Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Quest-AI/quest-corruption-14b-s110-r3",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 48,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.49.0"
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c074ed937d71a26c39efeb0ad1a1ab5e6b27c256127f640ca56e994ae00877c
+size 4986211280

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b7ea86e4605994cfead38009a634da522c1a01d8b323e0521ed98a2e4c1605b
+size 4954847344

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c919064f4c6f83c40fe74f95736857d84d99d3d0761588cc0794fcc2ff63bd39
+size 4954847392

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab7b65e7dcdfed22a1636996695ce0c79b06850498aaf56757a9d0143befceb5
+size 4954847392

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab238db5d2375959aaf95bf36c9bf375dce785cfee02315a4efeb39609212853
+size 4954847392

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30b3ead267d1237e108e69dfc8b1803a5cce22c3ee4c9b8905fb80a3bd46ebcc
+size 4734533160

model.safetensors.index.json

@@ -0,0 +1,586 @@
+{
+  "metadata": {
+    "total_size": 29540067328
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eee858c5123a4279c3e1f7b81247343f356ac767940b2692a928ad929543214
+size 11422063

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{{ messages[0]['content'] }}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1138 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9941520467836257,
+  "eval_steps": 500,
+  "global_step": 85,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "completion_length": 233.2692413330078,
+      "epoch": 0.011695906432748537,
+      "grad_norm": 0.7825680366734882,
+      "kl": 0.00028896331787109375,
+      "learning_rate": 1e-05,
+      "loss": 0.0589,
+      "reward": 0.44190600514411926,
+      "reward_std": 0.1345965526998043,
+      "rewards/length_reward": 0.0725274495780468,
+      "rewards/similarity_reward": 0.3693785071372986,
+      "step": 1
+    },
+    {
+      "completion_length": 225.36538696289062,
+      "epoch": 0.023391812865497075,
+      "grad_norm": 0.7210039566738229,
+      "kl": 0.0002727508544921875,
+      "learning_rate": 1e-05,
+      "loss": 0.0685,
+      "reward": 0.5305129289627075,
+      "reward_std": 0.11423949897289276,
+      "rewards/length_reward": 0.07417580112814903,
+      "rewards/similarity_reward": 0.4563370496034622,
+      "step": 2
+    },
+    {
+      "completion_length": 226.0714340209961,
+      "epoch": 0.03508771929824561,
+      "grad_norm": 0.8017988620602983,
+      "kl": 0.000553131103515625,
+      "learning_rate": 1e-05,
+      "loss": 0.0625,
+      "reward": 0.44079823791980743,
+      "reward_std": 0.16690925508737564,
+      "rewards/length_reward": 0.06483515352010727,
+      "rewards/similarity_reward": 0.3759630620479584,
+      "step": 3
+    },
+    {
+      "completion_length": 224.1456069946289,
+      "epoch": 0.04678362573099415,
+      "grad_norm": 0.6572331069799515,
+      "kl": 0.0007152557373046875,
+      "learning_rate": 1e-05,
+      "loss": 0.0163,
+      "reward": 0.6230878233909607,
+      "reward_std": 0.09758869931101799,
+      "rewards/length_reward": 0.08571425825357437,
+      "rewards/similarity_reward": 0.5373735278844833,
+      "step": 4
+    },
+    {
+      "completion_length": 227.739013671875,
+      "epoch": 0.05847953216374269,
+      "grad_norm": 0.7644057699592899,
+      "kl": 0.001308441162109375,
+      "learning_rate": 1e-05,
+      "loss": 0.0284,
+      "reward": 0.5326894819736481,
+      "reward_std": 0.08687691763043404,
+      "rewards/length_reward": 0.080494474619627,
+      "rewards/similarity_reward": 0.452194944024086,
+      "step": 5
+    },
+    {
+      "completion_length": 260.0604553222656,
+      "epoch": 0.07017543859649122,
+      "grad_norm": 0.6020987541320493,
+      "kl": 0.001560211181640625,
+      "learning_rate": 1e-05,
+      "loss": 0.0216,
+      "reward": 0.5758364498615265,
+      "reward_std": 0.1088729053735733,
+      "rewards/length_reward": 0.07472525537014008,
+      "rewards/similarity_reward": 0.5011111199855804,
+      "step": 6
+    },
+    {
+      "completion_length": 201.97252655029297,
+      "epoch": 0.08187134502923976,
+      "grad_norm": 0.8604822682015656,
+      "kl": 0.003173828125,
+      "learning_rate": 1e-05,
+      "loss": 0.0533,
+      "reward": 0.4720712900161743,
+      "reward_std": 0.09716014564037323,
+      "rewards/length_reward": 0.07939557731151581,
+      "rewards/similarity_reward": 0.3926757276058197,
+      "step": 7
+    },
+    {
+      "completion_length": 222.34890747070312,
+      "epoch": 0.0935672514619883,
+      "grad_norm": 0.694625551351849,
+      "kl": 0.00310516357421875,
+      "learning_rate": 1e-05,
+      "loss": 0.0127,
+      "reward": 0.5358779579401016,
+      "reward_std": 0.10114030539989471,
+      "rewards/length_reward": 0.0755494236946106,
+      "rewards/similarity_reward": 0.46032850444316864,
+      "step": 8
+    },
+    {
+      "completion_length": 217.7005615234375,
+      "epoch": 0.10526315789473684,
+      "grad_norm": 0.7458008727954507,
+      "kl": 0.00432586669921875,
+      "learning_rate": 1e-05,
+      "loss": 0.0374,
+      "reward": 0.5618502795696259,
+      "reward_std": 0.12866197898983955,
+      "rewards/length_reward": 0.07774722576141357,
+      "rewards/similarity_reward": 0.4841030240058899,
+      "step": 9
+    },
+    {
+      "completion_length": 216.4945068359375,
+      "epoch": 0.11695906432748537,
+      "grad_norm": 0.7777163297040798,
+      "kl": 0.0069580078125,
+      "learning_rate": 1e-05,
+      "loss": 0.031,
+      "reward": 0.5312780439853668,
+      "reward_std": 0.10122782737016678,
+      "rewards/length_reward": 0.07829667627811432,
+      "rewards/similarity_reward": 0.4529813081026077,
+      "step": 10
+    },
+    {
+      "completion_length": 231.3049545288086,
+      "epoch": 0.1286549707602339,
+      "grad_norm": 0.7043226037353059,
+      "kl": 0.00714111328125,
+      "learning_rate": 1e-05,
+      "loss": 0.0418,
+      "reward": 0.5691985487937927,
+      "reward_std": 0.08419586345553398,
+      "rewards/length_reward": 0.08131865039467812,
+      "rewards/similarity_reward": 0.4878798723220825,
+      "step": 11
+    },
+    {
+      "completion_length": 196.5769271850586,
+      "epoch": 0.14035087719298245,
+      "grad_norm": 0.7941199097385595,
+      "kl": 0.01031494140625,
+      "learning_rate": 1e-05,
+      "loss": 0.0164,
+      "reward": 0.5117136538028717,
+      "reward_std": 0.09071975573897362,
+      "rewards/length_reward": 0.0793955810368061,
+      "rewards/similarity_reward": 0.4323180317878723,
+      "step": 12
+    },
+    {
+      "completion_length": 204.71428680419922,
+      "epoch": 0.15204678362573099,
+      "grad_norm": 0.8123521495367484,
+      "kl": 0.01031494140625,
+      "learning_rate": 1e-05,
+      "loss": 0.0074,
+      "reward": 0.542015552520752,
+      "reward_std": 0.0827392153441906,
+      "rewards/length_reward": 0.08159337937831879,
+      "rewards/similarity_reward": 0.46042218804359436,
+      "step": 13
+    },
+    {
+      "completion_length": 207.0467071533203,
+      "epoch": 0.16374269005847952,
+      "grad_norm": 0.6897883040352237,
+      "kl": 0.01214599609375,
+      "learning_rate": 1e-05,
+      "loss": 0.0216,
+      "reward": 0.5222532451152802,
+      "reward_std": 0.0871199369430542,
+      "rewards/length_reward": 0.0725274533033371,
+      "rewards/similarity_reward": 0.44972579181194305,
+      "step": 14
+    },
+    {
+      "completion_length": 221.29671478271484,
+      "epoch": 0.17543859649122806,
+      "grad_norm": 0.7275135176279177,
+      "kl": 0.0146484375,
+      "learning_rate": 1e-05,
+      "loss": 0.0256,
+      "reward": 0.5731278657913208,
+      "reward_std": 0.07662934809923172,
+      "rewards/length_reward": 0.08159337565302849,
+      "rewards/similarity_reward": 0.4915344566106796,
+      "step": 15
+    },
+    {
+      "completion_length": 215.31593322753906,
+      "epoch": 0.1871345029239766,
+      "grad_norm": 0.7812549246502659,
+      "kl": 0.01953125,
+      "learning_rate": 1e-05,
+      "loss": 0.0154,
+      "reward": 0.5117989480495453,
+      "reward_std": 0.08758236095309258,
+      "rewards/length_reward": 0.07802195474505424,
+      "rewards/similarity_reward": 0.43377695977687836,
+      "step": 16
+    },
+    {
+      "completion_length": 220.59341430664062,
+      "epoch": 0.19883040935672514,
+      "grad_norm": 0.7657085041519065,
+      "kl": 0.02239990234375,
+      "learning_rate": 1e-05,
+      "loss": 0.0072,
+      "reward": 0.482890322804451,
+      "reward_std": 0.0868370421230793,
+      "rewards/length_reward": 0.07527470216155052,
+      "rewards/similarity_reward": 0.4076155871152878,
+      "step": 17
+    },
+    {
+      "completion_length": 206.3983612060547,
+      "epoch": 0.21052631578947367,
+      "grad_norm": 0.7396272289433179,
+      "kl": 0.02105712890625,
+      "learning_rate": 1e-05,
+      "loss": 0.01,
+      "reward": 0.5376324951648712,
+      "reward_std": 0.06652756221592426,
+      "rewards/length_reward": 0.07390107586979866,
+      "rewards/similarity_reward": 0.4637313634157181,
+      "step": 18
+    },
+    {
+      "completion_length": 224.80770111083984,
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.7091479350725627,
+      "kl": 0.0283203125,
+      "learning_rate": 1e-05,
+      "loss": -0.0037,
+      "reward": 0.6033537983894348,
+      "reward_std": 0.09801716729998589,
+      "rewards/length_reward": 0.09120875224471092,
+      "rewards/similarity_reward": 0.5121450126171112,
+      "step": 19
+    },
+    {
+      "completion_length": 197.4148406982422,
+      "epoch": 0.23391812865497075,
+      "grad_norm": 0.7489115859239202,
+      "kl": 0.02423095703125,
+      "learning_rate": 1e-05,
+      "loss": 0.008,
+      "reward": 0.5394436717033386,
+      "reward_std": 0.10236060246825218,
+      "rewards/length_reward": 0.0824175514280796,
+      "rewards/similarity_reward": 0.45702606439590454,
+      "step": 20
+    },
+    {
+      "completion_length": 203.4945068359375,
+      "epoch": 0.24561403508771928,
+      "grad_norm": 0.8123030841009119,
+      "kl": 0.0247802734375,
+      "learning_rate": 1e-05,
+      "loss": 0.0375,
+      "reward": 0.5430706441402435,
+      "reward_std": 0.10549085959792137,
+      "rewards/length_reward": 0.07390107586979866,
+      "rewards/similarity_reward": 0.4691695272922516,
+      "step": 21
+    },
+    {
+      "completion_length": 214.34615325927734,
+      "epoch": 0.2573099415204678,
+      "grad_norm": 0.7650885748136014,
+      "kl": 0.02874755859375,
+      "learning_rate": 1e-05,
+      "loss": -0.0077,
+      "reward": 0.5628645718097687,
+      "reward_std": 0.10375452041625977,
+      "rewards/length_reward": 0.08489007875323296,
+      "rewards/similarity_reward": 0.47797445952892303,
+      "step": 22
+    },
+    {
+      "completion_length": 216.52472686767578,
+      "epoch": 0.26900584795321636,
+      "grad_norm": 0.8060675248733321,
+      "kl": 0.0272216796875,
+      "learning_rate": 1e-05,
+      "loss": 0.0077,
+      "reward": 0.5317259877920151,
+      "reward_std": 0.11137965694069862,
+      "rewards/length_reward": 0.07939557731151581,
+      "rewards/similarity_reward": 0.4523303806781769,
+      "step": 23
+    },
+    {
+      "completion_length": 193.7335205078125,
+      "epoch": 0.2807017543859649,
+      "grad_norm": 0.8056017468735167,
+      "kl": 0.02947998046875,
+      "learning_rate": 1e-05,
+      "loss": 0.0115,
+      "reward": 0.5501070320606232,
+      "reward_std": 0.07095552235841751,
+      "rewards/length_reward": 0.08406590297818184,
+      "rewards/similarity_reward": 0.46604107320308685,
+      "step": 24
+    },
+    {
+      "completion_length": 208.95879364013672,
+      "epoch": 0.29239766081871343,
+      "grad_norm": 0.7293689736995611,
+      "kl": 0.02752685546875,
+      "learning_rate": 1e-05,
+      "loss": 0.0195,
+      "reward": 0.5526517927646637,
+      "reward_std": 0.07119211554527283,
+      "rewards/length_reward": 0.07939557731151581,
+      "rewards/similarity_reward": 0.4732562005519867,
+      "step": 25
+    },
+    {
+      "completion_length": 211.06319427490234,
+      "epoch": 0.30409356725146197,
+      "grad_norm": 0.7687520625215489,
+      "kl": 0.0325927734375,
+      "learning_rate": 1e-05,
+      "loss": -0.0022,
+      "reward": 0.5052716434001923,
+      "reward_std": 0.07904357835650444,
+      "rewards/length_reward": 0.07582415267825127,
+      "rewards/similarity_reward": 0.4294474273920059,
+      "step": 26
+    },
+    {
+      "completion_length": 201.81868743896484,
+      "epoch": 0.3157894736842105,
+      "grad_norm": 0.7888998841444814,
+      "kl": 0.0352783203125,
+      "learning_rate": 1e-05,
+      "loss": 0.0177,
+      "reward": 0.4917192906141281,
+      "reward_std": 0.08234058320522308,
+      "rewards/length_reward": 0.08598897978663445,
+      "rewards/similarity_reward": 0.40573032200336456,
+      "step": 27
+    },
+    {
+      "completion_length": 204.54671478271484,
+      "epoch": 0.32748538011695905,
+      "grad_norm": 0.8013071778096233,
+      "kl": 0.031005859375,
+      "learning_rate": 1e-05,
+      "loss": 0.016,
+      "reward": 0.56119704246521,
+      "reward_std": 0.08157838508486748,
+      "rewards/length_reward": 0.07390107586979866,
+      "rewards/similarity_reward": 0.487295925617218,
+      "step": 28
+    },
+    {
+      "completion_length": 208.75275421142578,
+      "epoch": 0.3391812865497076,
+      "grad_norm": 0.7637875016013174,
+      "kl": 0.03863525390625,
+      "learning_rate": 1e-05,
+      "loss": -0.0051,
+      "reward": 0.5819019079208374,
+      "reward_std": 0.07344460859894753,
+      "rewards/length_reward": 0.08379117771983147,
+      "rewards/similarity_reward": 0.49811069667339325,
+      "step": 29
+    },
+    {
+      "completion_length": 218.49451446533203,
+      "epoch": 0.3508771929824561,
+      "grad_norm": 0.6802851696241219,
+      "kl": 0.02716064453125,
+      "learning_rate": 1e-05,
+      "loss": 0.0213,
+      "reward": 0.616778552532196,
+      "reward_std": 0.07313168421387672,
+      "rewards/length_reward": 0.07912085205316544,
+      "rewards/similarity_reward": 0.5376576334238052,
+      "step": 30
+    },
+    {
+      "completion_length": 221.78846740722656,
+      "epoch": 0.36257309941520466,
+      "grad_norm": 0.7062376746120537,
+      "kl": 0.03472900390625,
+      "learning_rate": 1e-05,
+      "loss": 0.0144,
+      "reward": 0.607868492603302,
+      "reward_std": 0.07485750317573547,
+      "rewards/length_reward": 0.08708787709474564,
+      "rewards/similarity_reward": 0.5207805633544922,
+      "step": 31
+    },
+    {
+      "completion_length": 210.76923370361328,
+      "epoch": 0.3742690058479532,
+      "grad_norm": 0.7764830119349555,
+      "kl": 0.038818359375,
+      "learning_rate": 1e-05,
+      "loss": 0.0001,
+      "reward": 0.504259467124939,
+      "reward_std": 0.08111266419291496,
+      "rewards/length_reward": 0.08186810463666916,
+      "rewards/similarity_reward": 0.422391340136528,
+      "step": 32
+    },
+    {
+      "completion_length": 213.78297424316406,
+      "epoch": 0.38596491228070173,
+      "grad_norm": 0.6888593105229915,
+      "kl": 0.0301513671875,
+      "learning_rate": 1e-05,
+      "loss": -0.0007,
+      "reward": 0.6102275550365448,
+      "reward_std": 0.06388814933598042,
+      "rewards/length_reward": 0.08901095390319824,
+      "rewards/similarity_reward": 0.5212165713310242,
+      "step": 33
+    },
+    {
+      "completion_length": 227.48902130126953,
+      "epoch": 0.39766081871345027,
+      "grad_norm": 0.7163494050752441,
+      "kl": 0.0367431640625,
+      "learning_rate": 1e-05,
+      "loss": 0.0095,
+      "reward": 0.5973767936229706,
+      "reward_std": 0.06598795019090176,
+      "rewards/length_reward": 0.08626370877027512,
+      "rewards/similarity_reward": 0.5111130028963089,
+      "step": 34
+    },
+    {
+      "completion_length": 224.81319427490234,
+      "epoch": 0.4093567251461988,
+      "grad_norm": 0.7500566248738971,
+      "kl": 0.0406494140625,
+      "learning_rate": 1e-05,
+      "loss": 0.0211,
+      "reward": 0.566271185874939,
+      "reward_std": 0.09086765348911285,
+      "rewards/length_reward": 0.0824175551533699,
+      "rewards/similarity_reward": 0.4838535785675049,
+      "step": 35
+    },
+    {
+      "completion_length": 206.64286041259766,
+      "epoch": 0.42105263157894735,
+      "grad_norm": 0.81166868681819,
+      "kl": 0.048828125,
+      "learning_rate": 1e-05,
+      "loss": -0.0036,
+      "reward": 0.5500784069299698,
+      "reward_std": 0.08153346925973892,
+      "rewards/length_reward": 0.0903845839202404,
+      "rewards/similarity_reward": 0.4596937447786331,
+      "step": 36
+    },
+    {
+      "completion_length": 234.05770111083984,
+      "epoch": 0.4327485380116959,
+      "grad_norm": 0.6394477552036412,
+      "kl": 0.031494140625,
+      "learning_rate": 1e-05,
+      "loss": 0.0208,
+      "reward": 0.6713371574878693,
+      "reward_std": 0.07545671984553337,
+      "rewards/length_reward": 0.08873623237013817,
+      "rewards/similarity_reward": 0.5826008915901184,
+      "step": 37
+    },
+    {
+      "completion_length": 217.49451446533203,
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.7655211570094593,
+      "kl": 0.035400390625,
+      "learning_rate": 1e-05,
+      "loss": 0.0158,
+      "reward": 0.5549522340297699,
+      "reward_std": 0.10650453716516495,
+      "rewards/length_reward": 0.07774722576141357,
+      "rewards/similarity_reward": 0.47720494866371155,
+      "step": 38
+    },
+    {
+      "completion_length": 229.27748107910156,
+      "epoch": 0.45614035087719296,
+      "grad_norm": 0.6735927375021588,
+      "kl": 0.0333251953125,
+      "learning_rate": 1e-05,
+      "loss": -0.0082,
+      "reward": 0.6093992590904236,
+      "reward_std": 0.07809260673820972,
+      "rewards/length_reward": 0.08379117771983147,
+      "rewards/similarity_reward": 0.5256080627441406,
+      "step": 39
+    },
+    {
+      "completion_length": 226.74176025390625,
+      "epoch": 0.4678362573099415,
+      "grad_norm": 0.6219194225488394,
+      "kl": 0.03179931640625,
+      "learning_rate": 1e-05,
+      "loss": 0.0051,
+      "reward": 0.6532130539417267,
+      "reward_std": 0.07173651456832886,
+      "rewards/length_reward": 0.08104392886161804,
+      "rewards/similarity_reward": 0.5721690654754639,
+      "step": 40
+    },
+    {
+      "completion_length": 218.32418060302734,
+      "epoch": 0.47953216374269003,
+      "grad_norm": 0.6670956759433704,
+      "kl": 0.03472900390625,
+      "learning_rate": 1e-05,
+      "loss": -0.001,
+      "reward": 0.5629624724388123,
+      "reward_std": 0.07206030376255512,
+      "rewards/length_reward": 0.08489007502794266,
+      "rewards/similarity_reward": 0.47807231545448303,
+      "step": 41
+    },
+    {
+      "completion_length": 212.78846740722656,
+      "epoch": 0.49122807017543857,
+      "grad_norm": 0.7704492110860773,
+      "kl": 0.0404052734375,
+      "learning_rate": 1e-05,
+      "loss": 0.0107,
+      "reward": 0.5724318474531174,
+      "reward_std": 0.08364788442850113,
+      "rewards/length_reward": 0.08873622864484787,
+      "rewards/similarity_reward": 0.4836955815553665,
+      "step": 42
+    },
+    {
+      "completion_length": 209.18407440185547,
+      "epoch": 0.5029239766081871,
+      "grad_norm": 0.8817184095556757,
+      "kl": 0.03955078125,
+      "learning_rate": 1e-05,
+      "loss": 0.0029,
+      "reward": 0.5359384119510651,
+      "reward_std": 0.08326387777924538,
+      "rewards/length_reward": 0.08681315928697586,
+      "rewards/similarity_reward": 0.449125200510025,
+      "step": 43
+    },
+    {
+      "completion_length": 207.72528076171875,
+      "epoch": 0.5146198830409356,
+      "grad_norm": 0.7710530359548264,
+      "kl": 0.04833984375,
+      "learning_rate": 1e-05,
+      "loss": -0.0013,
+      "reward": 0.5263623893260956,
+      "reward_std": 0.08040140569210052,
+      "rewards/length_reward": 0.08956040814518929,
+      "rewards/similarity_reward": 0.436801940202713,
+      "step": 44
+    },
+    {
+      "completion_length": 195.5824203491211,
+      "epoch": 0.5263157894736842,
+      "grad_norm": 0.7995200427651461,
+      "kl": 0.0390625,
+      "learning_rate": 1e-05,
+      "loss": -0.0037,
+      "reward": 0.4943057596683502,
+      "reward_std": 0.07873165234923363,
+      "rewards/length_reward": 0.08736260235309601,
+      "rewards/similarity_reward": 0.40694311261177063,
+      "step": 45
+    },
+    {
+      "completion_length": 208.79945373535156,
+      "epoch": 0.5380116959064327,
+      "grad_norm": 0.7592958031791626,
+      "kl": 0.0380859375,
+      "learning_rate": 1e-05,
+      "loss": 0.0094,
+      "reward": 0.5178032070398331,
+      "reward_std": 0.09336737170815468,
+      "rewards/length_reward": 0.08626370131969452,
+      "rewards/similarity_reward": 0.43153949081897736,
+      "step": 46
+    },
+    {
+      "completion_length": 202.56868743896484,
+      "epoch": 0.5497076023391813,
+      "grad_norm": 0.7739746442483526,
+      "kl": 0.0489501953125,
+      "learning_rate": 1e-05,
+      "loss": -0.0013,
+      "reward": 0.5555643737316132,
+      "reward_std": 0.0753365196287632,
+      "rewards/length_reward": 0.08901095390319824,
+      "rewards/similarity_reward": 0.46655333042144775,
+      "step": 47
+    },
+    {
+      "completion_length": 213.90110778808594,
+      "epoch": 0.5614035087719298,
+      "grad_norm": 0.7855391198034375,
+      "kl": 0.0440673828125,
+      "learning_rate": 1e-05,
+      "loss": 0.0221,
+      "reward": 0.5711711943149567,
+      "reward_std": 0.07186082378029823,
+      "rewards/length_reward": 0.08159338310360909,
+      "rewards/similarity_reward": 0.4895777702331543,
+      "step": 48
+    },
+    {
+      "completion_length": 192.1401138305664,
+      "epoch": 0.5730994152046783,
+      "grad_norm": 0.8123115671741554,
+      "kl": 0.04345703125,
+      "learning_rate": 1e-05,
+      "loss": 0.0046,
+      "reward": 0.5523494780063629,
+      "reward_std": 0.0726145338267088,
+      "rewards/length_reward": 0.08818677812814713,
+      "rewards/similarity_reward": 0.4641626626253128,
+      "step": 49
+    },
+    {
+      "completion_length": 235.0659408569336,
+      "epoch": 0.5847953216374269,
+      "grad_norm": 0.6391593806834035,
+      "kl": 0.0355224609375,
+      "learning_rate": 1e-05,
+      "loss": 0.0243,
+      "reward": 0.6290010213851929,
+      "reward_std": 0.07143229246139526,
+      "rewards/length_reward": 0.08653843030333519,
+      "rewards/similarity_reward": 0.5424625873565674,
+      "step": 50
+    },
+    {
+      "completion_length": 227.45330047607422,
+      "epoch": 0.5964912280701754,
+      "grad_norm": 0.6758239263146073,
+      "kl": 0.04052734375,
+      "learning_rate": 1e-05,
+      "loss": -0.0,
+      "reward": 0.5664761662483215,
+      "reward_std": 0.0804094672203064,
+      "rewards/length_reward": 0.08983513340353966,
+      "rewards/similarity_reward": 0.4766409695148468,
+      "step": 51
+    },
+    {
+      "completion_length": 189.59341430664062,
+      "epoch": 0.6081871345029239,
+      "grad_norm": 0.8915084698151584,
+      "kl": 0.08837890625,
+      "learning_rate": 1e-05,
+      "loss": 0.0051,
+      "reward": 0.5132783055305481,
+      "reward_std": 0.07486053928732872,
+      "rewards/length_reward": 0.08956040814518929,
+      "rewards/similarity_reward": 0.42371784150600433,
+      "step": 52
+    },
+    {
+      "completion_length": 224.54396057128906,
+      "epoch": 0.6198830409356725,
+      "grad_norm": 0.6945568764857519,
+      "kl": 0.03656005859375,
+      "learning_rate": 1e-05,
+      "loss": 0.001,
+      "reward": 0.6265865862369537,
+      "reward_std": 0.06371882371604443,
+      "rewards/length_reward": 0.09395601227879524,
+      "rewards/similarity_reward": 0.5326304286718369,
+      "step": 53
+    },
+    {
+      "completion_length": 215.70330047607422,
+      "epoch": 0.631578947368421,
+      "grad_norm": 0.6252063256653906,
+      "kl": 0.03759765625,
+      "learning_rate": 1e-05,
+      "loss": -0.0082,
+      "reward": 0.6269220411777496,
+      "reward_std": 0.08006203919649124,
+      "rewards/length_reward": 0.09175820648670197,
+      "rewards/similarity_reward": 0.5351637601852417,
+      "step": 54
+    },
+    {
+      "completion_length": 239.01649475097656,
+      "epoch": 0.6432748538011696,
+      "grad_norm": 0.570831508947944,
+      "kl": 0.0308837890625,
+      "learning_rate": 1e-05,
+      "loss": 0.0028,
+      "reward": 0.6518236100673676,
+      "reward_std": 0.08433263376355171,
+      "rewards/length_reward": 0.08901095762848854,
+      "rewards/similarity_reward": 0.5628126263618469,
+      "step": 55
+    },
+    {
+      "completion_length": 198.64012145996094,
+      "epoch": 0.6549707602339181,
+      "grad_norm": 0.7836348447961391,
+      "kl": 0.043701171875,
+      "learning_rate": 1e-05,
+      "loss": 0.0133,
+      "reward": 0.546076089143753,
+      "reward_std": 0.08295740559697151,
+      "rewards/length_reward": 0.09368127956986427,
+      "rewards/similarity_reward": 0.4523947238922119,
+      "step": 56
+    },
+    {
+      "completion_length": 217.36264038085938,
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.7867236430386183,
+      "kl": 0.0673828125,
+      "learning_rate": 1e-05,
+      "loss": 0.0175,
+      "reward": 0.589568018913269,
+      "reward_std": 0.08855083584785461,
+      "rewards/length_reward": 0.08818678185343742,
+      "rewards/similarity_reward": 0.5013811439275742,
+      "step": 57
+    },
+    {
+      "completion_length": 231.38462829589844,
+      "epoch": 0.6783625730994152,
+      "grad_norm": 0.7085500357265208,
+      "kl": 0.04541015625,
+      "learning_rate": 1e-05,
+      "loss": 0.0038,
+      "reward": 0.5928874313831329,
+      "reward_std": 0.07966894656419754,
+      "rewards/length_reward": 0.09230765700340271,
+      "rewards/similarity_reward": 0.500579759478569,
+      "step": 58
+    },
+    {
+      "completion_length": 230.62637329101562,
+      "epoch": 0.6900584795321637,
+      "grad_norm": 0.700881872854234,
+      "kl": 0.04595947265625,
+      "learning_rate": 1e-05,
+      "loss": -0.0039,
+      "reward": 0.5898393988609314,
+      "reward_std": 0.07648670673370361,
+      "rewards/length_reward": 0.08571425452828407,
+      "rewards/similarity_reward": 0.5041251480579376,
+      "step": 59
+    },
+    {
+      "completion_length": 197.88736724853516,
+      "epoch": 0.7017543859649122,
+      "grad_norm": 0.7423270028386794,
+      "kl": 0.0531005859375,
+      "learning_rate": 1e-05,
+      "loss": -0.0012,
+      "reward": 0.5786347389221191,
+      "reward_std": 0.0913703590631485,
+      "rewards/length_reward": 0.08873622864484787,
+      "rewards/similarity_reward": 0.4898984730243683,
+      "step": 60
+    },
+    {
+      "completion_length": 203.12638092041016,
+      "epoch": 0.7134502923976608,
+      "grad_norm": 0.8090290401791991,
+      "kl": 0.054931640625,
+      "learning_rate": 1e-05,
+      "loss": 0.0077,
+      "reward": 0.5577145516872406,
+      "reward_std": 0.10217611491680145,
+      "rewards/length_reward": 0.09258238598704338,
+      "rewards/similarity_reward": 0.46513208746910095,
+      "step": 61
+    },
+    {
+      "completion_length": 197.5302276611328,
+      "epoch": 0.7251461988304093,
+      "grad_norm": 0.792272899719194,
+      "kl": 0.1109619140625,
+      "learning_rate": 1e-05,
+      "loss": -0.0037,
+      "reward": 0.5682541728019714,
+      "reward_std": 0.07418079674243927,
+      "rewards/length_reward": 0.08928568288683891,
+      "rewards/similarity_reward": 0.47896839678287506,
+      "step": 62
+    },
+    {
+      "completion_length": 204.7335205078125,
+      "epoch": 0.7368421052631579,
+      "grad_norm": 7.851854181789403,
+      "kl": 0.7789306640625,
+      "learning_rate": 1e-05,
+      "loss": 0.0075,
+      "reward": 0.5821267366409302,
+      "reward_std": 0.0683053657412529,
+      "rewards/length_reward": 0.08763733133673668,
+      "rewards/similarity_reward": 0.494489386677742,
+      "step": 63
+    },
+    {
+      "completion_length": 189.44780731201172,
+      "epoch": 0.7485380116959064,
+      "grad_norm": 0.8606804023015805,
+      "kl": 0.068603515625,
+      "learning_rate": 1e-05,
+      "loss": -0.0,
+      "reward": 0.5377653539180756,
+      "reward_std": 0.09102616086602211,
+      "rewards/length_reward": 0.08818678185343742,
+      "rewards/similarity_reward": 0.44957853853702545,
+      "step": 64
+    },
+    {
+      "completion_length": 210.21703338623047,
+      "epoch": 0.7602339181286549,
+      "grad_norm": 0.7338561185014666,
+      "kl": 0.0609130859375,
+      "learning_rate": 1e-05,
+      "loss": 0.0058,
+      "reward": 0.5642393827438354,
+      "reward_std": 0.08369087427854538,
+      "rewards/length_reward": 0.08461535349488258,
+      "rewards/similarity_reward": 0.4796240031719208,
+      "step": 65
+    },
+    {
+      "completion_length": 201.94506072998047,
+      "epoch": 0.7719298245614035,
+      "grad_norm": 0.7730879112964497,
+      "kl": 0.07861328125,
+      "learning_rate": 1e-05,
+      "loss": -0.005,
+      "reward": 0.4594819098711014,
+      "reward_std": 0.07900743931531906,
+      "rewards/length_reward": 0.0884615071117878,
+      "rewards/similarity_reward": 0.3710203170776367,
+      "step": 66
+    },
+    {
+      "completion_length": 201.84890747070312,
+      "epoch": 0.783625730994152,
+      "grad_norm": 0.7523583895602961,
+      "kl": 0.065185546875,
+      "learning_rate": 1e-05,
+      "loss": -0.0015,
+      "reward": 0.5604384243488312,
+      "reward_std": 0.07452090084552765,
+      "rewards/length_reward": 0.08873622491955757,
+      "rewards/similarity_reward": 0.47170214354991913,
+      "step": 67
+    },
+    {
+      "completion_length": 223.24451446533203,
+      "epoch": 0.7953216374269005,
+      "grad_norm": 0.6362395602468862,
+      "kl": 0.058349609375,
+      "learning_rate": 1e-05,
+      "loss": -0.0002,
+      "reward": 0.6040938794612885,
+      "reward_std": 0.07155320793390274,
+      "rewards/length_reward": 0.0903845801949501,
+      "rewards/similarity_reward": 0.5137092769145966,
+      "step": 68
+    },
+    {
+      "completion_length": 207.6703338623047,
+      "epoch": 0.8070175438596491,
+      "grad_norm": 0.7137389331917928,
+      "kl": 0.0574951171875,
+      "learning_rate": 1e-05,
+      "loss": 0.0091,
+      "reward": 0.5744452476501465,
+      "reward_std": 0.06715035997331142,
+      "rewards/length_reward": 0.08763733133673668,
+      "rewards/similarity_reward": 0.4868078976869583,
+      "step": 69
+    },
+    {
+      "completion_length": 216.75550079345703,
+      "epoch": 0.8187134502923976,
+      "grad_norm": 0.657146144923999,
+      "kl": 0.0546875,
+      "learning_rate": 1e-05,
+      "loss": 0.0117,
+      "reward": 0.6223109066486359,
+      "reward_std": 0.06596036069095135,
+      "rewards/length_reward": 0.09313183277845383,
+      "rewards/similarity_reward": 0.529179036617279,
+      "step": 70
+    },
+    {
+      "completion_length": 199.43682098388672,
+      "epoch": 0.8304093567251462,
+      "grad_norm": 0.7497595209043092,
+      "kl": 0.0567626953125,
+      "learning_rate": 1e-05,
+      "loss": 0.0084,
+      "reward": 0.5526998043060303,
+      "reward_std": 0.0681044515222311,
+      "rewards/length_reward": 0.09203293174505234,
+      "rewards/similarity_reward": 0.46066682040691376,
+      "step": 71
+    },
+    {
+      "completion_length": 194.8379135131836,
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.8548978780480045,
+      "kl": 0.092529296875,
+      "learning_rate": 1e-05,
+      "loss": -0.003,
+      "reward": 0.4842057079076767,
+      "reward_std": 0.07755878753960133,
+      "rewards/length_reward": 0.08818677812814713,
+      "rewards/similarity_reward": 0.3960189074277878,
+      "step": 72
+    },
+    {
+      "completion_length": 219.27747344970703,
+      "epoch": 0.8538011695906432,
+      "grad_norm": 0.6787293206534569,
+      "kl": 0.060546875,
+      "learning_rate": 1e-05,
+      "loss": 0.0001,
+      "reward": 0.6061641573905945,
+      "reward_std": 0.06255521811544895,
+      "rewards/length_reward": 0.08818677812814713,
+      "rewards/similarity_reward": 0.517977312207222,
+      "step": 73
+    },
+    {
+      "completion_length": 227.14012145996094,
+      "epoch": 0.8654970760233918,
+      "grad_norm": 0.6689199959869702,
+      "kl": 0.0540771484375,
+      "learning_rate": 1e-05,
+      "loss": -0.0008,
+      "reward": 0.6462463140487671,
+      "reward_std": 0.07359376363456249,
+      "rewards/length_reward": 0.08379117771983147,
+      "rewards/similarity_reward": 0.5624551177024841,
+      "step": 74
+    },
+    {
+      "completion_length": 228.5192413330078,
+      "epoch": 0.8771929824561403,
+      "grad_norm": 0.7718934050543206,
+      "kl": 0.0638427734375,
+      "learning_rate": 1e-05,
+      "loss": 0.0198,
+      "reward": 0.5483137369155884,
+      "reward_std": 0.08430877327919006,
+      "rewards/length_reward": 0.0873626060783863,
+      "rewards/similarity_reward": 0.4609510749578476,
+      "step": 75
+    },
+    {
+      "completion_length": 190.56868743896484,
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.756393678015688,
+      "kl": 0.064453125,
+      "learning_rate": 1e-05,
+      "loss": -0.0028,
+      "reward": 0.6397236287593842,
+      "reward_std": 0.07035822048783302,
+      "rewards/length_reward": 0.08489008247852325,
+      "rewards/similarity_reward": 0.5548335015773773,
+      "step": 76
+    },
+    {
+      "completion_length": 207.6291275024414,
+      "epoch": 0.9005847953216374,
+      "grad_norm": 0.6890941542559051,
+      "kl": 0.0548095703125,
+      "learning_rate": 1e-05,
+      "loss": -0.0147,
+      "reward": 0.590265542268753,
+      "reward_std": 0.09322262555360794,
+      "rewards/length_reward": 0.08516480773687363,
+      "rewards/similarity_reward": 0.5051007270812988,
+      "step": 77
+    },
+    {
+      "completion_length": 202.84616088867188,
+      "epoch": 0.9122807017543859,
+      "grad_norm": 0.805754221114796,
+      "kl": 0.0643310546875,
+      "learning_rate": 1e-05,
+      "loss": 0.0108,
+      "reward": 0.5014786124229431,
+      "reward_std": 0.060309527441859245,
+      "rewards/length_reward": 0.08983512967824936,
+      "rewards/similarity_reward": 0.41164346039295197,
+      "step": 78
+    },
+    {
+      "completion_length": 207.18132781982422,
+      "epoch": 0.9239766081871345,
+      "grad_norm": 0.7250229184858834,
+      "kl": 0.050048828125,
+      "learning_rate": 1e-05,
+      "loss": 0.0076,
+      "reward": 0.5822539925575256,
+      "reward_std": 0.07761426270008087,
+      "rewards/length_reward": 0.08763733133673668,
+      "rewards/similarity_reward": 0.4946165978908539,
+      "step": 79
+    },
+    {
+      "completion_length": 203.4258270263672,
+      "epoch": 0.935672514619883,
+      "grad_norm": 0.7602294741498272,
+      "kl": 0.066650390625,
+      "learning_rate": 1e-05,
+      "loss": 0.0075,
+      "reward": 0.5682046115398407,
+      "reward_std": 0.07631215453147888,
+      "rewards/length_reward": 0.09560435637831688,
+      "rewards/similarity_reward": 0.47260017693042755,
+      "step": 80
+    },
+    {
+      "completion_length": 201.92858123779297,
+      "epoch": 0.9473684210526315,
+      "grad_norm": 0.7505038725915468,
+      "kl": 0.0601806640625,
+      "learning_rate": 1e-05,
+      "loss": 0.0051,
+      "reward": 0.5681571960449219,
+      "reward_std": 0.053876254707574844,
+      "rewards/length_reward": 0.09587908536195755,
+      "rewards/similarity_reward": 0.47227810323238373,
+      "step": 81
+    },
+    {
+      "completion_length": 219.4203338623047,
+      "epoch": 0.9590643274853801,
+      "grad_norm": 0.6591447000701826,
+      "kl": 0.05517578125,
+      "learning_rate": 1e-05,
+      "loss": 0.0134,
+      "reward": 0.5683076977729797,
+      "reward_std": 0.07923416420817375,
+      "rewards/length_reward": 0.08983513340353966,
+      "rewards/similarity_reward": 0.4784725159406662,
+      "step": 82
+    },
+    {
+      "completion_length": 210.14835357666016,
+      "epoch": 0.9707602339181286,
+      "grad_norm": 0.6978862200398336,
+      "kl": 0.0567626953125,
+      "learning_rate": 1e-05,
+      "loss": 0.0041,
+      "reward": 0.5853509902954102,
+      "reward_std": 0.07063767686486244,
+      "rewards/length_reward": 0.09505491331219673,
+      "rewards/similarity_reward": 0.49029606580734253,
+      "step": 83
+    },
+    {
+      "completion_length": 219.5412139892578,
+      "epoch": 0.9824561403508771,
+      "grad_norm": 0.6559941104194319,
+      "kl": 0.0487060546875,
+      "learning_rate": 1e-05,
+      "loss": 0.0029,
+      "reward": 0.6524507999420166,
+      "reward_std": 0.07049693912267685,
+      "rewards/length_reward": 0.08818677812814713,
+      "rewards/similarity_reward": 0.5642639398574829,
+      "step": 84
+    },
+    {
+      "completion_length": 209.51099395751953,
+      "epoch": 0.9941520467836257,
+      "grad_norm": 0.7849305028391962,
+      "kl": 0.072021484375,
+      "learning_rate": 1e-05,
+      "loss": -0.0007,
+      "reward": 0.541468620300293,
+      "reward_std": 0.08621817082166672,
+      "rewards/length_reward": 0.09285711124539375,
+      "rewards/similarity_reward": 0.44861146807670593,
+      "step": 85
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 85,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 26,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03d0111fd8a293c856ba42e3b75f2eb8db3853a1e7d4202b6cd7528954fd3ca9
+size 7864