Upload 9 files

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "microsoft/phi-2",
+  "architectures": [
+    "PhiForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "microsoft/phi-2--configuration_phi.PhiConfig",
+    "AutoModelForCausalLM": "microsoft/phi-2--modeling_phi.PhiForCausalLM"
+  },
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 50256,
+  "hidden_act": "gelu_new",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 10240,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "phi",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "partial_rotary_factor": 0.4,
+  "qk_layernorm": false,
+  "resid_pdrop": 0.1,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.0.dev0",
+  "use_cache": true,
+  "vocab_size": 51200
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.40.0.dev0"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd819c09cd73d6e898d52748b5fe578e88608e390f60f8c55692ddea528aaf9d
+size 4982355512

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f7b02cc202935cbfa1159c386b355f79fc5068a21d60347796d1ff8500b4f1b
+size 4982541984

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de0c27216f0b13e28fd46eaf6dd53783d783f050b917567feab7ac85c48d88a7
+size 1153887616

model.safetensors.index.json

@@ -0,0 +1,460 @@
+{
+  "metadata": {
+    "total_size": 11118735360
+  },
+  "weight_map": {
+    "lm_head.bias": "model-00003-of-00003.safetensors",
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.final_layernorm.bias": "model-00003-of-00003.safetensors",
+    "model.final_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.0.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.dense.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.dense.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.dense.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.dense.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.dense.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.dense.bias": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.dense.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.fc1.bias": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.fc1.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.fc2.bias": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.fc2.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.dense.bias": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.dense.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.3.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.dense.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.dense.bias": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.dense.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.dense.bias": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.dense.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.dense.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.dense.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.dense.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.dense.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.dense.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.fc1.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.fc1.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.fc2.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.fc2.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.dense.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.dense.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors"
+  }
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab8811ec7cb13eed66db07f6a02938280994cb06c5445b4cd3ba1d4a061c9e6e
+size 14244

trainer_state.json

@@ -0,0 +1,621 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.4562002275312855,
+  "eval_steps": 200,
+  "global_step": 4000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.4095656871795654,
+      "learning_rate": 9.999e-06,
+      "loss": 0.1224,
+      "step": 100
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 1.1863898038864136,
+      "learning_rate": 9.998000000000002e-06,
+      "loss": 0.1054,
+      "step": 200
+    },
+    {
+      "epoch": 0.07,
+      "eval_validation_loss": 0.09953554719686508,
+      "eval_validation_runtime": 712.7055,
+      "eval_validation_samples_per_second": 1.625,
+      "eval_validation_steps_per_second": 0.203,
+      "step": 200
+    },
+    {
+      "epoch": 0.07,
+      "eval_benchmark_loss": 0.32548987865448,
+      "eval_benchmark_runtime": 17.5172,
+      "eval_benchmark_samples_per_second": 1.484,
+      "eval_benchmark_steps_per_second": 0.228,
+      "step": 200
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 1.5735375881195068,
+      "learning_rate": 9.997000000000001e-06,
+      "loss": 0.101,
+      "step": 300
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 1.6928790807724,
+      "learning_rate": 9.996e-06,
+      "loss": 0.0968,
+      "step": 400
+    },
+    {
+      "epoch": 0.15,
+      "eval_validation_loss": 0.0932546928524971,
+      "eval_validation_runtime": 709.1289,
+      "eval_validation_samples_per_second": 1.633,
+      "eval_validation_steps_per_second": 0.204,
+      "step": 400
+    },
+    {
+      "epoch": 0.15,
+      "eval_benchmark_loss": 0.31784072518348694,
+      "eval_benchmark_runtime": 17.5221,
+      "eval_benchmark_samples_per_second": 1.484,
+      "eval_benchmark_steps_per_second": 0.228,
+      "step": 400
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 2.1487505435943604,
+      "learning_rate": 9.995000000000002e-06,
+      "loss": 0.0959,
+      "step": 500
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.6419602036476135,
+      "learning_rate": 9.994000000000001e-06,
+      "loss": 0.0998,
+      "step": 600
+    },
+    {
+      "epoch": 0.22,
+      "eval_validation_loss": 0.0911107286810875,
+      "eval_validation_runtime": 708.9068,
+      "eval_validation_samples_per_second": 1.634,
+      "eval_validation_steps_per_second": 0.205,
+      "step": 600
+    },
+    {
+      "epoch": 0.22,
+      "eval_benchmark_loss": 0.3297904133796692,
+      "eval_benchmark_runtime": 17.5622,
+      "eval_benchmark_samples_per_second": 1.48,
+      "eval_benchmark_steps_per_second": 0.228,
+      "step": 600
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 1.2389020919799805,
+      "learning_rate": 9.993e-06,
+      "loss": 0.097,
+      "step": 700
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 2.500471353530884,
+      "learning_rate": 9.992e-06,
+      "loss": 0.0988,
+      "step": 800
+    },
+    {
+      "epoch": 0.29,
+      "eval_validation_loss": 0.09039539098739624,
+      "eval_validation_runtime": 709.2212,
+      "eval_validation_samples_per_second": 1.633,
+      "eval_validation_steps_per_second": 0.204,
+      "step": 800
+    },
+    {
+      "epoch": 0.29,
+      "eval_benchmark_loss": 0.3489764630794525,
+      "eval_benchmark_runtime": 17.6053,
+      "eval_benchmark_samples_per_second": 1.477,
+      "eval_benchmark_steps_per_second": 0.227,
+      "step": 800
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.7160820960998535,
+      "learning_rate": 9.991000000000001e-06,
+      "loss": 0.0918,
+      "step": 900
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.9196050763130188,
+      "learning_rate": 9.990000000000001e-06,
+      "loss": 0.097,
+      "step": 1000
+    },
+    {
+      "epoch": 0.36,
+      "eval_validation_loss": 0.08984846621751785,
+      "eval_validation_runtime": 709.6339,
+      "eval_validation_samples_per_second": 1.632,
+      "eval_validation_steps_per_second": 0.204,
+      "step": 1000
+    },
+    {
+      "epoch": 0.36,
+      "eval_benchmark_loss": 0.35091081261634827,
+      "eval_benchmark_runtime": 17.5252,
+      "eval_benchmark_samples_per_second": 1.484,
+      "eval_benchmark_steps_per_second": 0.228,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.5167059898376465,
+      "learning_rate": 9.989e-06,
+      "loss": 0.0932,
+      "step": 1100
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.0317384004592896,
+      "learning_rate": 9.988000000000002e-06,
+      "loss": 0.0919,
+      "step": 1200
+    },
+    {
+      "epoch": 0.44,
+      "eval_validation_loss": 0.08784810453653336,
+      "eval_validation_runtime": 709.1851,
+      "eval_validation_samples_per_second": 1.633,
+      "eval_validation_steps_per_second": 0.204,
+      "step": 1200
+    },
+    {
+      "epoch": 0.44,
+      "eval_benchmark_loss": 0.3649544417858124,
+      "eval_benchmark_runtime": 17.5537,
+      "eval_benchmark_samples_per_second": 1.481,
+      "eval_benchmark_steps_per_second": 0.228,
+      "step": 1200
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.9792326092720032,
+      "learning_rate": 9.987000000000001e-06,
+      "loss": 0.0978,
+      "step": 1300
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 1.5393081903457642,
+      "learning_rate": 9.986e-06,
+      "loss": 0.0967,
+      "step": 1400
+    },
+    {
+      "epoch": 0.51,
+      "eval_validation_loss": 0.08623290061950684,
+      "eval_validation_runtime": 709.2989,
+      "eval_validation_samples_per_second": 1.633,
+      "eval_validation_steps_per_second": 0.204,
+      "step": 1400
+    },
+    {
+      "epoch": 0.51,
+      "eval_benchmark_loss": 0.35636618733406067,
+      "eval_benchmark_runtime": 17.52,
+      "eval_benchmark_samples_per_second": 1.484,
+      "eval_benchmark_steps_per_second": 0.228,
+      "step": 1400
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 1.099972128868103,
+      "learning_rate": 9.985000000000002e-06,
+      "loss": 0.0945,
+      "step": 1500
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.371626377105713,
+      "learning_rate": 9.984e-06,
+      "loss": 0.0884,
+      "step": 1600
+    },
+    {
+      "epoch": 0.58,
+      "eval_validation_loss": 0.08641818910837173,
+      "eval_validation_runtime": 709.0375,
+      "eval_validation_samples_per_second": 1.633,
+      "eval_validation_steps_per_second": 0.205,
+      "step": 1600
+    },
+    {
+      "epoch": 0.58,
+      "eval_benchmark_loss": 0.3572656214237213,
+      "eval_benchmark_runtime": 17.5451,
+      "eval_benchmark_samples_per_second": 1.482,
+      "eval_benchmark_steps_per_second": 0.228,
+      "step": 1600
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.2601964473724365,
+      "learning_rate": 9.983e-06,
+      "loss": 0.0858,
+      "step": 1700
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.709611713886261,
+      "learning_rate": 9.982e-06,
+      "loss": 0.0909,
+      "step": 1800
+    },
+    {
+      "epoch": 0.66,
+      "eval_validation_loss": 0.08525099605321884,
+      "eval_validation_runtime": 709.1501,
+      "eval_validation_samples_per_second": 1.633,
+      "eval_validation_steps_per_second": 0.204,
+      "step": 1800
+    },
+    {
+      "epoch": 0.66,
+      "eval_benchmark_loss": 0.36886686086654663,
+      "eval_benchmark_runtime": 17.5384,
+      "eval_benchmark_samples_per_second": 1.482,
+      "eval_benchmark_steps_per_second": 0.228,
+      "step": 1800
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 1.529994249343872,
+      "learning_rate": 9.981000000000002e-06,
+      "loss": 0.0922,
+      "step": 1900
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 1.118903636932373,
+      "learning_rate": 9.980000000000001e-06,
+      "loss": 0.0865,
+      "step": 2000
+    },
+    {
+      "epoch": 0.73,
+      "eval_validation_loss": 0.08593959361314774,
+      "eval_validation_runtime": 708.9421,
+      "eval_validation_samples_per_second": 1.633,
+      "eval_validation_steps_per_second": 0.205,
+      "step": 2000
+    },
+    {
+      "epoch": 0.73,
+      "eval_benchmark_loss": 0.373639851808548,
+      "eval_benchmark_runtime": 17.5649,
+      "eval_benchmark_samples_per_second": 1.48,
+      "eval_benchmark_steps_per_second": 0.228,
+      "step": 2000
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.64658522605896,
+      "learning_rate": 9.979e-06,
+      "loss": 0.0853,
+      "step": 2100
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.2276527881622314,
+      "learning_rate": 9.978000000000002e-06,
+      "loss": 0.0842,
+      "step": 2200
+    },
+    {
+      "epoch": 0.8,
+      "eval_validation_loss": 0.08536743372678757,
+      "eval_validation_runtime": 709.101,
+      "eval_validation_samples_per_second": 1.633,
+      "eval_validation_steps_per_second": 0.204,
+      "step": 2200
+    },
+    {
+      "epoch": 0.8,
+      "eval_benchmark_loss": 0.37157073616981506,
+      "eval_benchmark_runtime": 17.527,
+      "eval_benchmark_samples_per_second": 1.483,
+      "eval_benchmark_steps_per_second": 0.228,
+      "step": 2200
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.052180528640747,
+      "learning_rate": 9.977000000000001e-06,
+      "loss": 0.0897,
+      "step": 2300
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 1.211391806602478,
+      "learning_rate": 9.976e-06,
+      "loss": 0.0943,
+      "step": 2400
+    },
+    {
+      "epoch": 0.87,
+      "eval_validation_loss": 0.08370199054479599,
+      "eval_validation_runtime": 709.1222,
+      "eval_validation_samples_per_second": 1.633,
+      "eval_validation_steps_per_second": 0.204,
+      "step": 2400
+    },
+    {
+      "epoch": 0.87,
+      "eval_benchmark_loss": 0.392040878534317,
+      "eval_benchmark_runtime": 17.5514,
+      "eval_benchmark_samples_per_second": 1.481,
+      "eval_benchmark_steps_per_second": 0.228,
+      "step": 2400
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 1.0776712894439697,
+      "learning_rate": 9.975000000000002e-06,
+      "loss": 0.0845,
+      "step": 2500
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.919306218624115,
+      "learning_rate": 9.974e-06,
+      "loss": 0.0849,
+      "step": 2600
+    },
+    {
+      "epoch": 0.95,
+      "eval_validation_loss": 0.08564597368240356,
+      "eval_validation_runtime": 709.0841,
+      "eval_validation_samples_per_second": 1.633,
+      "eval_validation_steps_per_second": 0.204,
+      "step": 2600
+    },
+    {
+      "epoch": 0.95,
+      "eval_benchmark_loss": 0.3918878436088562,
+      "eval_benchmark_runtime": 17.5531,
+      "eval_benchmark_samples_per_second": 1.481,
+      "eval_benchmark_steps_per_second": 0.228,
+      "step": 2600
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.2274926900863647,
+      "learning_rate": 9.973000000000001e-06,
+      "loss": 0.0827,
+      "step": 2700
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 1.0446745157241821,
+      "learning_rate": 9.972e-06,
+      "loss": 0.0648,
+      "step": 2800
+    },
+    {
+      "epoch": 1.02,
+      "eval_validation_loss": 0.08917231112718582,
+      "eval_validation_runtime": 708.8767,
+      "eval_validation_samples_per_second": 1.634,
+      "eval_validation_steps_per_second": 0.205,
+      "step": 2800
+    },
+    {
+      "epoch": 1.02,
+      "eval_benchmark_loss": 0.4130290150642395,
+      "eval_benchmark_runtime": 17.5261,
+      "eval_benchmark_samples_per_second": 1.484,
+      "eval_benchmark_steps_per_second": 0.228,
+      "step": 2800
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 0.5209759473800659,
+      "learning_rate": 9.971e-06,
+      "loss": 0.0389,
+      "step": 2900
+    },
+    {
+      "epoch": 1.09,
+      "grad_norm": 0.7747032642364502,
+      "learning_rate": 9.970000000000001e-06,
+      "loss": 0.0425,
+      "step": 3000
+    },
+    {
+      "epoch": 1.09,
+      "eval_validation_loss": 0.0874892994761467,
+      "eval_validation_runtime": 709.0226,
+      "eval_validation_samples_per_second": 1.633,
+      "eval_validation_steps_per_second": 0.205,
+      "step": 3000
+    },
+    {
+      "epoch": 1.09,
+      "eval_benchmark_loss": 0.41068679094314575,
+      "eval_benchmark_runtime": 17.5438,
+      "eval_benchmark_samples_per_second": 1.482,
+      "eval_benchmark_steps_per_second": 0.228,
+      "step": 3000
+    },
+    {
+      "epoch": 1.13,
+      "grad_norm": 0.7112635374069214,
+      "learning_rate": 9.969e-06,
+      "loss": 0.0391,
+      "step": 3100
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.6574044227600098,
+      "learning_rate": 9.968000000000002e-06,
+      "loss": 0.0407,
+      "step": 3200
+    },
+    {
+      "epoch": 1.16,
+      "eval_validation_loss": 0.08782221376895905,
+      "eval_validation_runtime": 708.8262,
+      "eval_validation_samples_per_second": 1.634,
+      "eval_validation_steps_per_second": 0.205,
+      "step": 3200
+    },
+    {
+      "epoch": 1.16,
+      "eval_benchmark_loss": 0.40687239170074463,
+      "eval_benchmark_runtime": 17.5555,
+      "eval_benchmark_samples_per_second": 1.481,
+      "eval_benchmark_steps_per_second": 0.228,
+      "step": 3200
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.3925846815109253,
+      "learning_rate": 9.967000000000001e-06,
+      "loss": 0.039,
+      "step": 3300
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.7560076713562012,
+      "learning_rate": 9.966e-06,
+      "loss": 0.0395,
+      "step": 3400
+    },
+    {
+      "epoch": 1.24,
+      "eval_validation_loss": 0.08419103175401688,
+      "eval_validation_runtime": 708.8516,
+      "eval_validation_samples_per_second": 1.634,
+      "eval_validation_steps_per_second": 0.205,
+      "step": 3400
+    },
+    {
+      "epoch": 1.24,
+      "eval_benchmark_loss": 0.38862425088882446,
+      "eval_benchmark_runtime": 17.5289,
+      "eval_benchmark_samples_per_second": 1.483,
+      "eval_benchmark_steps_per_second": 0.228,
+      "step": 3400
+    },
+    {
+      "epoch": 1.27,
+      "grad_norm": 0.716073215007782,
+      "learning_rate": 9.965000000000002e-06,
+      "loss": 0.0386,
+      "step": 3500
+    },
+    {
+      "epoch": 1.31,
+      "grad_norm": 1.1741386651992798,
+      "learning_rate": 9.964e-06,
+      "loss": 0.0405,
+      "step": 3600
+    },
+    {
+      "epoch": 1.31,
+      "eval_validation_loss": 0.08967277407646179,
+      "eval_validation_runtime": 708.8983,
+      "eval_validation_samples_per_second": 1.634,
+      "eval_validation_steps_per_second": 0.205,
+      "step": 3600
+    },
+    {
+      "epoch": 1.31,
+      "eval_benchmark_loss": 0.3966710865497589,
+      "eval_benchmark_runtime": 17.5289,
+      "eval_benchmark_samples_per_second": 1.483,
+      "eval_benchmark_steps_per_second": 0.228,
+      "step": 3600
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 1.2536277770996094,
+      "learning_rate": 9.963000000000001e-06,
+      "loss": 0.0396,
+      "step": 3700
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 1.1809356212615967,
+      "learning_rate": 9.962e-06,
+      "loss": 0.0444,
+      "step": 3800
+    },
+    {
+      "epoch": 1.38,
+      "eval_validation_loss": 0.08714079856872559,
+      "eval_validation_runtime": 709.1882,
+      "eval_validation_samples_per_second": 1.633,
+      "eval_validation_steps_per_second": 0.204,
+      "step": 3800
+    },
+    {
+      "epoch": 1.38,
+      "eval_benchmark_loss": 0.3916112780570984,
+      "eval_benchmark_runtime": 17.538,
+      "eval_benchmark_samples_per_second": 1.482,
+      "eval_benchmark_steps_per_second": 0.228,
+      "step": 3800
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 0.5824371576309204,
+      "learning_rate": 9.961e-06,
+      "loss": 0.0389,
+      "step": 3900
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 0.8065107464790344,
+      "learning_rate": 9.960000000000001e-06,
+      "loss": 0.0392,
+      "step": 4000
+    },
+    {
+      "epoch": 1.46,
+      "eval_validation_loss": 0.08596936613321304,
+      "eval_validation_runtime": 708.8196,
+      "eval_validation_samples_per_second": 1.634,
+      "eval_validation_steps_per_second": 0.205,
+      "step": 4000
+    },
+    {
+      "epoch": 1.46,
+      "eval_benchmark_loss": 0.4028017818927765,
+      "eval_benchmark_runtime": 17.5338,
+      "eval_benchmark_samples_per_second": 1.483,
+      "eval_benchmark_steps_per_second": 0.228,
+      "step": 4000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1000000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 365,
+  "save_steps": 200,
+  "total_flos": 2.608121981079552e+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:f0e6ffda392cfe05bd26fac35b7e45e1efa9f531ad162517295c40090a40b674
+size 4856