upload checkpoint-700 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:dd0cd5aa925b47ce8ec9eec254a19f02300d91b5698f79f423177d48815c4026
+size 4976698672

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2afe194dfa395f37c9ab3a9e0db00c6fe7680c974995976f14b466e3f6ac4cc2
+size 4999802720

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:452a1131d5c39d73f2982c7133661fdb6546068db5ca7cc5fc302d1c732ba57d
+size 4915916176

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1272d87275cfef267048aeb5a9fcdc5d1d3be686b6709c4cae0d426b1c1bb8e9
+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:f430e35966d1db5f1af55ed96b3a4eea291637d25eee6a4c73245015aa5e1b68
+size 30019986218

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d10ad6c90de119ae0a3eeecda7366634ce107ef267b5fdd3ddd046f0a5ae742
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a85483408e78fde14a406fe71df79afd4012e4c02e9e2cdf65955c78b10299c9
+size 1064

trainer_state.json

@@ -0,0 +1,705 @@
+{
+  "best_metric": 0.8464566929133859,
+  "best_model_checkpoint": "./llama_reward_model_1e5-bz32/checkpoint-500",
+  "epoch": 4.861111111111111,
+  "eval_steps": 50,
+  "global_step": 700,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06944444444444445,
+      "grad_norm": 111.5,
+      "learning_rate": 1.3888888888888892e-06,
+      "loss": 1.451,
+      "step": 10
+    },
+    {
+      "epoch": 0.1388888888888889,
+      "grad_norm": 241.0,
+      "learning_rate": 2.7777777777777783e-06,
+      "loss": 0.9891,
+      "step": 20
+    },
+    {
+      "epoch": 0.20833333333333334,
+      "grad_norm": 55.5,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 0.6873,
+      "step": 30
+    },
+    {
+      "epoch": 0.2777777777777778,
+      "grad_norm": 89.5,
+      "learning_rate": 5.555555555555557e-06,
+      "loss": 0.5822,
+      "step": 40
+    },
+    {
+      "epoch": 0.3472222222222222,
+      "grad_norm": 41.25,
+      "learning_rate": 6.944444444444445e-06,
+      "loss": 0.5683,
+      "step": 50
+    },
+    {
+      "epoch": 0.3472222222222222,
+      "eval_accuracy": 0.7637795275590551,
+      "eval_auc": 0.8218052109181142,
+      "eval_f1": 0.7619047619047619,
+      "eval_loss": 0.5505948066711426,
+      "eval_precision": 0.75,
+      "eval_recall": 0.7741935483870968,
+      "eval_runtime": 17.2811,
+      "eval_samples_per_second": 14.698,
+      "eval_steps_per_second": 0.231,
+      "step": 50
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 50.0,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.663,
+      "step": 60
+    },
+    {
+      "epoch": 0.4861111111111111,
+      "grad_norm": 20.25,
+      "learning_rate": 9.722222222222223e-06,
+      "loss": 0.5973,
+      "step": 70
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 75.0,
+      "learning_rate": 9.996239762521152e-06,
+      "loss": 0.5811,
+      "step": 80
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 38.25,
+      "learning_rate": 9.980973490458728e-06,
+      "loss": 0.5726,
+      "step": 90
+    },
+    {
+      "epoch": 0.6944444444444444,
+      "grad_norm": 148.0,
+      "learning_rate": 9.954002016824226e-06,
+      "loss": 0.5948,
+      "step": 100
+    },
+    {
+      "epoch": 0.6944444444444444,
+      "eval_accuracy": 0.6732283464566929,
+      "eval_auc": 0.8793424317617865,
+      "eval_f1": 0.546448087431694,
+      "eval_loss": 0.5765186548233032,
+      "eval_precision": 0.847457627118644,
+      "eval_recall": 0.4032258064516129,
+      "eval_runtime": 17.3424,
+      "eval_samples_per_second": 14.646,
+      "eval_steps_per_second": 0.231,
+      "step": 100
+    },
+    {
+      "epoch": 0.7638888888888888,
+      "grad_norm": 41.0,
+      "learning_rate": 9.915388724114301e-06,
+      "loss": 0.5116,
+      "step": 110
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 15.6875,
+      "learning_rate": 9.86522435289912e-06,
+      "loss": 0.5211,
+      "step": 120
+    },
+    {
+      "epoch": 0.9027777777777778,
+      "grad_norm": 79.0,
+      "learning_rate": 9.803626788583603e-06,
+      "loss": 0.5657,
+      "step": 130
+    },
+    {
+      "epoch": 0.9722222222222222,
+      "grad_norm": 44.5,
+      "learning_rate": 9.730740784378755e-06,
+      "loss": 0.4961,
+      "step": 140
+    },
+    {
+      "epoch": 1.0416666666666667,
+      "grad_norm": 33.25,
+      "learning_rate": 9.646737621134112e-06,
+      "loss": 0.4932,
+      "step": 150
+    },
+    {
+      "epoch": 1.0416666666666667,
+      "eval_accuracy": 0.8188976377952756,
+      "eval_auc": 0.8933002481389578,
+      "eval_f1": 0.8435374149659864,
+      "eval_loss": 0.4920627772808075,
+      "eval_precision": 0.7294117647058823,
+      "eval_recall": 1.0,
+      "eval_runtime": 17.2166,
+      "eval_samples_per_second": 14.753,
+      "eval_steps_per_second": 0.232,
+      "step": 150
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 37.5,
+      "learning_rate": 9.551814704830734e-06,
+      "loss": 0.4114,
+      "step": 160
+    },
+    {
+      "epoch": 1.1805555555555556,
+      "grad_norm": 22.0,
+      "learning_rate": 9.446195102680531e-06,
+      "loss": 0.4434,
+      "step": 170
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 48.25,
+      "learning_rate": 9.330127018922195e-06,
+      "loss": 0.5029,
+      "step": 180
+    },
+    {
+      "epoch": 1.3194444444444444,
+      "grad_norm": 10.1875,
+      "learning_rate": 9.203883211545517e-06,
+      "loss": 0.36,
+      "step": 190
+    },
+    {
+      "epoch": 1.3888888888888888,
+      "grad_norm": 22.5,
+      "learning_rate": 9.067760351314838e-06,
+      "loss": 0.3651,
+      "step": 200
+    },
+    {
+      "epoch": 1.3888888888888888,
+      "eval_accuracy": 0.8110236220472441,
+      "eval_auc": 0.8889267990074442,
+      "eval_f1": 0.8248175182481752,
+      "eval_loss": 0.4430588185787201,
+      "eval_precision": 0.7533333333333333,
+      "eval_recall": 0.9112903225806451,
+      "eval_runtime": 17.3222,
+      "eval_samples_per_second": 14.663,
+      "eval_steps_per_second": 0.231,
+      "step": 200
+    },
+    {
+      "epoch": 1.4583333333333333,
+      "grad_norm": 19.0,
+      "learning_rate": 8.92207832459788e-06,
+      "loss": 0.3805,
+      "step": 210
+    },
+    {
+      "epoch": 1.5277777777777777,
+      "grad_norm": 43.0,
+      "learning_rate": 8.767179481638303e-06,
+      "loss": 0.3689,
+      "step": 220
+    },
+    {
+      "epoch": 1.5972222222222223,
+      "grad_norm": 26.5,
+      "learning_rate": 8.603427832038574e-06,
+      "loss": 0.3745,
+      "step": 230
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 68.0,
+      "learning_rate": 8.43120818934367e-06,
+      "loss": 0.3921,
+      "step": 240
+    },
+    {
+      "epoch": 1.7361111111111112,
+      "grad_norm": 25.75,
+      "learning_rate": 8.25092526673592e-06,
+      "loss": 0.434,
+      "step": 250
+    },
+    {
+      "epoch": 1.7361111111111112,
+      "eval_accuracy": 0.84251968503937,
+      "eval_auc": 0.9133374689826302,
+      "eval_f1": 0.8461538461538461,
+      "eval_loss": 0.36681872606277466,
+      "eval_precision": 0.8088235294117647,
+      "eval_recall": 0.8870967741935484,
+      "eval_runtime": 17.2167,
+      "eval_samples_per_second": 14.753,
+      "eval_steps_per_second": 0.232,
+      "step": 250
+    },
+    {
+      "epoch": 1.8055555555555556,
+      "grad_norm": 11.9375,
+      "learning_rate": 8.063002725966014e-06,
+      "loss": 0.3524,
+      "step": 260
+    },
+    {
+      "epoch": 1.875,
+      "grad_norm": 26.25,
+      "learning_rate": 7.86788218175523e-06,
+      "loss": 0.3992,
+      "step": 270
+    },
+    {
+      "epoch": 1.9444444444444444,
+      "grad_norm": 32.75,
+      "learning_rate": 7.666022164008458e-06,
+      "loss": 0.4295,
+      "step": 280
+    },
+    {
+      "epoch": 2.013888888888889,
+      "grad_norm": 10.4375,
+      "learning_rate": 7.457897040276853e-06,
+      "loss": 0.3542,
+      "step": 290
+    },
+    {
+      "epoch": 2.0833333333333335,
+      "grad_norm": 26.125,
+      "learning_rate": 7.243995901002312e-06,
+      "loss": 0.2434,
+      "step": 300
+    },
+    {
+      "epoch": 2.0833333333333335,
+      "eval_accuracy": 0.7992125984251969,
+      "eval_auc": 0.9068238213399503,
+      "eval_f1": 0.8197879858657244,
+      "eval_loss": 0.5410435199737549,
+      "eval_precision": 0.7295597484276729,
+      "eval_recall": 0.9354838709677419,
+      "eval_runtime": 17.3565,
+      "eval_samples_per_second": 14.634,
+      "eval_steps_per_second": 0.23,
+      "step": 300
+    },
+    {
+      "epoch": 2.1527777777777777,
+      "grad_norm": 14.75,
+      "learning_rate": 7.0248214101633685e-06,
+      "loss": 0.2442,
+      "step": 310
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 13.375,
+      "learning_rate": 6.800888624023552e-06,
+      "loss": 0.211,
+      "step": 320
+    },
+    {
+      "epoch": 2.2916666666666665,
+      "grad_norm": 44.25,
+      "learning_rate": 6.572723780758069e-06,
+      "loss": 0.175,
+      "step": 330
+    },
+    {
+      "epoch": 2.361111111111111,
+      "grad_norm": 20.0,
+      "learning_rate": 6.340863063803187e-06,
+      "loss": 0.1647,
+      "step": 340
+    },
+    {
+      "epoch": 2.4305555555555554,
+      "grad_norm": 32.5,
+      "learning_rate": 6.105851341834439e-06,
+      "loss": 0.2687,
+      "step": 350
+    },
+    {
+      "epoch": 2.4305555555555554,
+      "eval_accuracy": 0.8385826771653543,
+      "eval_auc": 0.8970843672456575,
+      "eval_f1": 0.846441947565543,
+      "eval_loss": 0.45397356152534485,
+      "eval_precision": 0.7902097902097902,
+      "eval_recall": 0.9112903225806451,
+      "eval_runtime": 17.2257,
+      "eval_samples_per_second": 14.745,
+      "eval_steps_per_second": 0.232,
+      "step": 350
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 34.25,
+      "learning_rate": 5.8682408883346535e-06,
+      "loss": 0.2253,
+      "step": 360
+    },
+    {
+      "epoch": 2.5694444444444446,
+      "grad_norm": 42.25,
+      "learning_rate": 5.628590083760815e-06,
+      "loss": 0.2023,
+      "step": 370
+    },
+    {
+      "epoch": 2.638888888888889,
+      "grad_norm": 23.5,
+      "learning_rate": 5.387462103359655e-06,
+      "loss": 0.1633,
+      "step": 380
+    },
+    {
+      "epoch": 2.7083333333333335,
+      "grad_norm": 23.375,
+      "learning_rate": 5.145423593715558e-06,
+      "loss": 0.2195,
+      "step": 390
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 31.75,
+      "learning_rate": 4.903043341140879e-06,
+      "loss": 0.1774,
+      "step": 400
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "eval_accuracy": 0.8149606299212598,
+      "eval_auc": 0.90462158808933,
+      "eval_f1": 0.8226415094339623,
+      "eval_loss": 0.44090235233306885,
+      "eval_precision": 0.7730496453900709,
+      "eval_recall": 0.8790322580645161,
+      "eval_runtime": 17.1892,
+      "eval_samples_per_second": 14.777,
+      "eval_steps_per_second": 0.233,
+      "step": 400
+    },
+    {
+      "epoch": 2.8472222222222223,
+      "grad_norm": 40.5,
+      "learning_rate": 4.660890935037954e-06,
+      "loss": 0.1502,
+      "step": 410
+    },
+    {
+      "epoch": 2.9166666666666665,
+      "grad_norm": 33.25,
+      "learning_rate": 4.4195354293738484e-06,
+      "loss": 0.1355,
+      "step": 420
+    },
+    {
+      "epoch": 2.986111111111111,
+      "grad_norm": 30.125,
+      "learning_rate": 4.17954400541338e-06,
+      "loss": 0.1545,
+      "step": 430
+    },
+    {
+      "epoch": 3.0555555555555554,
+      "grad_norm": 5.96875,
+      "learning_rate": 3.941480638852948e-06,
+      "loss": 0.0917,
+      "step": 440
+    },
+    {
+      "epoch": 3.125,
+      "grad_norm": 3.90625,
+      "learning_rate": 3.705904774487396e-06,
+      "loss": 0.0732,
+      "step": 450
+    },
+    {
+      "epoch": 3.125,
+      "eval_accuracy": 0.8385826771653543,
+      "eval_auc": 0.9099565756823821,
+      "eval_f1": 0.8452830188679246,
+      "eval_loss": 0.47704994678497314,
+      "eval_precision": 0.7943262411347518,
+      "eval_recall": 0.9032258064516129,
+      "eval_runtime": 17.2377,
+      "eval_samples_per_second": 14.735,
+      "eval_steps_per_second": 0.232,
+      "step": 450
+    },
+    {
+      "epoch": 3.1944444444444446,
+      "grad_norm": 50.25,
+      "learning_rate": 3.473370011524435e-06,
+      "loss": 0.0313,
+      "step": 460
+    },
+    {
+      "epoch": 3.263888888888889,
+      "grad_norm": 21.75,
+      "learning_rate": 3.244422802636057e-06,
+      "loss": 0.0233,
+      "step": 470
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 14.5625,
+      "learning_rate": 3.019601169804216e-06,
+      "loss": 0.0316,
+      "step": 480
+    },
+    {
+      "epoch": 3.4027777777777777,
+      "grad_norm": 9.5,
+      "learning_rate": 2.7994334399784773e-06,
+      "loss": 0.0272,
+      "step": 490
+    },
+    {
+      "epoch": 3.4722222222222223,
+      "grad_norm": 29.0,
+      "learning_rate": 2.5844370035168077e-06,
+      "loss": 0.0598,
+      "step": 500
+    },
+    {
+      "epoch": 3.4722222222222223,
+      "eval_accuracy": 0.8464566929133859,
+      "eval_auc": 0.9099255583126551,
+      "eval_f1": 0.8446215139442231,
+      "eval_loss": 0.5372636318206787,
+      "eval_precision": 0.8346456692913385,
+      "eval_recall": 0.8548387096774194,
+      "eval_runtime": 17.3025,
+      "eval_samples_per_second": 14.68,
+      "eval_steps_per_second": 0.231,
+      "step": 500
+    },
+    {
+      "epoch": 3.5416666666666665,
+      "grad_norm": 4.09375,
+      "learning_rate": 2.3751170983272e-06,
+      "loss": 0.0248,
+      "step": 510
+    },
+    {
+      "epoch": 3.611111111111111,
+      "grad_norm": 1.1484375,
+      "learning_rate": 2.171965622567308e-06,
+      "loss": 0.0152,
+      "step": 520
+    },
+    {
+      "epoch": 3.6805555555555554,
+      "grad_norm": 2.546875,
+      "learning_rate": 1.9754599786922913e-06,
+      "loss": 0.0366,
+      "step": 530
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 5.0,
+      "learning_rate": 1.7860619515673034e-06,
+      "loss": 0.0311,
+      "step": 540
+    },
+    {
+      "epoch": 3.8194444444444446,
+      "grad_norm": 3.46875,
+      "learning_rate": 1.6042166232810346e-06,
+      "loss": 0.0283,
+      "step": 550
+    },
+    {
+      "epoch": 3.8194444444444446,
+      "eval_accuracy": 0.8385826771653543,
+      "eval_auc": 0.9107009925558313,
+      "eval_f1": 0.8404669260700389,
+      "eval_loss": 0.6065385341644287,
+      "eval_precision": 0.8120300751879699,
+      "eval_recall": 0.8709677419354839,
+      "eval_runtime": 17.1801,
+      "eval_samples_per_second": 14.785,
+      "eval_steps_per_second": 0.233,
+      "step": 550
+    },
+    {
+      "epoch": 3.888888888888889,
+      "grad_norm": 10.0625,
+      "learning_rate": 1.4303513272105057e-06,
+      "loss": 0.0166,
+      "step": 560
+    },
+    {
+      "epoch": 3.9583333333333335,
+      "grad_norm": 4.90625,
+      "learning_rate": 1.264874643795021e-06,
+      "loss": 0.0146,
+      "step": 570
+    },
+    {
+      "epoch": 4.027777777777778,
+      "grad_norm": 13.3125,
+      "learning_rate": 1.1081754403792e-06,
+      "loss": 0.0125,
+      "step": 580
+    },
+    {
+      "epoch": 4.097222222222222,
+      "grad_norm": 0.50390625,
+      "learning_rate": 9.606219573814447e-07,
+      "loss": 0.0019,
+      "step": 590
+    },
+    {
+      "epoch": 4.166666666666667,
+      "grad_norm": 1.2734375,
+      "learning_rate": 8.225609429353187e-07,
+      "loss": 0.0161,
+      "step": 600
+    },
+    {
+      "epoch": 4.166666666666667,
+      "eval_accuracy": 0.8464566929133859,
+      "eval_auc": 0.9123138957816378,
+      "eval_f1": 0.8482490272373541,
+      "eval_loss": 0.6167948246002197,
+      "eval_precision": 0.8195488721804511,
+      "eval_recall": 0.8790322580645161,
+      "eval_runtime": 17.3503,
+      "eval_samples_per_second": 14.64,
+      "eval_steps_per_second": 0.231,
+      "step": 600
+    },
+    {
+      "epoch": 4.236111111111111,
+      "grad_norm": 1.3515625,
+      "learning_rate": 6.94316838037431e-07,
+      "loss": 0.0045,
+      "step": 610
+    },
+    {
+      "epoch": 4.305555555555555,
+      "grad_norm": 0.84765625,
+      "learning_rate": 5.76191014116711e-07,
+      "loss": 0.005,
+      "step": 620
+    },
+    {
+      "epoch": 4.375,
+      "grad_norm": 4.34375,
+      "learning_rate": 4.6846106481675035e-07,
+      "loss": 0.0101,
+      "step": 630
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 5.6875,
+      "learning_rate": 3.7138015365554834e-07,
+      "loss": 0.0091,
+      "step": 640
+    },
+    {
+      "epoch": 4.513888888888889,
+      "grad_norm": 8.875,
+      "learning_rate": 2.8517641909562075e-07,
+      "loss": 0.0091,
+      "step": 650
+    },
+    {
+      "epoch": 4.513888888888889,
+      "eval_accuracy": 0.8464566929133859,
+      "eval_auc": 0.9123449131513648,
+      "eval_f1": 0.8482490272373541,
+      "eval_loss": 0.6211294531822205,
+      "eval_precision": 0.8195488721804511,
+      "eval_recall": 0.8790322580645161,
+      "eval_runtime": 17.3655,
+      "eval_samples_per_second": 14.627,
+      "eval_steps_per_second": 0.23,
+      "step": 650
+    },
+    {
+      "epoch": 4.583333333333333,
+      "grad_norm": 1.484375,
+      "learning_rate": 2.1005243842255552e-07,
+      "loss": 0.0037,
+      "step": 660
+    },
+    {
+      "epoch": 4.652777777777778,
+      "grad_norm": 3.265625,
+      "learning_rate": 1.4618475169190017e-07,
+      "loss": 0.0033,
+      "step": 670
+    },
+    {
+      "epoch": 4.722222222222222,
+      "grad_norm": 7.1875,
+      "learning_rate": 9.372344686307655e-08,
+      "loss": 0.0079,
+      "step": 680
+    },
+    {
+      "epoch": 4.791666666666667,
+      "grad_norm": 0.6953125,
+      "learning_rate": 5.279180709527765e-08,
+      "loss": 0.0044,
+      "step": 690
+    },
+    {
+      "epoch": 4.861111111111111,
+      "grad_norm": 0.41796875,
+      "learning_rate": 2.3486021034170857e-08,
+      "loss": 0.007,
+      "step": 700
+    },
+    {
+      "epoch": 4.861111111111111,
+      "eval_accuracy": 0.8464566929133859,
+      "eval_auc": 0.9124069478908188,
+      "eval_f1": 0.8482490272373541,
+      "eval_loss": 0.6205126047134399,
+      "eval_precision": 0.8195488721804511,
+      "eval_recall": 0.8790322580645161,
+      "eval_runtime": 17.3822,
+      "eval_samples_per_second": 14.613,
+      "eval_steps_per_second": 0.23,
+      "step": 700
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 720,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 1.5117205872894935e+18,
+  "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:aef4bf873a75c3381619bc484de3173613a391aaac55a07206c963fc0d6140ff
+size 5368