Hugging Face's logo

konstantinkozhin
/
IIvanIIvanovich

Safetensors
qwen2
Model card Files
xet
Community
konstantinkozhin commited on
Commit
fd04d67
·
verified ·
1 Parent(s): 114d9b3

Upload folder using huggingface_hub

Browse files
Files changed (16) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +24 -0
  3. chat_template.jinja +54 -0
  4. config.json +55 -0
  5. generation_config.json +8 -0
  6. merges.txt +0 -0
  7. model.safetensors +3 -0
  8. optimizer.pt +3 -0
  9. rng_state.pth +3 -0
  10. scheduler.pt +3 -0
  11. special_tokens_map.json +31 -0
  12. tokenizer.json +3 -0
  13. tokenizer_config.json +207 -0
  14. trainer_state.json +464 -0
  15. training_args.bin +3 -0
  16. vocab.json +0 -0
.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
+ }
chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\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>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\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" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "dtype": "bfloat16",
7
+ "eos_token_id": 151643,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 896,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 4864,
12
+ "layer_types": [
13
+ "full_attention",
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention"
37
+ ],
38
+ "max_position_embeddings": 32768,
39
+ "max_window_layers": 24,
40
+ "model_type": "qwen2",
41
+ "num_attention_heads": 14,
42
+ "num_hidden_layers": 24,
43
+ "num_key_value_heads": 2,
44
+ "pad_token_id": 151643,
45
+ "rms_norm_eps": 1e-06,
46
+ "rope_scaling": null,
47
+ "rope_theta": 1000000.0,
48
+ "sliding_window": null,
49
+ "tie_word_embeddings": true,
50
+ "transformers_version": "4.57.1",
51
+ "use_cache": true,
52
+ "use_mrope": false,
53
+ "use_sliding_window": false,
54
+ "vocab_size": 151936
55
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token_id": [
3
+ 151643
4
+ ],
5
+ "max_new_tokens": 2048,
6
+ "pad_token_id": 151643,
7
+ "transformers_version": "4.57.1"
8
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9430917b7f4d24e588c67e99d955e3cbf01827a8be89082b4fdc94f1a0153bf
3
+ size 988097824
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e8aa55d156b7c0582d067fe8899c0323363475859e37110204d5945c185db23
3
+ size 1976374202
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdf4d700cdd7ef81bf005d2842e2f669e1810471cfce670ab79872c6ee698af7
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:018c5bac0d392eec5a91f579ccf98f417f86197e466a99cf54219088e9be3670
3
+ size 1064
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": "<|endoftext|>",
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 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|endoftext|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }
trainer_state.json ADDED
@@ -0,0 +1,464 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 43960,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "entropy": 2.494273384451866,
14
+ "epoch": 0.022747952684258416,
15
+ "grad_norm": 18.375,
16
+ "learning_rate": 6.991084023229653e-05,
17
+ "loss": 2.56,
18
+ "mean_token_accuracy": 0.47454266212880614,
19
+ "num_tokens": 137746.0,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "entropy": 2.1963223298788073,
24
+ "epoch": 0.04549590536851683,
25
+ "grad_norm": 36.75,
26
+ "learning_rate": 6.964345916042913e-05,
27
+ "loss": 2.2203,
28
+ "mean_token_accuracy": 0.5251638530790805,
29
+ "num_tokens": 274474.0,
30
+ "step": 2000
31
+ },
32
+ {
33
+ "entropy": 2.071790741562843,
34
+ "epoch": 0.06824385805277525,
35
+ "grad_norm": 18.625,
36
+ "learning_rate": 6.919922168729661e-05,
37
+ "loss": 2.0846,
38
+ "mean_token_accuracy": 0.5476762084960938,
39
+ "num_tokens": 410511.0,
40
+ "step": 3000
41
+ },
42
+ {
43
+ "entropy": 1.9665795323848725,
44
+ "epoch": 0.09099181073703366,
45
+ "grad_norm": 19.375,
46
+ "learning_rate": 6.858039566497577e-05,
47
+ "loss": 1.9827,
48
+ "mean_token_accuracy": 0.5608653167784214,
49
+ "num_tokens": 546387.0,
50
+ "step": 4000
51
+ },
52
+ {
53
+ "entropy": 1.8746658574938775,
54
+ "epoch": 0.11373976342129208,
55
+ "grad_norm": 14.5,
56
+ "learning_rate": 6.779014022785937e-05,
57
+ "loss": 1.878,
58
+ "mean_token_accuracy": 0.5797940475940704,
59
+ "num_tokens": 685188.0,
60
+ "step": 5000
61
+ },
62
+ {
63
+ "entropy": 1.8111666428446769,
64
+ "epoch": 0.1364877161055505,
65
+ "grad_norm": 25.375,
66
+ "learning_rate": 6.683248966513431e-05,
67
+ "loss": 1.8199,
68
+ "mean_token_accuracy": 0.5904675594568253,
69
+ "num_tokens": 823629.0,
70
+ "step": 6000
71
+ },
72
+ {
73
+ "entropy": 1.7517779313921928,
74
+ "epoch": 0.1592356687898089,
75
+ "grad_norm": 15.0625,
76
+ "learning_rate": 6.571233282555582e-05,
77
+ "loss": 1.7533,
78
+ "mean_token_accuracy": 0.6037232976555824,
79
+ "num_tokens": 962974.0,
80
+ "step": 7000
81
+ },
82
+ {
83
+ "entropy": 1.7067503632903098,
84
+ "epoch": 0.18198362147406733,
85
+ "grad_norm": 15.25,
86
+ "learning_rate": 6.443538815965688e-05,
87
+ "loss": 1.7095,
88
+ "mean_token_accuracy": 0.6099362835586071,
89
+ "num_tokens": 1097086.0,
90
+ "step": 8000
91
+ },
92
+ {
93
+ "entropy": 1.6539168149232863,
94
+ "epoch": 0.20473157415832574,
95
+ "grad_norm": 21.25,
96
+ "learning_rate": 6.300817452680371e-05,
97
+ "loss": 1.6574,
98
+ "mean_token_accuracy": 0.6192078518867493,
99
+ "num_tokens": 1241889.0,
100
+ "step": 9000
101
+ },
102
+ {
103
+ "entropy": 1.6205334926843644,
104
+ "epoch": 0.22747952684258416,
105
+ "grad_norm": 11.5625,
106
+ "learning_rate": 6.143797791612843e-05,
107
+ "loss": 1.623,
108
+ "mean_token_accuracy": 0.6248027366697788,
109
+ "num_tokens": 1378131.0,
110
+ "step": 10000
111
+ },
112
+ {
113
+ "entropy": 1.5953178288936616,
114
+ "epoch": 0.2502274795268426,
115
+ "grad_norm": 16.25,
116
+ "learning_rate": 5.9732814251230294e-05,
117
+ "loss": 1.5932,
118
+ "mean_token_accuracy": 0.6300182574093341,
119
+ "num_tokens": 1513496.0,
120
+ "step": 11000
121
+ },
122
+ {
123
+ "entropy": 1.5745678083896637,
124
+ "epoch": 0.272975432211101,
125
+ "grad_norm": 16.5,
126
+ "learning_rate": 5.7901388468528755e-05,
127
+ "loss": 1.5751,
128
+ "mean_token_accuracy": 0.6331984028220177,
129
+ "num_tokens": 1651603.0,
130
+ "step": 12000
131
+ },
132
+ {
133
+ "entropy": 1.576361115962267,
134
+ "epoch": 0.29572338489535943,
135
+ "grad_norm": 19.5,
136
+ "learning_rate": 5.595305007817556e-05,
137
+ "loss": 1.5795,
138
+ "mean_token_accuracy": 0.6308481710553169,
139
+ "num_tokens": 1790851.0,
140
+ "step": 13000
141
+ },
142
+ {
143
+ "entropy": 1.506616612225771,
144
+ "epoch": 0.3184713375796178,
145
+ "grad_norm": 15.8125,
146
+ "learning_rate": 5.3897745434389274e-05,
147
+ "loss": 1.504,
148
+ "mean_token_accuracy": 0.6438729543685913,
149
+ "num_tokens": 1926179.0,
150
+ "step": 14000
151
+ },
152
+ {
153
+ "entropy": 1.4861243069171906,
154
+ "epoch": 0.34121929026387626,
155
+ "grad_norm": 17.75,
156
+ "learning_rate": 5.1745966958874055e-05,
157
+ "loss": 1.4832,
158
+ "mean_token_accuracy": 0.6503438740372658,
159
+ "num_tokens": 2062340.0,
160
+ "step": 15000
161
+ },
162
+ {
163
+ "entropy": 1.4704010844826698,
164
+ "epoch": 0.36396724294813465,
165
+ "grad_norm": 21.0,
166
+ "learning_rate": 4.9508699576539914e-05,
167
+ "loss": 1.4694,
168
+ "mean_token_accuracy": 0.6534121400117874,
169
+ "num_tokens": 2207639.0,
170
+ "step": 16000
171
+ },
172
+ {
173
+ "entropy": 1.4741187323331832,
174
+ "epoch": 0.3867151956323931,
175
+ "grad_norm": 19.375,
176
+ "learning_rate": 4.7197364636971925e-05,
177
+ "loss": 1.4749,
178
+ "mean_token_accuracy": 0.6518012735545635,
179
+ "num_tokens": 2348887.0,
180
+ "step": 17000
181
+ },
182
+ {
183
+ "entropy": 1.4345429268479348,
184
+ "epoch": 0.4094631483166515,
185
+ "grad_norm": 19.25,
186
+ "learning_rate": 4.482376160793216e-05,
187
+ "loss": 1.4354,
188
+ "mean_token_accuracy": 0.6596047645211219,
189
+ "num_tokens": 2483718.0,
190
+ "step": 18000
191
+ },
192
+ {
193
+ "entropy": 1.4003090425133704,
194
+ "epoch": 0.4322111010009099,
195
+ "grad_norm": 20.625,
196
+ "learning_rate": 4.240000783855147e-05,
197
+ "loss": 1.3979,
198
+ "mean_token_accuracy": 0.6681542407870292,
199
+ "num_tokens": 2622656.0,
200
+ "step": 19000
201
+ },
202
+ {
203
+ "entropy": 1.4163592108488083,
204
+ "epoch": 0.4549590536851683,
205
+ "grad_norm": 16.5,
206
+ "learning_rate": 3.993847669972281e-05,
207
+ "loss": 1.4083,
208
+ "mean_token_accuracy": 0.664802198857069,
209
+ "num_tokens": 2760831.0,
210
+ "step": 20000
211
+ },
212
+ {
213
+ "entropy": 1.4052879491746426,
214
+ "epoch": 0.47770700636942676,
215
+ "grad_norm": 23.875,
216
+ "learning_rate": 3.745173441749185e-05,
217
+ "loss": 1.4074,
218
+ "mean_token_accuracy": 0.6652796367108822,
219
+ "num_tokens": 2900387.0,
220
+ "step": 21000
221
+ },
222
+ {
223
+ "entropy": 1.3997035399377347,
224
+ "epoch": 0.5004549590536852,
225
+ "grad_norm": 25.875,
226
+ "learning_rate": 3.495247592191375e-05,
227
+ "loss": 1.3972,
228
+ "mean_token_accuracy": 0.6675955319404602,
229
+ "num_tokens": 3037204.0,
230
+ "step": 22000
231
+ },
232
+ {
233
+ "entropy": 1.415595789283514,
234
+ "epoch": 0.5232029117379435,
235
+ "grad_norm": 26.75,
236
+ "learning_rate": 3.245346003886994e-05,
237
+ "loss": 1.4129,
238
+ "mean_token_accuracy": 0.6636776500046253,
239
+ "num_tokens": 3179823.0,
240
+ "step": 23000
241
+ },
242
+ {
243
+ "entropy": 1.379241144567728,
244
+ "epoch": 0.545950864422202,
245
+ "grad_norm": 20.0,
246
+ "learning_rate": 2.996744435569409e-05,
247
+ "loss": 1.3739,
248
+ "mean_token_accuracy": 0.6730512301325798,
249
+ "num_tokens": 3318434.0,
250
+ "step": 24000
251
+ },
252
+ {
253
+ "entropy": 1.3975665314793586,
254
+ "epoch": 0.5686988171064604,
255
+ "grad_norm": 20.875,
256
+ "learning_rate": 2.7507120093120825e-05,
257
+ "loss": 1.3976,
258
+ "mean_token_accuracy": 0.6678333807885647,
259
+ "num_tokens": 3461132.0,
260
+ "step": 25000
261
+ },
262
+ {
263
+ "entropy": 1.380986104875803,
264
+ "epoch": 0.5914467697907189,
265
+ "grad_norm": 14.6875,
266
+ "learning_rate": 2.5085047316038814e-05,
267
+ "loss": 1.3817,
268
+ "mean_token_accuracy": 0.6719385531246662,
269
+ "num_tokens": 3601560.0,
270
+ "step": 26000
271
+ },
272
+ {
273
+ "entropy": 1.385195587992668,
274
+ "epoch": 0.6141947224749773,
275
+ "grad_norm": 21.25,
276
+ "learning_rate": 2.271359081380046e-05,
277
+ "loss": 1.3815,
278
+ "mean_token_accuracy": 0.6699076734781265,
279
+ "num_tokens": 3745377.0,
280
+ "step": 27000
281
+ },
282
+ {
283
+ "entropy": 1.3656318633258342,
284
+ "epoch": 0.6369426751592356,
285
+ "grad_norm": 22.5,
286
+ "learning_rate": 2.040485697742177e-05,
287
+ "loss": 1.357,
288
+ "mean_token_accuracy": 0.6759414212107658,
289
+ "num_tokens": 3879126.0,
290
+ "step": 28000
291
+ },
292
+ {
293
+ "entropy": 1.3772443866729736,
294
+ "epoch": 0.6596906278434941,
295
+ "grad_norm": 26.0,
296
+ "learning_rate": 1.8170631995917233e-05,
297
+ "loss": 1.3745,
298
+ "mean_token_accuracy": 0.6744600256979465,
299
+ "num_tokens": 4017925.0,
300
+ "step": 29000
301
+ },
302
+ {
303
+ "entropy": 1.365410826742649,
304
+ "epoch": 0.6824385805277525,
305
+ "grad_norm": 22.5,
306
+ "learning_rate": 1.602232168728024e-05,
307
+ "loss": 1.3584,
308
+ "mean_token_accuracy": 0.675611907929182,
309
+ "num_tokens": 4156599.0,
310
+ "step": 30000
311
+ },
312
+ {
313
+ "entropy": 1.3873618737459184,
314
+ "epoch": 0.705186533212011,
315
+ "grad_norm": 13.25,
316
+ "learning_rate": 1.3970893271274471e-05,
317
+ "loss": 1.3803,
318
+ "mean_token_accuracy": 0.6701690441966057,
319
+ "num_tokens": 4295734.0,
320
+ "step": 31000
321
+ },
322
+ {
323
+ "entropy": 1.359022274851799,
324
+ "epoch": 0.7279344858962693,
325
+ "grad_norm": 16.75,
326
+ "learning_rate": 1.202681938128876e-05,
327
+ "loss": 1.3556,
328
+ "mean_token_accuracy": 0.6761138562858104,
329
+ "num_tokens": 4431490.0,
330
+ "step": 32000
331
+ },
332
+ {
333
+ "entropy": 1.3703680724203586,
334
+ "epoch": 0.7506824385805277,
335
+ "grad_norm": 19.0,
336
+ "learning_rate": 1.0200024601077386e-05,
337
+ "loss": 1.362,
338
+ "mean_token_accuracy": 0.6743936349153519,
339
+ "num_tokens": 4571660.0,
340
+ "step": 33000
341
+ },
342
+ {
343
+ "entropy": 1.3698465181291104,
344
+ "epoch": 0.7734303912647862,
345
+ "grad_norm": 24.25,
346
+ "learning_rate": 8.49983479931827e-06,
347
+ "loss": 1.3757,
348
+ "mean_token_accuracy": 0.6719635992050171,
349
+ "num_tokens": 4707985.0,
350
+ "step": 34000
351
+ },
352
+ {
353
+ "entropy": 1.3624781457483768,
354
+ "epoch": 0.7961783439490446,
355
+ "grad_norm": 16.875,
356
+ "learning_rate": 6.9349295206380985e-06,
357
+ "loss": 1.3518,
358
+ "mean_token_accuracy": 0.6769196209311485,
359
+ "num_tokens": 4844765.0,
360
+ "step": 35000
361
+ },
362
+ {
363
+ "entropy": 1.3442125609219073,
364
+ "epoch": 0.818926296633303,
365
+ "grad_norm": 15.25,
366
+ "learning_rate": 5.513297676150713e-06,
367
+ "loss": 1.3335,
368
+ "mean_token_accuracy": 0.6805432761013508,
369
+ "num_tokens": 4978615.0,
370
+ "step": 36000
371
+ },
372
+ {
373
+ "entropy": 1.355837997198105,
374
+ "epoch": 0.8416742493175614,
375
+ "grad_norm": 16.0,
376
+ "learning_rate": 4.242196759710179e-06,
377
+ "loss": 1.3377,
378
+ "mean_token_accuracy": 0.6823569060564041,
379
+ "num_tokens": 5117536.0,
380
+ "step": 37000
381
+ },
382
+ {
383
+ "entropy": 1.3855277094841003,
384
+ "epoch": 0.8644222020018199,
385
+ "grad_norm": 17.625,
386
+ "learning_rate": 3.1281157980815473e-06,
387
+ "loss": 1.3731,
388
+ "mean_token_accuracy": 0.6734900210201741,
389
+ "num_tokens": 5258021.0,
390
+ "step": 38000
391
+ },
392
+ {
393
+ "entropy": 1.3616491684913634,
394
+ "epoch": 0.8871701546860783,
395
+ "grad_norm": 33.25,
396
+ "learning_rate": 2.1767422241703795e-06,
397
+ "loss": 1.3462,
398
+ "mean_token_accuracy": 0.6789434304237366,
399
+ "num_tokens": 5395368.0,
400
+ "step": 39000
401
+ },
402
+ {
403
+ "entropy": 1.3761241393685342,
404
+ "epoch": 0.9099181073703366,
405
+ "grad_norm": 16.0,
406
+ "learning_rate": 1.392932842424574e-06,
407
+ "loss": 1.3787,
408
+ "mean_token_accuracy": 0.6720339168906212,
409
+ "num_tokens": 5533958.0,
410
+ "step": 40000
411
+ },
412
+ {
413
+ "entropy": 1.3613062560856342,
414
+ "epoch": 0.9326660600545951,
415
+ "grad_norm": 31.375,
416
+ "learning_rate": 7.806890346314221e-07,
417
+ "loss": 1.3621,
418
+ "mean_token_accuracy": 0.6752942685186863,
419
+ "num_tokens": 5668914.0,
420
+ "step": 41000
421
+ },
422
+ {
423
+ "entropy": 1.3506658849716187,
424
+ "epoch": 0.9554140127388535,
425
+ "grad_norm": 13.8125,
426
+ "learning_rate": 3.431363326854719e-07,
427
+ "loss": 1.3478,
428
+ "mean_token_accuracy": 0.6773408466875553,
429
+ "num_tokens": 5806407.0,
430
+ "step": 42000
431
+ },
432
+ {
433
+ "entropy": 1.3391023662090302,
434
+ "epoch": 0.978161965423112,
435
+ "grad_norm": 13.125,
436
+ "learning_rate": 8.250846260903998e-08,
437
+ "loss": 1.3275,
438
+ "mean_token_accuracy": 0.68198375582695,
439
+ "num_tokens": 5942532.0,
440
+ "step": 43000
441
+ }
442
+ ],
443
+ "logging_steps": 1000,
444
+ "max_steps": 43960,
445
+ "num_input_tokens_seen": 0,
446
+ "num_train_epochs": 1,
447
+ "save_steps": 1000,
448
+ "stateful_callbacks": {
449
+ "TrainerControl": {
450
+ "args": {
451
+ "should_epoch_stop": false,
452
+ "should_evaluate": false,
453
+ "should_log": false,
454
+ "should_save": true,
455
+ "should_training_stop": true
456
+ },
457
+ "attributes": {}
458
+ }
459
+ },
460
+ "total_flos": 1.3040032742440704e+16,
461
+ "train_batch_size": 1,
462
+ "trial_name": null,
463
+ "trial_params": null
464
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d676bc70e2962b1cbc9dcbe2a152c8fc52a0a73519a60fb1533fa75a9c4576aa
3
+ size 5816
vocab.json ADDED
The diff for this file is too large to render. See raw diff