Upload 8 files

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "microsoft/phi-1_5",
+  "architectures": [
+    "PhiForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "microsoft/phi-1_5--configuration_phi.PhiConfig",
+    "AutoModelForCausalLM": "microsoft/phi-1_5--modeling_phi.PhiForCausalLM"
+  },
+  "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": "float32",
+  "transformers_version": "4.40.0.dev0",
+  "use_cache": true,
+  "vocab_size": 51200
+}

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.40.0.dev0"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:405ab540656989da80ba9df89253fc0108f988e4e2edcc99124742d906fc100f
+size 4984916152

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d4b997597d2971f9d04a65de50cc9ccd0beee6d27d605cdd5eeda28f298e5d7
+size 688204064

model.safetensors.index.json

@@ -0,0 +1,348 @@
+{
+  "metadata": {
+    "total_size": 5673082880
+  },
+  "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-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"
+  }
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8ff17ad8275aaab889de49950978c13c1e8be2f90923bebd009f6bb2324c58b
+size 14244

trainer_state.json

@@ -0,0 +1,771 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.820250284414107,
+  "eval_steps": 200,
+  "global_step": 5000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.7517368793487549,
+      "learning_rate": 9.999e-07,
+      "loss": 0.2253,
+      "step": 100
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 1.4760167598724365,
+      "learning_rate": 9.998e-07,
+      "loss": 0.1588,
+      "step": 200
+    },
+    {
+      "epoch": 0.07,
+      "eval_validation_loss": 0.1540723592042923,
+      "eval_validation_runtime": 386.0092,
+      "eval_validation_samples_per_second": 3.0,
+      "eval_validation_steps_per_second": 0.376,
+      "step": 200
+    },
+    {
+      "epoch": 0.07,
+      "eval_benchmark_loss": 0.3658876121044159,
+      "eval_benchmark_runtime": 9.4993,
+      "eval_benchmark_samples_per_second": 2.737,
+      "eval_benchmark_steps_per_second": 0.421,
+      "step": 200
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 1.4102065563201904,
+      "learning_rate": 9.997e-07,
+      "loss": 0.1423,
+      "step": 300
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 1.657212495803833,
+      "learning_rate": 9.996e-07,
+      "loss": 0.1345,
+      "step": 400
+    },
+    {
+      "epoch": 0.15,
+      "eval_validation_loss": 0.13775885105133057,
+      "eval_validation_runtime": 383.1365,
+      "eval_validation_samples_per_second": 3.022,
+      "eval_validation_steps_per_second": 0.378,
+      "step": 400
+    },
+    {
+      "epoch": 0.15,
+      "eval_benchmark_loss": 0.3596523106098175,
+      "eval_benchmark_runtime": 9.4551,
+      "eval_benchmark_samples_per_second": 2.75,
+      "eval_benchmark_steps_per_second": 0.423,
+      "step": 400
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.1109451055526733,
+      "learning_rate": 9.995e-07,
+      "loss": 0.1278,
+      "step": 500
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.219743013381958,
+      "learning_rate": 9.994e-07,
+      "loss": 0.128,
+      "step": 600
+    },
+    {
+      "epoch": 0.22,
+      "eval_validation_loss": 0.1310659945011139,
+      "eval_validation_runtime": 382.987,
+      "eval_validation_samples_per_second": 3.024,
+      "eval_validation_steps_per_second": 0.379,
+      "step": 600
+    },
+    {
+      "epoch": 0.22,
+      "eval_benchmark_loss": 0.35413601994514465,
+      "eval_benchmark_runtime": 9.452,
+      "eval_benchmark_samples_per_second": 2.751,
+      "eval_benchmark_steps_per_second": 0.423,
+      "step": 600
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 1.3631513118743896,
+      "learning_rate": 9.993e-07,
+      "loss": 0.1251,
+      "step": 700
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 1.6779521703720093,
+      "learning_rate": 9.992e-07,
+      "loss": 0.1198,
+      "step": 800
+    },
+    {
+      "epoch": 0.29,
+      "eval_validation_loss": 0.12629443407058716,
+      "eval_validation_runtime": 383.2491,
+      "eval_validation_samples_per_second": 3.022,
+      "eval_validation_steps_per_second": 0.378,
+      "step": 800
+    },
+    {
+      "epoch": 0.29,
+      "eval_benchmark_loss": 0.35233384370803833,
+      "eval_benchmark_runtime": 9.4696,
+      "eval_benchmark_samples_per_second": 2.746,
+      "eval_benchmark_steps_per_second": 0.422,
+      "step": 800
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 2.0499491691589355,
+      "learning_rate": 9.990999999999999e-07,
+      "loss": 0.1127,
+      "step": 900
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 2.0875236988067627,
+      "learning_rate": 9.989999999999999e-07,
+      "loss": 0.1227,
+      "step": 1000
+    },
+    {
+      "epoch": 0.36,
+      "eval_validation_loss": 0.12267088890075684,
+      "eval_validation_runtime": 383.4228,
+      "eval_validation_samples_per_second": 3.02,
+      "eval_validation_steps_per_second": 0.378,
+      "step": 1000
+    },
+    {
+      "epoch": 0.36,
+      "eval_benchmark_loss": 0.35131120681762695,
+      "eval_benchmark_runtime": 9.4614,
+      "eval_benchmark_samples_per_second": 2.748,
+      "eval_benchmark_steps_per_second": 0.423,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.061170816421509,
+      "learning_rate": 9.988999999999999e-07,
+      "loss": 0.1178,
+      "step": 1100
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.5514030456542969,
+      "learning_rate": 9.988e-07,
+      "loss": 0.1157,
+      "step": 1200
+    },
+    {
+      "epoch": 0.44,
+      "eval_validation_loss": 0.12000161409378052,
+      "eval_validation_runtime": 383.1507,
+      "eval_validation_samples_per_second": 3.022,
+      "eval_validation_steps_per_second": 0.378,
+      "step": 1200
+    },
+    {
+      "epoch": 0.44,
+      "eval_benchmark_loss": 0.3518659174442291,
+      "eval_benchmark_runtime": 9.4808,
+      "eval_benchmark_samples_per_second": 2.742,
+      "eval_benchmark_steps_per_second": 0.422,
+      "step": 1200
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 1.9566336870193481,
+      "learning_rate": 9.987e-07,
+      "loss": 0.1114,
+      "step": 1300
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 1.365792155265808,
+      "learning_rate": 9.986e-07,
+      "loss": 0.115,
+      "step": 1400
+    },
+    {
+      "epoch": 0.51,
+      "eval_validation_loss": 0.117983378469944,
+      "eval_validation_runtime": 383.1539,
+      "eval_validation_samples_per_second": 3.022,
+      "eval_validation_steps_per_second": 0.378,
+      "step": 1400
+    },
+    {
+      "epoch": 0.51,
+      "eval_benchmark_loss": 0.3509116470813751,
+      "eval_benchmark_runtime": 9.4708,
+      "eval_benchmark_samples_per_second": 2.745,
+      "eval_benchmark_steps_per_second": 0.422,
+      "step": 1400
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 1.6281362771987915,
+      "learning_rate": 9.985e-07,
+      "loss": 0.1192,
+      "step": 1500
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.7361140251159668,
+      "learning_rate": 9.983999999999998e-07,
+      "loss": 0.1114,
+      "step": 1600
+    },
+    {
+      "epoch": 0.58,
+      "eval_validation_loss": 0.11662287265062332,
+      "eval_validation_runtime": 383.2086,
+      "eval_validation_samples_per_second": 3.022,
+      "eval_validation_steps_per_second": 0.378,
+      "step": 1600
+    },
+    {
+      "epoch": 0.58,
+      "eval_benchmark_loss": 0.3516782522201538,
+      "eval_benchmark_runtime": 9.4592,
+      "eval_benchmark_samples_per_second": 2.749,
+      "eval_benchmark_steps_per_second": 0.423,
+      "step": 1600
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 2.332932710647583,
+      "learning_rate": 9.982999999999998e-07,
+      "loss": 0.1128,
+      "step": 1700
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.4797985553741455,
+      "learning_rate": 9.982e-07,
+      "loss": 0.1036,
+      "step": 1800
+    },
+    {
+      "epoch": 0.66,
+      "eval_validation_loss": 0.11438746005296707,
+      "eval_validation_runtime": 383.1904,
+      "eval_validation_samples_per_second": 3.022,
+      "eval_validation_steps_per_second": 0.378,
+      "step": 1800
+    },
+    {
+      "epoch": 0.66,
+      "eval_benchmark_loss": 0.34705713391304016,
+      "eval_benchmark_runtime": 9.4646,
+      "eval_benchmark_samples_per_second": 2.747,
+      "eval_benchmark_steps_per_second": 0.423,
+      "step": 1800
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 1.546353816986084,
+      "learning_rate": 9.981e-07,
+      "loss": 0.1132,
+      "step": 1900
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 2.1084446907043457,
+      "learning_rate": 9.98e-07,
+      "loss": 0.1125,
+      "step": 2000
+    },
+    {
+      "epoch": 0.73,
+      "eval_validation_loss": 0.11280551552772522,
+      "eval_validation_runtime": 383.2179,
+      "eval_validation_samples_per_second": 3.022,
+      "eval_validation_steps_per_second": 0.378,
+      "step": 2000
+    },
+    {
+      "epoch": 0.73,
+      "eval_benchmark_loss": 0.34782856702804565,
+      "eval_benchmark_runtime": 9.4577,
+      "eval_benchmark_samples_per_second": 2.749,
+      "eval_benchmark_steps_per_second": 0.423,
+      "step": 2000
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 1.3358793258666992,
+      "learning_rate": 9.979e-07,
+      "loss": 0.1155,
+      "step": 2100
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.6584503650665283,
+      "learning_rate": 9.978e-07,
+      "loss": 0.1034,
+      "step": 2200
+    },
+    {
+      "epoch": 0.8,
+      "eval_validation_loss": 0.11192985624074936,
+      "eval_validation_runtime": 383.2409,
+      "eval_validation_samples_per_second": 3.022,
+      "eval_validation_steps_per_second": 0.378,
+      "step": 2200
+    },
+    {
+      "epoch": 0.8,
+      "eval_benchmark_loss": 0.3532721698284149,
+      "eval_benchmark_runtime": 9.4718,
+      "eval_benchmark_samples_per_second": 2.745,
+      "eval_benchmark_steps_per_second": 0.422,
+      "step": 2200
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.2788842916488647,
+      "learning_rate": 9.977e-07,
+      "loss": 0.1091,
+      "step": 2300
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 1.3015437126159668,
+      "learning_rate": 9.976e-07,
+      "loss": 0.1024,
+      "step": 2400
+    },
+    {
+      "epoch": 0.87,
+      "eval_validation_loss": 0.11032804101705551,
+      "eval_validation_runtime": 383.3623,
+      "eval_validation_samples_per_second": 3.021,
+      "eval_validation_steps_per_second": 0.378,
+      "step": 2400
+    },
+    {
+      "epoch": 0.87,
+      "eval_benchmark_loss": 0.34818902611732483,
+      "eval_benchmark_runtime": 9.4633,
+      "eval_benchmark_samples_per_second": 2.747,
+      "eval_benchmark_steps_per_second": 0.423,
+      "step": 2400
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 1.2690401077270508,
+      "learning_rate": 9.975e-07,
+      "loss": 0.0981,
+      "step": 2500
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 1.4752624034881592,
+      "learning_rate": 9.974e-07,
+      "loss": 0.1036,
+      "step": 2600
+    },
+    {
+      "epoch": 0.95,
+      "eval_validation_loss": 0.10945109277963638,
+      "eval_validation_runtime": 383.3638,
+      "eval_validation_samples_per_second": 3.021,
+      "eval_validation_steps_per_second": 0.378,
+      "step": 2600
+    },
+    {
+      "epoch": 0.95,
+      "eval_benchmark_loss": 0.3477522134780884,
+      "eval_benchmark_runtime": 9.4688,
+      "eval_benchmark_samples_per_second": 2.746,
+      "eval_benchmark_steps_per_second": 0.422,
+      "step": 2600
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.502576231956482,
+      "learning_rate": 9.973e-07,
+      "loss": 0.11,
+      "step": 2700
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 0.9190167784690857,
+      "learning_rate": 9.972e-07,
+      "loss": 0.086,
+      "step": 2800
+    },
+    {
+      "epoch": 1.02,
+      "eval_validation_loss": 0.11021959781646729,
+      "eval_validation_runtime": 383.4523,
+      "eval_validation_samples_per_second": 3.02,
+      "eval_validation_steps_per_second": 0.378,
+      "step": 2800
+    },
+    {
+      "epoch": 1.02,
+      "eval_benchmark_loss": 0.35620927810668945,
+      "eval_benchmark_runtime": 9.4715,
+      "eval_benchmark_samples_per_second": 2.745,
+      "eval_benchmark_steps_per_second": 0.422,
+      "step": 2800
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 2.0933382511138916,
+      "learning_rate": 9.971e-07,
+      "loss": 0.0849,
+      "step": 2900
+    },
+    {
+      "epoch": 1.09,
+      "grad_norm": 1.020569920539856,
+      "learning_rate": 9.97e-07,
+      "loss": 0.0858,
+      "step": 3000
+    },
+    {
+      "epoch": 1.09,
+      "eval_validation_loss": 0.10909596085548401,
+      "eval_validation_runtime": 383.3001,
+      "eval_validation_samples_per_second": 3.021,
+      "eval_validation_steps_per_second": 0.378,
+      "step": 3000
+    },
+    {
+      "epoch": 1.09,
+      "eval_benchmark_loss": 0.3547273278236389,
+      "eval_benchmark_runtime": 9.4578,
+      "eval_benchmark_samples_per_second": 2.749,
+      "eval_benchmark_steps_per_second": 0.423,
+      "step": 3000
+    },
+    {
+      "epoch": 1.13,
+      "grad_norm": 1.2632180452346802,
+      "learning_rate": 9.969e-07,
+      "loss": 0.0834,
+      "step": 3100
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 1.0163979530334473,
+      "learning_rate": 9.968e-07,
+      "loss": 0.0786,
+      "step": 3200
+    },
+    {
+      "epoch": 1.16,
+      "eval_validation_loss": 0.11020828038454056,
+      "eval_validation_runtime": 383.4418,
+      "eval_validation_samples_per_second": 3.02,
+      "eval_validation_steps_per_second": 0.378,
+      "step": 3200
+    },
+    {
+      "epoch": 1.16,
+      "eval_benchmark_loss": 0.35691550374031067,
+      "eval_benchmark_runtime": 9.4772,
+      "eval_benchmark_samples_per_second": 2.743,
+      "eval_benchmark_steps_per_second": 0.422,
+      "step": 3200
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 1.0731770992279053,
+      "learning_rate": 9.967e-07,
+      "loss": 0.0817,
+      "step": 3300
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 1.4652243852615356,
+      "learning_rate": 9.966e-07,
+      "loss": 0.0885,
+      "step": 3400
+    },
+    {
+      "epoch": 1.24,
+      "eval_validation_loss": 0.10934263467788696,
+      "eval_validation_runtime": 383.3702,
+      "eval_validation_samples_per_second": 3.021,
+      "eval_validation_steps_per_second": 0.378,
+      "step": 3400
+    },
+    {
+      "epoch": 1.24,
+      "eval_benchmark_loss": 0.35489001870155334,
+      "eval_benchmark_runtime": 9.4613,
+      "eval_benchmark_samples_per_second": 2.748,
+      "eval_benchmark_steps_per_second": 0.423,
+      "step": 3400
+    },
+    {
+      "epoch": 1.27,
+      "grad_norm": 1.1992924213409424,
+      "learning_rate": 9.965e-07,
+      "loss": 0.078,
+      "step": 3500
+    },
+    {
+      "epoch": 1.31,
+      "grad_norm": 1.3917715549468994,
+      "learning_rate": 9.964e-07,
+      "loss": 0.0857,
+      "step": 3600
+    },
+    {
+      "epoch": 1.31,
+      "eval_validation_loss": 0.10760623216629028,
+      "eval_validation_runtime": 383.3793,
+      "eval_validation_samples_per_second": 3.021,
+      "eval_validation_steps_per_second": 0.378,
+      "step": 3600
+    },
+    {
+      "epoch": 1.31,
+      "eval_benchmark_loss": 0.35664084553718567,
+      "eval_benchmark_runtime": 9.4529,
+      "eval_benchmark_samples_per_second": 2.75,
+      "eval_benchmark_steps_per_second": 0.423,
+      "step": 3600
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 0.9880099892616272,
+      "learning_rate": 9.962999999999999e-07,
+      "loss": 0.084,
+      "step": 3700
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 1.15889310836792,
+      "learning_rate": 9.961999999999999e-07,
+      "loss": 0.0833,
+      "step": 3800
+    },
+    {
+      "epoch": 1.38,
+      "eval_validation_loss": 0.10785996913909912,
+      "eval_validation_runtime": 383.3503,
+      "eval_validation_samples_per_second": 3.021,
+      "eval_validation_steps_per_second": 0.378,
+      "step": 3800
+    },
+    {
+      "epoch": 1.38,
+      "eval_benchmark_loss": 0.3560557961463928,
+      "eval_benchmark_runtime": 9.457,
+      "eval_benchmark_samples_per_second": 2.749,
+      "eval_benchmark_steps_per_second": 0.423,
+      "step": 3800
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 1.4265196323394775,
+      "learning_rate": 9.960999999999999e-07,
+      "loss": 0.0831,
+      "step": 3900
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 1.4567248821258545,
+      "learning_rate": 9.959999999999999e-07,
+      "loss": 0.084,
+      "step": 4000
+    },
+    {
+      "epoch": 1.46,
+      "eval_validation_loss": 0.1076769158244133,
+      "eval_validation_runtime": 383.3556,
+      "eval_validation_samples_per_second": 3.021,
+      "eval_validation_steps_per_second": 0.378,
+      "step": 4000
+    },
+    {
+      "epoch": 1.46,
+      "eval_benchmark_loss": 0.3554157614707947,
+      "eval_benchmark_runtime": 9.4598,
+      "eval_benchmark_samples_per_second": 2.748,
+      "eval_benchmark_steps_per_second": 0.423,
+      "step": 4000
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 1.7788864374160767,
+      "learning_rate": 9.958999999999999e-07,
+      "loss": 0.0813,
+      "step": 4100
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 1.4983494281768799,
+      "learning_rate": 9.958e-07,
+      "loss": 0.0815,
+      "step": 4200
+    },
+    {
+      "epoch": 1.53,
+      "eval_validation_loss": 0.10664806514978409,
+      "eval_validation_runtime": 383.2552,
+      "eval_validation_samples_per_second": 3.021,
+      "eval_validation_steps_per_second": 0.378,
+      "step": 4200
+    },
+    {
+      "epoch": 1.53,
+      "eval_benchmark_loss": 0.35523322224617004,
+      "eval_benchmark_runtime": 9.4557,
+      "eval_benchmark_samples_per_second": 2.75,
+      "eval_benchmark_steps_per_second": 0.423,
+      "step": 4200
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 0.7813511490821838,
+      "learning_rate": 9.957e-07,
+      "loss": 0.0877,
+      "step": 4300
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 1.3383861780166626,
+      "learning_rate": 9.956e-07,
+      "loss": 0.0812,
+      "step": 4400
+    },
+    {
+      "epoch": 1.6,
+      "eval_validation_loss": 0.10593847930431366,
+      "eval_validation_runtime": 383.4244,
+      "eval_validation_samples_per_second": 3.02,
+      "eval_validation_steps_per_second": 0.378,
+      "step": 4400
+    },
+    {
+      "epoch": 1.6,
+      "eval_benchmark_loss": 0.3536509871482849,
+      "eval_benchmark_runtime": 9.4751,
+      "eval_benchmark_samples_per_second": 2.744,
+      "eval_benchmark_steps_per_second": 0.422,
+      "step": 4400
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 1.5067020654678345,
+      "learning_rate": 9.955e-07,
+      "loss": 0.0821,
+      "step": 4500
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 1.46514093875885,
+      "learning_rate": 9.953999999999998e-07,
+      "loss": 0.0841,
+      "step": 4600
+    },
+    {
+      "epoch": 1.67,
+      "eval_validation_loss": 0.10573519766330719,
+      "eval_validation_runtime": 383.3608,
+      "eval_validation_samples_per_second": 3.021,
+      "eval_validation_steps_per_second": 0.378,
+      "step": 4600
+    },
+    {
+      "epoch": 1.67,
+      "eval_benchmark_loss": 0.35240989923477173,
+      "eval_benchmark_runtime": 9.4682,
+      "eval_benchmark_samples_per_second": 2.746,
+      "eval_benchmark_steps_per_second": 0.422,
+      "step": 4600
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 1.124515175819397,
+      "learning_rate": 9.952999999999998e-07,
+      "loss": 0.0833,
+      "step": 4700
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 1.2566176652908325,
+      "learning_rate": 9.952e-07,
+      "loss": 0.0822,
+      "step": 4800
+    },
+    {
+      "epoch": 1.75,
+      "eval_validation_loss": 0.10490844398736954,
+      "eval_validation_runtime": 383.3754,
+      "eval_validation_samples_per_second": 3.021,
+      "eval_validation_steps_per_second": 0.378,
+      "step": 4800
+    },
+    {
+      "epoch": 1.75,
+      "eval_benchmark_loss": 0.3501981496810913,
+      "eval_benchmark_runtime": 9.4492,
+      "eval_benchmark_samples_per_second": 2.752,
+      "eval_benchmark_steps_per_second": 0.423,
+      "step": 4800
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 1.4075120687484741,
+      "learning_rate": 9.951e-07,
+      "loss": 0.0824,
+      "step": 4900
+    },
+    {
+      "epoch": 1.82,
+      "grad_norm": 0.9538173079490662,
+      "learning_rate": 9.95e-07,
+      "loss": 0.0809,
+      "step": 5000
+    },
+    {
+      "epoch": 1.82,
+      "eval_validation_loss": 0.10531202703714371,
+      "eval_validation_runtime": 383.2794,
+      "eval_validation_samples_per_second": 3.021,
+      "eval_validation_steps_per_second": 0.378,
+      "step": 5000
+    },
+    {
+      "epoch": 1.82,
+      "eval_benchmark_loss": 0.3513197898864746,
+      "eval_benchmark_runtime": 9.4616,
+      "eval_benchmark_samples_per_second": 2.748,
+      "eval_benchmark_steps_per_second": 0.423,
+      "step": 5000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1000000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 365,
+  "save_steps": 200,
+  "total_flos": 1.617395756875776e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fded323245cded55947594fb1c831172129c67b57f24c2454fa1eea80158d7a
+size 4856