upload checkpoint-latest to repo root

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "meta-llama/Llama-3.1-8B",
+  "architectures": [
+    "LlamaForSequenceClassification"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128001,
+  "pretraining_tp": 1,
+  "problem_type": "single_label_classification",
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": true,
+  "vocab_size": 128256
+}

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 15009865728
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors",
+    "score.weight": "model-00004-of-00004.safetensors"
+  }
+}

trainer_state.json

@@ -0,0 +1,465 @@
+{
+  "best_metric": 0.725,
+  "best_model_checkpoint": "./llama_acc_reward_model_1e5-bz32/checkpoint-450",
+  "epoch": 1.6605166051660518,
+  "eval_steps": 50,
+  "global_step": 450,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03690036900369004,
+      "grad_norm": 296.0,
+      "learning_rate": 6.097560975609757e-07,
+      "loss": 2.0714,
+      "step": 10
+    },
+    {
+      "epoch": 0.07380073800738007,
+      "grad_norm": 134.0,
+      "learning_rate": 1.2195121951219514e-06,
+      "loss": 1.3405,
+      "step": 20
+    },
+    {
+      "epoch": 0.11070110701107011,
+      "grad_norm": 165.0,
+      "learning_rate": 1.8292682926829268e-06,
+      "loss": 1.0594,
+      "step": 30
+    },
+    {
+      "epoch": 0.14760147601476015,
+      "grad_norm": 82.5,
+      "learning_rate": 2.4390243902439027e-06,
+      "loss": 0.7465,
+      "step": 40
+    },
+    {
+      "epoch": 0.18450184501845018,
+      "grad_norm": 112.5,
+      "learning_rate": 3.0487804878048782e-06,
+      "loss": 0.7614,
+      "step": 50
+    },
+    {
+      "epoch": 0.18450184501845018,
+      "eval_accuracy": 0.6625,
+      "eval_auc": 0.646309322741699,
+      "eval_f1": 0.7774725274725275,
+      "eval_loss": 0.8604010343551636,
+      "eval_precision": 0.6627634660421545,
+      "eval_recall": 0.9401993355481728,
+      "eval_runtime": 35.5813,
+      "eval_samples_per_second": 13.49,
+      "eval_steps_per_second": 0.225,
+      "step": 50
+    },
+    {
+      "epoch": 0.22140221402214022,
+      "grad_norm": 117.0,
+      "learning_rate": 3.6585365853658537e-06,
+      "loss": 0.8597,
+      "step": 60
+    },
+    {
+      "epoch": 0.25830258302583026,
+      "grad_norm": 66.5,
+      "learning_rate": 4.268292682926829e-06,
+      "loss": 0.6187,
+      "step": 70
+    },
+    {
+      "epoch": 0.2952029520295203,
+      "grad_norm": 83.0,
+      "learning_rate": 4.8780487804878055e-06,
+      "loss": 0.6943,
+      "step": 80
+    },
+    {
+      "epoch": 0.33210332103321033,
+      "grad_norm": 56.5,
+      "learning_rate": 4.998522552024294e-06,
+      "loss": 0.712,
+      "step": 90
+    },
+    {
+      "epoch": 0.36900369003690037,
+      "grad_norm": 42.0,
+      "learning_rate": 4.992523412393142e-06,
+      "loss": 0.6032,
+      "step": 100
+    },
+    {
+      "epoch": 0.36900369003690037,
+      "eval_accuracy": 0.6875,
+      "eval_auc": 0.7196217450212513,
+      "eval_f1": 0.7516556291390728,
+      "eval_loss": 0.6358558535575867,
+      "eval_precision": 0.7491749174917491,
+      "eval_recall": 0.7541528239202658,
+      "eval_runtime": 35.6806,
+      "eval_samples_per_second": 13.453,
+      "eval_steps_per_second": 0.224,
+      "step": 100
+    },
+    {
+      "epoch": 0.4059040590405904,
+      "grad_norm": 41.75,
+      "learning_rate": 4.981921310736951e-06,
+      "loss": 0.6242,
+      "step": 110
+    },
+    {
+      "epoch": 0.44280442804428044,
+      "grad_norm": 44.5,
+      "learning_rate": 4.9667358260378365e-06,
+      "loss": 0.5803,
+      "step": 120
+    },
+    {
+      "epoch": 0.4797047970479705,
+      "grad_norm": 83.0,
+      "learning_rate": 4.946995001446388e-06,
+      "loss": 0.6009,
+      "step": 130
+    },
+    {
+      "epoch": 0.5166051660516605,
+      "grad_norm": 67.0,
+      "learning_rate": 4.92273529249417e-06,
+      "loss": 0.5519,
+      "step": 140
+    },
+    {
+      "epoch": 0.5535055350553506,
+      "grad_norm": 41.25,
+      "learning_rate": 4.894001499771015e-06,
+      "loss": 0.5813,
+      "step": 150
+    },
+    {
+      "epoch": 0.5535055350553506,
+      "eval_accuracy": 0.63125,
+      "eval_auc": 0.7061471074073385,
+      "eval_f1": 0.665406427221172,
+      "eval_loss": 0.719116747379303,
+      "eval_precision": 0.7719298245614035,
+      "eval_recall": 0.584717607973422,
+      "eval_runtime": 35.5686,
+      "eval_samples_per_second": 13.495,
+      "eval_steps_per_second": 0.225,
+      "step": 150
+    },
+    {
+      "epoch": 0.5904059040590406,
+      "grad_norm": 80.5,
+      "learning_rate": 4.860846686191431e-06,
+      "loss": 0.5751,
+      "step": 160
+    },
+    {
+      "epoch": 0.6273062730627307,
+      "grad_norm": 69.5,
+      "learning_rate": 4.823332079002911e-06,
+      "loss": 0.5819,
+      "step": 170
+    },
+    {
+      "epoch": 0.6642066420664207,
+      "grad_norm": 30.625,
+      "learning_rate": 4.781526956717109e-06,
+      "loss": 0.5991,
+      "step": 180
+    },
+    {
+      "epoch": 0.7011070110701108,
+      "grad_norm": 22.375,
+      "learning_rate": 4.735508521172682e-06,
+      "loss": 0.5535,
+      "step": 190
+    },
+    {
+      "epoch": 0.7380073800738007,
+      "grad_norm": 46.0,
+      "learning_rate": 4.685361754966066e-06,
+      "loss": 0.5817,
+      "step": 200
+    },
+    {
+      "epoch": 0.7380073800738007,
+      "eval_accuracy": 0.6791666666666667,
+      "eval_auc": 0.7208467120770616,
+      "eval_f1": 0.759375,
+      "eval_loss": 0.6730554103851318,
+      "eval_precision": 0.7168141592920354,
+      "eval_recall": 0.8073089700996677,
+      "eval_runtime": 35.6102,
+      "eval_samples_per_second": 13.479,
+      "eval_steps_per_second": 0.225,
+      "step": 200
+    },
+    {
+      "epoch": 0.7749077490774908,
+      "grad_norm": 24.75,
+      "learning_rate": 4.631179264513467e-06,
+      "loss": 0.5654,
+      "step": 210
+    },
+    {
+      "epoch": 0.8118081180811808,
+      "grad_norm": 58.5,
+      "learning_rate": 4.573061109033879e-06,
+      "loss": 0.5312,
+      "step": 220
+    },
+    {
+      "epoch": 0.8487084870848709,
+      "grad_norm": 127.0,
+      "learning_rate": 4.51111461576897e-06,
+      "loss": 0.5733,
+      "step": 230
+    },
+    {
+      "epoch": 0.8856088560885609,
+      "grad_norm": 57.0,
+      "learning_rate": 4.4454541817810344e-06,
+      "loss": 0.5488,
+      "step": 240
+    },
+    {
+      "epoch": 0.922509225092251,
+      "grad_norm": 53.25,
+      "learning_rate": 4.376201062695073e-06,
+      "loss": 0.6011,
+      "step": 250
+    },
+    {
+      "epoch": 0.922509225092251,
+      "eval_accuracy": 0.6666666666666666,
+      "eval_auc": 0.7354720763191596,
+      "eval_f1": 0.7342192691029901,
+      "eval_loss": 0.6163088083267212,
+      "eval_precision": 0.7342192691029901,
+      "eval_recall": 0.7342192691029901,
+      "eval_runtime": 35.5158,
+      "eval_samples_per_second": 13.515,
+      "eval_steps_per_second": 0.225,
+      "step": 250
+    },
+    {
+      "epoch": 0.959409594095941,
+      "grad_norm": 77.0,
+      "learning_rate": 4.303483148775096e-06,
+      "loss": 0.5681,
+      "step": 260
+    },
+    {
+      "epoch": 0.996309963099631,
+      "grad_norm": 87.0,
+      "learning_rate": 4.227434728748203e-06,
+      "loss": 0.6055,
+      "step": 270
+    },
+    {
+      "epoch": 1.033210332103321,
+      "grad_norm": 58.25,
+      "learning_rate": 4.14819624181256e-06,
+      "loss": 0.4911,
+      "step": 280
+    },
+    {
+      "epoch": 1.070110701107011,
+      "grad_norm": 27.875,
+      "learning_rate": 4.065914018287263e-06,
+      "loss": 0.5676,
+      "step": 290
+    },
+    {
+      "epoch": 1.1070110701107012,
+      "grad_norm": 81.5,
+      "learning_rate": 3.980740009383014e-06,
+      "loss": 0.4769,
+      "step": 300
+    },
+    {
+      "epoch": 1.1070110701107012,
+      "eval_accuracy": 0.6770833333333334,
+      "eval_auc": 0.7363536813972049,
+      "eval_f1": 0.7566718995290423,
+      "eval_loss": 0.6269359588623047,
+      "eval_precision": 0.7172619047619048,
+      "eval_recall": 0.8006644518272426,
+      "eval_runtime": 35.6218,
+      "eval_samples_per_second": 13.475,
+      "eval_steps_per_second": 0.225,
+      "step": 300
+    },
+    {
+      "epoch": 1.1439114391143912,
+      "grad_norm": 53.75,
+      "learning_rate": 3.892831506592669e-06,
+      "loss": 0.4707,
+      "step": 310
+    },
+    {
+      "epoch": 1.1808118081180812,
+      "grad_norm": 16.25,
+      "learning_rate": 3.802350851219826e-06,
+      "loss": 0.4779,
+      "step": 320
+    },
+    {
+      "epoch": 1.2177121771217712,
+      "grad_norm": 45.25,
+      "learning_rate": 3.7094651345819076e-06,
+      "loss": 0.4996,
+      "step": 330
+    },
+    {
+      "epoch": 1.2546125461254611,
+      "grad_norm": 31.125,
+      "learning_rate": 3.6143458894413463e-06,
+      "loss": 0.4441,
+      "step": 340
+    },
+    {
+      "epoch": 1.2915129151291513,
+      "grad_norm": 39.0,
+      "learning_rate": 3.517168773234718e-06,
+      "loss": 0.4846,
+      "step": 350
+    },
+    {
+      "epoch": 1.2915129151291513,
+      "eval_accuracy": 0.7104166666666667,
+      "eval_auc": 0.7483435104586201,
+      "eval_f1": 0.7890743550834598,
+      "eval_loss": 0.6057602167129517,
+      "eval_precision": 0.7262569832402235,
+      "eval_recall": 0.8637873754152824,
+      "eval_runtime": 35.5326,
+      "eval_samples_per_second": 13.509,
+      "eval_steps_per_second": 0.225,
+      "step": 350
+    },
+    {
+      "epoch": 1.3284132841328413,
+      "grad_norm": 83.5,
+      "learning_rate": 3.4181132436848196e-06,
+      "loss": 0.4715,
+      "step": 360
+    },
+    {
+      "epoch": 1.3653136531365313,
+      "grad_norm": 76.0,
+      "learning_rate": 3.3173622273947166e-06,
+      "loss": 0.46,
+      "step": 370
+    },
+    {
+      "epoch": 1.4022140221402215,
+      "grad_norm": 76.5,
+      "learning_rate": 3.215101782035785e-06,
+      "loss": 0.4568,
+      "step": 380
+    },
+    {
+      "epoch": 1.4391143911439115,
+      "grad_norm": 33.25,
+      "learning_rate": 3.1115207527535973e-06,
+      "loss": 0.4563,
+      "step": 390
+    },
+    {
+      "epoch": 1.4760147601476015,
+      "grad_norm": 72.0,
+      "learning_rate": 3.006810423426142e-06,
+      "loss": 0.5175,
+      "step": 400
+    },
+    {
+      "epoch": 1.4760147601476015,
+      "eval_accuracy": 0.7145833333333333,
+      "eval_auc": 0.7466731008370611,
+      "eval_f1": 0.8005822416302766,
+      "eval_loss": 0.6509066820144653,
+      "eval_precision": 0.7124352331606217,
+      "eval_recall": 0.9136212624584718,
+      "eval_runtime": 35.6573,
+      "eval_samples_per_second": 13.461,
+      "eval_steps_per_second": 0.224,
+      "step": 400
+    },
+    {
+      "epoch": 1.5129151291512914,
+      "grad_norm": 106.5,
+      "learning_rate": 2.9011641634184266e-06,
+      "loss": 0.4401,
+      "step": 410
+    },
+    {
+      "epoch": 1.5498154981549814,
+      "grad_norm": 43.0,
+      "learning_rate": 2.7947770704857975e-06,
+      "loss": 0.4476,
+      "step": 420
+    },
+    {
+      "epoch": 1.5867158671586716,
+      "grad_norm": 26.0,
+      "learning_rate": 2.6878456104854193e-06,
+      "loss": 0.4674,
+      "step": 430
+    },
+    {
+      "epoch": 1.6236162361623616,
+      "grad_norm": 23.125,
+      "learning_rate": 2.580567254561282e-06,
+      "loss": 0.4795,
+      "step": 440
+    },
+    {
+      "epoch": 1.6605166051660518,
+      "grad_norm": 48.5,
+      "learning_rate": 2.4731401144727267e-06,
+      "loss": 0.4623,
+      "step": 450
+    },
+    {
+      "epoch": 1.6605166051660518,
+      "eval_accuracy": 0.725,
+      "eval_auc": 0.7526401752074092,
+      "eval_f1": 0.8064516129032258,
+      "eval_loss": 0.6564527750015259,
+      "eval_precision": 0.7217847769028871,
+      "eval_recall": 0.9136212624584718,
+      "eval_runtime": 35.5728,
+      "eval_samples_per_second": 13.493,
+      "eval_steps_per_second": 0.225,
+      "step": 450
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 813,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.950300079721021e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8484e22639ff9d49e8623d6ccb6931dea30b80e4c6012ac0ca9e066606a1f75c
+size 5368