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 +1,30 @@
+{
+  "_name_or_path": "microsoft/phi-1_5",
+  "architectures": [
+    "PhiForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "embd_pdrop": 0.0,
+  "eos_token_id": null,
+  "hidden_act": "gelu_new",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "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,
+  "partial_rotary_factor": 0.5,
+  "qk_layernorm": false,
+  "resid_pdrop": 0.0,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "vocab_size": 51200
+}

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.44.2"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56ca7f6577f13f576371180c92d351e4dc43b3f853691b135cbbf9ab07ef5148
+size 4976430784

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4a19f67ce191d9bf7069ca6f805039fb8c77b478e67794387a1d85ccd5d0601
+size 276951856

model.safetensors.index.json

@@ -0,0 +1,348 @@
+{
+  "metadata": {
+    "total_size": 5253345280
+  },
+  "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-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-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-00002-of-00002.safetensors",
+    "model.layers.23.mlp.fc2.weight": "model-00002-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.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"
+  }
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88b0ce88f0d6cb47c7c7e87103222d5f708612bcf40223477d1b75c6356a59c1
+size 2883245588

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98657e815d59c2d56b4a0b604f3c84ffbcae54e14dcbf89d0672074af82338c8
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8078c703aa7f876a72894cfe81d32548d710feab02ab5af2a6e2b5fcff507bf5
+size 1064

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 +1,325 @@
+{
+  "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|>",
+  "return_token_type_ids": false,
+  "tokenizer_class": "CodeGenTokenizer",
+  "unk_token": "<|endoftext|>"
+}

trainer_state.json

@@ -0,0 +1,568 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.09090909090909091,
+  "eval_steps": 500000000,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0018181818181818182,
+      "grad_norm": 0.04132210090756416,
+      "learning_rate": 1.0714285714285714e-06,
+      "loss": 0.0017,
+      "loss/crossentropy": 2.7622933089733124,
+      "loss/l2l": 0.0009595408992026933,
+      "loss/logits": 0.0007168808369897306,
+      "step": 1
+    },
+    {
+      "epoch": 0.0036363636363636364,
+      "grad_norm": 0.04106639698147774,
+      "learning_rate": 2.1428571428571427e-06,
+      "loss": 0.0017,
+      "loss/crossentropy": 2.802927404642105,
+      "loss/l2l": 0.0009558729943819344,
+      "loss/logits": 0.0006968109883018769,
+      "step": 2
+    },
+    {
+      "epoch": 0.005454545454545455,
+      "grad_norm": 0.02860172837972641,
+      "learning_rate": 3.2142857142857143e-06,
+      "loss": 0.0017,
+      "loss/crossentropy": 2.988768607378006,
+      "loss/l2l": 0.0009686681005405262,
+      "loss/logits": 0.0007133364561013877,
+      "step": 3
+    },
+    {
+      "epoch": 0.007272727272727273,
+      "grad_norm": 0.03197884559631348,
+      "learning_rate": 4.2857142857142855e-06,
+      "loss": 0.0016,
+      "loss/crossentropy": 2.84404656291008,
+      "loss/l2l": 0.0009548350426484831,
+      "loss/logits": 0.0006914191690157168,
+      "step": 4
+    },
+    {
+      "epoch": 0.00909090909090909,
+      "grad_norm": 0.0603456124663353,
+      "learning_rate": 5.357142857142857e-06,
+      "loss": 0.0016,
+      "loss/crossentropy": 2.7517194747924805,
+      "loss/l2l": 0.0009491091695963405,
+      "loss/logits": 0.0006914378391229548,
+      "step": 5
+    },
+    {
+      "epoch": 0.01090909090909091,
+      "grad_norm": 0.06845366209745407,
+      "learning_rate": 6.428571428571429e-06,
+      "loss": 0.0017,
+      "loss/crossentropy": 2.8530552983283997,
+      "loss/l2l": 0.0009954559864127077,
+      "loss/logits": 0.0007379417365882546,
+      "step": 6
+    },
+    {
+      "epoch": 0.012727272727272728,
+      "grad_norm": 0.05178389325737953,
+      "learning_rate": 7.5e-06,
+      "loss": 0.0017,
+      "loss/crossentropy": 2.90425181388855,
+      "loss/l2l": 0.0010071553260786459,
+      "loss/logits": 0.0007108178760972805,
+      "step": 7
+    },
+    {
+      "epoch": 0.014545454545454545,
+      "grad_norm": 0.054048214107751846,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 0.0017,
+      "loss/crossentropy": 2.7971068024635315,
+      "loss/l2l": 0.0009961284813471138,
+      "loss/logits": 0.0007163036207202822,
+      "step": 8
+    },
+    {
+      "epoch": 0.016363636363636365,
+      "grad_norm": 0.05026344209909439,
+      "learning_rate": 9.642857142857144e-06,
+      "loss": 0.0017,
+      "loss/crossentropy": 2.763449639081955,
+      "loss/l2l": 0.0009856029428192414,
+      "loss/logits": 0.0007231404961203225,
+      "step": 9
+    },
+    {
+      "epoch": 0.01818181818181818,
+      "grad_norm": 0.04901633411645889,
+      "learning_rate": 1.0714285714285714e-05,
+      "loss": 0.0017,
+      "loss/crossentropy": 2.680813044309616,
+      "loss/l2l": 0.0009604957012925297,
+      "loss/logits": 0.0007101441151462495,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.04477398097515106,
+      "learning_rate": 1.1785714285714286e-05,
+      "loss": 0.0017,
+      "loss/crossentropy": 2.8599877655506134,
+      "loss/l2l": 0.0009750521421665326,
+      "loss/logits": 0.0007274709205375984,
+      "step": 11
+    },
+    {
+      "epoch": 0.02181818181818182,
+      "grad_norm": 0.04958652704954147,
+      "learning_rate": 1.2857142857142857e-05,
+      "loss": 0.0017,
+      "loss/crossentropy": 2.7687041759490967,
+      "loss/l2l": 0.0009934628105838783,
+      "loss/logits": 0.0007402823903248645,
+      "step": 12
+    },
+    {
+      "epoch": 0.023636363636363636,
+      "grad_norm": 0.12496338784694672,
+      "learning_rate": 1.3928571428571429e-05,
+      "loss": 0.0018,
+      "loss/crossentropy": 2.858030617237091,
+      "loss/l2l": 0.0010261749412165955,
+      "loss/logits": 0.000771270235418342,
+      "step": 13
+    },
+    {
+      "epoch": 0.025454545454545455,
+      "grad_norm": 0.04944896697998047,
+      "learning_rate": 1.5e-05,
+      "loss": 0.0018,
+      "loss/crossentropy": 2.756019741296768,
+      "loss/l2l": 0.0009996299122576602,
+      "loss/logits": 0.0007917642433312722,
+      "step": 14
+    },
+    {
+      "epoch": 0.02727272727272727,
+      "grad_norm": 0.06439656019210815,
+      "learning_rate": 1.6071428571428572e-05,
+      "loss": 0.0018,
+      "loss/crossentropy": 2.781382232904434,
+      "loss/l2l": 0.0010389333037892357,
+      "loss/logits": 0.0007701097056269646,
+      "step": 15
+    },
+    {
+      "epoch": 0.02909090909090909,
+      "grad_norm": 0.102299265563488,
+      "grad_norm_var": 0.0006137877952514486,
+      "learning_rate": 1.7142857142857142e-05,
+      "loss": 0.0019,
+      "loss/crossentropy": 2.7935314774513245,
+      "loss/l2l": 0.0011146899196319282,
+      "loss/logits": 0.0008049706520978361,
+      "step": 16
+    },
+    {
+      "epoch": 0.03090909090909091,
+      "grad_norm": 0.19919118285179138,
+      "grad_norm_var": 0.0018409868011518837,
+      "learning_rate": 1.8214285714285712e-05,
+      "loss": 0.0022,
+      "loss/crossentropy": 2.7489033937454224,
+      "loss/l2l": 0.0013128551217960194,
+      "loss/logits": 0.0009216610269504599,
+      "step": 17
+    },
+    {
+      "epoch": 0.03272727272727273,
+      "grad_norm": 0.22971968352794647,
+      "grad_norm_var": 0.003415839283849396,
+      "learning_rate": 1.928571428571429e-05,
+      "loss": 0.0024,
+      "loss/crossentropy": 2.694430410861969,
+      "loss/l2l": 0.0014057953376322985,
+      "loss/logits": 0.0010042465873993933,
+      "step": 18
+    },
+    {
+      "epoch": 0.034545454545454546,
+      "grad_norm": 0.11894722282886505,
+      "grad_norm_var": 0.0033227439551323863,
+      "learning_rate": 2.0357142857142858e-05,
+      "loss": 0.0021,
+      "loss/crossentropy": 2.711204618215561,
+      "loss/l2l": 0.0012379496038192883,
+      "loss/logits": 0.0008569380661356263,
+      "step": 19
+    },
+    {
+      "epoch": 0.03636363636363636,
+      "grad_norm": 0.20271238684654236,
+      "grad_norm_var": 0.003952958885461364,
+      "learning_rate": 2.1428571428571428e-05,
+      "loss": 0.0024,
+      "loss/crossentropy": 2.8350090086460114,
+      "loss/l2l": 0.001426140035619028,
+      "loss/logits": 0.0010106879126396962,
+      "step": 20
+    },
+    {
+      "epoch": 0.038181818181818185,
+      "grad_norm": 0.27637943625450134,
+      "grad_norm_var": 0.005871758985536903,
+      "learning_rate": 2.25e-05,
+      "loss": 0.0029,
+      "loss/crossentropy": 2.817220240831375,
+      "loss/l2l": 0.0017183992604259402,
+      "loss/logits": 0.0011377454939065501,
+      "step": 21
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.1483398973941803,
+      "grad_norm_var": 0.005844079211650998,
+      "learning_rate": 2.357142857142857e-05,
+      "loss": 0.0026,
+      "loss/crossentropy": 2.6629598140716553,
+      "loss/l2l": 0.0014414641191251576,
+      "loss/logits": 0.0011263474370935,
+      "step": 22
+    },
+    {
+      "epoch": 0.04181818181818182,
+      "grad_norm": 0.31231889128685,
+      "grad_norm_var": 0.007942871853842676,
+      "learning_rate": 2.464285714285714e-05,
+      "loss": 0.0032,
+      "loss/crossentropy": 2.793576240539551,
+      "loss/l2l": 0.001893703723908402,
+      "loss/logits": 0.0012791378394467756,
+      "step": 23
+    },
+    {
+      "epoch": 0.04363636363636364,
+      "grad_norm": 0.31379568576812744,
+      "grad_norm_var": 0.009537011533626879,
+      "learning_rate": 2.5714285714285714e-05,
+      "loss": 0.0036,
+      "loss/crossentropy": 2.7321319580078125,
+      "loss/l2l": 0.0020761291089002043,
+      "loss/logits": 0.0014983194414526224,
+      "step": 24
+    },
+    {
+      "epoch": 0.045454545454545456,
+      "grad_norm": 0.19541873037815094,
+      "grad_norm_var": 0.009000816225916248,
+      "learning_rate": 2.6785714285714288e-05,
+      "loss": 0.003,
+      "loss/crossentropy": 2.934973895549774,
+      "loss/l2l": 0.0017724485078360885,
+      "loss/logits": 0.0011901934776687995,
+      "step": 25
+    },
+    {
+      "epoch": 0.04727272727272727,
+      "grad_norm": 0.3694976568222046,
+      "grad_norm_var": 0.010887818603336133,
+      "learning_rate": 2.7857142857142858e-05,
+      "loss": 0.0041,
+      "loss/crossentropy": 2.648868441581726,
+      "loss/l2l": 0.002608713912195526,
+      "loss/logits": 0.0014832951128482819,
+      "step": 26
+    },
+    {
+      "epoch": 0.04909090909090909,
+      "grad_norm": 0.28969135880470276,
+      "grad_norm_var": 0.01038058362472228,
+      "learning_rate": 2.892857142857143e-05,
+      "loss": 0.0042,
+      "loss/crossentropy": 2.814437657594681,
+      "loss/l2l": 0.0024781901156529784,
+      "loss/logits": 0.0016786862252047285,
+      "step": 27
+    },
+    {
+      "epoch": 0.05090909090909091,
+      "grad_norm": 0.4098244607448578,
+      "grad_norm_var": 0.011726859112086265,
+      "learning_rate": 3e-05,
+      "loss": 0.0049,
+      "loss/crossentropy": 2.72132471203804,
+      "loss/l2l": 0.003102809627307579,
+      "loss/logits": 0.0018214373558294028,
+      "step": 28
+    },
+    {
+      "epoch": 0.05272727272727273,
+      "grad_norm": 0.2779841423034668,
+      "grad_norm_var": 0.01139547365533376,
+      "learning_rate": 2.9942528735632184e-05,
+      "loss": 0.0048,
+      "loss/crossentropy": 2.838561028242111,
+      "loss/l2l": 0.003084438241785392,
+      "loss/logits": 0.0017654862313065678,
+      "step": 29
+    },
+    {
+      "epoch": 0.05454545454545454,
+      "grad_norm": 0.3950014114379883,
+      "grad_norm_var": 0.010885384331246674,
+      "learning_rate": 2.9885057471264367e-05,
+      "loss": 0.0056,
+      "loss/crossentropy": 2.8434397280216217,
+      "loss/l2l": 0.003621049108915031,
+      "loss/logits": 0.001961167756235227,
+      "step": 30
+    },
+    {
+      "epoch": 0.056363636363636366,
+      "grad_norm": 0.3249872028827667,
+      "grad_norm_var": 0.008885908834825448,
+      "learning_rate": 2.982758620689655e-05,
+      "loss": 0.0058,
+      "loss/crossentropy": 2.747708946466446,
+      "loss/l2l": 0.0036792022874578834,
+      "loss/logits": 0.002109401611960493,
+      "step": 31
+    },
+    {
+      "epoch": 0.05818181818181818,
+      "grad_norm": 0.4117155373096466,
+      "grad_norm_var": 0.008347786678573365,
+      "learning_rate": 2.977011494252874e-05,
+      "loss": 0.0069,
+      "loss/crossentropy": 2.9122725427150726,
+      "loss/l2l": 0.004092101618880406,
+      "loss/logits": 0.0027858328976435587,
+      "step": 32
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.4446941316127777,
+      "grad_norm_var": 0.009478749519190586,
+      "learning_rate": 2.9712643678160922e-05,
+      "loss": 0.0066,
+      "loss/crossentropy": 2.771754503250122,
+      "loss/l2l": 0.004197572561679408,
+      "loss/logits": 0.0024471503566019237,
+      "step": 33
+    },
+    {
+      "epoch": 0.06181818181818182,
+      "grad_norm": 0.2749296724796295,
+      "grad_norm_var": 0.009212599074280207,
+      "learning_rate": 2.9655172413793105e-05,
+      "loss": 0.0062,
+      "loss/crossentropy": 2.9203065037727356,
+      "loss/l2l": 0.003709066630108282,
+      "loss/logits": 0.002450398402288556,
+      "step": 34
+    },
+    {
+      "epoch": 0.06363636363636363,
+      "grad_norm": 0.3359372913837433,
+      "grad_norm_var": 0.006978222057891476,
+      "learning_rate": 2.9597701149425288e-05,
+      "loss": 0.0069,
+      "loss/crossentropy": 2.830071836709976,
+      "loss/l2l": 0.004047285532578826,
+      "loss/logits": 0.0028313595394138247,
+      "step": 35
+    },
+    {
+      "epoch": 0.06545454545454546,
+      "grad_norm": 0.37310054898262024,
+      "grad_norm_var": 0.006322343372460803,
+      "learning_rate": 2.954022988505747e-05,
+      "loss": 0.0077,
+      "loss/crossentropy": 2.791083812713623,
+      "loss/l2l": 0.004737939627375454,
+      "loss/logits": 0.0029615768289659172,
+      "step": 36
+    },
+    {
+      "epoch": 0.06727272727272728,
+      "grad_norm": 0.28037551045417786,
+      "grad_norm_var": 0.006298980507163872,
+      "learning_rate": 2.9482758620689654e-05,
+      "loss": 0.0059,
+      "loss/crossentropy": 2.976668804883957,
+      "loss/l2l": 0.00370109683717601,
+      "loss/logits": 0.002237219858216122,
+      "step": 37
+    },
+    {
+      "epoch": 0.06909090909090909,
+      "grad_norm": 0.3025270700454712,
+      "grad_norm_var": 0.004207470086681992,
+      "learning_rate": 2.942528735632184e-05,
+      "loss": 0.0066,
+      "loss/crossentropy": 2.733677864074707,
+      "loss/l2l": 0.004086089436896145,
+      "loss/logits": 0.0025196410133503377,
+      "step": 38
+    },
+    {
+      "epoch": 0.07090909090909091,
+      "grad_norm": 0.24721340835094452,
+      "grad_norm_var": 0.00464312785515946,
+      "learning_rate": 2.9367816091954026e-05,
+      "loss": 0.0062,
+      "loss/crossentropy": 2.6666863560676575,
+      "loss/l2l": 0.003797793237026781,
+      "loss/logits": 0.0024291283334605396,
+      "step": 39
+    },
+    {
+      "epoch": 0.07272727272727272,
+      "grad_norm": 0.289936900138855,
+      "grad_norm_var": 0.004723632117874236,
+      "learning_rate": 2.931034482758621e-05,
+      "loss": 0.0069,
+      "loss/crossentropy": 2.892277777194977,
+      "loss/l2l": 0.004447819956112653,
+      "loss/logits": 0.0024559909652452916,
+      "step": 40
+    },
+    {
+      "epoch": 0.07454545454545454,
+      "grad_norm": 0.30753007531166077,
+      "grad_norm_var": 0.0035508537798317817,
+      "learning_rate": 2.9252873563218392e-05,
+      "loss": 0.0073,
+      "loss/crossentropy": 2.8552375435829163,
+      "loss/l2l": 0.004510597180342302,
+      "loss/logits": 0.00280093660694547,
+      "step": 41
+    },
+    {
+      "epoch": 0.07636363636363637,
+      "grad_norm": 0.2965009808540344,
+      "grad_norm_var": 0.003532883786427161,
+      "learning_rate": 2.9195402298850575e-05,
+      "loss": 0.0067,
+      "loss/crossentropy": 2.8460004329681396,
+      "loss/l2l": 0.004156478098593652,
+      "loss/logits": 0.002593511962913908,
+      "step": 42
+    },
+    {
+      "epoch": 0.07818181818181819,
+      "grad_norm": 0.2612462043762207,
+      "grad_norm_var": 0.003732053586203957,
+      "learning_rate": 2.9137931034482758e-05,
+      "loss": 0.0077,
+      "loss/crossentropy": 2.8262108862400055,
+      "loss/l2l": 0.004398627730552107,
+      "loss/logits": 0.0032597231620457023,
+      "step": 43
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.3191143870353699,
+      "grad_norm_var": 0.0032457256840179,
+      "learning_rate": 2.908045977011494e-05,
+      "loss": 0.0072,
+      "loss/crossentropy": 2.8497148752212524,
+      "loss/l2l": 0.004310946678742766,
+      "loss/logits": 0.0028486791998147964,
+      "step": 44
+    },
+    {
+      "epoch": 0.08181818181818182,
+      "grad_norm": 0.2747066915035248,
+      "grad_norm_var": 0.0032653802581926435,
+      "learning_rate": 2.9022988505747127e-05,
+      "loss": 0.0076,
+      "loss/crossentropy": 2.8268313109874725,
+      "loss/l2l": 0.00447584519861266,
+      "loss/logits": 0.003080013470025733,
+      "step": 45
+    },
+    {
+      "epoch": 0.08363636363636363,
+      "grad_norm": 0.2777577042579651,
+      "grad_norm_var": 0.0029711202872247555,
+      "learning_rate": 2.8965517241379313e-05,
+      "loss": 0.0084,
+      "loss/crossentropy": 2.7914853394031525,
+      "loss/l2l": 0.00501172652002424,
+      "loss/logits": 0.003353950713062659,
+      "step": 46
+    },
+    {
+      "epoch": 0.08545454545454545,
+      "grad_norm": 0.30310961604118347,
+      "grad_norm_var": 0.002968669992424177,
+      "learning_rate": 2.8908045977011496e-05,
+      "loss": 0.0078,
+      "loss/crossentropy": 2.768044173717499,
+      "loss/l2l": 0.004455980146303773,
+      "loss/logits": 0.0032976260408759117,
+      "step": 47
+    },
+    {
+      "epoch": 0.08727272727272728,
+      "grad_norm": 0.315398246049881,
+      "grad_norm_var": 0.0022746451695018943,
+      "learning_rate": 2.885057471264368e-05,
+      "loss": 0.0115,
+      "loss/crossentropy": 2.8318784832954407,
+      "loss/l2l": 0.00476662625442259,
+      "loss/logits": 0.006771241663955152,
+      "step": 48
+    },
+    {
+      "epoch": 0.0890909090909091,
+      "grad_norm": 0.3326970934867859,
+      "grad_norm_var": 0.0009950324545609317,
+      "learning_rate": 2.8793103448275862e-05,
+      "loss": 0.0079,
+      "loss/crossentropy": 2.9197411835193634,
+      "loss/l2l": 0.005106233642436564,
+      "loss/logits": 0.0027626882947515696,
+      "step": 49
+    },
+    {
+      "epoch": 0.09090909090909091,
+      "grad_norm": 0.32663774490356445,
+      "grad_norm_var": 0.0009927072727197533,
+      "learning_rate": 2.8735632183908045e-05,
+      "loss": 0.0085,
+      "loss/crossentropy": 2.664418041706085,
+      "loss/l2l": 0.0049499672604724765,
+      "loss/logits": 0.003536010714014992,
+      "step": 50
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 550,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9223372036854775807,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.5822752669696e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e09cbc0bffafb5aecd58cb8b1df2f7affc2b2c84f3ef070008f59b0462e58f4
+size 5240