
+      "loss": 0.7878,
+      "step": 44500
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 246179.9375,
+      "learning_rate": 2.6769230769230772e-05,
+      "loss": 0.7566,
+      "step": 45000
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 192624.828125,
+      "learning_rate": 2.64e-05,
+      "loss": 0.7549,
+      "step": 45500
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 298613.28125,
+      "learning_rate": 2.603076923076923e-05,
+      "loss": 0.7586,
+      "step": 46000
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 188642.6875,
+      "learning_rate": 2.5661538461538463e-05,
+      "loss": 0.7435,
+      "step": 46500
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 170600.96875,
+      "learning_rate": 2.5292307692307693e-05,
+      "loss": 0.7559,
+      "step": 47000
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 114553.796875,
+      "learning_rate": 2.4923076923076926e-05,
+      "loss": 0.7369,
+      "step": 47500
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 177816.875,
+      "learning_rate": 2.4553846153846155e-05,
+      "loss": 0.7704,
+      "step": 48000
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 137487.265625,
+      "learning_rate": 2.4184615384615384e-05,
+      "loss": 0.7455,
+      "step": 48500
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 245769.703125,
+      "learning_rate": 2.3815384615384617e-05,
+      "loss": 0.7404,
+      "step": 49000
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 119365.515625,
+      "learning_rate": 2.3446153846153846e-05,
+      "loss": 0.7554,
+      "step": 49500
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 236374.578125,
+      "learning_rate": 2.307692307692308e-05,
+      "loss": 0.7582,
+      "step": 50000
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 167086.234375,
+      "learning_rate": 2.270769230769231e-05,
+      "loss": 0.7535,
+      "step": 50500
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 162424.609375,
+      "learning_rate": 2.2338461538461538e-05,
+      "loss": 0.7548,
+      "step": 51000
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 184460.578125,
+      "learning_rate": 2.196923076923077e-05,
+      "loss": 0.7365,
+      "step": 51500
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 82718.4375,
+      "learning_rate": 2.16e-05,
+      "loss": 0.7843,
+      "step": 52000
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 192023.21875,
+      "learning_rate": 2.1230769230769233e-05,
+      "loss": 0.7276,
+      "step": 52500
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 168197.328125,
+      "learning_rate": 2.0861538461538462e-05,
+      "loss": 0.759,
+      "step": 53000
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 215071.3125,
+      "learning_rate": 2.049230769230769e-05,
+      "loss": 0.733,
+      "step": 53500
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 215896.6875,
+      "learning_rate": 2.0123076923076924e-05,
+      "loss": 0.7423,
+      "step": 54000
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 231679.890625,
+      "learning_rate": 1.9753846153846153e-05,
+      "loss": 0.7586,
+      "step": 54500
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 198304.984375,
+      "learning_rate": 1.9384615384615386e-05,
+      "loss": 0.7276,
+      "step": 55000
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 154414.9375,
+      "learning_rate": 1.9015384615384616e-05,
+      "loss": 0.7266,
+      "step": 55500
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 104532.3984375,
+      "learning_rate": 1.8646153846153845e-05,
+      "loss": 0.7646,
+      "step": 56000
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 135327.46875,
+      "learning_rate": 1.8276923076923078e-05,
+      "loss": 0.7516,
+      "step": 56500
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 211435.890625,
+      "learning_rate": 1.7907692307692307e-05,
+      "loss": 0.748,
+      "step": 57000
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 198907.0,
+      "learning_rate": 1.753846153846154e-05,
+      "loss": 0.7445,
+      "step": 57500
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 159631.171875,
+      "learning_rate": 1.716923076923077e-05,
+      "loss": 0.738,
+      "step": 58000
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 99158.5234375,
+      "learning_rate": 1.6800000000000002e-05,
+      "loss": 0.7502,
+      "step": 58500
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 211235.359375,
+      "learning_rate": 1.643076923076923e-05,
+      "loss": 0.7467,
+      "step": 59000
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 196873.21875,
+      "learning_rate": 1.606153846153846e-05,
+      "loss": 0.7409,
+      "step": 59500
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 129529.453125,
+      "learning_rate": 1.5692307692307693e-05,
+      "loss": 0.7482,
+      "step": 60000
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 377672.9375,
+      "learning_rate": 1.5323076923076923e-05,
+      "loss": 0.7327,
+      "step": 60500
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 193886.515625,
+      "learning_rate": 1.4953846153846154e-05,
+      "loss": 0.7412,
+      "step": 61000
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 381785.875,
+      "learning_rate": 1.4584615384615385e-05,
+      "loss": 0.7404,
+      "step": 61500
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 180874.8125,
+      "learning_rate": 1.4215384615384616e-05,
+      "loss": 0.7358,
+      "step": 62000
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 128392.703125,
+      "learning_rate": 1.3846153846153847e-05,
+      "loss": 0.7432,
+      "step": 62500
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 86952.875,
+      "learning_rate": 1.3476923076923076e-05,
+      "loss": 0.7302,
+      "step": 63000
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 149977.921875,
+      "learning_rate": 1.3107692307692307e-05,
+      "loss": 0.7252,
+      "step": 63500
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 294148.46875,
+      "learning_rate": 1.2738461538461538e-05,
+      "loss": 0.7197,
+      "step": 64000
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 165598.09375,
+      "learning_rate": 1.236923076923077e-05,
+      "loss": 0.7557,
+      "step": 64500
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 70225.3125,
+      "learning_rate": 1.2e-05,
+      "loss": 0.7364,
+      "step": 65000
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 182316.828125,
+      "learning_rate": 1.163076923076923e-05,
+      "loss": 0.7468,
+      "step": 65500
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 214259.90625,
+      "learning_rate": 1.126153846153846e-05,
+      "loss": 0.7108,
+      "step": 66000
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 149377.9375,
+      "learning_rate": 1.0892307692307692e-05,
+      "loss": 0.7428,
+      "step": 66500
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 204207.546875,
+      "learning_rate": 1.0523076923076923e-05,
+      "loss": 0.709,
+      "step": 67000
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 117305.4296875,
+      "learning_rate": 1.0153846153846154e-05,
+      "loss": 0.7298,
+      "step": 67500
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 102029.6015625,
+      "learning_rate": 9.784615384615385e-06,
+      "loss": 0.7149,
+      "step": 68000
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 128112.8046875,
+      "learning_rate": 9.415384615384616e-06,
+      "loss": 0.7377,
+      "step": 68500
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 152489.640625,
+      "learning_rate": 9.046153846153847e-06,
+      "loss": 0.7092,
+      "step": 69000
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 163935.234375,
+      "learning_rate": 8.676923076923078e-06,
+      "loss": 0.7336,
+      "step": 69500
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 280511.15625,
+      "learning_rate": 8.307692307692309e-06,
+      "loss": 0.7268,
+      "step": 70000
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 99928.0234375,
+      "learning_rate": 7.93846153846154e-06,
+      "loss": 0.7194,
+      "step": 70500
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 154504.671875,
+      "learning_rate": 7.569230769230769e-06,
+      "loss": 0.7235,
+      "step": 71000
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 164383.453125,
+      "learning_rate": 7.2e-06,
+      "loss": 0.7418,
+      "step": 71500
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 228512.703125,
+      "learning_rate": 6.830769230769231e-06,
+      "loss": 0.7193,
+      "step": 72000
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 245047.8125,
+      "learning_rate": 6.461538461538462e-06,
+      "loss": 0.7192,
+      "step": 72500
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 159019.28125,
+      "learning_rate": 6.092307692307692e-06,
+      "loss": 0.7181,
+      "step": 73000
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 175369.8125,
+      "learning_rate": 5.723076923076923e-06,
+      "loss": 0.7187,
+      "step": 73500
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 328376.28125,
+      "learning_rate": 5.353846153846153e-06,
+      "loss": 0.728,
+      "step": 74000
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 217310.265625,
+      "learning_rate": 4.984615384615385e-06,
+      "loss": 0.7318,
+      "step": 74500
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 260174.71875,
+      "learning_rate": 4.615384615384616e-06,
+      "loss": 0.7076,
+      "step": 75000
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 208830.875,
+      "learning_rate": 4.246153846153846e-06,
+      "loss": 0.7062,
+      "step": 75500
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 293483.0,
+      "learning_rate": 3.876923076923077e-06,
+      "loss": 0.7124,
+      "step": 76000
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 120294.0078125,
+      "learning_rate": 3.5076923076923076e-06,
+      "loss": 0.7144,
+      "step": 76500
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 161758.796875,
+      "learning_rate": 3.1384615384615382e-06,
+      "loss": 0.7206,
+      "step": 77000
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 218907.75,
+      "learning_rate": 2.7692307692307693e-06,
+      "loss": 0.71,
+      "step": 77500
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 185302.8125,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 0.7216,
+      "step": 78000
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 178341.28125,
+      "learning_rate": 2.030769230769231e-06,
+      "loss": 0.7362,
+      "step": 78500
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 149915.484375,
+      "learning_rate": 1.6615384615384616e-06,
+      "loss": 0.709,
+      "step": 79000
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 167170.640625,
+      "learning_rate": 1.2923076923076922e-06,
+      "loss": 0.7186,
+      "step": 79500
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 184650.28125,
+      "learning_rate": 9.230769230769231e-07,
+      "loss": 0.7077,
+      "step": 80000
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 111304.5078125,
+      "learning_rate": 5.53846153846154e-07,
+      "loss": 0.6904,
+      "step": 80500
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 277845.34375,
+      "learning_rate": 1.846153846153846e-07,
+      "loss": 0.7259,
+      "step": 81000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.68412,
+      "eval_loss": 0.7210479974746704,
+      "eval_runtime": 1756.6277,
+      "eval_samples_per_second": 28.464,
+      "eval_steps_per_second": 3.558,
+      "step": 81250
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 81250,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 2.1137491040083968e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:838959b28fa34c99afd61e7eb4a021a42c8de0fb9a85cd10bb1e97311ef8c962
+size 4539