Upload folder using huggingface_hub

config.json

@@ -1,7 +1,7 @@
 {
-  "_name_or_path": "output_deepseek_v0.0.3/checkpoint-1400",
+  "_name_or_path": "output_deepseek_v0.0.2/checkpoint-2400",
   "architectures": [
-    "LlamaModel"
+    "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 32013,
+  "eos_token_id": 32021,
+  "transformers_version": "4.44.0"
+}

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48a54d19c337625a865c6dde984bcbf248ffcbb38ff096071c99418610bace20
-size 4986378792
+oid sha256:34a7e0c12737c54f1c824032489551825c626a1643c93ff05baa82cd588d83ab
+size 4986380064

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66da5a74fe93ff87bb1d6d5f3f5bd32469fcd6d2a6875d60f3b1d6950d80e742
-size 135291512
+oid sha256:983686ed30eb67909631f0c5c3a97233409d5b38b9c32b06ab2913ff5293def3
+size 399532808

model.safetensors.index.json

@@ -1,225 +1,226 @@
 {
   "metadata": {
-    "total_size": 5121646592
+    "total_size": 5385887744
   },
   "weight_map": {
-    "embed_tokens.weight": "model-00001-of-00002.safetensors",
-    "layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "norm.weight": "model-00002-of-00002.safetensors"
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-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-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.weight": "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-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-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.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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:db84075a90fba35fd8d31611a65ce75095ea0bddea9d2781edeb239cf25a9d16
+size 10771909506

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e33c1a835a3506bc9c891b6d79847ac4178eb35f120b8d91a5656ec1b3016528
+size 14960

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0de18c0c41258210fc5df6f484fa8ff2f740d8f622268d7d7f77acd7f4685c8
+size 14960

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f08d210bbe20cfaf8c036275434f6d66d7847cfa2e495379e69d0a918685b80
+size 14960

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4bb6b0131250ccf76ecc2baec6b26f8f1c1973f6094ba98c71fe79aee9426eb
+size 1064

trainer_state.json

@@ -0,0 +1,1023 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0213386832026263,
+  "eval_steps": 500,
+  "global_step": 1400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.007295276308590188,
+      "grad_norm": 0.9992304444313049,
+      "learning_rate": 9.999671349822887e-06,
+      "loss": 0.087,
+      "step": 10
+    },
+    {
+      "epoch": 0.014590552617180376,
+      "grad_norm": 1.0456160306930542,
+      "learning_rate": 9.998685442495921e-06,
+      "loss": 0.0757,
+      "step": 20
+    },
+    {
+      "epoch": 0.021885828925770564,
+      "grad_norm": 1.014310598373413,
+      "learning_rate": 9.99704240762655e-06,
+      "loss": 0.0901,
+      "step": 30
+    },
+    {
+      "epoch": 0.029181105234360752,
+      "grad_norm": 0.9391605257987976,
+      "learning_rate": 9.994742461208251e-06,
+      "loss": 0.0811,
+      "step": 40
+    },
+    {
+      "epoch": 0.036476381542950936,
+      "grad_norm": 0.7982305884361267,
+      "learning_rate": 9.991785905592149e-06,
+      "loss": 0.0818,
+      "step": 50
+    },
+    {
+      "epoch": 0.04377165785154113,
+      "grad_norm": 0.9946795701980591,
+      "learning_rate": 9.988173129447251e-06,
+      "loss": 0.0905,
+      "step": 60
+    },
+    {
+      "epoch": 0.05106693416013131,
+      "grad_norm": 0.8562415242195129,
+      "learning_rate": 9.983904607709365e-06,
+      "loss": 0.0831,
+      "step": 70
+    },
+    {
+      "epoch": 0.058362210468721504,
+      "grad_norm": 1.054521918296814,
+      "learning_rate": 9.978980901518663e-06,
+      "loss": 0.083,
+      "step": 80
+    },
+    {
+      "epoch": 0.06565748677731169,
+      "grad_norm": 1.0189253091812134,
+      "learning_rate": 9.973402658145908e-06,
+      "loss": 0.0891,
+      "step": 90
+    },
+    {
+      "epoch": 0.07295276308590187,
+      "grad_norm": 0.7745731472969055,
+      "learning_rate": 9.96717061090737e-06,
+      "loss": 0.0846,
+      "step": 100
+    },
+    {
+      "epoch": 0.08024803939449207,
+      "grad_norm": 0.8214731812477112,
+      "learning_rate": 9.960285579068419e-06,
+      "loss": 0.0895,
+      "step": 110
+    },
+    {
+      "epoch": 0.08754331570308226,
+      "grad_norm": 0.9114850759506226,
+      "learning_rate": 9.95274846773583e-06,
+      "loss": 0.0862,
+      "step": 120
+    },
+    {
+      "epoch": 0.09483859201167244,
+      "grad_norm": 1.216098427772522,
+      "learning_rate": 9.944560267738792e-06,
+      "loss": 0.0896,
+      "step": 130
+    },
+    {
+      "epoch": 0.10213386832026262,
+      "grad_norm": 0.7587252855300903,
+      "learning_rate": 9.935722055498655e-06,
+      "loss": 0.0888,
+      "step": 140
+    },
+    {
+      "epoch": 0.10942914462885282,
+      "grad_norm": 0.8791028261184692,
+      "learning_rate": 9.92623499288743e-06,
+      "loss": 0.0832,
+      "step": 150
+    },
+    {
+      "epoch": 0.11672442093744301,
+      "grad_norm": 1.133716344833374,
+      "learning_rate": 9.916100327075038e-06,
+      "loss": 0.0854,
+      "step": 160
+    },
+    {
+      "epoch": 0.12401969724603319,
+      "grad_norm": 0.7774285674095154,
+      "learning_rate": 9.905319390365364e-06,
+      "loss": 0.0873,
+      "step": 170
+    },
+    {
+      "epoch": 0.13131497355462338,
+      "grad_norm": 0.7029784321784973,
+      "learning_rate": 9.893893600021112e-06,
+      "loss": 0.0786,
+      "step": 180
+    },
+    {
+      "epoch": 0.13861024986321357,
+      "grad_norm": 1.0894945859909058,
+      "learning_rate": 9.881824458077491e-06,
+      "loss": 0.089,
+      "step": 190
+    },
+    {
+      "epoch": 0.14590552617180375,
+      "grad_norm": 0.7053947448730469,
+      "learning_rate": 9.869113551144754e-06,
+      "loss": 0.0843,
+      "step": 200
+    },
+    {
+      "epoch": 0.15320080248039394,
+      "grad_norm": 0.9423328638076782,
+      "learning_rate": 9.85576255019963e-06,
+      "loss": 0.0887,
+      "step": 210
+    },
+    {
+      "epoch": 0.16049607878898414,
+      "grad_norm": 1.1778377294540405,
+      "learning_rate": 9.841773210365646e-06,
+      "loss": 0.0939,
+      "step": 220
+    },
+    {
+      "epoch": 0.1677913550975743,
+      "grad_norm": 0.8132289052009583,
+      "learning_rate": 9.82714737068241e-06,
+      "loss": 0.0812,
+      "step": 230
+    },
+    {
+      "epoch": 0.1750866314061645,
+      "grad_norm": 0.925722062587738,
+      "learning_rate": 9.811886953863841e-06,
+      "loss": 0.091,
+      "step": 240
+    },
+    {
+      "epoch": 0.1823819077147547,
+      "grad_norm": 0.8174653649330139,
+      "learning_rate": 9.795993966045418e-06,
+      "loss": 0.0868,
+      "step": 250
+    },
+    {
+      "epoch": 0.18967718402334488,
+      "grad_norm": 1.086427092552185,
+      "learning_rate": 9.779470496520442e-06,
+      "loss": 0.0882,
+      "step": 260
+    },
+    {
+      "epoch": 0.19697246033193508,
+      "grad_norm": 0.8431033492088318,
+      "learning_rate": 9.76231871746539e-06,
+      "loss": 0.0819,
+      "step": 270
+    },
+    {
+      "epoch": 0.20426773664052525,
+      "grad_norm": 0.9793428778648376,
+      "learning_rate": 9.744540883654348e-06,
+      "loss": 0.0838,
+      "step": 280
+    },
+    {
+      "epoch": 0.21156301294911545,
+      "grad_norm": 1.1424306631088257,
+      "learning_rate": 9.726139332162613e-06,
+      "loss": 0.0923,
+      "step": 290
+    },
+    {
+      "epoch": 0.21885828925770565,
+      "grad_norm": 0.8779186010360718,
+      "learning_rate": 9.707116482059447e-06,
+      "loss": 0.0909,
+      "step": 300
+    },
+    {
+      "epoch": 0.22615356556629582,
+      "grad_norm": 0.862575113773346,
+      "learning_rate": 9.68747483409007e-06,
+      "loss": 0.094,
+      "step": 310
+    },
+    {
+      "epoch": 0.23344884187488602,
+      "grad_norm": 0.8033697009086609,
+      "learning_rate": 9.667216970346916e-06,
+      "loss": 0.0821,
+      "step": 320
+    },
+    {
+      "epoch": 0.24074411818347619,
+      "grad_norm": 1.136168360710144,
+      "learning_rate": 9.646345553930187e-06,
+      "loss": 0.084,
+      "step": 330
+    },
+    {
+      "epoch": 0.24803939449206638,
+      "grad_norm": 1.227287769317627,
+      "learning_rate": 9.624863328597767e-06,
+      "loss": 0.0867,
+      "step": 340
+    },
+    {
+      "epoch": 0.2553346708006566,
+      "grad_norm": 0.8906837105751038,
+      "learning_rate": 9.602773118404518e-06,
+      "loss": 0.0845,
+      "step": 350
+    },
+    {
+      "epoch": 0.26262994710924675,
+      "grad_norm": 0.9557612538337708,
+      "learning_rate": 9.580077827331038e-06,
+      "loss": 0.0896,
+      "step": 360
+    },
+    {
+      "epoch": 0.2699252234178369,
+      "grad_norm": 0.8804728984832764,
+      "learning_rate": 9.556780438901899e-06,
+      "loss": 0.0799,
+      "step": 370
+    },
+    {
+      "epoch": 0.27722049972642715,
+      "grad_norm": 0.8825680017471313,
+      "learning_rate": 9.532884015793432e-06,
+      "loss": 0.0879,
+      "step": 380
+    },
+    {
+      "epoch": 0.2845157760350173,
+      "grad_norm": 1.216217041015625,
+      "learning_rate": 9.508391699431114e-06,
+      "loss": 0.0878,
+      "step": 390
+    },
+    {
+      "epoch": 0.2918110523436075,
+      "grad_norm": 1.0918773412704468,
+      "learning_rate": 9.48330670957659e-06,
+      "loss": 0.0842,
+      "step": 400
+    },
+    {
+      "epoch": 0.2991063286521977,
+      "grad_norm": 0.8797096014022827,
+      "learning_rate": 9.457632343904404e-06,
+      "loss": 0.075,
+      "step": 410
+    },
+    {
+      "epoch": 0.3064016049607879,
+      "grad_norm": 0.9638001322746277,
+      "learning_rate": 9.431371977568483e-06,
+      "loss": 0.0834,
+      "step": 420
+    },
+    {
+      "epoch": 0.31369688126937806,
+      "grad_norm": 0.7447642683982849,
+      "learning_rate": 9.404529062758447e-06,
+      "loss": 0.0909,
+      "step": 430
+    },
+    {
+      "epoch": 0.3209921575779683,
+      "grad_norm": 1.179291844367981,
+      "learning_rate": 9.377107128245782e-06,
+      "loss": 0.0832,
+      "step": 440
+    },
+    {
+      "epoch": 0.32828743388655846,
+      "grad_norm": 0.6798911094665527,
+      "learning_rate": 9.349109778919938e-06,
+      "loss": 0.0842,
+      "step": 450
+    },
+    {
+      "epoch": 0.3355827101951486,
+      "grad_norm": 0.9468401670455933,
+      "learning_rate": 9.32054069531444e-06,
+      "loss": 0.0937,
+      "step": 460
+    },
+    {
+      "epoch": 0.34287798650373885,
+      "grad_norm": 0.9600223898887634,
+      "learning_rate": 9.291403633123046e-06,
+      "loss": 0.0909,
+      "step": 470
+    },
+    {
+      "epoch": 0.350173262812329,
+      "grad_norm": 0.7957492470741272,
+      "learning_rate": 9.261702422706014e-06,
+      "loss": 0.0924,
+      "step": 480
+    },
+    {
+      "epoch": 0.3574685391209192,
+      "grad_norm": 0.9197902083396912,
+      "learning_rate": 9.231440968586572e-06,
+      "loss": 0.0852,
+      "step": 490
+    },
+    {
+      "execution_accuracy": 37.0,
+      "selected_difficulty": "challenging",
+      "step": 500
+    },
+    {
+      "epoch": 0.3647638154295094,
+      "grad_norm": 1.0779783725738525,
+      "learning_rate": 9.200623248937619e-06,
+      "loss": 0.0872,
+      "step": 500
+    },
+    {
+      "epoch": 0.3720590917380996,
+      "grad_norm": 1.0330190658569336,
+      "learning_rate": 9.169253315058764e-06,
+      "loss": 0.0884,
+      "step": 510
+    },
+    {
+      "epoch": 0.37935436804668976,
+      "grad_norm": 0.8854564428329468,
+      "learning_rate": 9.13733529084374e-06,
+      "loss": 0.0888,
+      "step": 520
+    },
+    {
+      "epoch": 0.38664964435527993,
+      "grad_norm": 0.7928789258003235,
+      "learning_rate": 9.104873372238269e-06,
+      "loss": 0.0858,
+      "step": 530
+    },
+    {
+      "epoch": 0.39394492066387016,
+      "grad_norm": 1.1074901819229126,
+      "learning_rate": 9.071871826688472e-06,
+      "loss": 0.0866,
+      "step": 540
+    },
+    {
+      "epoch": 0.40124019697246033,
+      "grad_norm": 0.9030365347862244,
+      "learning_rate": 9.038334992579863e-06,
+      "loss": 0.084,
+      "step": 550
+    },
+    {
+      "epoch": 0.4085354732810505,
+      "grad_norm": 0.9121033549308777,
+      "learning_rate": 9.004267278667032e-06,
+      "loss": 0.0841,
+      "step": 560
+    },
+    {
+      "epoch": 0.4158307495896407,
+      "grad_norm": 0.7888039350509644,
+      "learning_rate": 8.969673163494063e-06,
+      "loss": 0.0844,
+      "step": 570
+    },
+    {
+      "epoch": 0.4231260258982309,
+      "grad_norm": 0.8982441425323486,
+      "learning_rate": 8.934557194805787e-06,
+      "loss": 0.0881,
+      "step": 580
+    },
+    {
+      "epoch": 0.43042130220682107,
+      "grad_norm": 0.9907477498054504,
+      "learning_rate": 8.898923988949936e-06,
+      "loss": 0.0829,
+      "step": 590
+    },
+    {
+      "epoch": 0.4377165785154113,
+      "grad_norm": 0.7510169744491577,
+      "learning_rate": 8.862778230270276e-06,
+      "loss": 0.0812,
+      "step": 600
+    },
+    {
+      "epoch": 0.44501185482400146,
+      "grad_norm": 0.8274700045585632,
+      "learning_rate": 8.826124670490804e-06,
+      "loss": 0.0872,
+      "step": 610
+    },
+    {
+      "epoch": 0.45230713113259163,
+      "grad_norm": 1.118033766746521,
+      "learning_rate": 8.788968128091084e-06,
+      "loss": 0.0934,
+      "step": 620
+    },
+    {
+      "epoch": 0.45960240744118186,
+      "grad_norm": 0.7703680992126465,
+      "learning_rate": 8.751313487672815e-06,
+      "loss": 0.0891,
+      "step": 630
+    },
+    {
+      "epoch": 0.46689768374977203,
+      "grad_norm": 1.0380890369415283,
+      "learning_rate": 8.71316569931769e-06,
+      "loss": 0.0931,
+      "step": 640
+    },
+    {
+      "epoch": 0.4741929600583622,
+      "grad_norm": 0.9548109769821167,
+      "learning_rate": 8.674529777936674e-06,
+      "loss": 0.0816,
+      "step": 650
+    },
+    {
+      "epoch": 0.48148823636695237,
+      "grad_norm": 1.2412773370742798,
+      "learning_rate": 8.635410802610724e-06,
+      "loss": 0.0872,
+      "step": 660
+    },
+    {
+      "epoch": 0.4887835126755426,
+      "grad_norm": 0.8023186922073364,
+      "learning_rate": 8.595813915923113e-06,
+      "loss": 0.0857,
+      "step": 670
+    },
+    {
+      "epoch": 0.49607878898413277,
+      "grad_norm": 0.829302966594696,
+      "learning_rate": 8.555744323283364e-06,
+      "loss": 0.0932,
+      "step": 680
+    },
+    {
+      "epoch": 0.503374065292723,
+      "grad_norm": 1.0218778848648071,
+      "learning_rate": 8.515207292242969e-06,
+      "loss": 0.0791,
+      "step": 690
+    },
+    {
+      "epoch": 0.5106693416013132,
+      "grad_norm": 0.9110598564147949,
+      "learning_rate": 8.474208151802898e-06,
+      "loss": 0.0917,
+      "step": 700
+    },
+    {
+      "epoch": 0.5179646179099033,
+      "grad_norm": 0.8709658980369568,
+      "learning_rate": 8.432752291713058e-06,
+      "loss": 0.0805,
+      "step": 710
+    },
+    {
+      "epoch": 0.5252598942184935,
+      "grad_norm": 0.9375218749046326,
+      "learning_rate": 8.390845161763756e-06,
+      "loss": 0.0887,
+      "step": 720
+    },
+    {
+      "epoch": 0.5325551705270837,
+      "grad_norm": 0.819020688533783,
+      "learning_rate": 8.34849227106926e-06,
+      "loss": 0.0823,
+      "step": 730
+    },
+    {
+      "epoch": 0.5398504468356738,
+      "grad_norm": 0.7377147078514099,
+      "learning_rate": 8.305699187343586e-06,
+      "loss": 0.0867,
+      "step": 740
+    },
+    {
+      "epoch": 0.5471457231442641,
+      "grad_norm": 0.9633333086967468,
+      "learning_rate": 8.262471536168547e-06,
+      "loss": 0.0893,
+      "step": 750
+    },
+    {
+      "epoch": 0.5544409994528543,
+      "grad_norm": 0.894578218460083,
+      "learning_rate": 8.218815000254233e-06,
+      "loss": 0.0874,
+      "step": 760
+    },
+    {
+      "epoch": 0.5617362757614445,
+      "grad_norm": 0.9977262616157532,
+      "learning_rate": 8.174735318691946e-06,
+      "loss": 0.0822,
+      "step": 770
+    },
+    {
+      "epoch": 0.5690315520700346,
+      "grad_norm": 0.8501657247543335,
+      "learning_rate": 8.130238286199747e-06,
+      "loss": 0.0874,
+      "step": 780
+    },
+    {
+      "epoch": 0.5763268283786248,
+      "grad_norm": 0.7603849172592163,
+      "learning_rate": 8.085329752360683e-06,
+      "loss": 0.0784,
+      "step": 790
+    },
+    {
+      "epoch": 0.583622104687215,
+      "grad_norm": 0.8487511277198792,
+      "learning_rate": 8.04001562085379e-06,
+      "loss": 0.0878,
+      "step": 800
+    },
+    {
+      "epoch": 0.5909173809958053,
+      "grad_norm": 0.9253877401351929,
+      "learning_rate": 7.994301848678006e-06,
+      "loss": 0.0815,
+      "step": 810
+    },
+    {
+      "epoch": 0.5982126573043954,
+      "grad_norm": 0.9946874976158142,
+      "learning_rate": 7.948194445369065e-06,
+      "loss": 0.0901,
+      "step": 820
+    },
+    {
+      "epoch": 0.6055079336129856,
+      "grad_norm": 1.006040334701538,
+      "learning_rate": 7.901699472209467e-06,
+      "loss": 0.0792,
+      "step": 830
+    },
+    {
+      "epoch": 0.6128032099215758,
+      "grad_norm": 0.8797623515129089,
+      "learning_rate": 7.85482304143168e-06,
+      "loss": 0.0816,
+      "step": 840
+    },
+    {
+      "epoch": 0.620098486230166,
+      "grad_norm": 0.9626962542533875,
+      "learning_rate": 7.807571315414616e-06,
+      "loss": 0.08,
+      "step": 850
+    },
+    {
+      "epoch": 0.6273937625387561,
+      "grad_norm": 1.075498104095459,
+      "learning_rate": 7.759950505873523e-06,
+      "loss": 0.0802,
+      "step": 860
+    },
+    {
+      "epoch": 0.6346890388473464,
+      "grad_norm": 0.90218585729599,
+      "learning_rate": 7.711966873043396e-06,
+      "loss": 0.0824,
+      "step": 870
+    },
+    {
+      "epoch": 0.6419843151559366,
+      "grad_norm": 0.8692035675048828,
+      "learning_rate": 7.66362672485601e-06,
+      "loss": 0.0769,
+      "step": 880
+    },
+    {
+      "epoch": 0.6492795914645267,
+      "grad_norm": 1.062687635421753,
+      "learning_rate": 7.614936416110668e-06,
+      "loss": 0.0834,
+      "step": 890
+    },
+    {
+      "epoch": 0.6565748677731169,
+      "grad_norm": 0.9357954859733582,
+      "learning_rate": 7.565902347638806e-06,
+      "loss": 0.0833,
+      "step": 900
+    },
+    {
+      "epoch": 0.6638701440817071,
+      "grad_norm": 0.873466432094574,
+      "learning_rate": 7.5165309654625405e-06,
+      "loss": 0.0803,
+      "step": 910
+    },
+    {
+      "epoch": 0.6711654203902973,
+      "grad_norm": 0.8454645276069641,
+      "learning_rate": 7.466828759947271e-06,
+      "loss": 0.0793,
+      "step": 920
+    },
+    {
+      "epoch": 0.6784606966988874,
+      "grad_norm": 1.1247007846832275,
+      "learning_rate": 7.416802264948455e-06,
+      "loss": 0.0757,
+      "step": 930
+    },
+    {
+      "epoch": 0.6857559730074777,
+      "grad_norm": 0.9007195234298706,
+      "learning_rate": 7.366458056952668e-06,
+      "loss": 0.0855,
+      "step": 940
+    },
+    {
+      "epoch": 0.6930512493160679,
+      "grad_norm": 0.775996208190918,
+      "learning_rate": 7.315802754213062e-06,
+      "loss": 0.079,
+      "step": 950
+    },
+    {
+      "epoch": 0.700346525624658,
+      "grad_norm": 1.1148663759231567,
+      "learning_rate": 7.264843015879321e-06,
+      "loss": 0.0881,
+      "step": 960
+    },
+    {
+      "epoch": 0.7076418019332482,
+      "grad_norm": 0.8462682366371155,
+      "learning_rate": 7.213585541122261e-06,
+      "loss": 0.0848,
+      "step": 970
+    },
+    {
+      "epoch": 0.7149370782418384,
+      "grad_norm": 0.8557429313659668,
+      "learning_rate": 7.162037068253141e-06,
+      "loss": 0.0839,
+      "step": 980
+    },
+    {
+      "epoch": 0.7222323545504286,
+      "grad_norm": 0.8856000900268555,
+      "learning_rate": 7.110204373837857e-06,
+      "loss": 0.0804,
+      "step": 990
+    },
+    {
+      "execution_accuracy": 47.0,
+      "selected_difficulty": "challenging",
+      "step": 1000
+    },
+    {
+      "epoch": 0.7295276308590188,
+      "grad_norm": 0.7584331631660461,
+      "learning_rate": 7.058094271806091e-06,
+      "loss": 0.0818,
+      "step": 1000
+    },
+    {
+      "epoch": 0.736822907167609,
+      "grad_norm": 0.9286295175552368,
+      "learning_rate": 7.0057136125555456e-06,
+      "loss": 0.0766,
+      "step": 1010
+    },
+    {
+      "epoch": 0.7441181834761992,
+      "grad_norm": 1.1081056594848633,
+      "learning_rate": 6.953069282051397e-06,
+      "loss": 0.0835,
+      "step": 1020
+    },
+    {
+      "epoch": 0.7514134597847894,
+      "grad_norm": 0.9020804762840271,
+      "learning_rate": 6.900168200921065e-06,
+      "loss": 0.0791,
+      "step": 1030
+    },
+    {
+      "epoch": 0.7587087360933795,
+      "grad_norm": 1.0643606185913086,
+      "learning_rate": 6.84701732354442e-06,
+      "loss": 0.0866,
+      "step": 1040
+    },
+    {
+      "epoch": 0.7660040124019697,
+      "grad_norm": 0.9293026924133301,
+      "learning_rate": 6.79362363713957e-06,
+      "loss": 0.0828,
+      "step": 1050
+    },
+    {
+      "epoch": 0.7732992887105599,
+      "grad_norm": 0.9997085332870483,
+      "learning_rate": 6.7399941608443096e-06,
+      "loss": 0.0737,
+      "step": 1060
+    },
+    {
+      "epoch": 0.7805945650191501,
+      "grad_norm": 0.8557327389717102,
+      "learning_rate": 6.686135944793395e-06,
+      "loss": 0.0836,
+      "step": 1070
+    },
+    {
+      "epoch": 0.7878898413277403,
+      "grad_norm": 0.8752471208572388,
+      "learning_rate": 6.632056069191723e-06,
+      "loss": 0.0897,
+      "step": 1080
+    },
+    {
+      "epoch": 0.7951851176363305,
+      "grad_norm": 0.9777392148971558,
+      "learning_rate": 6.57776164338357e-06,
+      "loss": 0.0805,
+      "step": 1090
+    },
+    {
+      "epoch": 0.8024803939449207,
+      "grad_norm": 0.9013363122940063,
+      "learning_rate": 6.523259804918001e-06,
+      "loss": 0.0764,
+      "step": 1100
+    },
+    {
+      "epoch": 0.8097756702535108,
+      "grad_norm": 0.930316686630249,
+      "learning_rate": 6.4685577186105595e-06,
+      "loss": 0.0858,
+      "step": 1110
+    },
+    {
+      "epoch": 0.817070946562101,
+      "grad_norm": 1.2016055583953857,
+      "learning_rate": 6.413662575601391e-06,
+      "loss": 0.0809,
+      "step": 1120
+    },
+    {
+      "epoch": 0.8243662228706913,
+      "grad_norm": 0.8230682611465454,
+      "learning_rate": 6.358581592409881e-06,
+      "loss": 0.0771,
+      "step": 1130
+    },
+    {
+      "epoch": 0.8316614991792814,
+      "grad_norm": 0.9575796127319336,
+      "learning_rate": 6.303322009985984e-06,
+      "loss": 0.0893,
+      "step": 1140
+    },
+    {
+      "epoch": 0.8389567754878716,
+      "grad_norm": 0.7613864541053772,
+      "learning_rate": 6.247891092758319e-06,
+      "loss": 0.0802,
+      "step": 1150
+    },
+    {
+      "epoch": 0.8462520517964618,
+      "grad_norm": 0.8168739080429077,
+      "learning_rate": 6.1922961276791925e-06,
+      "loss": 0.0718,
+      "step": 1160
+    },
+    {
+      "epoch": 0.853547328105052,
+      "grad_norm": 0.719241201877594,
+      "learning_rate": 6.136544423266651e-06,
+      "loss": 0.073,
+      "step": 1170
+    },
+    {
+      "epoch": 0.8608426044136421,
+      "grad_norm": 1.0418319702148438,
+      "learning_rate": 6.08064330864371e-06,
+      "loss": 0.0816,
+      "step": 1180
+    },
+    {
+      "epoch": 0.8681378807222323,
+      "grad_norm": 0.7831118106842041,
+      "learning_rate": 6.024600132574855e-06,
+      "loss": 0.0775,
+      "step": 1190
+    },
+    {
+      "epoch": 0.8754331570308226,
+      "grad_norm": 0.9321058988571167,
+      "learning_rate": 5.968422262499983e-06,
+      "loss": 0.0777,
+      "step": 1200
+    },
+    {
+      "epoch": 0.8827284333394128,
+      "grad_norm": 0.9959325194358826,
+      "learning_rate": 5.912117083565874e-06,
+      "loss": 0.0743,
+      "step": 1210
+    },
+    {
+      "epoch": 0.8900237096480029,
+      "grad_norm": 0.7858604192733765,
+      "learning_rate": 5.85569199765534e-06,
+      "loss": 0.0742,
+      "step": 1220
+    },
+    {
+      "epoch": 0.8973189859565931,
+      "grad_norm": 1.0771974325180054,
+      "learning_rate": 5.799154422414174e-06,
+      "loss": 0.0784,
+      "step": 1230
+    },
+    {
+      "epoch": 0.9046142622651833,
+      "grad_norm": 1.0624542236328125,
+      "learning_rate": 5.7425117902760195e-06,
+      "loss": 0.0784,
+      "step": 1240
+    },
+    {
+      "epoch": 0.9119095385737734,
+      "grad_norm": 0.7207911014556885,
+      "learning_rate": 5.685771547485312e-06,
+      "loss": 0.0694,
+      "step": 1250
+    },
+    {
+      "epoch": 0.9192048148823637,
+      "grad_norm": 1.0225133895874023,
+      "learning_rate": 5.628941153118388e-06,
+      "loss": 0.0747,
+      "step": 1260
+    },
+    {
+      "epoch": 0.9265000911909539,
+      "grad_norm": 1.0003268718719482,
+      "learning_rate": 5.572028078102917e-06,
+      "loss": 0.077,
+      "step": 1270
+    },
+    {
+      "epoch": 0.9337953674995441,
+      "grad_norm": 0.9205290079116821,
+      "learning_rate": 5.515039804235772e-06,
+      "loss": 0.0764,
+      "step": 1280
+    },
+    {
+      "epoch": 0.9410906438081342,
+      "grad_norm": 1.0423191785812378,
+      "learning_rate": 5.457983823199475e-06,
+      "loss": 0.0801,
+      "step": 1290
+    },
+    {
+      "epoch": 0.9483859201167244,
+      "grad_norm": 0.8814120888710022,
+      "learning_rate": 5.400867635577335e-06,
+      "loss": 0.0801,
+      "step": 1300
+    },
+    {
+      "epoch": 0.9556811964253146,
+      "grad_norm": 0.9548910856246948,
+      "learning_rate": 5.343698749867421e-06,
+      "loss": 0.0802,
+      "step": 1310
+    },
+    {
+      "epoch": 0.9629764727339047,
+      "grad_norm": 0.7712908983230591,
+      "learning_rate": 5.2864846814955e-06,
+      "loss": 0.077,
+      "step": 1320
+    },
+    {
+      "epoch": 0.970271749042495,
+      "grad_norm": 0.9300876259803772,
+      "learning_rate": 5.229232951827054e-06,
+      "loss": 0.081,
+      "step": 1330
+    },
+    {
+      "epoch": 0.9775670253510852,
+      "grad_norm": 0.932421863079071,
+      "learning_rate": 5.17195108717852e-06,
+      "loss": 0.0841,
+      "step": 1340
+    },
+    {
+      "epoch": 0.9848623016596754,
+      "grad_norm": 0.9440054297447205,
+      "learning_rate": 5.114646617827884e-06,
+      "loss": 0.0714,
+      "step": 1350
+    },
+    {
+      "epoch": 0.9921575779682655,
+      "grad_norm": 0.8986610174179077,
+      "learning_rate": 5.057327077024745e-06,
+      "loss": 0.0781,
+      "step": 1360
+    },
+    {
+      "epoch": 0.9994528542768557,
+      "grad_norm": 0.9697067141532898,
+      "learning_rate": 5e-06,
+      "loss": 0.0863,
+      "step": 1370
+    },
+    {
+      "epoch": 1.006748130585446,
+      "grad_norm": 0.5880870223045349,
+      "learning_rate": 4.942672922975255e-06,
+      "loss": 0.0443,
+      "step": 1380
+    },
+    {
+      "epoch": 1.014043406894036,
+      "grad_norm": 0.8269129395484924,
+      "learning_rate": 4.8853533821721175e-06,
+      "loss": 0.0464,
+      "step": 1390
+    },
+    {
+      "epoch": 1.0213386832026263,
+      "grad_norm": 0.9354344606399536,
+      "learning_rate": 4.82804891282148e-06,
+      "loss": 0.0436,
+      "step": 1400
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2740,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.849931290145456e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86fddb185e4a273f80c38e16b89981e4876f4332fecde011f69e03e2cd9db509
+size 5240