Training in progress, step 200

.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 +1,29 @@
+{
+  "_name_or_path": "/home/ubuntu/austrailia-east-1/qwen2.5-32b-openalex-with-references",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 27648,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 64,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 64,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.2",
+  "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 sha256:7b6be58a30b46e023470a7e40cb1f5e6f069d35785357d8f3365162d038ea0f6
+size 4891730992

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32a477d7c15e655509748e7a0d8269fac1ce1f01a142900a90efd9562326df5d
+size 4876059352

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:664d5252a1a96cbaf4a290ac79f9119a0dd4dc3641f42b47ec6392f977c9abb0
+size 4876059384

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:746e7d47caf662081f800ec8d130f98d5cac08ad0272275ce8dc88ec785ef8b0
+size 4876059416

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c07d257324da6a9fdc7fc2fadfef5060cf9ea5ef105eadbbe65d78adbdb55a9
+size 4876059416

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbc212d2ae313de80cd6ca6d849e1028d1923aff76529ba75f06e31616d68619
+size 4876059416

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4812635e393150d615d0a256c9ef7b9f127604b542898b8a2dad499c9bc40610
+size 4876059416

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ef8b571450572624480c3ea496887c1c62863aa570570a85404e76fc1f2fca1
+size 4876059416

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6904ca59960efa1926ad65524aa5e20c81f5385bcf664321347af9138e2a9e2
+size 4876059416

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d20c2332b2a4ce861d131116c4b6c3dca00554f91f773a9db881ca0d8fa59b9
+size 4876059416

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6289f1ab203b1280c36e1b6460007133729eabf770a3848f72874ef4b41af24
+size 4876059416

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51c56c63898c0187c0dfc9cd8e44326b826e683c46ba78e55c6a1cdf62c7df57
+size 4876059416

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9741dde9cc59bb8e05139d64276306b013285b95dd310f3df0aa1df261af0c22
+size 4876059416

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bed10674ec9c4fc7c8c845252524dd301dc4262f45d2ef441df79d1f93213e06
+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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "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 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 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": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 8192,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_log.jsonl

@@ -0,0 +1,202 @@
+{"current_steps": 1, "total_steps": 322, "loss": 1.0755, "lr": 9.090909090909091e-07, "epoch": 0.006177606177606178, "percentage": 0.31, "elapsed_time": "0:03:56", "remaining_time": "21:03:17"}
+{"current_steps": 2, "total_steps": 322, "loss": 1.0857, "lr": 1.8181818181818183e-06, "epoch": 0.012355212355212355, "percentage": 0.62, "elapsed_time": "0:07:36", "remaining_time": "20:16:03"}
+{"current_steps": 3, "total_steps": 322, "loss": 1.1084, "lr": 2.7272727272727272e-06, "epoch": 0.018532818532818532, "percentage": 0.93, "elapsed_time": "0:11:07", "remaining_time": "19:43:40"}
+{"current_steps": 4, "total_steps": 322, "loss": 1.1061, "lr": 3.6363636363636366e-06, "epoch": 0.02471042471042471, "percentage": 1.24, "elapsed_time": "0:14:38", "remaining_time": "19:23:49"}
+{"current_steps": 5, "total_steps": 322, "loss": 1.0937, "lr": 4.5454545454545455e-06, "epoch": 0.03088803088803089, "percentage": 1.55, "elapsed_time": "0:18:03", "remaining_time": "19:05:12"}
+{"current_steps": 6, "total_steps": 322, "loss": 1.0966, "lr": 5.4545454545454545e-06, "epoch": 0.037065637065637064, "percentage": 1.86, "elapsed_time": "0:21:33", "remaining_time": "18:55:29"}
+{"current_steps": 7, "total_steps": 322, "loss": 1.0934, "lr": 6.363636363636364e-06, "epoch": 0.043243243243243246, "percentage": 2.17, "elapsed_time": "0:25:00", "remaining_time": "18:45:42"}
+{"current_steps": 8, "total_steps": 322, "loss": 1.0964, "lr": 7.272727272727273e-06, "epoch": 0.04942084942084942, "percentage": 2.48, "elapsed_time": "0:28:26", "remaining_time": "18:36:39"}
+{"current_steps": 9, "total_steps": 322, "loss": 1.0973, "lr": 8.181818181818181e-06, "epoch": 0.055598455598455596, "percentage": 2.8, "elapsed_time": "0:31:54", "remaining_time": "18:29:44"}
+{"current_steps": 10, "total_steps": 322, "loss": 1.1073, "lr": 9.090909090909091e-06, "epoch": 0.06177606177606178, "percentage": 3.11, "elapsed_time": "0:35:25", "remaining_time": "18:25:01"}
+{"current_steps": 11, "total_steps": 322, "loss": 1.0966, "lr": 9.999999999999999e-06, "epoch": 0.06795366795366796, "percentage": 3.42, "elapsed_time": "0:38:52", "remaining_time": "18:19:00"}
+{"current_steps": 12, "total_steps": 322, "loss": 1.1103, "lr": 1.0909090909090909e-05, "epoch": 0.07413127413127413, "percentage": 3.73, "elapsed_time": "0:42:18", "remaining_time": "18:12:59"}
+{"current_steps": 13, "total_steps": 322, "loss": 1.1097, "lr": 1.1818181818181819e-05, "epoch": 0.08030888030888031, "percentage": 4.04, "elapsed_time": "0:45:43", "remaining_time": "18:06:55"}
+{"current_steps": 14, "total_steps": 322, "loss": 1.0925, "lr": 1.2727272727272728e-05, "epoch": 0.08648648648648649, "percentage": 4.35, "elapsed_time": "0:49:11", "remaining_time": "18:02:08"}
+{"current_steps": 15, "total_steps": 322, "loss": 1.1059, "lr": 1.3636363636363637e-05, "epoch": 0.09266409266409266, "percentage": 4.66, "elapsed_time": "0:52:36", "remaining_time": "17:56:47"}
+{"current_steps": 16, "total_steps": 322, "loss": 1.1083, "lr": 1.4545454545454546e-05, "epoch": 0.09884169884169884, "percentage": 4.97, "elapsed_time": "0:56:04", "remaining_time": "17:52:29"}
+{"current_steps": 17, "total_steps": 322, "loss": 1.1083, "lr": 1.5454545454545454e-05, "epoch": 0.10501930501930502, "percentage": 5.28, "elapsed_time": "0:59:30", "remaining_time": "17:47:39"}
+{"current_steps": 18, "total_steps": 322, "loss": 1.1248, "lr": 1.6363636363636363e-05, "epoch": 0.11119691119691119, "percentage": 5.59, "elapsed_time": "1:02:59", "remaining_time": "17:43:57"}
+{"current_steps": 19, "total_steps": 322, "loss": 1.0965, "lr": 1.7272727272727274e-05, "epoch": 0.11737451737451737, "percentage": 5.9, "elapsed_time": "1:06:30", "remaining_time": "17:40:45"}
+{"current_steps": 20, "total_steps": 322, "loss": 1.0973, "lr": 1.8181818181818182e-05, "epoch": 0.12355212355212356, "percentage": 6.21, "elapsed_time": "1:09:56", "remaining_time": "17:36:13"}
+{"current_steps": 21, "total_steps": 322, "loss": 1.0804, "lr": 1.909090909090909e-05, "epoch": 0.12972972972972974, "percentage": 6.52, "elapsed_time": "1:13:24", "remaining_time": "17:32:15"}
+{"current_steps": 22, "total_steps": 322, "loss": 1.0753, "lr": 1.9999999999999998e-05, "epoch": 0.13590733590733592, "percentage": 6.83, "elapsed_time": "1:16:53", "remaining_time": "17:28:37"}
+{"current_steps": 23, "total_steps": 322, "loss": 1.0767, "lr": 2.090909090909091e-05, "epoch": 0.14208494208494207, "percentage": 7.14, "elapsed_time": "1:20:22", "remaining_time": "17:24:49"}
+{"current_steps": 24, "total_steps": 322, "loss": 1.0918, "lr": 2.1818181818181818e-05, "epoch": 0.14826254826254825, "percentage": 7.45, "elapsed_time": "1:23:51", "remaining_time": "17:21:14"}
+{"current_steps": 25, "total_steps": 322, "loss": 1.1037, "lr": 2.272727272727273e-05, "epoch": 0.15444015444015444, "percentage": 7.76, "elapsed_time": "1:27:21", "remaining_time": "17:17:44"}
+{"current_steps": 26, "total_steps": 322, "loss": 1.0654, "lr": 2.3636363636363637e-05, "epoch": 0.16061776061776062, "percentage": 8.07, "elapsed_time": "1:30:50", "remaining_time": "17:14:12"}
+{"current_steps": 27, "total_steps": 322, "loss": 1.0809, "lr": 2.454545454545455e-05, "epoch": 0.1667953667953668, "percentage": 8.39, "elapsed_time": "1:34:18", "remaining_time": "17:10:23"}
+{"current_steps": 28, "total_steps": 322, "loss": 1.083, "lr": 2.5454545454545457e-05, "epoch": 0.17297297297297298, "percentage": 8.7, "elapsed_time": "1:37:46", "remaining_time": "17:06:37"}
+{"current_steps": 29, "total_steps": 322, "loss": 1.0775, "lr": 2.6363636363636365e-05, "epoch": 0.17915057915057914, "percentage": 9.01, "elapsed_time": "1:41:14", "remaining_time": "17:02:52"}
+{"current_steps": 30, "total_steps": 322, "loss": 1.0792, "lr": 2.7272727272727273e-05, "epoch": 0.18532818532818532, "percentage": 9.32, "elapsed_time": "1:44:43", "remaining_time": "16:59:22"}
+{"current_steps": 31, "total_steps": 322, "loss": 1.0849, "lr": 2.8181818181818185e-05, "epoch": 0.1915057915057915, "percentage": 9.63, "elapsed_time": "1:48:13", "remaining_time": "16:55:53"}
+{"current_steps": 32, "total_steps": 322, "loss": 1.0772, "lr": 2.9090909090909093e-05, "epoch": 0.19768339768339768, "percentage": 9.94, "elapsed_time": "1:51:45", "remaining_time": "16:52:44"}
+{"current_steps": 33, "total_steps": 322, "loss": 1.0653, "lr": 3e-05, "epoch": 0.20386100386100386, "percentage": 10.25, "elapsed_time": "1:55:12", "remaining_time": "16:48:57"}
+{"current_steps": 34, "total_steps": 322, "loss": 1.0933, "lr": 2.999911374020804e-05, "epoch": 0.21003861003861005, "percentage": 10.56, "elapsed_time": "1:58:43", "remaining_time": "16:45:43"}
+{"current_steps": 35, "total_steps": 322, "loss": 1.0891, "lr": 2.9996455065559676e-05, "epoch": 0.21621621621621623, "percentage": 10.87, "elapsed_time": "2:02:12", "remaining_time": "16:42:10"}
+{"current_steps": 36, "total_steps": 322, "loss": 1.0557, "lr": 2.9992024290225105e-05, "epoch": 0.22239382239382238, "percentage": 11.18, "elapsed_time": "2:05:41", "remaining_time": "16:38:29"}
+{"current_steps": 37, "total_steps": 322, "loss": 1.0762, "lr": 2.9985821937780067e-05, "epoch": 0.22857142857142856, "percentage": 11.49, "elapsed_time": "2:09:10", "remaining_time": "16:34:56"}
+{"current_steps": 38, "total_steps": 322, "loss": 1.0742, "lr": 2.997784874114397e-05, "epoch": 0.23474903474903475, "percentage": 11.8, "elapsed_time": "2:12:39", "remaining_time": "16:31:27"}
+{"current_steps": 39, "total_steps": 322, "loss": 1.0968, "lr": 2.9968105642493287e-05, "epoch": 0.24092664092664093, "percentage": 12.11, "elapsed_time": "2:16:11", "remaining_time": "16:28:13"}
+{"current_steps": 40, "total_steps": 322, "loss": 1.081, "lr": 2.9956593793150235e-05, "epoch": 0.2471042471042471, "percentage": 12.42, "elapsed_time": "2:19:38", "remaining_time": "16:24:31"}
+{"current_steps": 41, "total_steps": 322, "loss": 1.0727, "lr": 2.994331455344671e-05, "epoch": 0.25328185328185326, "percentage": 12.73, "elapsed_time": "2:23:06", "remaining_time": "16:20:48"}
+{"current_steps": 42, "total_steps": 322, "loss": 1.0614, "lr": 2.992826949256354e-05, "epoch": 0.2594594594594595, "percentage": 13.04, "elapsed_time": "2:26:37", "remaining_time": "16:17:28"}
+{"current_steps": 43, "total_steps": 322, "loss": 1.0631, "lr": 2.9911460388345057e-05, "epoch": 0.26563706563706563, "percentage": 13.35, "elapsed_time": "2:30:06", "remaining_time": "16:13:59"}
+{"current_steps": 44, "total_steps": 322, "loss": 1.0662, "lr": 2.9892889227089025e-05, "epoch": 0.27181467181467184, "percentage": 13.66, "elapsed_time": "2:33:36", "remaining_time": "16:10:31"}
+{"current_steps": 45, "total_steps": 322, "loss": 1.0725, "lr": 2.9872558203311913e-05, "epoch": 0.277992277992278, "percentage": 13.98, "elapsed_time": "2:37:02", "remaining_time": "16:06:40"}
+{"current_steps": 46, "total_steps": 322, "loss": 1.085, "lr": 2.9850469719489576e-05, "epoch": 0.28416988416988415, "percentage": 14.29, "elapsed_time": "2:40:30", "remaining_time": "16:03:02"}
+{"current_steps": 47, "total_steps": 322, "loss": 1.0585, "lr": 2.9826626385773358e-05, "epoch": 0.29034749034749036, "percentage": 14.6, "elapsed_time": "2:43:58", "remaining_time": "15:59:27"}
+{"current_steps": 48, "total_steps": 322, "loss": 1.0599, "lr": 2.980103101968165e-05, "epoch": 0.2965250965250965, "percentage": 14.91, "elapsed_time": "2:47:25", "remaining_time": "15:55:42"}
+{"current_steps": 49, "total_steps": 322, "loss": 1.0696, "lr": 2.9773686645766963e-05, "epoch": 0.3027027027027027, "percentage": 15.22, "elapsed_time": "2:50:53", "remaining_time": "15:52:07"}
+{"current_steps": 50, "total_steps": 322, "loss": 1.0967, "lr": 2.974459649525853e-05, "epoch": 0.3088803088803089, "percentage": 15.53, "elapsed_time": "2:54:23", "remaining_time": "15:48:40"}
+{"current_steps": 51, "total_steps": 322, "loss": 1.0644, "lr": 2.9713764005680428e-05, "epoch": 0.3150579150579151, "percentage": 15.84, "elapsed_time": "2:57:52", "remaining_time": "15:45:08"}
+{"current_steps": 52, "total_steps": 322, "loss": 1.0761, "lr": 2.9681192820445445e-05, "epoch": 0.32123552123552124, "percentage": 16.15, "elapsed_time": "3:01:21", "remaining_time": "15:41:39"}
+{"current_steps": 53, "total_steps": 322, "loss": 1.0553, "lr": 2.964688678842449e-05, "epoch": 0.3274131274131274, "percentage": 16.46, "elapsed_time": "3:04:53", "remaining_time": "15:38:25"}
+{"current_steps": 54, "total_steps": 322, "loss": 1.0567, "lr": 2.96108499634918e-05, "epoch": 0.3335907335907336, "percentage": 16.77, "elapsed_time": "3:08:22", "remaining_time": "15:34:54"}
+{"current_steps": 55, "total_steps": 322, "loss": 1.0698, "lr": 2.9573086604045908e-05, "epoch": 0.33976833976833976, "percentage": 17.08, "elapsed_time": "3:11:48", "remaining_time": "15:31:08"}
+{"current_steps": 56, "total_steps": 322, "loss": 1.0617, "lr": 2.953360117250643e-05, "epoch": 0.34594594594594597, "percentage": 17.39, "elapsed_time": "3:15:15", "remaining_time": "15:27:30"}
+{"current_steps": 57, "total_steps": 322, "loss": 1.0529, "lr": 2.9492398334786734e-05, "epoch": 0.3521235521235521, "percentage": 17.7, "elapsed_time": "3:18:48", "remaining_time": "15:24:17"}
+{"current_steps": 58, "total_steps": 322, "loss": 1.0608, "lr": 2.944948295974261e-05, "epoch": 0.3583011583011583, "percentage": 18.01, "elapsed_time": "3:22:13", "remaining_time": "15:20:29"}
+{"current_steps": 59, "total_steps": 322, "loss": 1.0676, "lr": 2.9404860118596906e-05, "epoch": 0.3644787644787645, "percentage": 18.32, "elapsed_time": "3:25:44", "remaining_time": "15:17:05"}
+{"current_steps": 60, "total_steps": 322, "loss": 1.0632, "lr": 2.935853508434028e-05, "epoch": 0.37065637065637064, "percentage": 18.63, "elapsed_time": "3:29:09", "remaining_time": "15:13:20"}
+{"current_steps": 61, "total_steps": 322, "loss": 1.0612, "lr": 2.931051333110809e-05, "epoch": 0.37683397683397685, "percentage": 18.94, "elapsed_time": "3:32:34", "remaining_time": "15:09:31"}
+{"current_steps": 62, "total_steps": 322, "loss": 1.0384, "lr": 2.9260800533533537e-05, "epoch": 0.383011583011583, "percentage": 19.25, "elapsed_time": "3:35:58", "remaining_time": "15:05:43"}
+{"current_steps": 63, "total_steps": 322, "loss": 1.0472, "lr": 2.9209402566077113e-05, "epoch": 0.3891891891891892, "percentage": 19.57, "elapsed_time": "3:39:24", "remaining_time": "15:01:59"}
+{"current_steps": 64, "total_steps": 322, "loss": 1.0409, "lr": 2.9156325502332414e-05, "epoch": 0.39536679536679536, "percentage": 19.88, "elapsed_time": "3:42:54", "remaining_time": "14:58:37"}
+{"current_steps": 65, "total_steps": 322, "loss": 1.053, "lr": 2.9101575614308423e-05, "epoch": 0.4015444015444015, "percentage": 20.19, "elapsed_time": "3:46:22", "remaining_time": "14:55:03"}
+{"current_steps": 66, "total_steps": 322, "loss": 1.0589, "lr": 2.9045159371688403e-05, "epoch": 0.40772200772200773, "percentage": 20.5, "elapsed_time": "3:49:50", "remaining_time": "14:51:30"}
+{"current_steps": 67, "total_steps": 322, "loss": 1.0538, "lr": 2.8987083441065335e-05, "epoch": 0.4138996138996139, "percentage": 20.81, "elapsed_time": "3:53:16", "remaining_time": "14:47:50"}
+{"current_steps": 68, "total_steps": 322, "loss": 1.0505, "lr": 2.8927354685154188e-05, "epoch": 0.4200772200772201, "percentage": 21.12, "elapsed_time": "3:56:43", "remaining_time": "14:44:14"}
+{"current_steps": 69, "total_steps": 322, "loss": 1.0306, "lr": 2.8865980161980933e-05, "epoch": 0.42625482625482625, "percentage": 21.43, "elapsed_time": "4:00:13", "remaining_time": "14:40:50"}
+{"current_steps": 70, "total_steps": 322, "loss": 1.0506, "lr": 2.8802967124048512e-05, "epoch": 0.43243243243243246, "percentage": 21.74, "elapsed_time": "4:03:41", "remaining_time": "14:37:18"}
+{"current_steps": 71, "total_steps": 322, "loss": 1.0482, "lr": 2.873832301747985e-05, "epoch": 0.4386100386100386, "percentage": 22.05, "elapsed_time": "4:07:09", "remaining_time": "14:33:45"}
+{"current_steps": 72, "total_steps": 322, "loss": 1.0415, "lr": 2.867205548113794e-05, "epoch": 0.44478764478764476, "percentage": 22.36, "elapsed_time": "4:10:36", "remaining_time": "14:30:10"}
+{"current_steps": 73, "total_steps": 322, "loss": 1.0508, "lr": 2.860417234572318e-05, "epoch": 0.450965250965251, "percentage": 22.67, "elapsed_time": "4:14:07", "remaining_time": "14:26:48"}
+{"current_steps": 74, "total_steps": 322, "loss": 1.0512, "lr": 2.8534681632848027e-05, "epoch": 0.45714285714285713, "percentage": 22.98, "elapsed_time": "4:17:33", "remaining_time": "14:23:09"}
+{"current_steps": 75, "total_steps": 322, "loss": 1.0583, "lr": 2.8463591554089115e-05, "epoch": 0.46332046332046334, "percentage": 23.29, "elapsed_time": "4:20:58", "remaining_time": "14:19:27"}
+{"current_steps": 76, "total_steps": 322, "loss": 1.0306, "lr": 2.8390910510016898e-05, "epoch": 0.4694980694980695, "percentage": 23.6, "elapsed_time": "4:24:26", "remaining_time": "14:15:58"}
+{"current_steps": 77, "total_steps": 322, "loss": 1.0478, "lr": 2.831664708920298e-05, "epoch": 0.4756756756756757, "percentage": 23.91, "elapsed_time": "4:27:55", "remaining_time": "14:12:29"}
+{"current_steps": 78, "total_steps": 322, "loss": 1.0305, "lr": 2.8240810067205207e-05, "epoch": 0.48185328185328186, "percentage": 24.22, "elapsed_time": "4:31:24", "remaining_time": "14:09:00"}
+{"current_steps": 79, "total_steps": 322, "loss": 1.0542, "lr": 2.8163408405530692e-05, "epoch": 0.488030888030888, "percentage": 24.53, "elapsed_time": "4:34:54", "remaining_time": "14:05:34"}
+{"current_steps": 80, "total_steps": 322, "loss": 1.0293, "lr": 2.8084451250576847e-05, "epoch": 0.4942084942084942, "percentage": 24.84, "elapsed_time": "4:38:22", "remaining_time": "14:02:06"}
+{"current_steps": 81, "total_steps": 322, "loss": 1.0445, "lr": 2.8003947932550566e-05, "epoch": 0.5003861003861004, "percentage": 25.16, "elapsed_time": "4:41:48", "remaining_time": "13:58:28"}
+{"current_steps": 82, "total_steps": 322, "loss": 1.0491, "lr": 2.7921907964365703e-05, "epoch": 0.5065637065637065, "percentage": 25.47, "elapsed_time": "4:45:16", "remaining_time": "13:54:56"}
+{"current_steps": 83, "total_steps": 322, "loss": 1.048, "lr": 2.783834104051894e-05, "epoch": 0.5127413127413127, "percentage": 25.78, "elapsed_time": "4:48:45", "remaining_time": "13:51:29"}
+{"current_steps": 84, "total_steps": 322, "loss": 1.0354, "lr": 2.7753257035944216e-05, "epoch": 0.518918918918919, "percentage": 26.09, "elapsed_time": "4:52:17", "remaining_time": "13:48:08"}
+{"current_steps": 85, "total_steps": 322, "loss": 1.032, "lr": 2.7666666004845826e-05, "epoch": 0.525096525096525, "percentage": 26.4, "elapsed_time": "4:55:47", "remaining_time": "13:44:44"}
+{"current_steps": 86, "total_steps": 322, "loss": 1.0264, "lr": 2.7578578179510324e-05, "epoch": 0.5312741312741313, "percentage": 26.71, "elapsed_time": "4:59:13", "remaining_time": "13:41:09"}
+{"current_steps": 87, "total_steps": 322, "loss": 1.0319, "lr": 2.748900396909742e-05, "epoch": 0.5374517374517375, "percentage": 27.02, "elapsed_time": "5:02:42", "remaining_time": "13:37:40"}
+{"current_steps": 88, "total_steps": 322, "loss": 1.0396, "lr": 2.7397953958409925e-05, "epoch": 0.5436293436293437, "percentage": 27.33, "elapsed_time": "5:06:12", "remaining_time": "13:34:14"}
+{"current_steps": 89, "total_steps": 322, "loss": 1.0298, "lr": 2.730543890664297e-05, "epoch": 0.5498069498069498, "percentage": 27.64, "elapsed_time": "5:09:43", "remaining_time": "13:30:51"}
+{"current_steps": 90, "total_steps": 322, "loss": 1.0362, "lr": 2.7211469746112628e-05, "epoch": 0.555984555984556, "percentage": 27.95, "elapsed_time": "5:13:09", "remaining_time": "13:27:15"}
+{"current_steps": 91, "total_steps": 322, "loss": 1.0236, "lr": 2.711605758096406e-05, "epoch": 0.5621621621621622, "percentage": 28.26, "elapsed_time": "5:16:36", "remaining_time": "13:23:41"}
+{"current_steps": 92, "total_steps": 322, "loss": 1.0242, "lr": 2.7019213685859345e-05, "epoch": 0.5683397683397683, "percentage": 28.57, "elapsed_time": "5:20:02", "remaining_time": "13:20:06"}
+{"current_steps": 93, "total_steps": 322, "loss": 1.0205, "lr": 2.692094950464519e-05, "epoch": 0.5745173745173745, "percentage": 28.88, "elapsed_time": "5:23:31", "remaining_time": "13:16:38"}
+{"current_steps": 94, "total_steps": 322, "loss": 1.0311, "lr": 2.6821276649000643e-05, "epoch": 0.5806949806949807, "percentage": 29.19, "elapsed_time": "5:26:58", "remaining_time": "13:13:05"}
+{"current_steps": 95, "total_steps": 322, "loss": 1.0479, "lr": 2.6720206897064936e-05, "epoch": 0.5868725868725869, "percentage": 29.5, "elapsed_time": "5:30:24", "remaining_time": "13:09:29"}
+{"current_steps": 96, "total_steps": 322, "loss": 1.0384, "lr": 2.6617752192045723e-05, "epoch": 0.593050193050193, "percentage": 29.81, "elapsed_time": "5:33:52", "remaining_time": "13:06:00"}
+{"current_steps": 97, "total_steps": 322, "loss": 1.0388, "lr": 2.651392464080774e-05, "epoch": 0.5992277992277992, "percentage": 30.12, "elapsed_time": "5:37:18", "remaining_time": "13:02:23"}
+{"current_steps": 98, "total_steps": 322, "loss": 1.039, "lr": 2.640873651244218e-05, "epoch": 0.6054054054054054, "percentage": 30.43, "elapsed_time": "5:40:45", "remaining_time": "12:58:52"}
+{"current_steps": 99, "total_steps": 322, "loss": 1.0073, "lr": 2.6302200236816877e-05, "epoch": 0.6115830115830115, "percentage": 30.75, "elapsed_time": "5:44:17", "remaining_time": "12:55:32"}
+{"current_steps": 100, "total_steps": 322, "loss": 1.0123, "lr": 2.6194328403107493e-05, "epoch": 0.6177606177606177, "percentage": 31.06, "elapsed_time": "5:47:47", "remaining_time": "12:52:05"}
+{"current_steps": 101, "total_steps": 322, "loss": 1.0198, "lr": 2.6085133758309887e-05, "epoch": 0.623938223938224, "percentage": 31.37, "elapsed_time": "5:57:44", "remaining_time": "13:02:46"}
+{"current_steps": 102, "total_steps": 322, "loss": 1.0277, "lr": 2.5974629205733813e-05, "epoch": 0.6301158301158302, "percentage": 31.68, "elapsed_time": "6:01:13", "remaining_time": "12:59:07"}
+{"current_steps": 103, "total_steps": 322, "loss": 1.0194, "lr": 2.586282780347818e-05, "epoch": 0.6362934362934363, "percentage": 31.99, "elapsed_time": "6:04:40", "remaining_time": "12:55:21"}
+{"current_steps": 104, "total_steps": 322, "loss": 1.0079, "lr": 2.574974276288798e-05, "epoch": 0.6424710424710425, "percentage": 32.3, "elapsed_time": "6:08:08", "remaining_time": "12:51:40"}
+{"current_steps": 105, "total_steps": 322, "loss": 1.0161, "lr": 2.5635387446993157e-05, "epoch": 0.6486486486486487, "percentage": 32.61, "elapsed_time": "6:11:36", "remaining_time": "12:48:00"}
+{"current_steps": 106, "total_steps": 322, "loss": 1.008, "lr": 2.551977536892951e-05, "epoch": 0.6548262548262548, "percentage": 32.92, "elapsed_time": "6:15:02", "remaining_time": "12:44:14"}
+{"current_steps": 107, "total_steps": 322, "loss": 1.0102, "lr": 2.5402920190341864e-05, "epoch": 0.661003861003861, "percentage": 33.23, "elapsed_time": "6:18:33", "remaining_time": "12:40:39"}
+{"current_steps": 108, "total_steps": 322, "loss": 0.9876, "lr": 2.5284835719769735e-05, "epoch": 0.6671814671814672, "percentage": 33.54, "elapsed_time": "6:22:03", "remaining_time": "12:37:01"}
+{"current_steps": 109, "total_steps": 322, "loss": 1.0081, "lr": 2.516553591101555e-05, "epoch": 0.6733590733590734, "percentage": 33.85, "elapsed_time": "6:25:29", "remaining_time": "12:33:17"}
+{"current_steps": 110, "total_steps": 322, "loss": 1.0087, "lr": 2.5045034861495816e-05, "epoch": 0.6795366795366795, "percentage": 34.16, "elapsed_time": "6:28:54", "remaining_time": "12:29:32"}
+{"current_steps": 111, "total_steps": 322, "loss": 1.0135, "lr": 2.4923346810575197e-05, "epoch": 0.6857142857142857, "percentage": 34.47, "elapsed_time": "6:32:22", "remaining_time": "12:25:51"}
+{"current_steps": 112, "total_steps": 322, "loss": 1.018, "lr": 2.480048613788393e-05, "epoch": 0.6918918918918919, "percentage": 34.78, "elapsed_time": "6:35:50", "remaining_time": "12:22:12"}
+{"current_steps": 113, "total_steps": 322, "loss": 1.0104, "lr": 2.4676467361618565e-05, "epoch": 0.698069498069498, "percentage": 35.09, "elapsed_time": "6:39:21", "remaining_time": "12:18:38"}
+{"current_steps": 114, "total_steps": 322, "loss": 1.0211, "lr": 2.4551305136826426e-05, "epoch": 0.7042471042471042, "percentage": 35.4, "elapsed_time": "6:42:50", "remaining_time": "12:15:01"}
+{"current_steps": 115, "total_steps": 322, "loss": 1.0235, "lr": 2.4425014253673824e-05, "epoch": 0.7104247104247104, "percentage": 35.71, "elapsed_time": "6:46:19", "remaining_time": "12:11:23"}
+{"current_steps": 116, "total_steps": 322, "loss": 1.0089, "lr": 2.4297609635698322e-05, "epoch": 0.7166023166023165, "percentage": 36.02, "elapsed_time": "6:49:49", "remaining_time": "12:07:47"}
+{"current_steps": 117, "total_steps": 322, "loss": 1.0079, "lr": 2.416910633804529e-05, "epoch": 0.7227799227799228, "percentage": 36.34, "elapsed_time": "6:53:18", "remaining_time": "12:04:11"}
+{"current_steps": 118, "total_steps": 322, "loss": 1.0211, "lr": 2.4039519545688848e-05, "epoch": 0.728957528957529, "percentage": 36.65, "elapsed_time": "6:56:47", "remaining_time": "12:00:33"}
+{"current_steps": 119, "total_steps": 322, "loss": 1.0216, "lr": 2.3908864571637466e-05, "epoch": 0.7351351351351352, "percentage": 36.96, "elapsed_time": "7:00:16", "remaining_time": "11:56:57"}
+{"current_steps": 120, "total_steps": 322, "loss": 1.0082, "lr": 2.377715685512451e-05, "epoch": 0.7413127413127413, "percentage": 37.27, "elapsed_time": "7:03:46", "remaining_time": "11:53:20"}
+{"current_steps": 121, "total_steps": 322, "loss": 1.0163, "lr": 2.3644411959783753e-05, "epoch": 0.7474903474903475, "percentage": 37.58, "elapsed_time": "7:07:13", "remaining_time": "11:49:41"}
+{"current_steps": 122, "total_steps": 322, "loss": 1.0021, "lr": 2.3510645571810318e-05, "epoch": 0.7536679536679537, "percentage": 37.89, "elapsed_time": "7:10:39", "remaining_time": "11:45:59"}
+{"current_steps": 123, "total_steps": 322, "loss": 0.9861, "lr": 2.337587349810703e-05, "epoch": 0.7598455598455598, "percentage": 38.2, "elapsed_time": "7:14:06", "remaining_time": "11:42:19"}
+{"current_steps": 124, "total_steps": 322, "loss": 1.0104, "lr": 2.3240111664416545e-05, "epoch": 0.766023166023166, "percentage": 38.51, "elapsed_time": "7:17:35", "remaining_time": "11:38:43"}
+{"current_steps": 125, "total_steps": 322, "loss": 1.0108, "lr": 2.3103376113439474e-05, "epoch": 0.7722007722007722, "percentage": 38.82, "elapsed_time": "7:21:01", "remaining_time": "11:35:02"}
+{"current_steps": 126, "total_steps": 322, "loss": 1.0136, "lr": 2.29656830029386e-05, "epoch": 0.7783783783783784, "percentage": 39.13, "elapsed_time": "7:24:31", "remaining_time": "11:31:28"}
+{"current_steps": 127, "total_steps": 322, "loss": 1.0037, "lr": 2.28270486038296e-05, "epoch": 0.7845559845559845, "percentage": 39.44, "elapsed_time": "7:27:58", "remaining_time": "11:27:49"}
+{"current_steps": 128, "total_steps": 322, "loss": 0.9893, "lr": 2.2687489298258284e-05, "epoch": 0.7907335907335907, "percentage": 39.75, "elapsed_time": "7:31:26", "remaining_time": "11:24:12"}
+{"current_steps": 129, "total_steps": 322, "loss": 0.993, "lr": 2.254702157766482e-05, "epoch": 0.7969111969111969, "percentage": 40.06, "elapsed_time": "7:34:52", "remaining_time": "11:20:32"}
+{"current_steps": 130, "total_steps": 322, "loss": 0.9973, "lr": 2.2405662040834897e-05, "epoch": 0.803088803088803, "percentage": 40.37, "elapsed_time": "7:38:20", "remaining_time": "11:16:56"}
+{"current_steps": 131, "total_steps": 322, "loss": 0.9992, "lr": 2.2263427391938362e-05, "epoch": 0.8092664092664092, "percentage": 40.68, "elapsed_time": "7:41:48", "remaining_time": "11:13:19"}
+{"current_steps": 132, "total_steps": 322, "loss": 0.9943, "lr": 2.212033443855525e-05, "epoch": 0.8154440154440155, "percentage": 40.99, "elapsed_time": "7:45:19", "remaining_time": "11:09:47"}
+{"current_steps": 133, "total_steps": 322, "loss": 1.009, "lr": 2.1976400089689712e-05, "epoch": 0.8216216216216217, "percentage": 41.3, "elapsed_time": "7:48:47", "remaining_time": "11:06:10"}
+{"current_steps": 134, "total_steps": 322, "loss": 1.0021, "lr": 2.1831641353771887e-05, "epoch": 0.8277992277992278, "percentage": 41.61, "elapsed_time": "7:52:14", "remaining_time": "11:02:33"}
+{"current_steps": 135, "total_steps": 322, "loss": 1.026, "lr": 2.1686075336648075e-05, "epoch": 0.833976833976834, "percentage": 41.93, "elapsed_time": "7:55:43", "remaining_time": "10:58:58"}
+{"current_steps": 136, "total_steps": 322, "loss": 1.0069, "lr": 2.153971923955934e-05, "epoch": 0.8401544401544402, "percentage": 42.24, "elapsed_time": "7:59:11", "remaining_time": "10:55:21"}
+{"current_steps": 137, "total_steps": 322, "loss": 0.9936, "lr": 2.1392590357108906e-05, "epoch": 0.8463320463320463, "percentage": 42.55, "elapsed_time": "8:02:38", "remaining_time": "10:51:44"}
+{"current_steps": 138, "total_steps": 322, "loss": 0.9969, "lr": 2.1244706075218474e-05, "epoch": 0.8525096525096525, "percentage": 42.86, "elapsed_time": "8:06:08", "remaining_time": "10:48:11"}
+{"current_steps": 139, "total_steps": 322, "loss": 0.9924, "lr": 2.1096083869073767e-05, "epoch": 0.8586872586872587, "percentage": 43.17, "elapsed_time": "8:09:37", "remaining_time": "10:44:36"}
+{"current_steps": 140, "total_steps": 322, "loss": 1.0021, "lr": 2.0946741301059517e-05, "epoch": 0.8648648648648649, "percentage": 43.48, "elapsed_time": "8:13:08", "remaining_time": "10:41:04"}
+{"current_steps": 141, "total_steps": 322, "loss": 0.9928, "lr": 2.0796696018684154e-05, "epoch": 0.871042471042471, "percentage": 43.79, "elapsed_time": "8:16:33", "remaining_time": "10:37:26"}
+{"current_steps": 142, "total_steps": 322, "loss": 1.0013, "lr": 2.0645965752494447e-05, "epoch": 0.8772200772200772, "percentage": 44.1, "elapsed_time": "8:20:00", "remaining_time": "10:33:48"}
+{"current_steps": 143, "total_steps": 322, "loss": 1.0047, "lr": 2.049456831398031e-05, "epoch": 0.8833976833976834, "percentage": 44.41, "elapsed_time": "8:23:27", "remaining_time": "10:30:12"}
+{"current_steps": 144, "total_steps": 322, "loss": 0.995, "lr": 2.0342521593470055e-05, "epoch": 0.8895752895752895, "percentage": 44.72, "elapsed_time": "8:26:57", "remaining_time": "10:26:38"}
+{"current_steps": 145, "total_steps": 322, "loss": 0.9908, "lr": 2.018984355801634e-05, "epoch": 0.8957528957528957, "percentage": 45.03, "elapsed_time": "8:30:29", "remaining_time": "10:23:09"}
+{"current_steps": 146, "total_steps": 322, "loss": 0.9874, "lr": 2.0036552249273017e-05, "epoch": 0.901930501930502, "percentage": 45.34, "elapsed_time": "8:33:58", "remaining_time": "10:19:35"}
+{"current_steps": 147, "total_steps": 322, "loss": 0.9996, "lr": 1.988266578136321e-05, "epoch": 0.9081081081081082, "percentage": 45.65, "elapsed_time": "8:37:24", "remaining_time": "10:15:57"}
+{"current_steps": 148, "total_steps": 322, "loss": 0.9861, "lr": 1.9728202338738786e-05, "epoch": 0.9142857142857143, "percentage": 45.96, "elapsed_time": "8:40:52", "remaining_time": "10:12:23"}
+{"current_steps": 149, "total_steps": 322, "loss": 0.9723, "lr": 1.9573180174031558e-05, "epoch": 0.9204633204633205, "percentage": 46.27, "elapsed_time": "8:44:19", "remaining_time": "10:08:47"}
+{"current_steps": 150, "total_steps": 322, "loss": 0.9837, "lr": 1.941761760589637e-05, "epoch": 0.9266409266409267, "percentage": 46.58, "elapsed_time": "8:47:50", "remaining_time": "10:05:14"}
+{"current_steps": 151, "total_steps": 322, "loss": 0.9941, "lr": 1.926153301684647e-05, "epoch": 0.9328185328185328, "percentage": 46.89, "elapsed_time": "8:51:14", "remaining_time": "10:01:36"}
+{"current_steps": 152, "total_steps": 322, "loss": 0.9776, "lr": 1.9104944851081247e-05, "epoch": 0.938996138996139, "percentage": 47.2, "elapsed_time": "8:54:39", "remaining_time": "9:57:58"}
+{"current_steps": 153, "total_steps": 322, "loss": 0.9997, "lr": 1.8947871612306724e-05, "epoch": 0.9451737451737452, "percentage": 47.52, "elapsed_time": "8:58:11", "remaining_time": "9:54:28"}
+{"current_steps": 154, "total_steps": 322, "loss": 0.9867, "lr": 1.8790331861549025e-05, "epoch": 0.9513513513513514, "percentage": 47.83, "elapsed_time": "9:01:38", "remaining_time": "9:50:52"}
+{"current_steps": 155, "total_steps": 322, "loss": 0.967, "lr": 1.863234421496105e-05, "epoch": 0.9575289575289575, "percentage": 48.14, "elapsed_time": "9:05:04", "remaining_time": "9:47:16"}
+{"current_steps": 156, "total_steps": 322, "loss": 0.977, "lr": 1.8473927341622628e-05, "epoch": 0.9637065637065637, "percentage": 48.45, "elapsed_time": "9:08:32", "remaining_time": "9:43:42"}
+{"current_steps": 157, "total_steps": 322, "loss": 0.9771, "lr": 1.831509996133447e-05, "epoch": 0.9698841698841699, "percentage": 48.76, "elapsed_time": "9:11:58", "remaining_time": "9:40:06"}
+{"current_steps": 158, "total_steps": 322, "loss": 0.9936, "lr": 1.8155880842406042e-05, "epoch": 0.976061776061776, "percentage": 49.07, "elapsed_time": "9:15:24", "remaining_time": "9:36:29"}
+{"current_steps": 159, "total_steps": 322, "loss": 0.9914, "lr": 1.7996288799437762e-05, "epoch": 0.9822393822393822, "percentage": 49.38, "elapsed_time": "9:18:50", "remaining_time": "9:32:54"}
+{"current_steps": 160, "total_steps": 322, "loss": 0.9961, "lr": 1.7836342691097745e-05, "epoch": 0.9884169884169884, "percentage": 49.69, "elapsed_time": "9:22:19", "remaining_time": "9:29:20"}
+{"current_steps": 161, "total_steps": 322, "loss": 0.9809, "lr": 1.7676061417893278e-05, "epoch": 0.9945945945945946, "percentage": 50.0, "elapsed_time": "9:25:46", "remaining_time": "9:25:46"}
+{"current_steps": 162, "total_steps": 322, "loss": 1.9052, "lr": 1.7515463919937416e-05, "epoch": 1.0061776061776062, "percentage": 50.31, "elapsed_time": "9:29:38", "remaining_time": "9:22:36"}
+{"current_steps": 163, "total_steps": 322, "loss": 0.8504, "lr": 1.735456917471084e-05, "epoch": 1.0123552123552124, "percentage": 50.62, "elapsed_time": "9:33:08", "remaining_time": "9:19:04"}
+{"current_steps": 164, "total_steps": 322, "loss": 0.8583, "lr": 1.7193396194819332e-05, "epoch": 1.0185328185328186, "percentage": 50.93, "elapsed_time": "9:36:35", "remaining_time": "9:15:30"}
+{"current_steps": 165, "total_steps": 322, "loss": 0.8515, "lr": 1.703196402574712e-05, "epoch": 1.0247104247104246, "percentage": 51.24, "elapsed_time": "9:40:06", "remaining_time": "9:11:59"}
+{"current_steps": 166, "total_steps": 322, "loss": 0.8551, "lr": 1.6870291743606273e-05, "epoch": 1.0308880308880308, "percentage": 51.55, "elapsed_time": "9:43:36", "remaining_time": "9:08:26"}
+{"current_steps": 167, "total_steps": 322, "loss": 0.8667, "lr": 1.6708398452882552e-05, "epoch": 1.037065637065637, "percentage": 51.86, "elapsed_time": "9:47:02", "remaining_time": "9:04:51"}
+{"current_steps": 168, "total_steps": 322, "loss": 0.8531, "lr": 1.654630328417784e-05, "epoch": 1.0432432432432432, "percentage": 52.17, "elapsed_time": "9:50:27", "remaining_time": "9:01:14"}
+{"current_steps": 169, "total_steps": 322, "loss": 0.8642, "lr": 1.638402539194953e-05, "epoch": 1.0494208494208495, "percentage": 52.48, "elapsed_time": "9:53:52", "remaining_time": "8:57:38"}
+{"current_steps": 170, "total_steps": 322, "loss": 0.8718, "lr": 1.6221583952247098e-05, "epoch": 1.0555984555984557, "percentage": 52.8, "elapsed_time": "9:57:17", "remaining_time": "8:54:02"}
+{"current_steps": 171, "total_steps": 322, "loss": 0.8623, "lr": 1.605899816044608e-05, "epoch": 1.0617760617760619, "percentage": 53.11, "elapsed_time": "10:00:41", "remaining_time": "8:50:26"}
+{"current_steps": 172, "total_steps": 322, "loss": 0.8547, "lr": 1.589628722897982e-05, "epoch": 1.0679536679536679, "percentage": 53.42, "elapsed_time": "10:04:07", "remaining_time": "8:46:51"}
+{"current_steps": 173, "total_steps": 322, "loss": 0.8752, "lr": 1.5733470385069142e-05, "epoch": 1.074131274131274, "percentage": 53.73, "elapsed_time": "10:07:36", "remaining_time": "8:43:18"}
+{"current_steps": 174, "total_steps": 322, "loss": 0.8529, "lr": 1.5570566868450345e-05, "epoch": 1.0803088803088803, "percentage": 54.04, "elapsed_time": "10:11:04", "remaining_time": "8:39:45"}
+{"current_steps": 175, "total_steps": 322, "loss": 0.8453, "lr": 1.540759592910167e-05, "epoch": 1.0864864864864865, "percentage": 54.35, "elapsed_time": "10:14:35", "remaining_time": "8:36:15"}
+{"current_steps": 176, "total_steps": 322, "loss": 0.8521, "lr": 1.5244576824968541e-05, "epoch": 1.0926640926640927, "percentage": 54.66, "elapsed_time": "10:18:03", "remaining_time": "8:32:42"}
+{"current_steps": 177, "total_steps": 322, "loss": 0.8573, "lr": 1.5081528819687952e-05, "epoch": 1.098841698841699, "percentage": 54.97, "elapsed_time": "10:21:29", "remaining_time": "8:29:08"}
+{"current_steps": 178, "total_steps": 322, "loss": 0.8694, "lr": 1.4918471180312052e-05, "epoch": 1.1050193050193051, "percentage": 55.28, "elapsed_time": "10:24:54", "remaining_time": "8:25:32"}
+{"current_steps": 179, "total_steps": 322, "loss": 0.8429, "lr": 1.4755423175031461e-05, "epoch": 1.111196911196911, "percentage": 55.59, "elapsed_time": "10:28:20", "remaining_time": "8:21:58"}
+{"current_steps": 180, "total_steps": 322, "loss": 0.8474, "lr": 1.4592404070898337e-05, "epoch": 1.1173745173745173, "percentage": 55.9, "elapsed_time": "10:31:48", "remaining_time": "8:18:25"}
+{"current_steps": 181, "total_steps": 322, "loss": 0.8643, "lr": 1.4429433131549661e-05, "epoch": 1.1235521235521235, "percentage": 56.21, "elapsed_time": "10:35:17", "remaining_time": "8:14:53"}
+{"current_steps": 182, "total_steps": 322, "loss": 0.847, "lr": 1.4266529614930862e-05, "epoch": 1.1297297297297297, "percentage": 56.52, "elapsed_time": "10:38:46", "remaining_time": "8:11:22"}
+{"current_steps": 183, "total_steps": 322, "loss": 0.8416, "lr": 1.4103712771020188e-05, "epoch": 1.135907335907336, "percentage": 56.83, "elapsed_time": "10:42:14", "remaining_time": "8:07:49"}
+{"current_steps": 184, "total_steps": 322, "loss": 0.8808, "lr": 1.3941001839553921e-05, "epoch": 1.1420849420849422, "percentage": 57.14, "elapsed_time": "10:45:40", "remaining_time": "8:04:15"}
+{"current_steps": 185, "total_steps": 322, "loss": 0.8422, "lr": 1.3778416047752906e-05, "epoch": 1.1482625482625481, "percentage": 57.45, "elapsed_time": "10:49:05", "remaining_time": "8:00:40"}
+{"current_steps": 186, "total_steps": 322, "loss": 0.8537, "lr": 1.3615974608050472e-05, "epoch": 1.1544401544401544, "percentage": 57.76, "elapsed_time": "10:52:32", "remaining_time": "7:57:07"}
+{"current_steps": 187, "total_steps": 322, "loss": 0.853, "lr": 1.3453696715822165e-05, "epoch": 1.1606177606177606, "percentage": 58.07, "elapsed_time": "10:55:57", "remaining_time": "7:53:33"}
+{"current_steps": 188, "total_steps": 322, "loss": 0.8552, "lr": 1.329160154711745e-05, "epoch": 1.1667953667953668, "percentage": 58.39, "elapsed_time": "10:59:28", "remaining_time": "7:50:02"}
+{"current_steps": 189, "total_steps": 322, "loss": 0.8346, "lr": 1.3129708256393725e-05, "epoch": 1.172972972972973, "percentage": 58.7, "elapsed_time": "11:02:57", "remaining_time": "7:46:31"}
+{"current_steps": 190, "total_steps": 322, "loss": 0.8561, "lr": 1.2968035974252882e-05, "epoch": 1.1791505791505792, "percentage": 59.01, "elapsed_time": "11:06:25", "remaining_time": "7:42:59"}
+{"current_steps": 191, "total_steps": 322, "loss": 0.8518, "lr": 1.2806603805180668e-05, "epoch": 1.1853281853281854, "percentage": 59.32, "elapsed_time": "11:09:51", "remaining_time": "7:39:26"}
+{"current_steps": 192, "total_steps": 322, "loss": 0.8588, "lr": 1.2645430825289166e-05, "epoch": 1.1915057915057914, "percentage": 59.63, "elapsed_time": "11:13:20", "remaining_time": "7:35:54"}
+{"current_steps": 193, "total_steps": 322, "loss": 0.839, "lr": 1.2484536080062583e-05, "epoch": 1.1976833976833976, "percentage": 59.94, "elapsed_time": "11:16:51", "remaining_time": "7:32:24"}
+{"current_steps": 194, "total_steps": 322, "loss": 0.8534, "lr": 1.2323938582106725e-05, "epoch": 1.2038610038610038, "percentage": 60.25, "elapsed_time": "11:20:17", "remaining_time": "7:28:50"}
+{"current_steps": 195, "total_steps": 322, "loss": 0.8586, "lr": 1.2163657308902256e-05, "epoch": 1.21003861003861, "percentage": 60.56, "elapsed_time": "11:23:41", "remaining_time": "7:25:16"}
+{"current_steps": 196, "total_steps": 322, "loss": 0.8394, "lr": 1.2003711200562243e-05, "epoch": 1.2162162162162162, "percentage": 60.87, "elapsed_time": "11:27:06", "remaining_time": "7:21:42"}
+{"current_steps": 197, "total_steps": 322, "loss": 0.8434, "lr": 1.1844119157593962e-05, "epoch": 1.2223938223938224, "percentage": 61.18, "elapsed_time": "11:30:31", "remaining_time": "7:18:09"}
+{"current_steps": 198, "total_steps": 322, "loss": 0.8568, "lr": 1.1684900038665532e-05, "epoch": 1.2285714285714286, "percentage": 61.49, "elapsed_time": "11:34:00", "remaining_time": "7:14:37"}
+{"current_steps": 199, "total_steps": 322, "loss": 0.8499, "lr": 1.1526072658377371e-05, "epoch": 1.2347490347490346, "percentage": 61.8, "elapsed_time": "11:37:29", "remaining_time": "7:11:06"}
+{"current_steps": 200, "total_steps": 322, "loss": 0.8376, "lr": 1.1367655785038958e-05, "epoch": 1.2409266409266408, "percentage": 62.11, "elapsed_time": "11:41:00", "remaining_time": "7:07:36"}
+{"current_steps": 201, "total_steps": 322, "loss": 0.8401, "lr": 1.120966813845098e-05, "epoch": 1.247104247104247, "percentage": 62.42, "elapsed_time": "11:51:53", "remaining_time": "7:08:33"}
+{"current_steps": 202, "total_steps": 322, "loss": 0.8486, "lr": 1.1052128387693282e-05, "epoch": 1.2532818532818533, "percentage": 62.73, "elapsed_time": "11:55:22", "remaining_time": "7:04:58"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc51ce48253c31706cfe677ddc5c90072d374066fd669930926b5d1ab2ddf913
+size 7736