sedrickkeh commited on
Commit
20c59aa
·
verified ·
1 Parent(s): c652b33

Training in progress, epoch 0

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Qwen/Qwen2.5-7B",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151643,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 3584,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 18944,
13
+ "max_position_embeddings": 131072,
14
+ "max_window_layers": 28,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 28,
17
+ "num_hidden_layers": 28,
18
+ "num_key_value_heads": 4,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": null,
21
+ "rope_theta": 1000000.0,
22
+ "sliding_window": null,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.46.1",
26
+ "use_cache": false,
27
+ "use_mrope": false,
28
+ "use_sliding_window": false,
29
+ "vocab_size": 152064
30
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ee5139f41a182dba4a775ed56c035b7117381ccea51f265b1ac7e53e18fba82
3
+ size 4877660776
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e43525a1ef1114550b7f0676ff1ebb388651f8c53a1e7639870d074c89a29461
3
+ size 4932751008
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63f4cf96383069b35f750194a0cd2dbb9b2ca0b81ff466b9762284bf7a41bf98
3
+ size 4330865200
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b62c8f9fc4e2aad92644ed13e59abfbc27d774b96c5225b2bb837ca08bdf3ab
3
+ size 1089994880
model.safetensors.index.json ADDED
@@ -0,0 +1,346 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 15231233024
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
19
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
28
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
29
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
30
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
31
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
32
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
38
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
41
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
43
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
50
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
53
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
55
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
62
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
65
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
67
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
74
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
77
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
79
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
86
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
89
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
91
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
98
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
101
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
103
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
110
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
113
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
115
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
117
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
118
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
119
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
120
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
121
+ "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
122
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
123
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
124
+ "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
125
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
126
+ "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
127
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
133
+ "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
134
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
135
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
136
+ "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
137
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
138
+ "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
139
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
140
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
146
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
149
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
151
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
153
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
154
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
155
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
156
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
157
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
158
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
159
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
160
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
161
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
162
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
163
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
164
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
170
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
173
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
175
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
182
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
185
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
187
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
194
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
197
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
199
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
206
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
209
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
211
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
216
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
217
+ "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
218
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
219
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
220
+ "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
221
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
222
+ "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
223
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
224
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
230
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
233
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
234
+ "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
235
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
238
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
242
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
243
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
244
+ "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
245
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
246
+ "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
247
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
248
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
249
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
250
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
251
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
252
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
253
+ "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
254
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
255
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
256
+ "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
257
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
258
+ "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
259
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
260
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
266
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
269
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
271
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
278
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
281
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
283
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
288
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
289
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
290
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
291
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
292
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
293
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
294
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
295
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
296
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
297
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
298
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
299
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
300
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
301
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
302
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
303
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
304
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
305
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
306
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
307
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
308
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
309
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
310
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
311
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
312
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
313
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
314
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
315
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
316
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
317
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
318
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
319
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
320
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
321
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
322
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
323
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
324
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
325
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
326
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
327
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
328
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
329
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
330
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
331
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
332
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
333
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
334
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
335
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
336
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
337
+ "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
338
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
339
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
340
+ "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
341
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
342
+ "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
343
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
344
+ "model.norm.weight": "model-00003-of-00004.safetensors"
345
+ }
346
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "padding_side": "right",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,179 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 10, "total_steps": 5316, "loss": 0.5781, "lr": 5e-06, "epoch": 0.005641748942172073, "percentage": 0.19, "elapsed_time": "0:02:15", "remaining_time": "19:58:17"}
2
+ {"current_steps": 20, "total_steps": 5316, "loss": 0.5493, "lr": 5e-06, "epoch": 0.011283497884344146, "percentage": 0.38, "elapsed_time": "0:04:26", "remaining_time": "19:36:14"}
3
+ {"current_steps": 30, "total_steps": 5316, "loss": 0.5144, "lr": 5e-06, "epoch": 0.01692524682651622, "percentage": 0.56, "elapsed_time": "0:06:37", "remaining_time": "19:27:03"}
4
+ {"current_steps": 40, "total_steps": 5316, "loss": 0.5132, "lr": 5e-06, "epoch": 0.022566995768688293, "percentage": 0.75, "elapsed_time": "0:08:48", "remaining_time": "19:21:13"}
5
+ {"current_steps": 50, "total_steps": 5316, "loss": 0.4958, "lr": 5e-06, "epoch": 0.028208744710860368, "percentage": 0.94, "elapsed_time": "0:10:58", "remaining_time": "19:16:41"}
6
+ {"current_steps": 60, "total_steps": 5316, "loss": 0.5032, "lr": 5e-06, "epoch": 0.03385049365303244, "percentage": 1.13, "elapsed_time": "0:13:09", "remaining_time": "19:13:06"}
7
+ {"current_steps": 70, "total_steps": 5316, "loss": 0.4798, "lr": 5e-06, "epoch": 0.039492242595204514, "percentage": 1.32, "elapsed_time": "0:15:20", "remaining_time": "19:09:47"}
8
+ {"current_steps": 80, "total_steps": 5316, "loss": 0.4888, "lr": 5e-06, "epoch": 0.045133991537376586, "percentage": 1.5, "elapsed_time": "0:17:31", "remaining_time": "19:06:38"}
9
+ {"current_steps": 90, "total_steps": 5316, "loss": 0.4811, "lr": 5e-06, "epoch": 0.05077574047954866, "percentage": 1.69, "elapsed_time": "0:19:41", "remaining_time": "19:03:50"}
10
+ {"current_steps": 100, "total_steps": 5316, "loss": 0.468, "lr": 5e-06, "epoch": 0.056417489421720736, "percentage": 1.88, "elapsed_time": "0:21:52", "remaining_time": "19:01:07"}
11
+ {"current_steps": 110, "total_steps": 5316, "loss": 0.4829, "lr": 5e-06, "epoch": 0.06205923836389281, "percentage": 2.07, "elapsed_time": "0:24:03", "remaining_time": "18:58:28"}
12
+ {"current_steps": 120, "total_steps": 5316, "loss": 0.4737, "lr": 5e-06, "epoch": 0.06770098730606489, "percentage": 2.26, "elapsed_time": "0:26:13", "remaining_time": "18:55:52"}
13
+ {"current_steps": 130, "total_steps": 5316, "loss": 0.4787, "lr": 5e-06, "epoch": 0.07334273624823695, "percentage": 2.45, "elapsed_time": "0:28:24", "remaining_time": "18:53:24"}
14
+ {"current_steps": 140, "total_steps": 5316, "loss": 0.4848, "lr": 5e-06, "epoch": 0.07898448519040903, "percentage": 2.63, "elapsed_time": "0:30:35", "remaining_time": "18:51:01"}
15
+ {"current_steps": 150, "total_steps": 5316, "loss": 0.4776, "lr": 5e-06, "epoch": 0.0846262341325811, "percentage": 2.82, "elapsed_time": "0:32:46", "remaining_time": "18:48:38"}
16
+ {"current_steps": 160, "total_steps": 5316, "loss": 0.4765, "lr": 5e-06, "epoch": 0.09026798307475317, "percentage": 3.01, "elapsed_time": "0:34:57", "remaining_time": "18:46:17"}
17
+ {"current_steps": 170, "total_steps": 5316, "loss": 0.4744, "lr": 5e-06, "epoch": 0.09590973201692525, "percentage": 3.2, "elapsed_time": "0:37:07", "remaining_time": "18:43:58"}
18
+ {"current_steps": 180, "total_steps": 5316, "loss": 0.4789, "lr": 5e-06, "epoch": 0.10155148095909731, "percentage": 3.39, "elapsed_time": "0:39:18", "remaining_time": "18:41:41"}
19
+ {"current_steps": 190, "total_steps": 5316, "loss": 0.4763, "lr": 5e-06, "epoch": 0.1071932299012694, "percentage": 3.57, "elapsed_time": "0:41:29", "remaining_time": "18:39:25"}
20
+ {"current_steps": 200, "total_steps": 5316, "loss": 0.4687, "lr": 5e-06, "epoch": 0.11283497884344147, "percentage": 3.76, "elapsed_time": "0:43:40", "remaining_time": "18:37:07"}
21
+ {"current_steps": 210, "total_steps": 5316, "loss": 0.4615, "lr": 5e-06, "epoch": 0.11847672778561354, "percentage": 3.95, "elapsed_time": "0:45:51", "remaining_time": "18:34:51"}
22
+ {"current_steps": 220, "total_steps": 5316, "loss": 0.4713, "lr": 5e-06, "epoch": 0.12411847672778561, "percentage": 4.14, "elapsed_time": "0:48:01", "remaining_time": "18:32:35"}
23
+ {"current_steps": 230, "total_steps": 5316, "loss": 0.475, "lr": 5e-06, "epoch": 0.12976022566995768, "percentage": 4.33, "elapsed_time": "0:50:12", "remaining_time": "18:30:19"}
24
+ {"current_steps": 240, "total_steps": 5316, "loss": 0.4739, "lr": 5e-06, "epoch": 0.13540197461212977, "percentage": 4.51, "elapsed_time": "0:52:23", "remaining_time": "18:28:02"}
25
+ {"current_steps": 250, "total_steps": 5316, "loss": 0.4649, "lr": 5e-06, "epoch": 0.14104372355430184, "percentage": 4.7, "elapsed_time": "0:54:34", "remaining_time": "18:25:47"}
26
+ {"current_steps": 260, "total_steps": 5316, "loss": 0.4917, "lr": 5e-06, "epoch": 0.1466854724964739, "percentage": 4.89, "elapsed_time": "0:56:45", "remaining_time": "18:23:36"}
27
+ {"current_steps": 270, "total_steps": 5316, "loss": 0.4493, "lr": 5e-06, "epoch": 0.152327221438646, "percentage": 5.08, "elapsed_time": "0:58:55", "remaining_time": "18:21:23"}
28
+ {"current_steps": 280, "total_steps": 5316, "loss": 0.4664, "lr": 5e-06, "epoch": 0.15796897038081806, "percentage": 5.27, "elapsed_time": "1:01:07", "remaining_time": "18:19:14"}
29
+ {"current_steps": 290, "total_steps": 5316, "loss": 0.459, "lr": 5e-06, "epoch": 0.16361071932299012, "percentage": 5.46, "elapsed_time": "1:03:18", "remaining_time": "18:17:03"}
30
+ {"current_steps": 300, "total_steps": 5316, "loss": 0.4552, "lr": 5e-06, "epoch": 0.1692524682651622, "percentage": 5.64, "elapsed_time": "1:05:28", "remaining_time": "18:14:52"}
31
+ {"current_steps": 310, "total_steps": 5316, "loss": 0.4596, "lr": 5e-06, "epoch": 0.17489421720733428, "percentage": 5.83, "elapsed_time": "1:07:39", "remaining_time": "18:12:40"}
32
+ {"current_steps": 320, "total_steps": 5316, "loss": 0.4782, "lr": 5e-06, "epoch": 0.18053596614950634, "percentage": 6.02, "elapsed_time": "1:09:50", "remaining_time": "18:10:30"}
33
+ {"current_steps": 330, "total_steps": 5316, "loss": 0.4645, "lr": 5e-06, "epoch": 0.1861777150916784, "percentage": 6.21, "elapsed_time": "1:12:01", "remaining_time": "18:08:18"}
34
+ {"current_steps": 340, "total_steps": 5316, "loss": 0.4647, "lr": 5e-06, "epoch": 0.1918194640338505, "percentage": 6.4, "elapsed_time": "1:14:12", "remaining_time": "18:06:06"}
35
+ {"current_steps": 350, "total_steps": 5316, "loss": 0.4665, "lr": 5e-06, "epoch": 0.19746121297602257, "percentage": 6.58, "elapsed_time": "1:16:23", "remaining_time": "18:03:53"}
36
+ {"current_steps": 360, "total_steps": 5316, "loss": 0.4707, "lr": 5e-06, "epoch": 0.20310296191819463, "percentage": 6.77, "elapsed_time": "1:18:34", "remaining_time": "18:01:40"}
37
+ {"current_steps": 370, "total_steps": 5316, "loss": 0.4626, "lr": 5e-06, "epoch": 0.20874471086036672, "percentage": 6.96, "elapsed_time": "1:20:45", "remaining_time": "17:59:30"}
38
+ {"current_steps": 380, "total_steps": 5316, "loss": 0.4605, "lr": 5e-06, "epoch": 0.2143864598025388, "percentage": 7.15, "elapsed_time": "1:22:56", "remaining_time": "17:57:20"}
39
+ {"current_steps": 390, "total_steps": 5316, "loss": 0.4582, "lr": 5e-06, "epoch": 0.22002820874471085, "percentage": 7.34, "elapsed_time": "1:25:07", "remaining_time": "17:55:10"}
40
+ {"current_steps": 400, "total_steps": 5316, "loss": 0.4655, "lr": 5e-06, "epoch": 0.22566995768688294, "percentage": 7.52, "elapsed_time": "1:27:18", "remaining_time": "17:52:59"}
41
+ {"current_steps": 410, "total_steps": 5316, "loss": 0.4495, "lr": 5e-06, "epoch": 0.231311706629055, "percentage": 7.71, "elapsed_time": "1:29:29", "remaining_time": "17:50:48"}
42
+ {"current_steps": 420, "total_steps": 5316, "loss": 0.4529, "lr": 5e-06, "epoch": 0.23695345557122707, "percentage": 7.9, "elapsed_time": "1:31:40", "remaining_time": "17:48:37"}
43
+ {"current_steps": 430, "total_steps": 5316, "loss": 0.4569, "lr": 5e-06, "epoch": 0.24259520451339917, "percentage": 8.09, "elapsed_time": "1:33:51", "remaining_time": "17:46:26"}
44
+ {"current_steps": 440, "total_steps": 5316, "loss": 0.4613, "lr": 5e-06, "epoch": 0.24823695345557123, "percentage": 8.28, "elapsed_time": "1:36:02", "remaining_time": "17:44:15"}
45
+ {"current_steps": 450, "total_steps": 5316, "loss": 0.4472, "lr": 5e-06, "epoch": 0.2538787023977433, "percentage": 8.47, "elapsed_time": "1:38:13", "remaining_time": "17:42:05"}
46
+ {"current_steps": 460, "total_steps": 5316, "loss": 0.448, "lr": 5e-06, "epoch": 0.25952045133991536, "percentage": 8.65, "elapsed_time": "1:40:24", "remaining_time": "17:39:54"}
47
+ {"current_steps": 470, "total_steps": 5316, "loss": 0.4502, "lr": 5e-06, "epoch": 0.2651622002820874, "percentage": 8.84, "elapsed_time": "1:42:35", "remaining_time": "17:37:42"}
48
+ {"current_steps": 480, "total_steps": 5316, "loss": 0.4572, "lr": 5e-06, "epoch": 0.27080394922425954, "percentage": 9.03, "elapsed_time": "1:44:45", "remaining_time": "17:35:29"}
49
+ {"current_steps": 490, "total_steps": 5316, "loss": 0.4616, "lr": 5e-06, "epoch": 0.2764456981664316, "percentage": 9.22, "elapsed_time": "1:46:56", "remaining_time": "17:33:16"}
50
+ {"current_steps": 500, "total_steps": 5316, "loss": 0.4659, "lr": 5e-06, "epoch": 0.2820874471086037, "percentage": 9.41, "elapsed_time": "1:49:07", "remaining_time": "17:31:04"}
51
+ {"current_steps": 510, "total_steps": 5316, "loss": 0.4582, "lr": 5e-06, "epoch": 0.28772919605077574, "percentage": 9.59, "elapsed_time": "1:51:18", "remaining_time": "17:28:52"}
52
+ {"current_steps": 520, "total_steps": 5316, "loss": 0.4628, "lr": 5e-06, "epoch": 0.2933709449929478, "percentage": 9.78, "elapsed_time": "1:53:29", "remaining_time": "17:26:39"}
53
+ {"current_steps": 530, "total_steps": 5316, "loss": 0.4478, "lr": 5e-06, "epoch": 0.29901269393511987, "percentage": 9.97, "elapsed_time": "1:55:39", "remaining_time": "17:24:27"}
54
+ {"current_steps": 540, "total_steps": 5316, "loss": 0.4451, "lr": 5e-06, "epoch": 0.304654442877292, "percentage": 10.16, "elapsed_time": "1:57:50", "remaining_time": "17:22:14"}
55
+ {"current_steps": 550, "total_steps": 5316, "loss": 0.4702, "lr": 5e-06, "epoch": 0.31029619181946405, "percentage": 10.35, "elapsed_time": "2:00:01", "remaining_time": "17:20:02"}
56
+ {"current_steps": 560, "total_steps": 5316, "loss": 0.4561, "lr": 5e-06, "epoch": 0.3159379407616361, "percentage": 10.53, "elapsed_time": "2:02:11", "remaining_time": "17:17:48"}
57
+ {"current_steps": 570, "total_steps": 5316, "loss": 0.4457, "lr": 5e-06, "epoch": 0.3215796897038082, "percentage": 10.72, "elapsed_time": "2:04:22", "remaining_time": "17:15:36"}
58
+ {"current_steps": 580, "total_steps": 5316, "loss": 0.4498, "lr": 5e-06, "epoch": 0.32722143864598024, "percentage": 10.91, "elapsed_time": "2:06:33", "remaining_time": "17:13:24"}
59
+ {"current_steps": 590, "total_steps": 5316, "loss": 0.4698, "lr": 5e-06, "epoch": 0.3328631875881523, "percentage": 11.1, "elapsed_time": "2:08:44", "remaining_time": "17:11:12"}
60
+ {"current_steps": 600, "total_steps": 5316, "loss": 0.4524, "lr": 5e-06, "epoch": 0.3385049365303244, "percentage": 11.29, "elapsed_time": "2:10:55", "remaining_time": "17:09:00"}
61
+ {"current_steps": 610, "total_steps": 5316, "loss": 0.4481, "lr": 5e-06, "epoch": 0.3441466854724965, "percentage": 11.47, "elapsed_time": "2:13:05", "remaining_time": "17:06:47"}
62
+ {"current_steps": 620, "total_steps": 5316, "loss": 0.4522, "lr": 5e-06, "epoch": 0.34978843441466856, "percentage": 11.66, "elapsed_time": "2:15:16", "remaining_time": "17:04:36"}
63
+ {"current_steps": 630, "total_steps": 5316, "loss": 0.4529, "lr": 5e-06, "epoch": 0.3554301833568406, "percentage": 11.85, "elapsed_time": "2:17:27", "remaining_time": "17:02:23"}
64
+ {"current_steps": 640, "total_steps": 5316, "loss": 0.4585, "lr": 5e-06, "epoch": 0.3610719322990127, "percentage": 12.04, "elapsed_time": "2:19:37", "remaining_time": "17:00:11"}
65
+ {"current_steps": 650, "total_steps": 5316, "loss": 0.4531, "lr": 5e-06, "epoch": 0.36671368124118475, "percentage": 12.23, "elapsed_time": "2:21:48", "remaining_time": "16:57:59"}
66
+ {"current_steps": 660, "total_steps": 5316, "loss": 0.4499, "lr": 5e-06, "epoch": 0.3723554301833568, "percentage": 12.42, "elapsed_time": "2:23:59", "remaining_time": "16:55:46"}
67
+ {"current_steps": 670, "total_steps": 5316, "loss": 0.4591, "lr": 5e-06, "epoch": 0.37799717912552894, "percentage": 12.6, "elapsed_time": "2:26:10", "remaining_time": "16:53:34"}
68
+ {"current_steps": 680, "total_steps": 5316, "loss": 0.4617, "lr": 5e-06, "epoch": 0.383638928067701, "percentage": 12.79, "elapsed_time": "2:28:20", "remaining_time": "16:51:21"}
69
+ {"current_steps": 690, "total_steps": 5316, "loss": 0.4419, "lr": 5e-06, "epoch": 0.38928067700987307, "percentage": 12.98, "elapsed_time": "2:30:31", "remaining_time": "16:49:09"}
70
+ {"current_steps": 700, "total_steps": 5316, "loss": 0.4546, "lr": 5e-06, "epoch": 0.39492242595204513, "percentage": 13.17, "elapsed_time": "2:32:41", "remaining_time": "16:46:56"}
71
+ {"current_steps": 710, "total_steps": 5316, "loss": 0.4415, "lr": 5e-06, "epoch": 0.4005641748942172, "percentage": 13.36, "elapsed_time": "2:34:52", "remaining_time": "16:44:43"}
72
+ {"current_steps": 720, "total_steps": 5316, "loss": 0.4467, "lr": 5e-06, "epoch": 0.40620592383638926, "percentage": 13.54, "elapsed_time": "2:37:03", "remaining_time": "16:42:31"}
73
+ {"current_steps": 730, "total_steps": 5316, "loss": 0.4617, "lr": 5e-06, "epoch": 0.4118476727785614, "percentage": 13.73, "elapsed_time": "2:39:13", "remaining_time": "16:40:19"}
74
+ {"current_steps": 740, "total_steps": 5316, "loss": 0.4455, "lr": 5e-06, "epoch": 0.41748942172073344, "percentage": 13.92, "elapsed_time": "2:41:24", "remaining_time": "16:38:06"}
75
+ {"current_steps": 750, "total_steps": 5316, "loss": 0.4752, "lr": 5e-06, "epoch": 0.4231311706629055, "percentage": 14.11, "elapsed_time": "2:43:35", "remaining_time": "16:35:54"}
76
+ {"current_steps": 760, "total_steps": 5316, "loss": 0.4312, "lr": 5e-06, "epoch": 0.4287729196050776, "percentage": 14.3, "elapsed_time": "2:45:45", "remaining_time": "16:33:42"}
77
+ {"current_steps": 770, "total_steps": 5316, "loss": 0.4522, "lr": 5e-06, "epoch": 0.43441466854724964, "percentage": 14.48, "elapsed_time": "2:47:56", "remaining_time": "16:31:30"}
78
+ {"current_steps": 780, "total_steps": 5316, "loss": 0.4547, "lr": 5e-06, "epoch": 0.4400564174894217, "percentage": 14.67, "elapsed_time": "2:50:07", "remaining_time": "16:29:19"}
79
+ {"current_steps": 790, "total_steps": 5316, "loss": 0.4328, "lr": 5e-06, "epoch": 0.44569816643159377, "percentage": 14.86, "elapsed_time": "2:52:17", "remaining_time": "16:27:06"}
80
+ {"current_steps": 800, "total_steps": 5316, "loss": 0.4526, "lr": 5e-06, "epoch": 0.4513399153737659, "percentage": 15.05, "elapsed_time": "2:54:28", "remaining_time": "16:24:55"}
81
+ {"current_steps": 810, "total_steps": 5316, "loss": 0.4543, "lr": 5e-06, "epoch": 0.45698166431593795, "percentage": 15.24, "elapsed_time": "2:56:39", "remaining_time": "16:22:44"}
82
+ {"current_steps": 820, "total_steps": 5316, "loss": 0.4489, "lr": 5e-06, "epoch": 0.46262341325811, "percentage": 15.43, "elapsed_time": "2:58:50", "remaining_time": "16:20:32"}
83
+ {"current_steps": 830, "total_steps": 5316, "loss": 0.4635, "lr": 5e-06, "epoch": 0.4682651622002821, "percentage": 15.61, "elapsed_time": "3:01:00", "remaining_time": "16:18:20"}
84
+ {"current_steps": 840, "total_steps": 5316, "loss": 0.4414, "lr": 5e-06, "epoch": 0.47390691114245415, "percentage": 15.8, "elapsed_time": "3:03:11", "remaining_time": "16:16:08"}
85
+ {"current_steps": 850, "total_steps": 5316, "loss": 0.4702, "lr": 5e-06, "epoch": 0.4795486600846262, "percentage": 15.99, "elapsed_time": "3:05:22", "remaining_time": "16:13:57"}
86
+ {"current_steps": 860, "total_steps": 5316, "loss": 0.452, "lr": 5e-06, "epoch": 0.48519040902679833, "percentage": 16.18, "elapsed_time": "3:07:32", "remaining_time": "16:11:45"}
87
+ {"current_steps": 870, "total_steps": 5316, "loss": 0.4401, "lr": 5e-06, "epoch": 0.4908321579689704, "percentage": 16.37, "elapsed_time": "3:09:43", "remaining_time": "16:09:34"}
88
+ {"current_steps": 880, "total_steps": 5316, "loss": 0.4594, "lr": 5e-06, "epoch": 0.49647390691114246, "percentage": 16.55, "elapsed_time": "3:11:54", "remaining_time": "16:07:22"}
89
+ {"current_steps": 890, "total_steps": 5316, "loss": 0.4445, "lr": 5e-06, "epoch": 0.5021156558533145, "percentage": 16.74, "elapsed_time": "3:14:05", "remaining_time": "16:05:11"}
90
+ {"current_steps": 900, "total_steps": 5316, "loss": 0.4419, "lr": 5e-06, "epoch": 0.5077574047954866, "percentage": 16.93, "elapsed_time": "3:16:15", "remaining_time": "16:03:00"}
91
+ {"current_steps": 910, "total_steps": 5316, "loss": 0.4476, "lr": 5e-06, "epoch": 0.5133991537376587, "percentage": 17.12, "elapsed_time": "3:18:26", "remaining_time": "16:00:48"}
92
+ {"current_steps": 920, "total_steps": 5316, "loss": 0.4477, "lr": 5e-06, "epoch": 0.5190409026798307, "percentage": 17.31, "elapsed_time": "3:20:37", "remaining_time": "15:58:37"}
93
+ {"current_steps": 930, "total_steps": 5316, "loss": 0.4602, "lr": 5e-06, "epoch": 0.5246826516220028, "percentage": 17.49, "elapsed_time": "3:22:48", "remaining_time": "15:56:26"}
94
+ {"current_steps": 940, "total_steps": 5316, "loss": 0.4463, "lr": 5e-06, "epoch": 0.5303244005641748, "percentage": 17.68, "elapsed_time": "3:24:58", "remaining_time": "15:54:15"}
95
+ {"current_steps": 950, "total_steps": 5316, "loss": 0.4481, "lr": 5e-06, "epoch": 0.535966149506347, "percentage": 17.87, "elapsed_time": "3:27:09", "remaining_time": "15:52:04"}
96
+ {"current_steps": 960, "total_steps": 5316, "loss": 0.4547, "lr": 5e-06, "epoch": 0.5416078984485191, "percentage": 18.06, "elapsed_time": "3:29:20", "remaining_time": "15:49:53"}
97
+ {"current_steps": 970, "total_steps": 5316, "loss": 0.4342, "lr": 5e-06, "epoch": 0.5472496473906912, "percentage": 18.25, "elapsed_time": "3:31:31", "remaining_time": "15:47:42"}
98
+ {"current_steps": 980, "total_steps": 5316, "loss": 0.4391, "lr": 5e-06, "epoch": 0.5528913963328632, "percentage": 18.43, "elapsed_time": "3:33:42", "remaining_time": "15:45:30"}
99
+ {"current_steps": 990, "total_steps": 5316, "loss": 0.4477, "lr": 5e-06, "epoch": 0.5585331452750353, "percentage": 18.62, "elapsed_time": "3:35:52", "remaining_time": "15:43:19"}
100
+ {"current_steps": 1000, "total_steps": 5316, "loss": 0.4644, "lr": 5e-06, "epoch": 0.5641748942172073, "percentage": 18.81, "elapsed_time": "3:38:03", "remaining_time": "15:41:08"}
101
+ {"current_steps": 1010, "total_steps": 5316, "loss": 0.442, "lr": 5e-06, "epoch": 0.5698166431593794, "percentage": 19.0, "elapsed_time": "3:40:14", "remaining_time": "15:38:56"}
102
+ {"current_steps": 1020, "total_steps": 5316, "loss": 0.4363, "lr": 5e-06, "epoch": 0.5754583921015515, "percentage": 19.19, "elapsed_time": "3:42:25", "remaining_time": "15:36:46"}
103
+ {"current_steps": 1030, "total_steps": 5316, "loss": 0.4523, "lr": 5e-06, "epoch": 0.5811001410437235, "percentage": 19.38, "elapsed_time": "3:44:35", "remaining_time": "15:34:34"}
104
+ {"current_steps": 1040, "total_steps": 5316, "loss": 0.4452, "lr": 5e-06, "epoch": 0.5867418899858956, "percentage": 19.56, "elapsed_time": "3:46:46", "remaining_time": "15:32:24"}
105
+ {"current_steps": 1050, "total_steps": 5316, "loss": 0.4504, "lr": 5e-06, "epoch": 0.5923836389280677, "percentage": 19.75, "elapsed_time": "3:48:57", "remaining_time": "15:30:13"}
106
+ {"current_steps": 1060, "total_steps": 5316, "loss": 0.4414, "lr": 5e-06, "epoch": 0.5980253878702397, "percentage": 19.94, "elapsed_time": "3:51:08", "remaining_time": "15:28:02"}
107
+ {"current_steps": 1070, "total_steps": 5316, "loss": 0.4336, "lr": 5e-06, "epoch": 0.6036671368124118, "percentage": 20.13, "elapsed_time": "3:53:19", "remaining_time": "15:25:51"}
108
+ {"current_steps": 1080, "total_steps": 5316, "loss": 0.4446, "lr": 5e-06, "epoch": 0.609308885754584, "percentage": 20.32, "elapsed_time": "3:55:29", "remaining_time": "15:23:40"}
109
+ {"current_steps": 1090, "total_steps": 5316, "loss": 0.452, "lr": 5e-06, "epoch": 0.614950634696756, "percentage": 20.5, "elapsed_time": "3:57:40", "remaining_time": "15:21:28"}
110
+ {"current_steps": 1100, "total_steps": 5316, "loss": 0.4756, "lr": 5e-06, "epoch": 0.6205923836389281, "percentage": 20.69, "elapsed_time": "3:59:51", "remaining_time": "15:19:17"}
111
+ {"current_steps": 1110, "total_steps": 5316, "loss": 0.4427, "lr": 5e-06, "epoch": 0.6262341325811002, "percentage": 20.88, "elapsed_time": "4:02:02", "remaining_time": "15:17:07"}
112
+ {"current_steps": 1120, "total_steps": 5316, "loss": 0.4323, "lr": 5e-06, "epoch": 0.6318758815232722, "percentage": 21.07, "elapsed_time": "4:04:12", "remaining_time": "15:14:56"}
113
+ {"current_steps": 1130, "total_steps": 5316, "loss": 0.4488, "lr": 5e-06, "epoch": 0.6375176304654443, "percentage": 21.26, "elapsed_time": "4:06:23", "remaining_time": "15:12:45"}
114
+ {"current_steps": 1140, "total_steps": 5316, "loss": 0.4611, "lr": 5e-06, "epoch": 0.6431593794076164, "percentage": 21.44, "elapsed_time": "4:08:34", "remaining_time": "15:10:34"}
115
+ {"current_steps": 1150, "total_steps": 5316, "loss": 0.4438, "lr": 5e-06, "epoch": 0.6488011283497884, "percentage": 21.63, "elapsed_time": "4:10:45", "remaining_time": "15:08:23"}
116
+ {"current_steps": 1160, "total_steps": 5316, "loss": 0.4452, "lr": 5e-06, "epoch": 0.6544428772919605, "percentage": 21.82, "elapsed_time": "4:12:56", "remaining_time": "15:06:13"}
117
+ {"current_steps": 1170, "total_steps": 5316, "loss": 0.4397, "lr": 5e-06, "epoch": 0.6600846262341326, "percentage": 22.01, "elapsed_time": "4:15:07", "remaining_time": "15:04:02"}
118
+ {"current_steps": 1180, "total_steps": 5316, "loss": 0.4417, "lr": 5e-06, "epoch": 0.6657263751763046, "percentage": 22.2, "elapsed_time": "4:17:18", "remaining_time": "15:01:51"}
119
+ {"current_steps": 1190, "total_steps": 5316, "loss": 0.4539, "lr": 5e-06, "epoch": 0.6713681241184767, "percentage": 22.39, "elapsed_time": "4:19:29", "remaining_time": "14:59:41"}
120
+ {"current_steps": 1200, "total_steps": 5316, "loss": 0.4429, "lr": 5e-06, "epoch": 0.6770098730606487, "percentage": 22.57, "elapsed_time": "4:21:39", "remaining_time": "14:57:30"}
121
+ {"current_steps": 1210, "total_steps": 5316, "loss": 0.4481, "lr": 5e-06, "epoch": 0.6826516220028209, "percentage": 22.76, "elapsed_time": "4:23:50", "remaining_time": "14:55:20"}
122
+ {"current_steps": 1220, "total_steps": 5316, "loss": 0.44, "lr": 5e-06, "epoch": 0.688293370944993, "percentage": 22.95, "elapsed_time": "4:26:01", "remaining_time": "14:53:09"}
123
+ {"current_steps": 1230, "total_steps": 5316, "loss": 0.443, "lr": 5e-06, "epoch": 0.693935119887165, "percentage": 23.14, "elapsed_time": "4:28:12", "remaining_time": "14:50:59"}
124
+ {"current_steps": 1240, "total_steps": 5316, "loss": 0.4439, "lr": 5e-06, "epoch": 0.6995768688293371, "percentage": 23.33, "elapsed_time": "4:30:24", "remaining_time": "14:48:49"}
125
+ {"current_steps": 1250, "total_steps": 5316, "loss": 0.4252, "lr": 5e-06, "epoch": 0.7052186177715092, "percentage": 23.51, "elapsed_time": "4:32:35", "remaining_time": "14:46:40"}
126
+ {"current_steps": 1260, "total_steps": 5316, "loss": 0.4482, "lr": 5e-06, "epoch": 0.7108603667136812, "percentage": 23.7, "elapsed_time": "4:34:46", "remaining_time": "14:44:30"}
127
+ {"current_steps": 1270, "total_steps": 5316, "loss": 0.4402, "lr": 5e-06, "epoch": 0.7165021156558533, "percentage": 23.89, "elapsed_time": "4:36:57", "remaining_time": "14:42:20"}
128
+ {"current_steps": 1280, "total_steps": 5316, "loss": 0.4368, "lr": 5e-06, "epoch": 0.7221438645980254, "percentage": 24.08, "elapsed_time": "4:39:08", "remaining_time": "14:40:10"}
129
+ {"current_steps": 1290, "total_steps": 5316, "loss": 0.4577, "lr": 5e-06, "epoch": 0.7277856135401974, "percentage": 24.27, "elapsed_time": "4:41:19", "remaining_time": "14:38:01"}
130
+ {"current_steps": 1300, "total_steps": 5316, "loss": 0.4527, "lr": 5e-06, "epoch": 0.7334273624823695, "percentage": 24.45, "elapsed_time": "4:43:31", "remaining_time": "14:35:51"}
131
+ {"current_steps": 1310, "total_steps": 5316, "loss": 0.4421, "lr": 5e-06, "epoch": 0.7390691114245416, "percentage": 24.64, "elapsed_time": "4:45:42", "remaining_time": "14:33:41"}
132
+ {"current_steps": 1320, "total_steps": 5316, "loss": 0.4548, "lr": 5e-06, "epoch": 0.7447108603667136, "percentage": 24.83, "elapsed_time": "4:47:53", "remaining_time": "14:31:31"}
133
+ {"current_steps": 1330, "total_steps": 5316, "loss": 0.4349, "lr": 5e-06, "epoch": 0.7503526093088858, "percentage": 25.02, "elapsed_time": "4:50:04", "remaining_time": "14:29:20"}
134
+ {"current_steps": 1340, "total_steps": 5316, "loss": 0.4378, "lr": 5e-06, "epoch": 0.7559943582510579, "percentage": 25.21, "elapsed_time": "4:52:15", "remaining_time": "14:27:09"}
135
+ {"current_steps": 1350, "total_steps": 5316, "loss": 0.4408, "lr": 5e-06, "epoch": 0.7616361071932299, "percentage": 25.4, "elapsed_time": "4:54:25", "remaining_time": "14:24:58"}
136
+ {"current_steps": 1360, "total_steps": 5316, "loss": 0.4456, "lr": 5e-06, "epoch": 0.767277856135402, "percentage": 25.58, "elapsed_time": "4:56:36", "remaining_time": "14:22:47"}
137
+ {"current_steps": 1370, "total_steps": 5316, "loss": 0.4473, "lr": 5e-06, "epoch": 0.7729196050775741, "percentage": 25.77, "elapsed_time": "4:58:47", "remaining_time": "14:20:36"}
138
+ {"current_steps": 1380, "total_steps": 5316, "loss": 0.4434, "lr": 5e-06, "epoch": 0.7785613540197461, "percentage": 25.96, "elapsed_time": "5:00:58", "remaining_time": "14:18:25"}
139
+ {"current_steps": 1390, "total_steps": 5316, "loss": 0.4296, "lr": 5e-06, "epoch": 0.7842031029619182, "percentage": 26.15, "elapsed_time": "5:03:09", "remaining_time": "14:16:14"}
140
+ {"current_steps": 1400, "total_steps": 5316, "loss": 0.4447, "lr": 5e-06, "epoch": 0.7898448519040903, "percentage": 26.34, "elapsed_time": "5:05:20", "remaining_time": "14:14:03"}
141
+ {"current_steps": 1410, "total_steps": 5316, "loss": 0.437, "lr": 5e-06, "epoch": 0.7954866008462623, "percentage": 26.52, "elapsed_time": "5:07:31", "remaining_time": "14:11:53"}
142
+ {"current_steps": 1420, "total_steps": 5316, "loss": 0.4517, "lr": 5e-06, "epoch": 0.8011283497884344, "percentage": 26.71, "elapsed_time": "5:09:41", "remaining_time": "14:09:42"}
143
+ {"current_steps": 1430, "total_steps": 5316, "loss": 0.4458, "lr": 5e-06, "epoch": 0.8067700987306065, "percentage": 26.9, "elapsed_time": "5:11:52", "remaining_time": "14:07:31"}
144
+ {"current_steps": 1440, "total_steps": 5316, "loss": 0.4542, "lr": 5e-06, "epoch": 0.8124118476727785, "percentage": 27.09, "elapsed_time": "5:14:03", "remaining_time": "14:05:20"}
145
+ {"current_steps": 1450, "total_steps": 5316, "loss": 0.4405, "lr": 5e-06, "epoch": 0.8180535966149506, "percentage": 27.28, "elapsed_time": "5:16:14", "remaining_time": "14:03:09"}
146
+ {"current_steps": 1460, "total_steps": 5316, "loss": 0.4357, "lr": 5e-06, "epoch": 0.8236953455571228, "percentage": 27.46, "elapsed_time": "5:18:25", "remaining_time": "14:00:58"}
147
+ {"current_steps": 1470, "total_steps": 5316, "loss": 0.4404, "lr": 5e-06, "epoch": 0.8293370944992948, "percentage": 27.65, "elapsed_time": "5:20:35", "remaining_time": "13:58:47"}
148
+ {"current_steps": 1480, "total_steps": 5316, "loss": 0.4291, "lr": 5e-06, "epoch": 0.8349788434414669, "percentage": 27.84, "elapsed_time": "5:22:46", "remaining_time": "13:56:36"}
149
+ {"current_steps": 1490, "total_steps": 5316, "loss": 0.4446, "lr": 5e-06, "epoch": 0.840620592383639, "percentage": 28.03, "elapsed_time": "5:24:57", "remaining_time": "13:54:25"}
150
+ {"current_steps": 1500, "total_steps": 5316, "loss": 0.442, "lr": 5e-06, "epoch": 0.846262341325811, "percentage": 28.22, "elapsed_time": "5:27:08", "remaining_time": "13:52:14"}
151
+ {"current_steps": 1510, "total_steps": 5316, "loss": 0.4427, "lr": 5e-06, "epoch": 0.8519040902679831, "percentage": 28.4, "elapsed_time": "5:29:19", "remaining_time": "13:50:03"}
152
+ {"current_steps": 1520, "total_steps": 5316, "loss": 0.4493, "lr": 5e-06, "epoch": 0.8575458392101551, "percentage": 28.59, "elapsed_time": "5:31:30", "remaining_time": "13:47:52"}
153
+ {"current_steps": 1530, "total_steps": 5316, "loss": 0.4425, "lr": 5e-06, "epoch": 0.8631875881523272, "percentage": 28.78, "elapsed_time": "5:33:40", "remaining_time": "13:45:41"}
154
+ {"current_steps": 1540, "total_steps": 5316, "loss": 0.453, "lr": 5e-06, "epoch": 0.8688293370944993, "percentage": 28.97, "elapsed_time": "5:35:51", "remaining_time": "13:43:30"}
155
+ {"current_steps": 1550, "total_steps": 5316, "loss": 0.4667, "lr": 5e-06, "epoch": 0.8744710860366713, "percentage": 29.16, "elapsed_time": "5:38:02", "remaining_time": "13:41:19"}
156
+ {"current_steps": 1560, "total_steps": 5316, "loss": 0.4408, "lr": 5e-06, "epoch": 0.8801128349788434, "percentage": 29.35, "elapsed_time": "5:40:13", "remaining_time": "13:39:08"}
157
+ {"current_steps": 1570, "total_steps": 5316, "loss": 0.4323, "lr": 5e-06, "epoch": 0.8857545839210155, "percentage": 29.53, "elapsed_time": "5:42:24", "remaining_time": "13:36:57"}
158
+ {"current_steps": 1580, "total_steps": 5316, "loss": 0.4385, "lr": 5e-06, "epoch": 0.8913963328631875, "percentage": 29.72, "elapsed_time": "5:44:34", "remaining_time": "13:34:47"}
159
+ {"current_steps": 1590, "total_steps": 5316, "loss": 0.4398, "lr": 5e-06, "epoch": 0.8970380818053597, "percentage": 29.91, "elapsed_time": "5:46:46", "remaining_time": "13:32:36"}
160
+ {"current_steps": 1600, "total_steps": 5316, "loss": 0.4484, "lr": 5e-06, "epoch": 0.9026798307475318, "percentage": 30.1, "elapsed_time": "5:48:56", "remaining_time": "13:30:26"}
161
+ {"current_steps": 1610, "total_steps": 5316, "loss": 0.4463, "lr": 5e-06, "epoch": 0.9083215796897038, "percentage": 30.29, "elapsed_time": "5:51:08", "remaining_time": "13:28:15"}
162
+ {"current_steps": 1620, "total_steps": 5316, "loss": 0.4395, "lr": 5e-06, "epoch": 0.9139633286318759, "percentage": 30.47, "elapsed_time": "5:53:19", "remaining_time": "13:26:05"}
163
+ {"current_steps": 1630, "total_steps": 5316, "loss": 0.4548, "lr": 5e-06, "epoch": 0.919605077574048, "percentage": 30.66, "elapsed_time": "5:55:30", "remaining_time": "13:23:54"}
164
+ {"current_steps": 1640, "total_steps": 5316, "loss": 0.4402, "lr": 5e-06, "epoch": 0.92524682651622, "percentage": 30.85, "elapsed_time": "5:57:41", "remaining_time": "13:21:44"}
165
+ {"current_steps": 1650, "total_steps": 5316, "loss": 0.4524, "lr": 5e-06, "epoch": 0.9308885754583921, "percentage": 31.04, "elapsed_time": "5:59:52", "remaining_time": "13:19:34"}
166
+ {"current_steps": 1660, "total_steps": 5316, "loss": 0.4388, "lr": 5e-06, "epoch": 0.9365303244005642, "percentage": 31.23, "elapsed_time": "6:02:03", "remaining_time": "13:17:23"}
167
+ {"current_steps": 1670, "total_steps": 5316, "loss": 0.4373, "lr": 5e-06, "epoch": 0.9421720733427362, "percentage": 31.41, "elapsed_time": "6:04:14", "remaining_time": "13:15:12"}
168
+ {"current_steps": 1680, "total_steps": 5316, "loss": 0.4521, "lr": 5e-06, "epoch": 0.9478138222849083, "percentage": 31.6, "elapsed_time": "6:06:25", "remaining_time": "13:13:02"}
169
+ {"current_steps": 1690, "total_steps": 5316, "loss": 0.4387, "lr": 5e-06, "epoch": 0.9534555712270804, "percentage": 31.79, "elapsed_time": "6:08:36", "remaining_time": "13:10:52"}
170
+ {"current_steps": 1700, "total_steps": 5316, "loss": 0.4474, "lr": 5e-06, "epoch": 0.9590973201692524, "percentage": 31.98, "elapsed_time": "6:10:47", "remaining_time": "13:08:41"}
171
+ {"current_steps": 1710, "total_steps": 5316, "loss": 0.4402, "lr": 5e-06, "epoch": 0.9647390691114246, "percentage": 32.17, "elapsed_time": "6:12:58", "remaining_time": "13:06:31"}
172
+ {"current_steps": 1720, "total_steps": 5316, "loss": 0.448, "lr": 5e-06, "epoch": 0.9703808180535967, "percentage": 32.36, "elapsed_time": "6:15:09", "remaining_time": "13:04:21"}
173
+ {"current_steps": 1730, "total_steps": 5316, "loss": 0.4527, "lr": 5e-06, "epoch": 0.9760225669957687, "percentage": 32.54, "elapsed_time": "6:17:20", "remaining_time": "13:02:10"}
174
+ {"current_steps": 1740, "total_steps": 5316, "loss": 0.4458, "lr": 5e-06, "epoch": 0.9816643159379408, "percentage": 32.73, "elapsed_time": "6:19:31", "remaining_time": "13:00:00"}
175
+ {"current_steps": 1750, "total_steps": 5316, "loss": 0.4565, "lr": 5e-06, "epoch": 0.9873060648801129, "percentage": 32.92, "elapsed_time": "6:21:43", "remaining_time": "12:57:49"}
176
+ {"current_steps": 1760, "total_steps": 5316, "loss": 0.4481, "lr": 5e-06, "epoch": 0.9929478138222849, "percentage": 33.11, "elapsed_time": "6:23:54", "remaining_time": "12:55:39"}
177
+ {"current_steps": 1770, "total_steps": 5316, "loss": 0.4318, "lr": 5e-06, "epoch": 0.998589562764457, "percentage": 33.3, "elapsed_time": "6:26:05", "remaining_time": "12:53:29"}
178
+ {"current_steps": 1772, "total_steps": 5316, "eval_loss": 0.4379998743534088, "epoch": 0.9997179125528914, "percentage": 33.33, "elapsed_time": "6:34:03", "remaining_time": "13:08:06"}
179
+ {"current_steps": 1780, "total_steps": 5316, "loss": 0.4228, "lr": 5e-06, "epoch": 1.004231311706629, "percentage": 33.48, "elapsed_time": "6:36:46", "remaining_time": "13:08:12"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22f90db1cfe002713a35c41d07bf7df94b57591730375edcc60ae693000baa55
3
+ size 7160
vocab.json ADDED
The diff for this file is too large to render. See raw diff