Upload folder using huggingface_hub

config.json

@@ -19,7 +19,7 @@
   "rope_theta": 1000000.0,
   "sliding_window": 32768,
   "tie_word_embeddings": true,
-  "torch_dtype": "bfloat16",
+  "torch_dtype": "float32",
   "transformers_version": "4.41.2",
   "use_cache": false,
   "use_sliding_window": false,

generation_config.json

@@ -1,7 +1,7 @@
 {
   "_from_model_config": true,
   "bos_token_id": 151643,
-  "do_sample": false,
+  "do_sample": true,
   "eos_token_id": [
     151645,
     151643

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f66bfb42982b8c06c9bc25b8b99d14435f7a44a4827e6f1c4f4f62b47436fd6f
+size 4996670464

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c9c22855dcd0d98bb0e09d292039b2831909be91813061f03aa2692016df446
+size 1178224960

model.safetensors.index.json

@@ -0,0 +1,345 @@
+{
+  "metadata": {
+    "total_size": 6174857216
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a2af9d07fb61306ec347f800e5ef1d06cd08a760bc2a70df53fd800b38069f3
+size 3094642562

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aca84d21747b494f2647f19153afa27bad629c2a874992b2bbe3f010aee01c0c
+size 1064

trainer_state.json

@@ -0,0 +1,373 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.021066583570698138,
+  "eval_steps": 5000,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.001053329178534907,
+      "grad_norm": 217.68748474121094,
+      "learning_rate": 5.263157894736842e-06,
+      "logits/chosen": -2.8389856815338135,
+      "logits/rejected": -2.8396875858306885,
+      "logps/chosen": -5.6633830070495605,
+      "logps/rejected": -6.1086931228637695,
+      "loss": 5.7387,
+      "odds_ratio_loss": 12.78534984588623,
+      "rewards/accuracies": 0.6208333373069763,
+      "rewards/chosen": -0.5663383603096008,
+      "rewards/margins": 0.04453102499246597,
+      "rewards/rejected": -0.6108693480491638,
+      "sft_loss": 4.460188388824463,
+      "step": 10
+    },
+    {
+      "epoch": 0.002106658357069814,
+      "grad_norm": 59.99885177612305,
+      "learning_rate": 1.0526315789473684e-05,
+      "logits/chosen": -3.0334506034851074,
+      "logits/rejected": -3.034069299697876,
+      "logps/chosen": -2.313845634460449,
+      "logps/rejected": -3.318277597427368,
+      "loss": 2.3687,
+      "odds_ratio_loss": 3.849175214767456,
+      "rewards/accuracies": 0.7562500238418579,
+      "rewards/chosen": -0.23138457536697388,
+      "rewards/margins": 0.10044321417808533,
+      "rewards/rejected": -0.3318277597427368,
+      "sft_loss": 1.9837348461151123,
+      "step": 20
+    },
+    {
+      "epoch": 0.0031599875356047207,
+      "grad_norm": 21.754234313964844,
+      "learning_rate": 1.5789473684210526e-05,
+      "logits/chosen": -3.226034641265869,
+      "logits/rejected": -3.2263522148132324,
+      "logps/chosen": -1.0712947845458984,
+      "logps/rejected": -2.3490335941314697,
+      "loss": 1.1116,
+      "odds_ratio_loss": 2.9476191997528076,
+      "rewards/accuracies": 0.8083333373069763,
+      "rewards/chosen": -0.10712946206331253,
+      "rewards/margins": 0.12777391076087952,
+      "rewards/rejected": -0.23490336537361145,
+      "sft_loss": 0.816817581653595,
+      "step": 30
+    },
+    {
+      "epoch": 0.004213316714139628,
+      "grad_norm": 7.782005310058594,
+      "learning_rate": 2.105263157894737e-05,
+      "logits/chosen": -3.4438676834106445,
+      "logits/rejected": -3.4442031383514404,
+      "logps/chosen": -0.8733291625976562,
+      "logps/rejected": -2.5004069805145264,
+      "loss": 0.914,
+      "odds_ratio_loss": 3.1110053062438965,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.08733292669057846,
+      "rewards/margins": 0.16270779073238373,
+      "rewards/rejected": -0.2500407099723816,
+      "sft_loss": 0.6028769016265869,
+      "step": 40
+    },
+    {
+      "epoch": 0.0052666458926745345,
+      "grad_norm": 9.219217300415039,
+      "learning_rate": 2.631578947368421e-05,
+      "logits/chosen": -3.4509921073913574,
+      "logits/rejected": -3.451155662536621,
+      "logps/chosen": -0.7789952158927917,
+      "logps/rejected": -2.3700900077819824,
+      "loss": 0.8189,
+      "odds_ratio_loss": 2.722813367843628,
+      "rewards/accuracies": 0.8062499761581421,
+      "rewards/chosen": -0.0778995230793953,
+      "rewards/margins": 0.1591094583272934,
+      "rewards/rejected": -0.23700900375843048,
+      "sft_loss": 0.5466489195823669,
+      "step": 50
+    },
+    {
+      "epoch": 0.006319975071209441,
+      "grad_norm": 7.359012603759766,
+      "learning_rate": 3.157894736842105e-05,
+      "logits/chosen": -3.5323359966278076,
+      "logits/rejected": -3.532480001449585,
+      "logps/chosen": -0.7335668802261353,
+      "logps/rejected": -2.5415773391723633,
+      "loss": 0.7747,
+      "odds_ratio_loss": 2.7141709327697754,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.07335668057203293,
+      "rewards/margins": 0.18080104887485504,
+      "rewards/rejected": -0.2541577219963074,
+      "sft_loss": 0.5032956600189209,
+      "step": 60
+    },
+    {
+      "epoch": 0.007373304249744348,
+      "grad_norm": 16.543472290039062,
+      "learning_rate": 3.6842105263157895e-05,
+      "logits/chosen": -3.2315316200256348,
+      "logits/rejected": -3.2316715717315674,
+      "logps/chosen": -0.6829439997673035,
+      "logps/rejected": -2.482815980911255,
+      "loss": 0.7205,
+      "odds_ratio_loss": 2.6182825565338135,
+      "rewards/accuracies": 0.8374999761581421,
+      "rewards/chosen": -0.06829439848661423,
+      "rewards/margins": 0.17998717725276947,
+      "rewards/rejected": -0.2482815831899643,
+      "sft_loss": 0.4587023854255676,
+      "step": 70
+    },
+    {
+      "epoch": 0.008426633428279255,
+      "grad_norm": 5.6111907958984375,
+      "learning_rate": 4.210526315789474e-05,
+      "logits/chosen": -2.9154586791992188,
+      "logits/rejected": -2.9156744480133057,
+      "logps/chosen": -0.7533618807792664,
+      "logps/rejected": -2.669802665710449,
+      "loss": 0.7912,
+      "odds_ratio_loss": 2.688143730163574,
+      "rewards/accuracies": 0.8333333134651184,
+      "rewards/chosen": -0.07533618807792664,
+      "rewards/margins": 0.19164405763149261,
+      "rewards/rejected": -0.26698026061058044,
+      "sft_loss": 0.5223438739776611,
+      "step": 80
+    },
+    {
+      "epoch": 0.009479962606814161,
+      "grad_norm": 3.4394092559814453,
+      "learning_rate": 4.736842105263158e-05,
+      "logits/chosen": -3.0740275382995605,
+      "logits/rejected": -3.0744776725769043,
+      "logps/chosen": -0.6786951422691345,
+      "logps/rejected": -3.1611907482147217,
+      "loss": 0.7145,
+      "odds_ratio_loss": 2.766305446624756,
+      "rewards/accuracies": 0.8270833492279053,
+      "rewards/chosen": -0.06786951422691345,
+      "rewards/margins": 0.2482495754957199,
+      "rewards/rejected": -0.31611910462379456,
+      "sft_loss": 0.4378434419631958,
+      "step": 90
+    },
+    {
+      "epoch": 0.010533291785349069,
+      "grad_norm": 9.483699798583984,
+      "learning_rate": 5.263157894736842e-05,
+      "logits/chosen": -3.197289228439331,
+      "logits/rejected": -3.19758677482605,
+      "logps/chosen": -0.6806226372718811,
+      "logps/rejected": -3.0961530208587646,
+      "loss": 0.7172,
+      "odds_ratio_loss": 2.700289726257324,
+      "rewards/accuracies": 0.84375,
+      "rewards/chosen": -0.06806226074695587,
+      "rewards/margins": 0.24155308306217194,
+      "rewards/rejected": -0.3096153140068054,
+      "sft_loss": 0.44717150926589966,
+      "step": 100
+    },
+    {
+      "epoch": 0.011586620963883975,
+      "grad_norm": 7.847203731536865,
+      "learning_rate": 5.789473684210527e-05,
+      "logits/chosen": -3.01198673248291,
+      "logits/rejected": -3.0121328830718994,
+      "logps/chosen": -0.7313061356544495,
+      "logps/rejected": -3.1134066581726074,
+      "loss": 0.7701,
+      "odds_ratio_loss": 2.80288028717041,
+      "rewards/accuracies": 0.8416666388511658,
+      "rewards/chosen": -0.07313062250614166,
+      "rewards/margins": 0.2382100373506546,
+      "rewards/rejected": -0.31134068965911865,
+      "sft_loss": 0.489812970161438,
+      "step": 110
+    },
+    {
+      "epoch": 0.012639950142418883,
+      "grad_norm": 9.357610702514648,
+      "learning_rate": 6.31578947368421e-05,
+      "logits/chosen": -2.793389320373535,
+      "logits/rejected": -2.793593406677246,
+      "logps/chosen": -0.744411826133728,
+      "logps/rejected": -3.2574427127838135,
+      "loss": 0.781,
+      "odds_ratio_loss": 2.4383304119110107,
+      "rewards/accuracies": 0.8374999761581421,
+      "rewards/chosen": -0.07444119453430176,
+      "rewards/margins": 0.251303106546402,
+      "rewards/rejected": -0.32574430108070374,
+      "sft_loss": 0.5372061133384705,
+      "step": 120
+    },
+    {
+      "epoch": 0.013693279320953789,
+      "grad_norm": 4.926955699920654,
+      "learning_rate": 6.842105263157896e-05,
+      "logits/chosen": -2.829728603363037,
+      "logits/rejected": -2.829943895339966,
+      "logps/chosen": -0.5513553619384766,
+      "logps/rejected": -2.877117872238159,
+      "loss": 0.5817,
+      "odds_ratio_loss": 2.001354694366455,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": -0.055135536938905716,
+      "rewards/margins": 0.23257622122764587,
+      "rewards/rejected": -0.2877117693424225,
+      "sft_loss": 0.38156595826148987,
+      "step": 130
+    },
+    {
+      "epoch": 0.014746608499488697,
+      "grad_norm": 8.740342140197754,
+      "learning_rate": 7.368421052631579e-05,
+      "logits/chosen": -2.9767470359802246,
+      "logits/rejected": -2.9770071506500244,
+      "logps/chosen": -0.5641220211982727,
+      "logps/rejected": -4.819352149963379,
+      "loss": 0.589,
+      "odds_ratio_loss": 2.0714950561523438,
+      "rewards/accuracies": 0.8833333253860474,
+      "rewards/chosen": -0.05641220510005951,
+      "rewards/margins": 0.4255230724811554,
+      "rewards/rejected": -0.48193517327308655,
+      "sft_loss": 0.3818718194961548,
+      "step": 140
+    },
+    {
+      "epoch": 0.015799937678023603,
+      "grad_norm": 21.316011428833008,
+      "learning_rate": 7.894736842105263e-05,
+      "logits/chosen": -2.9424824714660645,
+      "logits/rejected": -2.942646026611328,
+      "logps/chosen": -0.6596536040306091,
+      "logps/rejected": -5.643968105316162,
+      "loss": 0.6873,
+      "odds_ratio_loss": 2.2379026412963867,
+      "rewards/accuracies": 0.8833333253860474,
+      "rewards/chosen": -0.06596536934375763,
+      "rewards/margins": 0.4984314739704132,
+      "rewards/rejected": -0.5643967986106873,
+      "sft_loss": 0.46346980333328247,
+      "step": 150
+    },
+    {
+      "epoch": 0.01685326685655851,
+      "grad_norm": 8.542074203491211,
+      "learning_rate": 8.421052631578948e-05,
+      "logits/chosen": -2.788573741912842,
+      "logits/rejected": -2.7887728214263916,
+      "logps/chosen": -0.5694094300270081,
+      "logps/rejected": -4.549073219299316,
+      "loss": 0.5953,
+      "odds_ratio_loss": 2.08962082862854,
+      "rewards/accuracies": 0.9083333611488342,
+      "rewards/chosen": -0.05694093927741051,
+      "rewards/margins": 0.3979664146900177,
+      "rewards/rejected": -0.4549073278903961,
+      "sft_loss": 0.3863413631916046,
+      "step": 160
+    },
+    {
+      "epoch": 0.017906596035093418,
+      "grad_norm": 10.086228370666504,
+      "learning_rate": 8.947368421052632e-05,
+      "logits/chosen": -2.747136354446411,
+      "logits/rejected": -2.7473561763763428,
+      "logps/chosen": -0.5511812567710876,
+      "logps/rejected": -4.04136848449707,
+      "loss": 0.5864,
+      "odds_ratio_loss": 2.00999116897583,
+      "rewards/accuracies": 0.8479166626930237,
+      "rewards/chosen": -0.0551181361079216,
+      "rewards/margins": 0.34901875257492065,
+      "rewards/rejected": -0.40413692593574524,
+      "sft_loss": 0.3853704035282135,
+      "step": 170
+    },
+    {
+      "epoch": 0.018959925213628322,
+      "grad_norm": 6.374107837677002,
+      "learning_rate": 9.473684210526316e-05,
+      "logits/chosen": -2.6502909660339355,
+      "logits/rejected": -2.650648593902588,
+      "logps/chosen": -0.5040014982223511,
+      "logps/rejected": -4.205493450164795,
+      "loss": 0.5236,
+      "odds_ratio_loss": 1.6211795806884766,
+      "rewards/accuracies": 0.9208333492279053,
+      "rewards/chosen": -0.050400152802467346,
+      "rewards/margins": 0.3701492249965668,
+      "rewards/rejected": -0.4205494225025177,
+      "sft_loss": 0.3614722490310669,
+      "step": 180
+    },
+    {
+      "epoch": 0.02001325439216323,
+      "grad_norm": 2.717724323272705,
+      "learning_rate": 0.0001,
+      "logits/chosen": -2.7677037715911865,
+      "logits/rejected": -2.7680699825286865,
+      "logps/chosen": -0.5834678411483765,
+      "logps/rejected": -4.945567607879639,
+      "loss": 0.6101,
+      "odds_ratio_loss": 2.1636292934417725,
+      "rewards/accuracies": 0.893750011920929,
+      "rewards/chosen": -0.05834679678082466,
+      "rewards/margins": 0.4362100064754486,
+      "rewards/rejected": -0.49455681443214417,
+      "sft_loss": 0.39376381039619446,
+      "step": 190
+    },
+    {
+      "epoch": 0.021066583570698138,
+      "grad_norm": 6.805058479309082,
+      "learning_rate": 0.00010526315789473683,
+      "logits/chosen": -2.722885847091675,
+      "logits/rejected": -2.723130226135254,
+      "logps/chosen": -0.6606806516647339,
+      "logps/rejected": -4.050003528594971,
+      "loss": 0.6941,
+      "odds_ratio_loss": 2.383312940597534,
+      "rewards/accuracies": 0.856249988079071,
+      "rewards/chosen": -0.06606806069612503,
+      "rewards/margins": 0.3389323055744171,
+      "rewards/rejected": -0.4050002992153168,
+      "sft_loss": 0.4557226896286011,
+      "step": 200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 9493,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.4746225175966515e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e837a34ab4844742aedf3dd3e7300b434f2db8149439013ddd4cef5ab4cee401
+size 5240