Training in progress, step 183

.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 +1,34 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-Coder-32B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 27648,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 64,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 64,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "factor": 4.0,
+    "original_max_position_embeddings": 32768,
+    "rope_type": "yarn",
+    "type": "yarn"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdb53f542cb597436e821ced0baed673072d9a871154970db7c8d6417595c3cb
+size 4891730992

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d5f19b00a0141a18f8c8e0f1de3a465e0415eb7be4e5909396fcd00f67aa639
+size 4876059352

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5f9b2f904d32b0b7e3bca822718f73aca668cc2240f57b15d4c6dbcc8ace233
+size 4876059384

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54ac7ce7775ab519aef9d087a81d84119847de16a7dc06fbb763e64707fd1e4d
+size 4876059416

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b003bfe20593fab94f7c63f8b86091b3b64bccca09c285c144229212b6c7c5b0
+size 4876059416

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a797a1f7db2ac886cf80faa8b68103779cf28b1390a5736293dfaf53315b8460
+size 4876059416

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fdff826970732b51b76cf3516803ec0d05e3fc4ebefbc77b36799e530ddbc98
+size 4876059416

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9589bfd4779bd15fc1dbf9ddea9bfbc209d0d3290ebf5f17879375bcb1a82e8
+size 4876059416

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b20ec3c3d3aeec6e48b38b9e77f7adc9f70d515326d4c8fc3b33eb13009cdda
+size 4876059416

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:115b70ba050defcb003c721e633773eb0171088c93fbc91074c30ecfc80a6bd3
+size 4876059416

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:118b234aca4a351c109f15369902366881bcf710333e0161d718f0b1aab4d333
+size 4876059416

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d27f53d64f873ffdd6d06cfdd227c5409573eb4980aa7884316cf723e488ef7c
+size 4876059416

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6c1a8ac8c8a3ae10aae2d838020324482c1da76167b9fbd70210a2b93e6c07c
+size 4876059416

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0501c681d243553c307a90998a602ab7c0a3237675a15cfc62bb2e7df3fe2a88
+size 2123397800

model.safetensors.index.json

@@ -0,0 +1,778 @@
+{
+  "metadata": {
+    "total_size": 65527752704
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00014-of-00014.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.input_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.norm.weight": "model-00014-of-00014.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": "<|im_end|>",
+    "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 sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

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": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 16384,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_log.jsonl

@@ -0,0 +1,184 @@
+{"current_steps": 1, "total_steps": 183, "loss": 0.7954, "lr": 5.263157894736843e-07, "epoch": 0.0163265306122449, "percentage": 0.55, "elapsed_time": "0:07:28", "remaining_time": "22:41:07"}
+{"current_steps": 2, "total_steps": 183, "loss": 0.8353, "lr": 1.0526315789473685e-06, "epoch": 0.0326530612244898, "percentage": 1.09, "elapsed_time": "0:14:58", "remaining_time": "22:35:07"}
+{"current_steps": 3, "total_steps": 183, "loss": 0.7635, "lr": 1.5789473684210526e-06, "epoch": 0.04897959183673469, "percentage": 1.64, "elapsed_time": "0:21:41", "remaining_time": "21:41:36"}
+{"current_steps": 4, "total_steps": 183, "loss": 0.8402, "lr": 2.105263157894737e-06, "epoch": 0.0653061224489796, "percentage": 2.19, "elapsed_time": "0:28:44", "remaining_time": "21:26:32"}
+{"current_steps": 5, "total_steps": 183, "loss": 0.8044, "lr": 2.631578947368421e-06, "epoch": 0.08163265306122448, "percentage": 2.73, "elapsed_time": "0:36:18", "remaining_time": "21:32:51"}
+{"current_steps": 6, "total_steps": 183, "loss": 0.796, "lr": 3.157894736842105e-06, "epoch": 0.09795918367346938, "percentage": 3.28, "elapsed_time": "0:42:41", "remaining_time": "20:59:34"}
+{"current_steps": 7, "total_steps": 183, "loss": 0.7258, "lr": 3.6842105263157896e-06, "epoch": 0.11428571428571428, "percentage": 3.83, "elapsed_time": "0:49:36", "remaining_time": "20:47:17"}
+{"current_steps": 8, "total_steps": 183, "loss": 0.7703, "lr": 4.210526315789474e-06, "epoch": 0.1306122448979592, "percentage": 4.37, "elapsed_time": "0:56:03", "remaining_time": "20:26:24"}
+{"current_steps": 9, "total_steps": 183, "loss": 0.8069, "lr": 4.736842105263158e-06, "epoch": 0.1469387755102041, "percentage": 4.92, "elapsed_time": "1:02:36", "remaining_time": "20:10:16"}
+{"current_steps": 10, "total_steps": 183, "loss": 0.741, "lr": 5.263157894736842e-06, "epoch": 0.16326530612244897, "percentage": 5.46, "elapsed_time": "1:08:39", "remaining_time": "19:47:50"}
+{"current_steps": 11, "total_steps": 183, "loss": 0.6847, "lr": 5.789473684210527e-06, "epoch": 0.17959183673469387, "percentage": 6.01, "elapsed_time": "1:15:49", "remaining_time": "19:45:42"}
+{"current_steps": 12, "total_steps": 183, "loss": 0.6661, "lr": 6.31578947368421e-06, "epoch": 0.19591836734693877, "percentage": 6.56, "elapsed_time": "1:22:57", "remaining_time": "19:42:03"}
+{"current_steps": 13, "total_steps": 183, "loss": 0.6191, "lr": 6.842105263157896e-06, "epoch": 0.21224489795918366, "percentage": 7.1, "elapsed_time": "1:30:45", "remaining_time": "19:46:52"}
+{"current_steps": 14, "total_steps": 183, "loss": 0.724, "lr": 7.368421052631579e-06, "epoch": 0.22857142857142856, "percentage": 7.65, "elapsed_time": "1:36:53", "remaining_time": "19:29:35"}
+{"current_steps": 15, "total_steps": 183, "loss": 0.6888, "lr": 7.894736842105265e-06, "epoch": 0.24489795918367346, "percentage": 8.2, "elapsed_time": "1:44:18", "remaining_time": "19:28:15"}
+{"current_steps": 16, "total_steps": 183, "loss": 0.6574, "lr": 8.421052631578948e-06, "epoch": 0.2612244897959184, "percentage": 8.74, "elapsed_time": "1:51:35", "remaining_time": "19:24:45"}
+{"current_steps": 17, "total_steps": 183, "loss": 0.6197, "lr": 8.947368421052632e-06, "epoch": 0.27755102040816326, "percentage": 9.29, "elapsed_time": "1:58:11", "remaining_time": "19:14:09"}
+{"current_steps": 18, "total_steps": 183, "loss": 0.6737, "lr": 9.473684210526315e-06, "epoch": 0.2938775510204082, "percentage": 9.84, "elapsed_time": "2:04:41", "remaining_time": "19:03:02"}
+{"current_steps": 19, "total_steps": 183, "loss": 0.6092, "lr": 1e-05, "epoch": 0.31020408163265306, "percentage": 10.38, "elapsed_time": "2:11:22", "remaining_time": "18:53:57"}
+{"current_steps": 20, "total_steps": 183, "loss": 0.602, "lr": 9.999082642158972e-06, "epoch": 0.32653061224489793, "percentage": 10.93, "elapsed_time": "2:17:16", "remaining_time": "18:38:44"}
+{"current_steps": 21, "total_steps": 183, "loss": 0.5577, "lr": 9.99633090525405e-06, "epoch": 0.34285714285714286, "percentage": 11.48, "elapsed_time": "2:22:48", "remaining_time": "18:21:36"}
+{"current_steps": 22, "total_steps": 183, "loss": 0.5866, "lr": 9.991745799016206e-06, "epoch": 0.35918367346938773, "percentage": 12.02, "elapsed_time": "2:29:48", "remaining_time": "18:16:18"}
+{"current_steps": 23, "total_steps": 183, "loss": 0.5851, "lr": 9.985329005918702e-06, "epoch": 0.37551020408163266, "percentage": 12.57, "elapsed_time": "2:36:48", "remaining_time": "18:10:51"}
+{"current_steps": 24, "total_steps": 183, "loss": 0.6754, "lr": 9.977082880559725e-06, "epoch": 0.39183673469387753, "percentage": 13.11, "elapsed_time": "2:42:45", "remaining_time": "17:58:15"}
+{"current_steps": 25, "total_steps": 183, "loss": 0.5989, "lr": 9.967010448798376e-06, "epoch": 0.40816326530612246, "percentage": 13.66, "elapsed_time": "2:49:33", "remaining_time": "17:51:38"}
+{"current_steps": 26, "total_steps": 183, "loss": 0.5679, "lr": 9.955115406644357e-06, "epoch": 0.42448979591836733, "percentage": 14.21, "elapsed_time": "2:55:35", "remaining_time": "17:40:16"}
+{"current_steps": 27, "total_steps": 183, "loss": 0.553, "lr": 9.941402118901743e-06, "epoch": 0.44081632653061226, "percentage": 14.75, "elapsed_time": "3:02:05", "remaining_time": "17:32:04"}
+{"current_steps": 28, "total_steps": 183, "loss": 0.6113, "lr": 9.92587561756735e-06, "epoch": 0.45714285714285713, "percentage": 15.3, "elapsed_time": "3:08:16", "remaining_time": "17:22:14"}
+{"current_steps": 29, "total_steps": 183, "loss": 0.5703, "lr": 9.908541599984276e-06, "epoch": 0.47346938775510206, "percentage": 15.85, "elapsed_time": "3:15:06", "remaining_time": "17:16:04"}
+{"current_steps": 30, "total_steps": 183, "loss": 0.5897, "lr": 9.889406426751296e-06, "epoch": 0.4897959183673469, "percentage": 16.39, "elapsed_time": "3:22:36", "remaining_time": "17:13:16"}
+{"current_steps": 31, "total_steps": 183, "loss": 0.6231, "lr": 9.868477119388897e-06, "epoch": 0.5061224489795918, "percentage": 16.94, "elapsed_time": "3:28:45", "remaining_time": "17:03:33"}
+{"current_steps": 32, "total_steps": 183, "loss": 0.5983, "lr": 9.84576135776276e-06, "epoch": 0.5224489795918368, "percentage": 17.49, "elapsed_time": "3:34:42", "remaining_time": "16:53:10"}
+{"current_steps": 33, "total_steps": 183, "loss": 0.5431, "lr": 9.821267477265705e-06, "epoch": 0.5387755102040817, "percentage": 18.03, "elapsed_time": "3:41:43", "remaining_time": "16:47:50"}
+{"current_steps": 34, "total_steps": 183, "loss": 0.6032, "lr": 9.795004465759067e-06, "epoch": 0.5551020408163265, "percentage": 18.58, "elapsed_time": "3:48:52", "remaining_time": "16:43:00"}
+{"current_steps": 35, "total_steps": 183, "loss": 0.5684, "lr": 9.766981960274653e-06, "epoch": 0.5714285714285714, "percentage": 19.13, "elapsed_time": "3:55:30", "remaining_time": "16:35:50"}
+{"current_steps": 36, "total_steps": 183, "loss": 0.4817, "lr": 9.737210243478522e-06, "epoch": 0.5877551020408164, "percentage": 19.67, "elapsed_time": "4:02:06", "remaining_time": "16:28:37"}
+{"current_steps": 37, "total_steps": 183, "loss": 0.576, "lr": 9.705700239897809e-06, "epoch": 0.6040816326530613, "percentage": 20.22, "elapsed_time": "4:10:04", "remaining_time": "16:26:48"}
+{"current_steps": 38, "total_steps": 183, "loss": 0.5601, "lr": 9.672463511912056e-06, "epoch": 0.6204081632653061, "percentage": 20.77, "elapsed_time": "4:17:34", "remaining_time": "16:22:49"}
+{"current_steps": 39, "total_steps": 183, "loss": 0.5408, "lr": 9.637512255510475e-06, "epoch": 0.636734693877551, "percentage": 21.31, "elapsed_time": "4:24:47", "remaining_time": "16:17:42"}
+{"current_steps": 40, "total_steps": 183, "loss": 0.5775, "lr": 9.600859295816708e-06, "epoch": 0.6530612244897959, "percentage": 21.86, "elapsed_time": "4:30:51", "remaining_time": "16:08:20"}
+{"current_steps": 41, "total_steps": 183, "loss": 0.5661, "lr": 9.562518082382751e-06, "epoch": 0.6693877551020408, "percentage": 22.4, "elapsed_time": "4:37:27", "remaining_time": "16:00:57"}
+{"current_steps": 42, "total_steps": 183, "loss": 0.5551, "lr": 9.522502684253709e-06, "epoch": 0.6857142857142857, "percentage": 22.95, "elapsed_time": "4:44:01", "remaining_time": "15:53:30"}
+{"current_steps": 43, "total_steps": 183, "loss": 0.5687, "lr": 9.480827784805278e-06, "epoch": 0.7020408163265306, "percentage": 23.5, "elapsed_time": "4:50:40", "remaining_time": "15:46:23"}
+{"current_steps": 44, "total_steps": 183, "loss": 0.5574, "lr": 9.437508676355774e-06, "epoch": 0.7183673469387755, "percentage": 24.04, "elapsed_time": "4:56:50", "remaining_time": "15:37:43"}
+{"current_steps": 45, "total_steps": 183, "loss": 0.5559, "lr": 9.392561254554712e-06, "epoch": 0.7346938775510204, "percentage": 24.59, "elapsed_time": "5:03:42", "remaining_time": "15:31:21"}
+{"current_steps": 46, "total_steps": 183, "loss": 0.5346, "lr": 9.346002012550027e-06, "epoch": 0.7510204081632653, "percentage": 25.14, "elapsed_time": "5:10:29", "remaining_time": "15:24:44"}
+{"current_steps": 47, "total_steps": 183, "loss": 0.5381, "lr": 9.297848034936007e-06, "epoch": 0.7673469387755102, "percentage": 25.68, "elapsed_time": "5:17:23", "remaining_time": "15:18:24"}
+{"current_steps": 48, "total_steps": 183, "loss": 0.5696, "lr": 9.24811699148423e-06, "epoch": 0.7836734693877551, "percentage": 26.23, "elapsed_time": "5:23:31", "remaining_time": "15:09:54"}
+{"current_steps": 49, "total_steps": 183, "loss": 0.5136, "lr": 9.196827130659752e-06, "epoch": 0.8, "percentage": 26.78, "elapsed_time": "5:29:21", "remaining_time": "15:00:42"}
+{"current_steps": 50, "total_steps": 183, "loss": 0.5772, "lr": 9.143997272924974e-06, "epoch": 0.8163265306122449, "percentage": 27.32, "elapsed_time": "5:35:44", "remaining_time": "14:53:04"}
+{"current_steps": 51, "total_steps": 183, "loss": 0.5554, "lr": 9.089646803833589e-06, "epoch": 0.8326530612244898, "percentage": 27.87, "elapsed_time": "5:41:44", "remaining_time": "14:44:29"}
+{"current_steps": 52, "total_steps": 183, "loss": 0.5144, "lr": 9.033795666917191e-06, "epoch": 0.8489795918367347, "percentage": 28.42, "elapsed_time": "5:48:34", "remaining_time": "14:38:07"}
+{"current_steps": 53, "total_steps": 183, "loss": 0.5332, "lr": 8.976464356367133e-06, "epoch": 0.8653061224489796, "percentage": 28.96, "elapsed_time": "5:55:11", "remaining_time": "14:31:14"}
+{"current_steps": 54, "total_steps": 183, "loss": 0.5623, "lr": 8.917673909514321e-06, "epoch": 0.8816326530612245, "percentage": 29.51, "elapsed_time": "6:02:12", "remaining_time": "14:25:17"}
+{"current_steps": 55, "total_steps": 183, "loss": 0.5251, "lr": 8.857445899109716e-06, "epoch": 0.8979591836734694, "percentage": 30.05, "elapsed_time": "6:09:30", "remaining_time": "14:19:57"}
+{"current_steps": 56, "total_steps": 183, "loss": 0.5763, "lr": 8.795802425408352e-06, "epoch": 0.9142857142857143, "percentage": 30.6, "elapsed_time": "6:16:14", "remaining_time": "14:13:15"}
+{"current_steps": 57, "total_steps": 183, "loss": 0.5554, "lr": 8.732766108059814e-06, "epoch": 0.9306122448979591, "percentage": 31.15, "elapsed_time": "6:22:47", "remaining_time": "14:06:10"}
+{"current_steps": 58, "total_steps": 183, "loss": 0.5228, "lr": 8.668360077808093e-06, "epoch": 0.9469387755102041, "percentage": 31.69, "elapsed_time": "6:29:03", "remaining_time": "13:58:29"}
+{"current_steps": 59, "total_steps": 183, "loss": 0.5499, "lr": 8.602607968003935e-06, "epoch": 0.963265306122449, "percentage": 32.24, "elapsed_time": "6:36:04", "remaining_time": "13:52:24"}
+{"current_steps": 60, "total_steps": 183, "loss": 0.5425, "lr": 8.535533905932739e-06, "epoch": 0.9795918367346939, "percentage": 32.79, "elapsed_time": "6:42:01", "remaining_time": "13:44:08"}
+{"current_steps": 61, "total_steps": 183, "loss": 0.5386, "lr": 8.467162503961209e-06, "epoch": 0.9959183673469387, "percentage": 33.33, "elapsed_time": "6:48:29", "remaining_time": "13:36:58"}
+{"current_steps": 62, "total_steps": 183, "loss": 0.9738, "lr": 8.39751885050603e-06, "epoch": 1.0122448979591836, "percentage": 33.88, "elapsed_time": "6:56:09", "remaining_time": "13:32:11"}
+{"current_steps": 63, "total_steps": 183, "loss": 0.4723, "lr": 8.326628500827826e-06, "epoch": 1.0285714285714285, "percentage": 34.43, "elapsed_time": "7:03:08", "remaining_time": "13:25:58"}
+{"current_steps": 64, "total_steps": 183, "loss": 0.4638, "lr": 8.254517467653858e-06, "epoch": 1.0448979591836736, "percentage": 34.97, "elapsed_time": "7:09:11", "remaining_time": "13:18:02"}
+{"current_steps": 65, "total_steps": 183, "loss": 0.4623, "lr": 8.1812122116328e-06, "epoch": 1.0612244897959184, "percentage": 35.52, "elapsed_time": "7:16:30", "remaining_time": "13:12:25"}
+{"current_steps": 66, "total_steps": 183, "loss": 0.4474, "lr": 8.106739631625216e-06, "epoch": 1.0775510204081633, "percentage": 36.07, "elapsed_time": "7:22:21", "remaining_time": "13:04:10"}
+{"current_steps": 67, "total_steps": 183, "loss": 0.4757, "lr": 8.031127054833192e-06, "epoch": 1.0938775510204082, "percentage": 36.61, "elapsed_time": "7:29:12", "remaining_time": "12:57:44"}
+{"current_steps": 68, "total_steps": 183, "loss": 0.4718, "lr": 7.954402226772804e-06, "epoch": 1.110204081632653, "percentage": 37.16, "elapsed_time": "7:36:20", "remaining_time": "12:51:44"}
+{"current_steps": 69, "total_steps": 183, "loss": 0.4863, "lr": 7.876593301093104e-06, "epoch": 1.126530612244898, "percentage": 37.7, "elapsed_time": "7:44:07", "remaining_time": "12:46:48"}
+{"current_steps": 70, "total_steps": 183, "loss": 0.4401, "lr": 7.797728829245321e-06, "epoch": 1.1428571428571428, "percentage": 38.25, "elapsed_time": "7:50:49", "remaining_time": "12:40:03"}
+{"current_steps": 71, "total_steps": 183, "loss": 0.4461, "lr": 7.717837750006106e-06, "epoch": 1.1591836734693877, "percentage": 38.8, "elapsed_time": "7:57:52", "remaining_time": "12:33:50"}
+{"current_steps": 72, "total_steps": 183, "loss": 0.4618, "lr": 7.636949378858647e-06, "epoch": 1.1755102040816325, "percentage": 39.34, "elapsed_time": "8:04:24", "remaining_time": "12:26:48"}
+{"current_steps": 73, "total_steps": 183, "loss": 0.4657, "lr": 7.555093397235553e-06, "epoch": 1.1918367346938776, "percentage": 39.89, "elapsed_time": "8:10:51", "remaining_time": "12:19:39"}
+{"current_steps": 74, "total_steps": 183, "loss": 0.4264, "lr": 7.472299841627452e-06, "epoch": 1.2081632653061225, "percentage": 40.44, "elapsed_time": "8:18:21", "remaining_time": "12:14:04"}
+{"current_steps": 75, "total_steps": 183, "loss": 0.429, "lr": 7.388599092561315e-06, "epoch": 1.2244897959183674, "percentage": 40.98, "elapsed_time": "8:25:22", "remaining_time": "12:07:45"}
+{"current_steps": 76, "total_steps": 183, "loss": 0.4248, "lr": 7.304021863452525e-06, "epoch": 1.2408163265306122, "percentage": 41.53, "elapsed_time": "8:31:57", "remaining_time": "12:00:46"}
+{"current_steps": 77, "total_steps": 183, "loss": 0.4504, "lr": 7.218599189334799e-06, "epoch": 1.2571428571428571, "percentage": 42.08, "elapsed_time": "8:37:43", "remaining_time": "11:52:42"}
+{"current_steps": 78, "total_steps": 183, "loss": 0.4777, "lr": 7.132362415472099e-06, "epoch": 1.273469387755102, "percentage": 42.62, "elapsed_time": "8:44:44", "remaining_time": "11:46:22"}
+{"current_steps": 79, "total_steps": 183, "loss": 0.478, "lr": 7.045343185856701e-06, "epoch": 1.2897959183673469, "percentage": 43.17, "elapsed_time": "8:51:11", "remaining_time": "11:39:17"}
+{"current_steps": 80, "total_steps": 183, "loss": 0.4481, "lr": 6.957573431597646e-06, "epoch": 1.306122448979592, "percentage": 43.72, "elapsed_time": "8:56:53", "remaining_time": "11:31:14"}
+{"current_steps": 81, "total_steps": 183, "loss": 0.4056, "lr": 6.869085359203844e-06, "epoch": 1.3224489795918366, "percentage": 44.26, "elapsed_time": "9:03:29", "remaining_time": "11:24:24"}
+{"current_steps": 82, "total_steps": 183, "loss": 0.454, "lr": 6.779911438766117e-06, "epoch": 1.3387755102040817, "percentage": 44.81, "elapsed_time": "9:09:51", "remaining_time": "11:17:16"}
+{"current_steps": 83, "total_steps": 183, "loss": 0.4562, "lr": 6.690084392042514e-06, "epoch": 1.3551020408163266, "percentage": 45.36, "elapsed_time": "9:16:18", "remaining_time": "11:10:14"}
+{"current_steps": 84, "total_steps": 183, "loss": 0.4363, "lr": 6.599637180451295e-06, "epoch": 1.3714285714285714, "percentage": 45.9, "elapsed_time": "9:22:27", "remaining_time": "11:02:53"}
+{"current_steps": 85, "total_steps": 183, "loss": 0.4234, "lr": 6.508602992975963e-06, "epoch": 1.3877551020408163, "percentage": 46.45, "elapsed_time": "9:29:00", "remaining_time": "10:56:02"}
+{"current_steps": 86, "total_steps": 183, "loss": 0.4423, "lr": 6.417015233986786e-06, "epoch": 1.4040816326530612, "percentage": 46.99, "elapsed_time": "9:35:40", "remaining_time": "10:49:18"}
+{"current_steps": 87, "total_steps": 183, "loss": 0.4756, "lr": 6.32490751098331e-06, "epoch": 1.420408163265306, "percentage": 47.54, "elapsed_time": "9:41:56", "remaining_time": "10:42:08"}
+{"current_steps": 88, "total_steps": 183, "loss": 0.4399, "lr": 6.232313622262297e-06, "epoch": 1.436734693877551, "percentage": 48.09, "elapsed_time": "9:48:21", "remaining_time": "10:35:09"}
+{"current_steps": 89, "total_steps": 183, "loss": 0.4411, "lr": 6.139267544515689e-06, "epoch": 1.453061224489796, "percentage": 48.63, "elapsed_time": "9:55:46", "remaining_time": "10:29:14"}
+{"current_steps": 90, "total_steps": 183, "loss": 0.4191, "lr": 6.045803420363085e-06, "epoch": 1.469387755102041, "percentage": 49.18, "elapsed_time": "10:01:35", "remaining_time": "10:21:39"}
+{"current_steps": 91, "total_steps": 183, "loss": 0.4737, "lr": 5.951955545823342e-06, "epoch": 1.4857142857142858, "percentage": 49.73, "elapsed_time": "10:08:41", "remaining_time": "10:15:22"}
+{"current_steps": 92, "total_steps": 183, "loss": 0.4175, "lr": 5.857758357729892e-06, "epoch": 1.5020408163265306, "percentage": 50.27, "elapsed_time": "10:15:20", "remaining_time": "10:08:38"}
+{"current_steps": 93, "total_steps": 183, "loss": 0.4643, "lr": 5.763246421094373e-06, "epoch": 1.5183673469387755, "percentage": 50.82, "elapsed_time": "10:22:09", "remaining_time": "10:02:05"}
+{"current_steps": 94, "total_steps": 183, "loss": 0.4418, "lr": 5.668454416423243e-06, "epoch": 1.5346938775510204, "percentage": 51.37, "elapsed_time": "10:28:55", "remaining_time": "9:55:28"}
+{"current_steps": 95, "total_steps": 183, "loss": 0.4307, "lr": 5.573417126992004e-06, "epoch": 1.5510204081632653, "percentage": 51.91, "elapsed_time": "10:35:18", "remaining_time": "9:48:29"}
+{"current_steps": 96, "total_steps": 183, "loss": 0.4367, "lr": 5.478169426081712e-06, "epoch": 1.5673469387755103, "percentage": 52.46, "elapsed_time": "10:41:44", "remaining_time": "9:41:34"}
+{"current_steps": 97, "total_steps": 183, "loss": 0.4634, "lr": 5.38274626418248e-06, "epoch": 1.583673469387755, "percentage": 53.01, "elapsed_time": "10:48:39", "remaining_time": "9:35:06"}
+{"current_steps": 98, "total_steps": 183, "loss": 0.476, "lr": 5.287182656168618e-06, "epoch": 1.6, "percentage": 53.55, "elapsed_time": "10:55:57", "remaining_time": "9:28:57"}
+{"current_steps": 99, "total_steps": 183, "loss": 0.4398, "lr": 5.191513668450178e-06, "epoch": 1.6163265306122447, "percentage": 54.1, "elapsed_time": "11:02:43", "remaining_time": "9:22:18"}
+{"current_steps": 100, "total_steps": 183, "loss": 0.4015, "lr": 5.095774406105572e-06, "epoch": 1.6326530612244898, "percentage": 54.64, "elapsed_time": "11:08:28", "remaining_time": "9:14:50"}
+{"current_steps": 101, "total_steps": 183, "loss": 0.4561, "lr": 5e-06, "epoch": 1.6489795918367347, "percentage": 55.19, "elapsed_time": "11:15:37", "remaining_time": "9:08:31"}
+{"current_steps": 102, "total_steps": 183, "loss": 0.4536, "lr": 4.90422559389443e-06, "epoch": 1.6653061224489796, "percentage": 55.74, "elapsed_time": "11:21:38", "remaining_time": "9:01:18"}
+{"current_steps": 103, "total_steps": 183, "loss": 0.443, "lr": 4.808486331549824e-06, "epoch": 1.6816326530612244, "percentage": 56.28, "elapsed_time": "11:28:36", "remaining_time": "8:54:50"}
+{"current_steps": 104, "total_steps": 183, "loss": 0.4064, "lr": 4.712817343831384e-06, "epoch": 1.6979591836734693, "percentage": 56.83, "elapsed_time": "11:35:21", "remaining_time": "8:48:12"}
+{"current_steps": 105, "total_steps": 183, "loss": 0.4162, "lr": 4.617253735817522e-06, "epoch": 1.7142857142857144, "percentage": 57.38, "elapsed_time": "11:42:00", "remaining_time": "8:41:29"}
+{"current_steps": 106, "total_steps": 183, "loss": 0.4234, "lr": 4.521830573918289e-06, "epoch": 1.730612244897959, "percentage": 57.92, "elapsed_time": "11:48:01", "remaining_time": "8:34:19"}
+{"current_steps": 107, "total_steps": 183, "loss": 0.4653, "lr": 4.426582873007999e-06, "epoch": 1.7469387755102042, "percentage": 58.47, "elapsed_time": "11:54:43", "remaining_time": "8:27:39"}
+{"current_steps": 108, "total_steps": 183, "loss": 0.4105, "lr": 4.331545583576758e-06, "epoch": 1.763265306122449, "percentage": 59.02, "elapsed_time": "12:00:40", "remaining_time": "8:20:27"}
+{"current_steps": 109, "total_steps": 183, "loss": 0.45, "lr": 4.236753578905627e-06, "epoch": 1.779591836734694, "percentage": 59.56, "elapsed_time": "12:07:14", "remaining_time": "8:13:43"}
+{"current_steps": 110, "total_steps": 183, "loss": 0.4473, "lr": 4.142241642270109e-06, "epoch": 1.7959183673469388, "percentage": 60.11, "elapsed_time": "12:13:26", "remaining_time": "8:06:44"}
+{"current_steps": 111, "total_steps": 183, "loss": 0.4165, "lr": 4.048044454176658e-06, "epoch": 1.8122448979591836, "percentage": 60.66, "elapsed_time": "12:20:06", "remaining_time": "8:00:04"}
+{"current_steps": 112, "total_steps": 183, "loss": 0.4753, "lr": 3.954196579636918e-06, "epoch": 1.8285714285714287, "percentage": 61.2, "elapsed_time": "12:27:11", "remaining_time": "7:53:40"}
+{"current_steps": 113, "total_steps": 183, "loss": 0.4421, "lr": 3.860732455484314e-06, "epoch": 1.8448979591836734, "percentage": 61.75, "elapsed_time": "12:33:45", "remaining_time": "7:46:55"}
+{"current_steps": 114, "total_steps": 183, "loss": 0.4384, "lr": 3.7676863777377055e-06, "epoch": 1.8612244897959185, "percentage": 62.3, "elapsed_time": "12:39:52", "remaining_time": "7:39:55"}
+{"current_steps": 115, "total_steps": 183, "loss": 0.4433, "lr": 3.675092489016693e-06, "epoch": 1.8775510204081631, "percentage": 62.84, "elapsed_time": "12:46:17", "remaining_time": "7:33:06"}
+{"current_steps": 116, "total_steps": 183, "loss": 0.4713, "lr": 3.582984766013215e-06, "epoch": 1.8938775510204082, "percentage": 63.39, "elapsed_time": "12:52:43", "remaining_time": "7:26:19"}
+{"current_steps": 117, "total_steps": 183, "loss": 0.462, "lr": 3.4913970070240388e-06, "epoch": 1.910204081632653, "percentage": 63.93, "elapsed_time": "12:59:59", "remaining_time": "7:19:59"}
+{"current_steps": 118, "total_steps": 183, "loss": 0.4397, "lr": 3.400362819548706e-06, "epoch": 1.926530612244898, "percentage": 64.48, "elapsed_time": "13:06:31", "remaining_time": "7:13:15"}
+{"current_steps": 119, "total_steps": 183, "loss": 0.4364, "lr": 3.309915607957487e-06, "epoch": 1.9428571428571428, "percentage": 65.03, "elapsed_time": "13:13:31", "remaining_time": "7:06:46"}
+{"current_steps": 120, "total_steps": 183, "loss": 0.437, "lr": 3.2200885612338846e-06, "epoch": 1.9591836734693877, "percentage": 65.57, "elapsed_time": "13:20:44", "remaining_time": "7:00:23"}
+{"current_steps": 121, "total_steps": 183, "loss": 0.4717, "lr": 3.1309146407961565e-06, "epoch": 1.9755102040816328, "percentage": 66.12, "elapsed_time": "13:27:57", "remaining_time": "6:53:59"}
+{"current_steps": 122, "total_steps": 183, "loss": 0.4099, "lr": 3.0424265684023556e-06, "epoch": 1.9918367346938775, "percentage": 66.67, "elapsed_time": "13:34:07", "remaining_time": "6:47:03"}
+{"current_steps": 123, "total_steps": 183, "loss": 0.7167, "lr": 2.9546568141433007e-06, "epoch": 2.0081632653061225, "percentage": 67.21, "elapsed_time": "13:40:32", "remaining_time": "6:40:15"}
+{"current_steps": 124, "total_steps": 183, "loss": 0.3293, "lr": 2.8676375845279013e-06, "epoch": 2.024489795918367, "percentage": 67.76, "elapsed_time": "13:46:06", "remaining_time": "6:33:04"}
+{"current_steps": 125, "total_steps": 183, "loss": 0.3724, "lr": 2.781400810665201e-06, "epoch": 2.0408163265306123, "percentage": 68.31, "elapsed_time": "13:53:04", "remaining_time": "6:26:32"}
+{"current_steps": 126, "total_steps": 183, "loss": 0.334, "lr": 2.695978136547476e-06, "epoch": 2.057142857142857, "percentage": 68.85, "elapsed_time": "13:59:39", "remaining_time": "6:19:50"}
+{"current_steps": 127, "total_steps": 183, "loss": 0.3827, "lr": 2.611400907438685e-06, "epoch": 2.073469387755102, "percentage": 69.4, "elapsed_time": "14:05:28", "remaining_time": "6:12:48"}
+{"current_steps": 128, "total_steps": 183, "loss": 0.347, "lr": 2.527700158372548e-06, "epoch": 2.089795918367347, "percentage": 69.95, "elapsed_time": "14:11:50", "remaining_time": "6:06:01"}
+{"current_steps": 129, "total_steps": 183, "loss": 0.3616, "lr": 2.4449066027644473e-06, "epoch": 2.1061224489795918, "percentage": 70.49, "elapsed_time": "14:18:44", "remaining_time": "5:59:28"}
+{"current_steps": 130, "total_steps": 183, "loss": 0.3509, "lr": 2.363050621141354e-06, "epoch": 2.122448979591837, "percentage": 71.04, "elapsed_time": "14:24:31", "remaining_time": "5:52:27"}
+{"current_steps": 131, "total_steps": 183, "loss": 0.3437, "lr": 2.282162249993895e-06, "epoch": 2.1387755102040815, "percentage": 71.58, "elapsed_time": "14:30:21", "remaining_time": "5:45:29"}
+{"current_steps": 132, "total_steps": 183, "loss": 0.3574, "lr": 2.20227117075468e-06, "epoch": 2.1551020408163266, "percentage": 72.13, "elapsed_time": "14:36:30", "remaining_time": "5:38:39"}
+{"current_steps": 133, "total_steps": 183, "loss": 0.3722, "lr": 2.1234066989068972e-06, "epoch": 2.1714285714285713, "percentage": 72.68, "elapsed_time": "14:42:33", "remaining_time": "5:31:47"}
+{"current_steps": 134, "total_steps": 183, "loss": 0.3181, "lr": 2.045597773227199e-06, "epoch": 2.1877551020408164, "percentage": 73.22, "elapsed_time": "14:48:49", "remaining_time": "5:25:01"}
+{"current_steps": 135, "total_steps": 183, "loss": 0.3783, "lr": 1.9688729451668116e-06, "epoch": 2.204081632653061, "percentage": 73.77, "elapsed_time": "14:55:42", "remaining_time": "5:18:28"}
+{"current_steps": 136, "total_steps": 183, "loss": 0.359, "lr": 1.8932603683747858e-06, "epoch": 2.220408163265306, "percentage": 74.32, "elapsed_time": "15:02:21", "remaining_time": "5:11:50"}
+{"current_steps": 137, "total_steps": 183, "loss": 0.3384, "lr": 1.8187877883672024e-06, "epoch": 2.236734693877551, "percentage": 74.86, "elapsed_time": "15:08:55", "remaining_time": "5:05:11"}
+{"current_steps": 138, "total_steps": 183, "loss": 0.3623, "lr": 1.745482532346145e-06, "epoch": 2.253061224489796, "percentage": 75.41, "elapsed_time": "15:14:43", "remaining_time": "4:58:16"}
+{"current_steps": 139, "total_steps": 183, "loss": 0.3658, "lr": 1.6733714991721738e-06, "epoch": 2.269387755102041, "percentage": 75.96, "elapsed_time": "15:20:46", "remaining_time": "4:51:28"}
+{"current_steps": 140, "total_steps": 183, "loss": 0.3552, "lr": 1.6024811494939723e-06, "epoch": 2.2857142857142856, "percentage": 76.5, "elapsed_time": "15:27:04", "remaining_time": "4:44:44"}
+{"current_steps": 141, "total_steps": 183, "loss": 0.3313, "lr": 1.532837496038792e-06, "epoch": 2.3020408163265307, "percentage": 77.05, "elapsed_time": "15:34:04", "remaining_time": "4:38:14"}
+{"current_steps": 142, "total_steps": 183, "loss": 0.3518, "lr": 1.4644660940672628e-06, "epoch": 2.3183673469387753, "percentage": 77.6, "elapsed_time": "15:40:43", "remaining_time": "4:31:37"}
+{"current_steps": 143, "total_steps": 183, "loss": 0.3601, "lr": 1.3973920319960654e-06, "epoch": 2.3346938775510204, "percentage": 78.14, "elapsed_time": "15:46:48", "remaining_time": "4:24:50"}
+{"current_steps": 144, "total_steps": 183, "loss": 0.3382, "lr": 1.3316399221919075e-06, "epoch": 2.351020408163265, "percentage": 78.69, "elapsed_time": "15:53:46", "remaining_time": "4:18:18"}
+{"current_steps": 145, "total_steps": 183, "loss": 0.3566, "lr": 1.2672338919401866e-06, "epoch": 2.36734693877551, "percentage": 79.23, "elapsed_time": "16:00:55", "remaining_time": "4:11:49"}
+{"current_steps": 146, "total_steps": 183, "loss": 0.3075, "lr": 1.2041975745916474e-06, "epoch": 2.3836734693877553, "percentage": 79.78, "elapsed_time": "16:06:46", "remaining_time": "4:05:00"}
+{"current_steps": 147, "total_steps": 183, "loss": 0.3725, "lr": 1.1425541008902852e-06, "epoch": 2.4, "percentage": 80.33, "elapsed_time": "16:13:09", "remaining_time": "3:58:19"}
+{"current_steps": 148, "total_steps": 183, "loss": 0.3797, "lr": 1.0823260904856791e-06, "epoch": 2.416326530612245, "percentage": 80.87, "elapsed_time": "16:21:31", "remaining_time": "3:52:07"}
+{"current_steps": 149, "total_steps": 183, "loss": 0.3668, "lr": 1.0235356436328675e-06, "epoch": 2.4326530612244897, "percentage": 81.42, "elapsed_time": "16:29:03", "remaining_time": "3:45:41"}
+{"current_steps": 150, "total_steps": 183, "loss": 0.4026, "lr": 9.662043330828086e-07, "epoch": 2.4489795918367347, "percentage": 81.97, "elapsed_time": "16:35:00", "remaining_time": "3:38:54"}
+{"current_steps": 151, "total_steps": 183, "loss": 0.3668, "lr": 9.10353196166412e-07, "epoch": 2.4653061224489794, "percentage": 82.51, "elapsed_time": "16:41:34", "remaining_time": "3:32:15"}
+{"current_steps": 152, "total_steps": 183, "loss": 0.3686, "lr": 8.560027270750276e-07, "epoch": 2.4816326530612245, "percentage": 83.06, "elapsed_time": "16:48:37", "remaining_time": "3:25:42"}
+{"current_steps": 153, "total_steps": 183, "loss": 0.3576, "lr": 8.031728693402502e-07, "epoch": 2.497959183673469, "percentage": 83.61, "elapsed_time": "16:54:38", "remaining_time": "3:18:56"}
+{"current_steps": 154, "total_steps": 183, "loss": 0.3683, "lr": 7.518830085157735e-07, "epoch": 2.5142857142857142, "percentage": 84.15, "elapsed_time": "17:01:04", "remaining_time": "3:12:16"}
+{"current_steps": 155, "total_steps": 183, "loss": 0.3451, "lr": 7.021519650639952e-07, "epoch": 2.5306122448979593, "percentage": 84.7, "elapsed_time": "17:07:27", "remaining_time": "3:05:36"}
+{"current_steps": 156, "total_steps": 183, "loss": 0.3631, "lr": 6.539979874499747e-07, "epoch": 2.546938775510204, "percentage": 85.25, "elapsed_time": "17:13:26", "remaining_time": "2:58:51"}
+{"current_steps": 157, "total_steps": 183, "loss": 0.4112, "lr": 6.074387454452891e-07, "epoch": 2.563265306122449, "percentage": 85.79, "elapsed_time": "17:20:27", "remaining_time": "2:52:18"}
+{"current_steps": 158, "total_steps": 183, "loss": 0.3455, "lr": 5.624913236442287e-07, "epoch": 2.5795918367346937, "percentage": 86.34, "elapsed_time": "17:27:46", "remaining_time": "2:45:47"}
+{"current_steps": 159, "total_steps": 183, "loss": 0.3597, "lr": 5.191722151947227e-07, "epoch": 2.595918367346939, "percentage": 86.89, "elapsed_time": "17:34:24", "remaining_time": "2:39:09"}
+{"current_steps": 160, "total_steps": 183, "loss": 0.3967, "lr": 4.77497315746292e-07, "epoch": 2.612244897959184, "percentage": 87.43, "elapsed_time": "17:41:10", "remaining_time": "2:32:32"}
+{"current_steps": 161, "total_steps": 183, "loss": 0.4031, "lr": 4.374819176172501e-07, "epoch": 2.6285714285714286, "percentage": 87.98, "elapsed_time": "17:48:02", "remaining_time": "2:25:56"}
+{"current_steps": 162, "total_steps": 183, "loss": 0.3484, "lr": 3.9914070418329123e-07, "epoch": 2.644897959183673, "percentage": 88.52, "elapsed_time": "17:54:16", "remaining_time": "2:19:15"}
+{"current_steps": 163, "total_steps": 183, "loss": 0.379, "lr": 3.6248774448952695e-07, "epoch": 2.6612244897959183, "percentage": 89.07, "elapsed_time": "18:00:56", "remaining_time": "2:12:37"}
+{"current_steps": 164, "total_steps": 183, "loss": 0.3687, "lr": 3.2753648808794505e-07, "epoch": 2.6775510204081634, "percentage": 89.62, "elapsed_time": "18:06:55", "remaining_time": "2:05:55"}
+{"current_steps": 165, "total_steps": 183, "loss": 0.3297, "lr": 2.942997601021924e-07, "epoch": 2.693877551020408, "percentage": 90.16, "elapsed_time": "18:13:42", "remaining_time": "1:59:18"}
+{"current_steps": 166, "total_steps": 183, "loss": 0.3701, "lr": 2.6278975652147875e-07, "epoch": 2.710204081632653, "percentage": 90.71, "elapsed_time": "18:20:28", "remaining_time": "1:52:41"}
+{"current_steps": 167, "total_steps": 183, "loss": 0.3629, "lr": 2.330180397253473e-07, "epoch": 2.726530612244898, "percentage": 91.26, "elapsed_time": "18:27:15", "remaining_time": "1:46:05"}
+{"current_steps": 168, "total_steps": 183, "loss": 0.3236, "lr": 2.049955342409349e-07, "epoch": 2.742857142857143, "percentage": 91.8, "elapsed_time": "18:33:05", "remaining_time": "1:39:22"}
+{"current_steps": 169, "total_steps": 183, "loss": 0.3174, "lr": 1.787325227342951e-07, "epoch": 2.759183673469388, "percentage": 92.35, "elapsed_time": "18:39:53", "remaining_time": "1:32:46"}
+{"current_steps": 170, "total_steps": 183, "loss": 0.3524, "lr": 1.542386422372405e-07, "epoch": 2.7755102040816326, "percentage": 92.9, "elapsed_time": "18:46:01", "remaining_time": "1:26:06"}
+{"current_steps": 171, "total_steps": 183, "loss": 0.3312, "lr": 1.3152288061110518e-07, "epoch": 2.7918367346938773, "percentage": 93.44, "elapsed_time": "18:52:14", "remaining_time": "1:19:27"}
+{"current_steps": 172, "total_steps": 183, "loss": 0.3431, "lr": 1.1059357324870456e-07, "epoch": 2.8081632653061224, "percentage": 93.99, "elapsed_time": "18:59:03", "remaining_time": "1:12:50"}
+{"current_steps": 173, "total_steps": 183, "loss": 0.356, "lr": 9.145840001572537e-08, "epoch": 2.8244897959183675, "percentage": 94.54, "elapsed_time": "19:05:44", "remaining_time": "1:06:13"}
+{"current_steps": 174, "total_steps": 183, "loss": 0.385, "lr": 7.41243824326504e-08, "epoch": 2.840816326530612, "percentage": 95.08, "elapsed_time": "19:12:51", "remaining_time": "0:59:37"}
+{"current_steps": 175, "total_steps": 183, "loss": 0.2999, "lr": 5.8597881098257924e-08, "epoch": 2.857142857142857, "percentage": 95.63, "elapsed_time": "19:19:46", "remaining_time": "0:53:01"}
+{"current_steps": 176, "total_steps": 183, "loss": 0.3271, "lr": 4.48845933556441e-08, "epoch": 2.873469387755102, "percentage": 96.17, "elapsed_time": "19:26:45", "remaining_time": "0:46:24"}
+{"current_steps": 177, "total_steps": 183, "loss": 0.3876, "lr": 3.2989551201624836e-08, "epoch": 2.889795918367347, "percentage": 96.72, "elapsed_time": "19:33:59", "remaining_time": "0:39:47"}
+{"current_steps": 178, "total_steps": 183, "loss": 0.3888, "lr": 2.2917119440275524e-08, "epoch": 2.906122448979592, "percentage": 97.27, "elapsed_time": "19:40:18", "remaining_time": "0:33:09"}
+{"current_steps": 179, "total_steps": 183, "loss": 0.3317, "lr": 1.4670994081297796e-08, "epoch": 2.9224489795918367, "percentage": 97.81, "elapsed_time": "19:47:00", "remaining_time": "0:26:31"}
+{"current_steps": 180, "total_steps": 183, "loss": 0.3809, "lr": 8.254200983794369e-09, "epoch": 2.938775510204082, "percentage": 98.36, "elapsed_time": "19:53:13", "remaining_time": "0:19:53"}
+{"current_steps": 181, "total_steps": 183, "loss": 0.3538, "lr": 3.669094745950008e-09, "epoch": 2.9551020408163264, "percentage": 98.91, "elapsed_time": "19:59:36", "remaining_time": "0:13:15"}
+{"current_steps": 182, "total_steps": 183, "loss": 0.3467, "lr": 9.173578410281992e-10, "epoch": 2.9714285714285715, "percentage": 99.45, "elapsed_time": "20:05:35", "remaining_time": "0:06:37"}
+{"current_steps": 183, "total_steps": 183, "loss": 0.352, "lr": 0.0, "epoch": 2.987755102040816, "percentage": 100.0, "elapsed_time": "20:11:56", "remaining_time": "0:00:00"}
+{"current_steps": 183, "total_steps": 183, "epoch": 2.987755102040816, "percentage": 100.0, "elapsed_time": "20:28:38", "remaining_time": "0:00:00"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7758d852bc7da24298c8a54312e12128f7e2b42fd69a42286ed77e199c7395b1
+size 8184