Training in progress, step 168

.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": "Qwen/Qwen2.5-Coder-32B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 27648,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 64,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 64,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.3",
+  "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:a8e9b5aeda2c2e61bec7c725ba61f37161d41b50fc28321cb8d67b3974526961
+size 4891730992

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76e9ab43f747af60e6e40e675945e0397c095a03ce42dd8a69050c26988dcd1a
+size 4876059352

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1cad2e2f81945d27eb8024d5f861fdde005975147b364597034473c6367056a
+size 4876059384

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:737884977bc15d1f5d60b5d5f0d4fd1e0a490bb472b3ab349bda070ca856ef99
+size 4876059416

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bb424bbcfb13786976277042e2d0ef15428e42e4db88c04fff31ff84eecaee2
+size 4876059416

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62effa507d8d36d09dc035ea8298620b1d254aa6eacc8cc9745b2062cb8cec59
+size 4876059416

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51997669fb710da2dfa746db066131c7c422c54028fe097f5e449e5f14077483
+size 4876059416

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dae32145f30c8acb45208ddb2c49e4f38bbc595af0dd324d5b9b1d6692bd88a
+size 4876059416

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4df81d1c922081fc67d3c69f83be4e9ae45c8a9c4dffab5264b32b7d2ab40531
+size 4876059416

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f17e213d6a457f95663be03ff084b5669209fa838aab136a07b16390bd3f7889
+size 4876059416

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1abb15cbf29f23c0e066113eb000b1c6c0153b84e8bee7c4e5b8de99ec4e1af9
+size 4876059416

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:325898b7d7af2080badf14f81fdf3a124b33095efc0275164640ad330cd79f74
+size 4876059416

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f15542e31b4a391d5509892f26adf638859eef1cfa65fd5305c0dff9cb139599
+size 4876059416

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d4cfb19476e814b82b21637f551abf76212c3148c9ff22bdc4bc1d8261b4175
+size 2123397800

model.safetensors.index.json

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

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "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 Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 16384,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_log.jsonl

@@ -0,0 +1,169 @@
+{"current_steps": 1, "total_steps": 168, "loss": 0.859, "lr": 5.882352941176471e-07, "epoch": 0.01775147928994083, "percentage": 0.6, "elapsed_time": "0:04:51", "remaining_time": "13:31:08"}
+{"current_steps": 2, "total_steps": 168, "loss": 1.0, "lr": 1.1764705882352942e-06, "epoch": 0.03550295857988166, "percentage": 1.19, "elapsed_time": "0:09:05", "remaining_time": "12:35:09"}
+{"current_steps": 3, "total_steps": 168, "loss": 0.9121, "lr": 1.7647058823529414e-06, "epoch": 0.05325443786982249, "percentage": 1.79, "elapsed_time": "0:13:20", "remaining_time": "12:13:56"}
+{"current_steps": 4, "total_steps": 168, "loss": 0.9152, "lr": 2.3529411764705885e-06, "epoch": 0.07100591715976332, "percentage": 2.38, "elapsed_time": "0:17:14", "remaining_time": "11:47:02"}
+{"current_steps": 5, "total_steps": 168, "loss": 0.9222, "lr": 2.9411764705882355e-06, "epoch": 0.08875739644970414, "percentage": 2.98, "elapsed_time": "0:20:44", "remaining_time": "11:16:18"}
+{"current_steps": 6, "total_steps": 168, "loss": 0.8336, "lr": 3.529411764705883e-06, "epoch": 0.10650887573964497, "percentage": 3.57, "elapsed_time": "0:24:20", "remaining_time": "10:57:10"}
+{"current_steps": 7, "total_steps": 168, "loss": 0.8381, "lr": 4.11764705882353e-06, "epoch": 0.1242603550295858, "percentage": 4.17, "elapsed_time": "0:28:33", "remaining_time": "10:56:51"}
+{"current_steps": 8, "total_steps": 168, "loss": 0.7733, "lr": 4.705882352941177e-06, "epoch": 0.14201183431952663, "percentage": 4.76, "elapsed_time": "0:32:57", "remaining_time": "10:59:10"}
+{"current_steps": 9, "total_steps": 168, "loss": 0.8138, "lr": 5.294117647058824e-06, "epoch": 0.15976331360946747, "percentage": 5.36, "elapsed_time": "0:36:29", "remaining_time": "10:44:40"}
+{"current_steps": 10, "total_steps": 168, "loss": 0.8417, "lr": 5.882352941176471e-06, "epoch": 0.17751479289940827, "percentage": 5.95, "elapsed_time": "0:40:10", "remaining_time": "10:34:46"}
+{"current_steps": 11, "total_steps": 168, "loss": 0.8356, "lr": 6.470588235294119e-06, "epoch": 0.1952662721893491, "percentage": 6.55, "elapsed_time": "0:43:48", "remaining_time": "10:25:21"}
+{"current_steps": 12, "total_steps": 168, "loss": 0.7625, "lr": 7.058823529411766e-06, "epoch": 0.21301775147928995, "percentage": 7.14, "elapsed_time": "0:47:47", "remaining_time": "10:21:11"}
+{"current_steps": 13, "total_steps": 168, "loss": 0.6551, "lr": 7.647058823529411e-06, "epoch": 0.23076923076923078, "percentage": 7.74, "elapsed_time": "0:50:32", "remaining_time": "10:02:32"}
+{"current_steps": 14, "total_steps": 168, "loss": 0.697, "lr": 8.23529411764706e-06, "epoch": 0.2485207100591716, "percentage": 8.33, "elapsed_time": "0:53:47", "remaining_time": "9:51:39"}
+{"current_steps": 15, "total_steps": 168, "loss": 0.7031, "lr": 8.823529411764707e-06, "epoch": 0.26627218934911245, "percentage": 8.93, "elapsed_time": "0:57:06", "remaining_time": "9:42:32"}
+{"current_steps": 16, "total_steps": 168, "loss": 0.7171, "lr": 9.411764705882354e-06, "epoch": 0.28402366863905326, "percentage": 9.52, "elapsed_time": "1:00:37", "remaining_time": "9:35:54"}
+{"current_steps": 17, "total_steps": 168, "loss": 0.6389, "lr": 1e-05, "epoch": 0.30177514792899407, "percentage": 10.12, "elapsed_time": "1:02:52", "remaining_time": "9:18:26"}
+{"current_steps": 18, "total_steps": 168, "loss": 0.7066, "lr": 9.998917893031615e-06, "epoch": 0.31952662721893493, "percentage": 10.71, "elapsed_time": "1:06:25", "remaining_time": "9:13:30"}
+{"current_steps": 19, "total_steps": 168, "loss": 0.6376, "lr": 9.995672040508656e-06, "epoch": 0.33727810650887574, "percentage": 11.31, "elapsed_time": "1:09:42", "remaining_time": "9:06:38"}
+{"current_steps": 20, "total_steps": 168, "loss": 0.6053, "lr": 9.990263847374976e-06, "epoch": 0.35502958579881655, "percentage": 11.9, "elapsed_time": "1:12:48", "remaining_time": "8:58:46"}
+{"current_steps": 21, "total_steps": 168, "loss": 0.597, "lr": 9.982695654527966e-06, "epoch": 0.3727810650887574, "percentage": 12.5, "elapsed_time": "1:15:18", "remaining_time": "8:47:11"}
+{"current_steps": 22, "total_steps": 168, "loss": 0.6535, "lr": 9.972970737805312e-06, "epoch": 0.3905325443786982, "percentage": 13.1, "elapsed_time": "1:18:59", "remaining_time": "8:44:11"}
+{"current_steps": 23, "total_steps": 168, "loss": 0.5634, "lr": 9.961093306567076e-06, "epoch": 0.40828402366863903, "percentage": 13.69, "elapsed_time": "1:22:55", "remaining_time": "8:42:50"}
+{"current_steps": 24, "total_steps": 168, "loss": 0.6174, "lr": 9.947068501873702e-06, "epoch": 0.4260355029585799, "percentage": 14.29, "elapsed_time": "1:25:31", "remaining_time": "8:33:07"}
+{"current_steps": 25, "total_steps": 168, "loss": 0.6219, "lr": 9.930902394260746e-06, "epoch": 0.4437869822485207, "percentage": 14.88, "elapsed_time": "1:29:01", "remaining_time": "8:29:14"}
+{"current_steps": 26, "total_steps": 168, "loss": 0.5234, "lr": 9.912601981111287e-06, "epoch": 0.46153846153846156, "percentage": 15.48, "elapsed_time": "1:32:24", "remaining_time": "8:24:41"}
+{"current_steps": 27, "total_steps": 168, "loss": 0.6021, "lr": 9.892175183627161e-06, "epoch": 0.47928994082840237, "percentage": 16.07, "elapsed_time": "1:35:43", "remaining_time": "8:19:52"}
+{"current_steps": 28, "total_steps": 168, "loss": 0.6139, "lr": 9.869630843400331e-06, "epoch": 0.4970414201183432, "percentage": 16.67, "elapsed_time": "1:38:58", "remaining_time": "8:14:52"}
+{"current_steps": 29, "total_steps": 168, "loss": 0.559, "lr": 9.844978718585855e-06, "epoch": 0.514792899408284, "percentage": 17.26, "elapsed_time": "1:42:13", "remaining_time": "8:09:58"}
+{"current_steps": 30, "total_steps": 168, "loss": 0.5757, "lr": 9.81822947967816e-06, "epoch": 0.5325443786982249, "percentage": 17.86, "elapsed_time": "1:44:40", "remaining_time": "8:01:30"}
+{"current_steps": 31, "total_steps": 168, "loss": 0.5677, "lr": 9.789394704892364e-06, "epoch": 0.5502958579881657, "percentage": 18.45, "elapsed_time": "1:46:55", "remaining_time": "7:52:31"}
+{"current_steps": 32, "total_steps": 168, "loss": 0.5718, "lr": 9.758486875152766e-06, "epoch": 0.5680473372781065, "percentage": 19.05, "elapsed_time": "1:49:15", "remaining_time": "7:44:20"}
+{"current_steps": 33, "total_steps": 168, "loss": 0.5719, "lr": 9.725519368690539e-06, "epoch": 0.5857988165680473, "percentage": 19.64, "elapsed_time": "1:51:36", "remaining_time": "7:36:35"}
+{"current_steps": 34, "total_steps": 168, "loss": 0.5494, "lr": 9.690506455253073e-06, "epoch": 0.6035502958579881, "percentage": 20.24, "elapsed_time": "1:54:11", "remaining_time": "7:30:03"}
+{"current_steps": 35, "total_steps": 168, "loss": 0.5455, "lr": 9.65346328992741e-06, "epoch": 0.621301775147929, "percentage": 20.83, "elapsed_time": "1:57:25", "remaining_time": "7:26:11"}
+{"current_steps": 36, "total_steps": 168, "loss": 0.5074, "lr": 9.614405906580486e-06, "epoch": 0.6390532544378699, "percentage": 21.43, "elapsed_time": "1:59:40", "remaining_time": "7:18:50"}
+{"current_steps": 37, "total_steps": 168, "loss": 0.5393, "lr": 9.573351210918976e-06, "epoch": 0.6568047337278107, "percentage": 22.02, "elapsed_time": "2:03:07", "remaining_time": "7:15:56"}
+{"current_steps": 38, "total_steps": 168, "loss": 0.5271, "lr": 9.53031697317178e-06, "epoch": 0.6745562130177515, "percentage": 22.62, "elapsed_time": "2:05:19", "remaining_time": "7:08:46"}
+{"current_steps": 39, "total_steps": 168, "loss": 0.5518, "lr": 9.485321820398321e-06, "epoch": 0.6923076923076923, "percentage": 23.21, "elapsed_time": "2:08:30", "remaining_time": "7:05:05"}
+{"current_steps": 40, "total_steps": 168, "loss": 0.5044, "lr": 9.43838522842594e-06, "epoch": 0.7100591715976331, "percentage": 23.81, "elapsed_time": "2:11:54", "remaining_time": "7:02:06"}
+{"current_steps": 41, "total_steps": 168, "loss": 0.582, "lr": 9.389527513419935e-06, "epoch": 0.727810650887574, "percentage": 24.4, "elapsed_time": "2:14:15", "remaining_time": "6:55:52"}
+{"current_steps": 42, "total_steps": 168, "loss": 0.5621, "lr": 9.338769823089853e-06, "epoch": 0.7455621301775148, "percentage": 25.0, "elapsed_time": "2:16:31", "remaining_time": "6:49:35"}
+{"current_steps": 43, "total_steps": 168, "loss": 0.5681, "lr": 9.286134127535859e-06, "epoch": 0.7633136094674556, "percentage": 25.6, "elapsed_time": "2:18:54", "remaining_time": "6:43:48"}
+{"current_steps": 44, "total_steps": 168, "loss": 0.5147, "lr": 9.231643209739128e-06, "epoch": 0.7810650887573964, "percentage": 26.19, "elapsed_time": "2:21:01", "remaining_time": "6:37:24"}
+{"current_steps": 45, "total_steps": 168, "loss": 0.509, "lr": 9.175320655700407e-06, "epoch": 0.7988165680473372, "percentage": 26.79, "elapsed_time": "2:23:40", "remaining_time": "6:32:42"}
+{"current_steps": 46, "total_steps": 168, "loss": 0.48, "lr": 9.117190844230971e-06, "epoch": 0.8165680473372781, "percentage": 27.38, "elapsed_time": "2:26:45", "remaining_time": "6:29:14"}
+{"current_steps": 47, "total_steps": 168, "loss": 0.512, "lr": 9.057278936400453e-06, "epoch": 0.834319526627219, "percentage": 27.98, "elapsed_time": "2:29:05", "remaining_time": "6:23:50"}
+{"current_steps": 48, "total_steps": 168, "loss": 0.4828, "lr": 8.99561086464603e-06, "epoch": 0.8520710059171598, "percentage": 28.57, "elapsed_time": "2:31:37", "remaining_time": "6:19:04"}
+{"current_steps": 49, "total_steps": 168, "loss": 0.4706, "lr": 8.932213321547769e-06, "epoch": 0.8698224852071006, "percentage": 29.17, "elapsed_time": "2:34:56", "remaining_time": "6:16:16"}
+{"current_steps": 50, "total_steps": 168, "loss": 0.5347, "lr": 8.86711374827494e-06, "epoch": 0.8875739644970414, "percentage": 29.76, "elapsed_time": "2:38:04", "remaining_time": "6:13:02"}
+{"current_steps": 51, "total_steps": 168, "loss": 0.5091, "lr": 8.800340322708291e-06, "epoch": 0.9053254437869822, "percentage": 30.36, "elapsed_time": "2:40:19", "remaining_time": "6:07:47"}
+{"current_steps": 52, "total_steps": 168, "loss": 0.5476, "lr": 8.73192194724347e-06, "epoch": 0.9230769230769231, "percentage": 30.95, "elapsed_time": "2:43:48", "remaining_time": "6:05:24"}
+{"current_steps": 53, "total_steps": 168, "loss": 0.5108, "lr": 8.661888236280813e-06, "epoch": 0.9408284023668639, "percentage": 31.55, "elapsed_time": "2:46:12", "remaining_time": "6:00:37"}
+{"current_steps": 54, "total_steps": 168, "loss": 0.5686, "lr": 8.590269503406986e-06, "epoch": 0.9585798816568047, "percentage": 32.14, "elapsed_time": "2:49:17", "remaining_time": "5:57:23"}
+{"current_steps": 55, "total_steps": 168, "loss": 0.4997, "lr": 8.517096748273951e-06, "epoch": 0.9763313609467456, "percentage": 32.74, "elapsed_time": "2:51:32", "remaining_time": "5:52:26"}
+{"current_steps": 56, "total_steps": 168, "loss": 0.4608, "lr": 8.442401643181e-06, "epoch": 0.9940828402366864, "percentage": 33.33, "elapsed_time": "2:53:43", "remaining_time": "5:47:26"}
+{"current_steps": 57, "total_steps": 168, "loss": 0.4543, "lr": 8.366216519365623e-06, "epoch": 1.0, "percentage": 33.93, "elapsed_time": "2:54:02", "remaining_time": "5:38:54"}
+{"current_steps": 58, "total_steps": 168, "loss": 0.4752, "lr": 8.288574353009164e-06, "epoch": 1.017751479289941, "percentage": 34.52, "elapsed_time": "2:56:30", "remaining_time": "5:34:44"}
+{"current_steps": 59, "total_steps": 168, "loss": 0.493, "lr": 8.20950875096333e-06, "epoch": 1.0355029585798816, "percentage": 35.12, "elapsed_time": "2:58:41", "remaining_time": "5:30:06"}
+{"current_steps": 60, "total_steps": 168, "loss": 0.4424, "lr": 8.129053936203688e-06, "epoch": 1.0532544378698225, "percentage": 35.71, "elapsed_time": "3:01:15", "remaining_time": "5:26:15"}
+{"current_steps": 61, "total_steps": 168, "loss": 0.5105, "lr": 8.04724473301652e-06, "epoch": 1.0710059171597632, "percentage": 36.31, "elapsed_time": "3:03:25", "remaining_time": "5:21:43"}
+{"current_steps": 62, "total_steps": 168, "loss": 0.4636, "lr": 7.964116551925365e-06, "epoch": 1.0887573964497042, "percentage": 36.9, "elapsed_time": "3:05:57", "remaining_time": "5:17:55"}
+{"current_steps": 63, "total_steps": 168, "loss": 0.4308, "lr": 7.879705374363831e-06, "epoch": 1.106508875739645, "percentage": 37.5, "elapsed_time": "3:08:13", "remaining_time": "5:13:42"}
+{"current_steps": 64, "total_steps": 168, "loss": 0.4514, "lr": 7.794047737101298e-06, "epoch": 1.1242603550295858, "percentage": 38.1, "elapsed_time": "3:10:33", "remaining_time": "5:09:40"}
+{"current_steps": 65, "total_steps": 168, "loss": 0.4329, "lr": 7.707180716428237e-06, "epoch": 1.1420118343195267, "percentage": 38.69, "elapsed_time": "3:13:15", "remaining_time": "5:06:14"}
+{"current_steps": 66, "total_steps": 168, "loss": 0.4527, "lr": 7.619141912108008e-06, "epoch": 1.1597633136094674, "percentage": 39.29, "elapsed_time": "3:15:52", "remaining_time": "5:02:43"}
+{"current_steps": 67, "total_steps": 168, "loss": 0.4663, "lr": 7.529969431102063e-06, "epoch": 1.1775147928994083, "percentage": 39.88, "elapsed_time": "3:18:13", "remaining_time": "4:58:48"}
+{"current_steps": 68, "total_steps": 168, "loss": 0.4019, "lr": 7.4397018710756415e-06, "epoch": 1.195266272189349, "percentage": 40.48, "elapsed_time": "3:21:02", "remaining_time": "4:55:38"}
+{"current_steps": 69, "total_steps": 168, "loss": 0.4751, "lr": 7.34837830369103e-06, "epoch": 1.21301775147929, "percentage": 41.07, "elapsed_time": "3:23:12", "remaining_time": "4:51:33"}
+{"current_steps": 70, "total_steps": 168, "loss": 0.3975, "lr": 7.2560382576956875e-06, "epoch": 1.2307692307692308, "percentage": 41.67, "elapsed_time": "3:25:38", "remaining_time": "4:47:54"}
+{"current_steps": 71, "total_steps": 168, "loss": 0.4074, "lr": 7.162721701812506e-06, "epoch": 1.2485207100591715, "percentage": 42.26, "elapsed_time": "3:27:52", "remaining_time": "4:44:00"}
+{"current_steps": 72, "total_steps": 168, "loss": 0.4657, "lr": 7.068469027439642e-06, "epoch": 1.2662721893491125, "percentage": 42.86, "elapsed_time": "3:30:31", "remaining_time": "4:40:41"}
+{"current_steps": 73, "total_steps": 168, "loss": 0.4549, "lr": 6.9733210311673826e-06, "epoch": 1.2840236686390534, "percentage": 43.45, "elapsed_time": "3:32:44", "remaining_time": "4:36:51"}
+{"current_steps": 74, "total_steps": 168, "loss": 0.4573, "lr": 6.8773188971196515e-06, "epoch": 1.301775147928994, "percentage": 44.05, "elapsed_time": "3:35:12", "remaining_time": "4:33:21"}
+{"current_steps": 75, "total_steps": 168, "loss": 0.4069, "lr": 6.780504179127735e-06, "epoch": 1.319526627218935, "percentage": 44.64, "elapsed_time": "3:37:34", "remaining_time": "4:29:47"}
+{"current_steps": 76, "total_steps": 168, "loss": 0.4515, "lr": 6.682918782744033e-06, "epoch": 1.3372781065088757, "percentage": 45.24, "elapsed_time": "3:39:47", "remaining_time": "4:26:03"}
+{"current_steps": 77, "total_steps": 168, "loss": 0.4605, "lr": 6.584604947103515e-06, "epoch": 1.3550295857988166, "percentage": 45.83, "elapsed_time": "3:41:54", "remaining_time": "4:22:15"}
+{"current_steps": 78, "total_steps": 168, "loss": 0.3898, "lr": 6.4856052266408375e-06, "epoch": 1.3727810650887573, "percentage": 46.43, "elapsed_time": "3:44:23", "remaining_time": "4:18:55"}
+{"current_steps": 79, "total_steps": 168, "loss": 0.4292, "lr": 6.385962472670953e-06, "epoch": 1.3905325443786982, "percentage": 47.02, "elapsed_time": "3:46:59", "remaining_time": "4:15:43"}
+{"current_steps": 80, "total_steps": 168, "loss": 0.4492, "lr": 6.28571981484123e-06, "epoch": 1.4082840236686391, "percentage": 47.62, "elapsed_time": "3:49:23", "remaining_time": "4:12:19"}
+{"current_steps": 81, "total_steps": 168, "loss": 0.4267, "lr": 6.184920642463095e-06, "epoch": 1.4260355029585798, "percentage": 48.21, "elapsed_time": "3:52:04", "remaining_time": "4:09:15"}
+{"current_steps": 82, "total_steps": 168, "loss": 0.426, "lr": 6.083608585731283e-06, "epoch": 1.4437869822485208, "percentage": 48.81, "elapsed_time": "3:54:32", "remaining_time": "4:05:58"}
+{"current_steps": 83, "total_steps": 168, "loss": 0.4598, "lr": 5.9818274968388225e-06, "epoch": 1.4615384615384617, "percentage": 49.4, "elapsed_time": "3:57:02", "remaining_time": "4:02:44"}
+{"current_steps": 84, "total_steps": 168, "loss": 0.4326, "lr": 5.879621430995927e-06, "epoch": 1.4792899408284024, "percentage": 50.0, "elapsed_time": "3:59:41", "remaining_time": "3:59:41"}
+{"current_steps": 85, "total_steps": 168, "loss": 0.4548, "lr": 5.777034627361025e-06, "epoch": 1.497041420118343, "percentage": 50.6, "elapsed_time": "4:02:12", "remaining_time": "3:56:30"}
+{"current_steps": 86, "total_steps": 168, "loss": 0.4053, "lr": 5.674111489892144e-06, "epoch": 1.514792899408284, "percentage": 51.19, "elapsed_time": "4:04:21", "remaining_time": "3:52:59"}
+{"current_steps": 87, "total_steps": 168, "loss": 0.4074, "lr": 5.570896568126994e-06, "epoch": 1.532544378698225, "percentage": 51.79, "elapsed_time": "4:07:18", "remaining_time": "3:50:14"}
+{"current_steps": 88, "total_steps": 168, "loss": 0.4656, "lr": 5.4674345379e-06, "epoch": 1.5502958579881656, "percentage": 52.38, "elapsed_time": "4:09:40", "remaining_time": "3:46:58"}
+{"current_steps": 89, "total_steps": 168, "loss": 0.4536, "lr": 5.36377018200472e-06, "epoch": 1.5680473372781065, "percentage": 52.98, "elapsed_time": "4:12:04", "remaining_time": "3:43:45"}
+{"current_steps": 90, "total_steps": 168, "loss": 0.4318, "lr": 5.259948370809902e-06, "epoch": 1.5857988165680474, "percentage": 53.57, "elapsed_time": "4:14:13", "remaining_time": "3:40:19"}
+{"current_steps": 91, "total_steps": 168, "loss": 0.4597, "lr": 5.156014042837696e-06, "epoch": 1.6035502958579881, "percentage": 54.17, "elapsed_time": "4:16:13", "remaining_time": "3:36:48"}
+{"current_steps": 92, "total_steps": 168, "loss": 0.4608, "lr": 5.052012185312322e-06, "epoch": 1.6213017751479288, "percentage": 54.76, "elapsed_time": "4:18:18", "remaining_time": "3:33:23"}
+{"current_steps": 93, "total_steps": 168, "loss": 0.4285, "lr": 4.94798781468768e-06, "epoch": 1.63905325443787, "percentage": 55.36, "elapsed_time": "4:20:33", "remaining_time": "3:30:07"}
+{"current_steps": 94, "total_steps": 168, "loss": 0.4281, "lr": 4.843985957162304e-06, "epoch": 1.6568047337278107, "percentage": 55.95, "elapsed_time": "4:23:13", "remaining_time": "3:27:13"}
+{"current_steps": 95, "total_steps": 168, "loss": 0.4722, "lr": 4.740051629190099e-06, "epoch": 1.6745562130177514, "percentage": 56.55, "elapsed_time": "4:25:22", "remaining_time": "3:23:55"}
+{"current_steps": 96, "total_steps": 168, "loss": 0.3911, "lr": 4.636229817995281e-06, "epoch": 1.6923076923076923, "percentage": 57.14, "elapsed_time": "4:27:40", "remaining_time": "3:20:45"}
+{"current_steps": 97, "total_steps": 168, "loss": 0.4207, "lr": 4.532565462099999e-06, "epoch": 1.7100591715976332, "percentage": 57.74, "elapsed_time": "4:29:58", "remaining_time": "3:17:36"}
+{"current_steps": 98, "total_steps": 168, "loss": 0.4096, "lr": 4.429103431873009e-06, "epoch": 1.727810650887574, "percentage": 58.33, "elapsed_time": "4:32:40", "remaining_time": "3:14:45"}
+{"current_steps": 99, "total_steps": 168, "loss": 0.4218, "lr": 4.3258885101078565e-06, "epoch": 1.7455621301775148, "percentage": 58.93, "elapsed_time": "4:35:21", "remaining_time": "3:11:54"}
+{"current_steps": 100, "total_steps": 168, "loss": 0.415, "lr": 4.2229653726389765e-06, "epoch": 1.7633136094674557, "percentage": 59.52, "elapsed_time": "4:37:51", "remaining_time": "3:08:56"}
+{"current_steps": 101, "total_steps": 168, "loss": 0.4377, "lr": 4.120378569004074e-06, "epoch": 1.7810650887573964, "percentage": 60.12, "elapsed_time": "4:40:23", "remaining_time": "3:05:59"}
+{"current_steps": 102, "total_steps": 168, "loss": 0.417, "lr": 4.018172503161179e-06, "epoch": 1.7988165680473371, "percentage": 60.71, "elapsed_time": "4:43:11", "remaining_time": "3:03:14"}
+{"current_steps": 103, "total_steps": 168, "loss": 0.4022, "lr": 3.9163914142687185e-06, "epoch": 1.816568047337278, "percentage": 61.31, "elapsed_time": "4:45:42", "remaining_time": "3:00:17"}
+{"current_steps": 104, "total_steps": 168, "loss": 0.4317, "lr": 3.815079357536907e-06, "epoch": 1.834319526627219, "percentage": 61.9, "elapsed_time": "4:48:11", "remaining_time": "2:57:21"}
+{"current_steps": 105, "total_steps": 168, "loss": 0.4247, "lr": 3.714280185158771e-06, "epoch": 1.8520710059171597, "percentage": 62.5, "elapsed_time": "4:50:36", "remaining_time": "2:54:21"}
+{"current_steps": 106, "total_steps": 168, "loss": 0.4348, "lr": 3.614037527329048e-06, "epoch": 1.8698224852071006, "percentage": 63.1, "elapsed_time": "4:53:11", "remaining_time": "2:51:29"}
+{"current_steps": 107, "total_steps": 168, "loss": 0.4222, "lr": 3.5143947733591633e-06, "epoch": 1.8875739644970415, "percentage": 63.69, "elapsed_time": "4:55:45", "remaining_time": "2:48:36"}
+{"current_steps": 108, "total_steps": 168, "loss": 0.4424, "lr": 3.4153950528964867e-06, "epoch": 1.9053254437869822, "percentage": 64.29, "elapsed_time": "4:58:06", "remaining_time": "2:45:37"}
+{"current_steps": 109, "total_steps": 168, "loss": 0.4477, "lr": 3.3170812172559695e-06, "epoch": 1.9230769230769231, "percentage": 64.88, "elapsed_time": "5:00:37", "remaining_time": "2:42:43"}
+{"current_steps": 110, "total_steps": 168, "loss": 0.3919, "lr": 3.2194958208722656e-06, "epoch": 1.940828402366864, "percentage": 65.48, "elapsed_time": "5:03:07", "remaining_time": "2:39:49"}
+{"current_steps": 111, "total_steps": 168, "loss": 0.4496, "lr": 3.1226811028803514e-06, "epoch": 1.9585798816568047, "percentage": 66.07, "elapsed_time": "5:05:39", "remaining_time": "2:36:57"}
+{"current_steps": 112, "total_steps": 168, "loss": 0.4264, "lr": 3.0266789688326187e-06, "epoch": 1.9763313609467454, "percentage": 66.67, "elapsed_time": "5:08:04", "remaining_time": "2:34:02"}
+{"current_steps": 113, "total_steps": 168, "loss": 0.4261, "lr": 2.9315309725603596e-06, "epoch": 1.9940828402366864, "percentage": 67.26, "elapsed_time": "5:10:42", "remaining_time": "2:31:13"}
+{"current_steps": 114, "total_steps": 168, "loss": 0.3394, "lr": 2.8372782981874964e-06, "epoch": 2.0, "percentage": 67.86, "elapsed_time": "5:11:04", "remaining_time": "2:27:20"}
+{"current_steps": 115, "total_steps": 168, "loss": 0.3895, "lr": 2.7439617423043146e-06, "epoch": 2.0177514792899407, "percentage": 68.45, "elapsed_time": "5:13:30", "remaining_time": "2:24:29"}
+{"current_steps": 116, "total_steps": 168, "loss": 0.395, "lr": 2.6516216963089698e-06, "epoch": 2.035502958579882, "percentage": 69.05, "elapsed_time": "5:16:06", "remaining_time": "2:21:42"}
+{"current_steps": 117, "total_steps": 168, "loss": 0.3928, "lr": 2.560298128924358e-06, "epoch": 2.0532544378698225, "percentage": 69.64, "elapsed_time": "5:18:42", "remaining_time": "2:18:55"}
+{"current_steps": 118, "total_steps": 168, "loss": 0.3912, "lr": 2.470030568897938e-06, "epoch": 2.0710059171597632, "percentage": 70.24, "elapsed_time": "5:21:01", "remaining_time": "2:16:01"}
+{"current_steps": 119, "total_steps": 168, "loss": 0.3735, "lr": 2.3808580878919948e-06, "epoch": 2.088757396449704, "percentage": 70.83, "elapsed_time": "5:23:08", "remaining_time": "2:13:03"}
+{"current_steps": 120, "total_steps": 168, "loss": 0.3829, "lr": 2.2928192835717642e-06, "epoch": 2.106508875739645, "percentage": 71.43, "elapsed_time": "5:25:37", "remaining_time": "2:10:14"}
+{"current_steps": 121, "total_steps": 168, "loss": 0.3912, "lr": 2.205952262898704e-06, "epoch": 2.1242603550295858, "percentage": 72.02, "elapsed_time": "5:27:39", "remaining_time": "2:07:16"}
+{"current_steps": 122, "total_steps": 168, "loss": 0.3573, "lr": 2.120294625636171e-06, "epoch": 2.1420118343195265, "percentage": 72.62, "elapsed_time": "5:29:59", "remaining_time": "2:04:25"}
+{"current_steps": 123, "total_steps": 168, "loss": 0.3767, "lr": 2.0358834480746363e-06, "epoch": 2.1597633136094676, "percentage": 73.21, "elapsed_time": "5:32:27", "remaining_time": "2:01:37"}
+{"current_steps": 124, "total_steps": 168, "loss": 0.3819, "lr": 1.9527552669834797e-06, "epoch": 2.1775147928994083, "percentage": 73.81, "elapsed_time": "5:35:15", "remaining_time": "1:58:57"}
+{"current_steps": 125, "total_steps": 168, "loss": 0.3865, "lr": 1.8709460637963123e-06, "epoch": 2.195266272189349, "percentage": 74.4, "elapsed_time": "5:37:34", "remaining_time": "1:56:07"}
+{"current_steps": 126, "total_steps": 168, "loss": 0.366, "lr": 1.7904912490366723e-06, "epoch": 2.21301775147929, "percentage": 75.0, "elapsed_time": "5:40:02", "remaining_time": "1:53:20"}
+{"current_steps": 127, "total_steps": 168, "loss": 0.3686, "lr": 1.711425646990838e-06, "epoch": 2.230769230769231, "percentage": 75.6, "elapsed_time": "5:42:32", "remaining_time": "1:50:34"}
+{"current_steps": 128, "total_steps": 168, "loss": 0.3727, "lr": 1.6337834806343783e-06, "epoch": 2.2485207100591715, "percentage": 76.19, "elapsed_time": "5:44:53", "remaining_time": "1:47:46"}
+{"current_steps": 129, "total_steps": 168, "loss": 0.3747, "lr": 1.557598356819e-06, "epoch": 2.2662721893491122, "percentage": 76.79, "elapsed_time": "5:47:27", "remaining_time": "1:45:02"}
+{"current_steps": 130, "total_steps": 168, "loss": 0.381, "lr": 1.482903251726049e-06, "epoch": 2.2840236686390534, "percentage": 77.38, "elapsed_time": "5:49:33", "remaining_time": "1:42:10"}
+{"current_steps": 131, "total_steps": 168, "loss": 0.3897, "lr": 1.409730496593016e-06, "epoch": 2.301775147928994, "percentage": 77.98, "elapsed_time": "5:51:46", "remaining_time": "1:39:21"}
+{"current_steps": 132, "total_steps": 168, "loss": 0.385, "lr": 1.3381117637191887e-06, "epoch": 2.3195266272189348, "percentage": 78.57, "elapsed_time": "5:54:03", "remaining_time": "1:36:33"}
+{"current_steps": 133, "total_steps": 168, "loss": 0.3677, "lr": 1.2680780527565313e-06, "epoch": 2.337278106508876, "percentage": 79.17, "elapsed_time": "5:56:39", "remaining_time": "1:33:51"}
+{"current_steps": 134, "total_steps": 168, "loss": 0.3758, "lr": 1.1996596772917091e-06, "epoch": 2.3550295857988166, "percentage": 79.76, "elapsed_time": "5:58:48", "remaining_time": "1:31:02"}
+{"current_steps": 135, "total_steps": 168, "loss": 0.3774, "lr": 1.132886251725061e-06, "epoch": 2.3727810650887573, "percentage": 80.36, "elapsed_time": "6:01:27", "remaining_time": "1:28:21"}
+{"current_steps": 136, "total_steps": 168, "loss": 0.4059, "lr": 1.0677866784522317e-06, "epoch": 2.390532544378698, "percentage": 80.95, "elapsed_time": "6:03:23", "remaining_time": "1:25:30"}
+{"current_steps": 137, "total_steps": 168, "loss": 0.3537, "lr": 1.004389135353972e-06, "epoch": 2.408284023668639, "percentage": 81.55, "elapsed_time": "6:05:26", "remaining_time": "1:22:41"}
+{"current_steps": 138, "total_steps": 168, "loss": 0.3986, "lr": 9.427210635995482e-07, "epoch": 2.42603550295858, "percentage": 82.14, "elapsed_time": "6:07:32", "remaining_time": "1:19:53"}
+{"current_steps": 139, "total_steps": 168, "loss": 0.3523, "lr": 8.828091557690288e-07, "epoch": 2.4437869822485205, "percentage": 82.74, "elapsed_time": "6:09:35", "remaining_time": "1:17:06"}
+{"current_steps": 140, "total_steps": 168, "loss": 0.4077, "lr": 8.246793442995954e-07, "epoch": 2.4615384615384617, "percentage": 83.33, "elapsed_time": "6:12:13", "remaining_time": "1:14:26"}
+{"current_steps": 141, "total_steps": 168, "loss": 0.3581, "lr": 7.68356790260873e-07, "epoch": 2.4792899408284024, "percentage": 83.93, "elapsed_time": "6:14:24", "remaining_time": "1:11:41"}
+{"current_steps": 142, "total_steps": 168, "loss": 0.3786, "lr": 7.138658724641417e-07, "epoch": 2.497041420118343, "percentage": 84.52, "elapsed_time": "6:16:33", "remaining_time": "1:08:56"}
+{"current_steps": 143, "total_steps": 168, "loss": 0.3925, "lr": 6.612301769101464e-07, "epoch": 2.5147928994082838, "percentage": 85.12, "elapsed_time": "6:18:46", "remaining_time": "1:06:13"}
+{"current_steps": 144, "total_steps": 168, "loss": 0.36, "lr": 6.104724865800665e-07, "epoch": 2.532544378698225, "percentage": 85.71, "elapsed_time": "6:21:01", "remaining_time": "1:03:30"}
+{"current_steps": 145, "total_steps": 168, "loss": 0.3716, "lr": 5.616147715740611e-07, "epoch": 2.5502958579881656, "percentage": 86.31, "elapsed_time": "6:23:10", "remaining_time": "1:00:46"}
+{"current_steps": 146, "total_steps": 168, "loss": 0.3817, "lr": 5.146781796016798e-07, "epoch": 2.5680473372781067, "percentage": 86.9, "elapsed_time": "6:25:10", "remaining_time": "0:58:02"}
+{"current_steps": 147, "total_steps": 168, "loss": 0.3484, "lr": 4.696830268282204e-07, "epoch": 2.5857988165680474, "percentage": 87.5, "elapsed_time": "6:27:15", "remaining_time": "0:55:19"}
+{"current_steps": 148, "total_steps": 168, "loss": 0.3723, "lr": 4.2664878908102556e-07, "epoch": 2.603550295857988, "percentage": 88.1, "elapsed_time": "6:29:26", "remaining_time": "0:52:37"}
+{"current_steps": 149, "total_steps": 168, "loss": 0.3875, "lr": 3.855940934195146e-07, "epoch": 2.621301775147929, "percentage": 88.69, "elapsed_time": "6:31:37", "remaining_time": "0:49:56"}
+{"current_steps": 150, "total_steps": 168, "loss": 0.3572, "lr": 3.4653671007259084e-07, "epoch": 2.63905325443787, "percentage": 89.29, "elapsed_time": "6:33:35", "remaining_time": "0:47:13"}
+{"current_steps": 151, "total_steps": 168, "loss": 0.3911, "lr": 3.0949354474692937e-07, "epoch": 2.6568047337278107, "percentage": 89.88, "elapsed_time": "6:36:05", "remaining_time": "0:44:35"}
+{"current_steps": 152, "total_steps": 168, "loss": 0.3559, "lr": 2.7448063130946224e-07, "epoch": 2.6745562130177514, "percentage": 90.48, "elapsed_time": "6:38:23", "remaining_time": "0:41:56"}
+{"current_steps": 153, "total_steps": 168, "loss": 0.3908, "lr": 2.4151312484723465e-07, "epoch": 2.6923076923076925, "percentage": 91.07, "elapsed_time": "6:40:44", "remaining_time": "0:39:17"}
+{"current_steps": 154, "total_steps": 168, "loss": 0.3657, "lr": 2.106052951076365e-07, "epoch": 2.710059171597633, "percentage": 91.67, "elapsed_time": "6:42:50", "remaining_time": "0:36:37"}
+{"current_steps": 155, "total_steps": 168, "loss": 0.3359, "lr": 1.8177052032184285e-07, "epoch": 2.727810650887574, "percentage": 92.26, "elapsed_time": "6:45:04", "remaining_time": "0:33:58"}
+{"current_steps": 156, "total_steps": 168, "loss": 0.3432, "lr": 1.5502128141414496e-07, "epoch": 2.7455621301775146, "percentage": 92.86, "elapsed_time": "6:47:33", "remaining_time": "0:31:21"}
+{"current_steps": 157, "total_steps": 168, "loss": 0.3723, "lr": 1.303691565996712e-07, "epoch": 2.7633136094674557, "percentage": 93.45, "elapsed_time": "6:49:41", "remaining_time": "0:28:42"}
+{"current_steps": 158, "total_steps": 168, "loss": 0.3844, "lr": 1.0782481637284014e-07, "epoch": 2.7810650887573964, "percentage": 94.05, "elapsed_time": "6:51:40", "remaining_time": "0:26:03"}
+{"current_steps": 159, "total_steps": 168, "loss": 0.3602, "lr": 8.739801888871468e-08, "epoch": 2.798816568047337, "percentage": 94.64, "elapsed_time": "6:53:40", "remaining_time": "0:23:24"}
+{"current_steps": 160, "total_steps": 168, "loss": 0.3646, "lr": 6.909760573925561e-08, "epoch": 2.8165680473372783, "percentage": 95.24, "elapsed_time": "6:55:40", "remaining_time": "0:20:47"}
+{"current_steps": 161, "total_steps": 168, "loss": 0.3906, "lr": 5.2931498126298495e-08, "epoch": 2.834319526627219, "percentage": 95.83, "elapsed_time": "6:57:47", "remaining_time": "0:18:09"}
+{"current_steps": 162, "total_steps": 168, "loss": 0.3849, "lr": 3.890669343292464e-08, "epoch": 2.8520710059171597, "percentage": 96.43, "elapsed_time": "7:00:24", "remaining_time": "0:15:34"}
+{"current_steps": 163, "total_steps": 168, "loss": 0.3647, "lr": 2.702926219468882e-08, "epoch": 2.8698224852071004, "percentage": 97.02, "elapsed_time": "7:02:29", "remaining_time": "0:12:57"}
+{"current_steps": 164, "total_steps": 168, "loss": 0.334, "lr": 1.7304345472035634e-08, "epoch": 2.8875739644970415, "percentage": 97.62, "elapsed_time": "7:04:56", "remaining_time": "0:10:21"}
+{"current_steps": 165, "total_steps": 168, "loss": 0.3896, "lr": 9.73615262502503e-09, "epoch": 2.905325443786982, "percentage": 98.21, "elapsed_time": "7:07:29", "remaining_time": "0:07:46"}
+{"current_steps": 166, "total_steps": 168, "loss": 0.3714, "lr": 4.327959491344791e-09, "epoch": 2.9230769230769234, "percentage": 98.81, "elapsed_time": "7:09:32", "remaining_time": "0:05:10"}
+{"current_steps": 167, "total_steps": 168, "loss": 0.3417, "lr": 1.082106968385288e-09, "epoch": 2.940828402366864, "percentage": 99.4, "elapsed_time": "7:11:59", "remaining_time": "0:02:35"}
+{"current_steps": 168, "total_steps": 168, "loss": 0.3881, "lr": 0.0, "epoch": 2.9585798816568047, "percentage": 100.0, "elapsed_time": "7:14:11", "remaining_time": "0:00:00"}
+{"current_steps": 168, "total_steps": 168, "epoch": 2.9585798816568047, "percentage": 100.0, "elapsed_time": "7:20:42", "remaining_time": "0:00:00"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d22176a387481f5af6ce80b37752f3a635e429910b70daed82940c1814174ea1
+size 8056