upload checkpoint-450 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-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b11b9198fba7e9aab152d05bfac78cf959665b4edf32bcf3751d75882ec1187
+size 4976698672

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f95b1492bc416003fb4c6e71af34a359bfc8e1de7800724928c6ed069d79033b
+size 4999802720

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20097b9c2f7d511f79a80344201f4b11ab0cc7a2f9bf6194409e07a460f6b38d
+size 4915916176

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:136a54cbed8574a15c0e48fe15122037b78e5624fdbe226097f58339875d02cd
+size 117482016

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"
+  }
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5afa5b7938904f147f347d2aa5009c9b57e6cb1c46fa4c7266c8166985fe830
+size 30019986218

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5edb34d031c0c2b447f3eaadb401a4c1e7e7e6d8c096e28b7092e01a8bd48c92
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36de27e193a80f0f00bd1b567f2c2ea17a1d741ab7905d512a42d54f54b38aa0
+size 1064

trainer_state.json

@@ -0,0 +1,465 @@
+{
+  "best_metric": 0.7169117647058824,
+  "best_model_checkpoint": "./llama_acc_reward_model_5e6-bz32/checkpoint-450",
+  "epoch": 1.4657980456026058,
+  "eval_steps": 50,
+  "global_step": 450,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03257328990228013,
+      "grad_norm": 276.0,
+      "learning_rate": 5.376344086021506e-07,
+      "loss": 1.7786,
+      "step": 10
+    },
+    {
+      "epoch": 0.06514657980456026,
+      "grad_norm": 237.0,
+      "learning_rate": 1.0752688172043011e-06,
+      "loss": 1.3394,
+      "step": 20
+    },
+    {
+      "epoch": 0.09771986970684039,
+      "grad_norm": 138.0,
+      "learning_rate": 1.6129032258064516e-06,
+      "loss": 1.1228,
+      "step": 30
+    },
+    {
+      "epoch": 0.13029315960912052,
+      "grad_norm": 143.0,
+      "learning_rate": 2.1505376344086023e-06,
+      "loss": 0.7784,
+      "step": 40
+    },
+    {
+      "epoch": 0.16286644951140064,
+      "grad_norm": 116.5,
+      "learning_rate": 2.688172043010753e-06,
+      "loss": 0.7774,
+      "step": 50
+    },
+    {
+      "epoch": 0.16286644951140064,
+      "eval_accuracy": 0.6102941176470589,
+      "eval_auc": 0.6131436599929752,
+      "eval_f1": 0.6927536231884058,
+      "eval_loss": 0.7961235046386719,
+      "eval_precision": 0.6547945205479452,
+      "eval_recall": 0.7353846153846154,
+      "eval_runtime": 37.3762,
+      "eval_samples_per_second": 14.555,
+      "eval_steps_per_second": 0.241,
+      "step": 50
+    },
+    {
+      "epoch": 0.19543973941368079,
+      "grad_norm": 78.5,
+      "learning_rate": 3.225806451612903e-06,
+      "loss": 0.6943,
+      "step": 60
+    },
+    {
+      "epoch": 0.2280130293159609,
+      "grad_norm": 85.5,
+      "learning_rate": 3.763440860215054e-06,
+      "loss": 0.6675,
+      "step": 70
+    },
+    {
+      "epoch": 0.26058631921824105,
+      "grad_norm": 55.0,
+      "learning_rate": 4.3010752688172045e-06,
+      "loss": 0.6086,
+      "step": 80
+    },
+    {
+      "epoch": 0.2931596091205212,
+      "grad_norm": 68.5,
+      "learning_rate": 4.838709677419355e-06,
+      "loss": 0.6427,
+      "step": 90
+    },
+    {
+      "epoch": 0.3257328990228013,
+      "grad_norm": 40.75,
+      "learning_rate": 4.999118302447079e-06,
+      "loss": 0.6428,
+      "step": 100
+    },
+    {
+      "epoch": 0.3257328990228013,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_auc": 0.7088092729188622,
+      "eval_f1": 0.7700534759358288,
+      "eval_loss": 0.7112210988998413,
+      "eval_precision": 0.6808510638297872,
+      "eval_recall": 0.8861538461538462,
+      "eval_runtime": 37.3678,
+      "eval_samples_per_second": 14.558,
+      "eval_steps_per_second": 0.241,
+      "step": 100
+    },
+    {
+      "epoch": 0.3583061889250814,
+      "grad_norm": 131.0,
+      "learning_rate": 4.994801280902408e-06,
+      "loss": 0.7228,
+      "step": 110
+    },
+    {
+      "epoch": 0.39087947882736157,
+      "grad_norm": 76.5,
+      "learning_rate": 4.986893197145238e-06,
+      "loss": 0.764,
+      "step": 120
+    },
+    {
+      "epoch": 0.4234527687296417,
+      "grad_norm": 87.0,
+      "learning_rate": 4.9754054342147574e-06,
+      "loss": 0.6319,
+      "step": 130
+    },
+    {
+      "epoch": 0.4560260586319218,
+      "grad_norm": 39.25,
+      "learning_rate": 4.960354527805286e-06,
+      "loss": 0.6535,
+      "step": 140
+    },
+    {
+      "epoch": 0.48859934853420195,
+      "grad_norm": 34.25,
+      "learning_rate": 4.941762142464491e-06,
+      "loss": 0.6484,
+      "step": 150
+    },
+    {
+      "epoch": 0.48859934853420195,
+      "eval_accuracy": 0.6985294117647058,
+      "eval_auc": 0.735461889708465,
+      "eval_f1": 0.7530120481927711,
+      "eval_loss": 0.609675407409668,
+      "eval_precision": 0.7374631268436578,
+      "eval_recall": 0.7692307692307693,
+      "eval_runtime": 37.2896,
+      "eval_samples_per_second": 14.589,
+      "eval_steps_per_second": 0.241,
+      "step": 150
+    },
+    {
+      "epoch": 0.5211726384364821,
+      "grad_norm": 78.5,
+      "learning_rate": 4.919655040409046e-06,
+      "loss": 0.6814,
+      "step": 160
+    },
+    {
+      "epoch": 0.5537459283387622,
+      "grad_norm": 56.0,
+      "learning_rate": 4.894065043002611e-06,
+      "loss": 0.5881,
+      "step": 170
+    },
+    {
+      "epoch": 0.5863192182410424,
+      "grad_norm": 60.25,
+      "learning_rate": 4.865028984951585e-06,
+      "loss": 0.6118,
+      "step": 180
+    },
+    {
+      "epoch": 0.6188925081433225,
+      "grad_norm": 46.5,
+      "learning_rate": 4.8325886612845586e-06,
+      "loss": 0.6507,
+      "step": 190
+    },
+    {
+      "epoch": 0.6514657980456026,
+      "grad_norm": 37.75,
+      "learning_rate": 4.7967907671917975e-06,
+      "loss": 0.5939,
+      "step": 200
+    },
+    {
+      "epoch": 0.6514657980456026,
+      "eval_accuracy": 0.7058823529411765,
+      "eval_auc": 0.7496803652968036,
+      "eval_f1": 0.7759103641456583,
+      "eval_loss": 0.6006419062614441,
+      "eval_precision": 0.712082262210797,
+      "eval_recall": 0.8523076923076923,
+      "eval_runtime": 37.4203,
+      "eval_samples_per_second": 14.538,
+      "eval_steps_per_second": 0.241,
+      "step": 200
+    },
+    {
+      "epoch": 0.6840390879478827,
+      "grad_norm": 25.875,
+      "learning_rate": 4.757686830811332e-06,
+      "loss": 0.568,
+      "step": 210
+    },
+    {
+      "epoch": 0.7166123778501629,
+      "grad_norm": 89.5,
+      "learning_rate": 4.715333139058425e-06,
+      "loss": 0.5802,
+      "step": 220
+    },
+    {
+      "epoch": 0.749185667752443,
+      "grad_norm": 144.0,
+      "learning_rate": 4.669790656605166e-06,
+      "loss": 0.5957,
+      "step": 230
+    },
+    {
+      "epoch": 0.7817589576547231,
+      "grad_norm": 21.125,
+      "learning_rate": 4.621124938126809e-06,
+      "loss": 0.5994,
+      "step": 240
+    },
+    {
+      "epoch": 0.8143322475570033,
+      "grad_norm": 48.75,
+      "learning_rate": 4.569406033941194e-06,
+      "loss": 0.568,
+      "step": 250
+    },
+    {
+      "epoch": 0.8143322475570033,
+      "eval_accuracy": 0.7022058823529411,
+      "eval_auc": 0.7719494204425712,
+      "eval_f1": 0.7387096774193549,
+      "eval_loss": 0.5732384920120239,
+      "eval_precision": 0.7762711864406779,
+      "eval_recall": 0.7046153846153846,
+      "eval_runtime": 37.3004,
+      "eval_samples_per_second": 14.584,
+      "eval_steps_per_second": 0.241,
+      "step": 250
+    },
+    {
+      "epoch": 0.8469055374592834,
+      "grad_norm": 38.5,
+      "learning_rate": 4.514708389177045e-06,
+      "loss": 0.5934,
+      "step": 260
+    },
+    {
+      "epoch": 0.8794788273615635,
+      "grad_norm": 50.5,
+      "learning_rate": 4.457110736616297e-06,
+      "loss": 0.57,
+      "step": 270
+    },
+    {
+      "epoch": 0.9120521172638436,
+      "grad_norm": 117.0,
+      "learning_rate": 4.396695983364708e-06,
+      "loss": 0.6622,
+      "step": 280
+    },
+    {
+      "epoch": 0.9446254071661238,
+      "grad_norm": 94.0,
+      "learning_rate": 4.3335510915138644e-06,
+      "loss": 0.6357,
+      "step": 290
+    },
+    {
+      "epoch": 0.9771986970684039,
+      "grad_norm": 72.0,
+      "learning_rate": 4.267766952966369e-06,
+      "loss": 0.5478,
+      "step": 300
+    },
+    {
+      "epoch": 0.9771986970684039,
+      "eval_accuracy": 0.7095588235294118,
+      "eval_auc": 0.7645732349841939,
+      "eval_f1": 0.7716763005780347,
+      "eval_loss": 0.573746919631958,
+      "eval_precision": 0.7275204359673024,
+      "eval_recall": 0.8215384615384616,
+      "eval_runtime": 37.2423,
+      "eval_samples_per_second": 14.607,
+      "eval_steps_per_second": 0.242,
+      "step": 300
+    },
+    {
+      "epoch": 1.009771986970684,
+      "grad_norm": 58.75,
+      "learning_rate": 4.199438258604389e-06,
+      "loss": 0.55,
+      "step": 310
+    },
+    {
+      "epoch": 1.0423452768729642,
+      "grad_norm": 59.25,
+      "learning_rate": 4.128663361989882e-06,
+      "loss": 0.4893,
+      "step": 320
+    },
+    {
+      "epoch": 1.0749185667752443,
+      "grad_norm": 73.0,
+      "learning_rate": 4.055544137792695e-06,
+      "loss": 0.4861,
+      "step": 330
+    },
+    {
+      "epoch": 1.1074918566775245,
+      "grad_norm": 31.0,
+      "learning_rate": 3.980185835150316e-06,
+      "loss": 0.4918,
+      "step": 340
+    },
+    {
+      "epoch": 1.1400651465798046,
+      "grad_norm": 26.0,
+      "learning_rate": 3.90269692617036e-06,
+      "loss": 0.4777,
+      "step": 350
+    },
+    {
+      "epoch": 1.1400651465798046,
+      "eval_accuracy": 0.7132352941176471,
+      "eval_auc": 0.7660203723217421,
+      "eval_f1": 0.7664670658682635,
+      "eval_loss": 0.5785877108573914,
+      "eval_precision": 0.7463556851311953,
+      "eval_recall": 0.7876923076923077,
+      "eval_runtime": 37.3143,
+      "eval_samples_per_second": 14.579,
+      "eval_steps_per_second": 0.241,
+      "step": 350
+    },
+    {
+      "epoch": 1.1726384364820848,
+      "grad_norm": 41.25,
+      "learning_rate": 3.8231889497938475e-06,
+      "loss": 0.434,
+      "step": 360
+    },
+    {
+      "epoch": 1.205211726384365,
+      "grad_norm": 92.5,
+      "learning_rate": 3.741776351244027e-06,
+      "loss": 0.5865,
+      "step": 370
+    },
+    {
+      "epoch": 1.237785016286645,
+      "grad_norm": 101.5,
+      "learning_rate": 3.65857631729185e-06,
+      "loss": 0.5187,
+      "step": 380
+    },
+    {
+      "epoch": 1.2703583061889252,
+      "grad_norm": 59.5,
+      "learning_rate": 3.5737086075752054e-06,
+      "loss": 0.4957,
+      "step": 390
+    },
+    {
+      "epoch": 1.3029315960912053,
+      "grad_norm": 47.5,
+      "learning_rate": 3.4872953822147233e-06,
+      "loss": 0.3976,
+      "step": 400
+    },
+    {
+      "epoch": 1.3029315960912053,
+      "eval_accuracy": 0.7113970588235294,
+      "eval_auc": 0.7714155251141552,
+      "eval_f1": 0.7773049645390071,
+      "eval_loss": 0.5780242085456848,
+      "eval_precision": 0.7210526315789474,
+      "eval_recall": 0.8430769230769231,
+      "eval_runtime": 37.4129,
+      "eval_samples_per_second": 14.54,
+      "eval_steps_per_second": 0.241,
+      "step": 400
+    },
+    {
+      "epoch": 1.3355048859934853,
+      "grad_norm": 52.75,
+      "learning_rate": 3.3994610259742846e-06,
+      "loss": 0.4786,
+      "step": 410
+    },
+    {
+      "epoch": 1.3680781758957654,
+      "grad_norm": 43.0,
+      "learning_rate": 3.310331969219332e-06,
+      "loss": 0.5328,
+      "step": 420
+    },
+    {
+      "epoch": 1.4006514657980456,
+      "grad_norm": 86.5,
+      "learning_rate": 3.2200365059307124e-06,
+      "loss": 0.4727,
+      "step": 430
+    },
+    {
+      "epoch": 1.4332247557003257,
+      "grad_norm": 37.0,
+      "learning_rate": 3.128704609035994e-06,
+      "loss": 0.5302,
+      "step": 440
+    },
+    {
+      "epoch": 1.4657980456026058,
+      "grad_norm": 57.75,
+      "learning_rate": 3.036467743324072e-06,
+      "loss": 0.5218,
+      "step": 450
+    },
+    {
+      "epoch": 1.4657980456026058,
+      "eval_accuracy": 0.7169117647058824,
+      "eval_auc": 0.7801404987706358,
+      "eval_f1": 0.7735294117647059,
+      "eval_loss": 0.5613196492195129,
+      "eval_precision": 0.7408450704225352,
+      "eval_recall": 0.8092307692307692,
+      "eval_runtime": 37.2673,
+      "eval_samples_per_second": 14.597,
+      "eval_steps_per_second": 0.241,
+      "step": 450
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 921,
+  "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": 9.778493129334129e+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 sha256:2dd3e968740b350013ac2cd899143931a17d006b072936c43d040b0837587b51
+size 5368