Hugging Face's logo

Jordansky
/
examp-final-6env

Safetensors
qwen2
Model card Files
xet
 Community
Jordansky commited on
Commit
79c8f1d
·
verified ·
1 Parent(s): c95abcb

Upload task output examp_final_6env

Browse files
Files changed (14) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +24 -0
  3. chat_template.jinja +54 -0
  4. config.json +58 -0
  5. generation_config.json +13 -0
  6. loss.txt +1 -0
  7. merges.txt +0 -0
  8. model.safetensors +3 -0
  9. special_tokens_map.json +31 -0
  10. tokenizer.json +3 -0
  11. tokenizer_config.json +207 -0
  12. trainer_state.json +424 -0
  13. training_args.bin +3 -0
  14. 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 Qwen, created by Alibaba Cloud. 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 Qwen, created by Alibaba Cloud. You 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 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "dtype": "bfloat16",
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 1536,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 8960,
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
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention"
41
+ ],
42
+ "max_position_embeddings": 32768,
43
+ "max_window_layers": 21,
44
+ "model_type": "qwen2",
45
+ "num_attention_heads": 12,
46
+ "num_hidden_layers": 28,
47
+ "num_key_value_heads": 2,
48
+ "pad_token_id": 151643,
49
+ "rms_norm_eps": 1e-06,
50
+ "rope_scaling": null,
51
+ "rope_theta": 1000000.0,
52
+ "sliding_window": null,
53
+ "tie_word_embeddings": true,
54
+ "transformers_version": "4.57.5",
55
+ "use_cache": false,
56
+ "use_sliding_window": false,
57
+ "vocab_size": 151936
58
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_sample": true,
3
+ "eos_token_id": [
4
+ 151645,
5
+ 151643
6
+ ],
7
+ "pad_token_id": 151643,
8
+ "repetition_penalty": 1.1,
9
+ "temperature": 0.7,
10
+ "top_k": 20,
11
+ "top_p": 0.8,
12
+ "transformers_version": "4.57.5"
13
+ }
loss.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ 390,no_eval
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 sha256:88b2dc1cdc46edc7b8de6b9ef58ad176967b1f253a023e43b52e99545cb96831
3
+ size 3087467144
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 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|im_end|>",
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 +1,424 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.9770992366412212,
6
+ "eval_steps": 500,
7
+ "global_step": 390,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "entropy": 1.153541599214077,
14
+ "epoch": 0.07633587786259542,
15
+ "grad_norm": 3.71875,
16
+ "learning_rate": 3.461538461538462e-05,
17
+ "loss": 0.5369,
18
+ "mean_token_accuracy": 0.8995052814483643,
19
+ "num_tokens": 915894.0,
20
+ "step": 10
21
+ },
22
+ {
23
+ "entropy": 0.9980269990861416,
24
+ "epoch": 0.15267175572519084,
25
+ "grad_norm": 1.9765625,
26
+ "learning_rate": 7.307692307692307e-05,
27
+ "loss": 0.0944,
28
+ "mean_token_accuracy": 0.9686855398118496,
29
+ "num_tokens": 1829473.0,
30
+ "step": 20
31
+ },
32
+ {
33
+ "entropy": 1.1567876577377318,
34
+ "epoch": 0.22900763358778625,
35
+ "grad_norm": 4.1875,
36
+ "learning_rate": 9.998763518763365e-05,
37
+ "loss": 0.1586,
38
+ "mean_token_accuracy": 0.9656276367604733,
39
+ "num_tokens": 2736915.0,
40
+ "step": 30
41
+ },
42
+ {
43
+ "entropy": 1.0751335889101028,
44
+ "epoch": 0.3053435114503817,
45
+ "grad_norm": 0.49609375,
46
+ "learning_rate": 9.976804306460788e-05,
47
+ "loss": 0.0682,
48
+ "mean_token_accuracy": 0.9742538303136825,
49
+ "num_tokens": 3644365.0,
50
+ "step": 40
51
+ },
52
+ {
53
+ "entropy": 1.0004250779747963,
54
+ "epoch": 0.3816793893129771,
55
+ "grad_norm": 0.40625,
56
+ "learning_rate": 9.927552866136169e-05,
57
+ "loss": 0.0579,
58
+ "mean_token_accuracy": 0.9773690737783909,
59
+ "num_tokens": 4554192.0,
60
+ "step": 50
61
+ },
62
+ {
63
+ "entropy": 1.0029304943978787,
64
+ "epoch": 0.4580152671755725,
65
+ "grad_norm": 0.578125,
66
+ "learning_rate": 9.851369877189127e-05,
67
+ "loss": 0.0612,
68
+ "mean_token_accuracy": 0.9769754238426686,
69
+ "num_tokens": 5454270.0,
70
+ "step": 60
71
+ },
72
+ {
73
+ "entropy": 1.0122574470937251,
74
+ "epoch": 0.5343511450381679,
75
+ "grad_norm": 0.44921875,
76
+ "learning_rate": 9.74881324482068e-05,
77
+ "loss": 0.0642,
78
+ "mean_token_accuracy": 0.9744108475744724,
79
+ "num_tokens": 6343987.0,
80
+ "step": 70
81
+ },
82
+ {
83
+ "entropy": 0.9858146071434021,
84
+ "epoch": 0.6106870229007634,
85
+ "grad_norm": 0.326171875,
86
+ "learning_rate": 9.62063401436769e-05,
87
+ "loss": 0.053,
88
+ "mean_token_accuracy": 0.9782996632158756,
89
+ "num_tokens": 7241839.0,
90
+ "step": 80
91
+ },
92
+ {
93
+ "entropy": 0.9321766041219235,
94
+ "epoch": 0.6870229007633588,
95
+ "grad_norm": 0.2890625,
96
+ "learning_rate": 9.467770871228569e-05,
97
+ "loss": 0.0502,
98
+ "mean_token_accuracy": 0.9778276771306992,
99
+ "num_tokens": 8149748.0,
100
+ "step": 90
101
+ },
102
+ {
103
+ "entropy": 0.9664321891963482,
104
+ "epoch": 0.7633587786259542,
105
+ "grad_norm": 0.322265625,
106
+ "learning_rate": 9.29134326665851e-05,
107
+ "loss": 0.0585,
108
+ "mean_token_accuracy": 0.9770526088774204,
109
+ "num_tokens": 9053166.0,
110
+ "step": 100
111
+ },
112
+ {
113
+ "entropy": 0.9390135675668716,
114
+ "epoch": 0.8396946564885496,
115
+ "grad_norm": 0.40625,
116
+ "learning_rate": 9.092643219775594e-05,
117
+ "loss": 0.0542,
118
+ "mean_token_accuracy": 0.9784163929522037,
119
+ "num_tokens": 9949074.0,
120
+ "step": 110
121
+ },
122
+ {
123
+ "entropy": 0.8867954194545746,
124
+ "epoch": 0.916030534351145,
125
+ "grad_norm": 0.28515625,
126
+ "learning_rate": 8.87312585581356e-05,
127
+ "loss": 0.0516,
128
+ "mean_token_accuracy": 0.978719773888588,
129
+ "num_tokens": 10850892.0,
130
+ "step": 120
131
+ },
132
+ {
133
+ "entropy": 0.8834987260401249,
134
+ "epoch": 0.9923664122137404,
135
+ "grad_norm": 0.40625,
136
+ "learning_rate": 8.634398749911691e-05,
137
+ "loss": 0.0539,
138
+ "mean_token_accuracy": 0.9772126525640488,
139
+ "num_tokens": 11751661.0,
140
+ "step": 130
141
+ },
142
+ {
143
+ "entropy": 0.8976177863776684,
144
+ "epoch": 1.0687022900763359,
145
+ "grad_norm": 0.36328125,
146
+ "learning_rate": 8.378210154479702e-05,
147
+ "loss": 0.0448,
148
+ "mean_token_accuracy": 0.980753519386053,
149
+ "num_tokens": 12646838.0,
150
+ "step": 140
151
+ },
152
+ {
153
+ "entropy": 0.8704435057938099,
154
+ "epoch": 1.1450381679389312,
155
+ "grad_norm": 0.333984375,
156
+ "learning_rate": 8.106436196351265e-05,
157
+ "loss": 0.0474,
158
+ "mean_token_accuracy": 0.9792590379714966,
159
+ "num_tokens": 13541728.0,
160
+ "step": 150
161
+ },
162
+ {
163
+ "entropy": 0.8593805082142353,
164
+ "epoch": 1.2213740458015268,
165
+ "grad_norm": 0.3125,
166
+ "learning_rate": 7.821067137484279e-05,
167
+ "loss": 0.0472,
168
+ "mean_token_accuracy": 0.9803130567073822,
169
+ "num_tokens": 14452617.0,
170
+ "step": 160
171
+ },
172
+ {
173
+ "entropy": 0.8790079154074192,
174
+ "epoch": 1.297709923664122,
175
+ "grad_norm": 0.3359375,
176
+ "learning_rate": 7.524192799823925e-05,
177
+ "loss": 0.0457,
178
+ "mean_token_accuracy": 0.9807212583720684,
179
+ "num_tokens": 15348770.0,
180
+ "step": 170
181
+ },
182
+ {
183
+ "entropy": 0.9099812150001526,
184
+ "epoch": 1.3740458015267176,
185
+ "grad_norm": 0.3125,
186
+ "learning_rate": 7.217987261065473e-05,
187
+ "loss": 0.0468,
188
+ "mean_token_accuracy": 0.9811236143112183,
189
+ "num_tokens": 16260924.0,
190
+ "step": 180
191
+ },
192
+ {
193
+ "entropy": 0.9149384334683418,
194
+ "epoch": 1.450381679389313,
195
+ "grad_norm": 0.28515625,
196
+ "learning_rate": 6.904692933393251e-05,
197
+ "loss": 0.0469,
198
+ "mean_token_accuracy": 0.9806007631123066,
199
+ "num_tokens": 17172435.0,
200
+ "step": 190
201
+ },
202
+ {
203
+ "entropy": 0.8875113040208816,
204
+ "epoch": 1.5267175572519083,
205
+ "grad_norm": 0.244140625,
206
+ "learning_rate": 6.586604141790736e-05,
207
+ "loss": 0.0413,
208
+ "mean_token_accuracy": 0.9820852629840374,
209
+ "num_tokens": 18072331.0,
210
+ "step": 200
211
+ },
212
+ {
213
+ "entropy": 0.8821073897182942,
214
+ "epoch": 1.6030534351145038,
215
+ "grad_norm": 0.34375,
216
+ "learning_rate": 6.266050322181522e-05,
217
+ "loss": 0.0463,
218
+ "mean_token_accuracy": 0.9804246053099632,
219
+ "num_tokens": 18986424.0,
220
+ "step": 210
221
+ },
222
+ {
223
+ "entropy": 0.8856651082634925,
224
+ "epoch": 1.6793893129770994,
225
+ "grad_norm": 0.30859375,
226
+ "learning_rate": 5.945378962444953e-05,
227
+ "loss": 0.0464,
228
+ "mean_token_accuracy": 0.979961882531643,
229
+ "num_tokens": 19881328.0,
230
+ "step": 220
231
+ },
232
+ {
233
+ "entropy": 0.8791401267051697,
234
+ "epoch": 1.7557251908396947,
235
+ "grad_norm": 0.25,
236
+ "learning_rate": 5.6269384112332246e-05,
237
+ "loss": 0.0447,
238
+ "mean_token_accuracy": 0.9799509704113006,
239
+ "num_tokens": 20777557.0,
240
+ "step": 230
241
+ },
242
+ {
243
+ "entropy": 0.8537083186209202,
244
+ "epoch": 1.83206106870229,
245
+ "grad_norm": 0.310546875,
246
+ "learning_rate": 5.313060680484838e-05,
247
+ "loss": 0.0434,
248
+ "mean_token_accuracy": 0.9819154985249042,
249
+ "num_tokens": 21679988.0,
250
+ "step": 240
251
+ },
252
+ {
253
+ "entropy": 0.8548756577074528,
254
+ "epoch": 1.9083969465648853,
255
+ "grad_norm": 0.2578125,
256
+ "learning_rate": 5.006044367575511e-05,
257
+ "loss": 0.0465,
258
+ "mean_token_accuracy": 0.9799104005098342,
259
+ "num_tokens": 22584307.0,
260
+ "step": 250
261
+ },
262
+ {
263
+ "entropy": 0.8446093052625656,
264
+ "epoch": 1.984732824427481,
265
+ "grad_norm": 0.271484375,
266
+ "learning_rate": 4.708137822171435e-05,
267
+ "loss": 0.045,
268
+ "mean_token_accuracy": 0.981216999143362,
269
+ "num_tokens": 23487511.0,
270
+ "step": 260
271
+ },
272
+ {
273
+ "entropy": 0.8299099013209343,
274
+ "epoch": 2.0610687022900764,
275
+ "grad_norm": 0.2216796875,
276
+ "learning_rate": 4.4215226810578697e-05,
277
+ "loss": 0.0388,
278
+ "mean_token_accuracy": 0.9837547279894352,
279
+ "num_tokens": 24391233.0,
280
+ "step": 270
281
+ },
282
+ {
283
+ "entropy": 0.7879593849182129,
284
+ "epoch": 2.1374045801526718,
285
+ "grad_norm": 0.2890625,
286
+ "learning_rate": 4.1482978915211736e-05,
287
+ "loss": 0.0401,
288
+ "mean_token_accuracy": 0.982824681699276,
289
+ "num_tokens": 25290459.0,
290
+ "step": 280
291
+ },
292
+ {
293
+ "entropy": 0.7747602254152298,
294
+ "epoch": 2.213740458015267,
295
+ "grad_norm": 0.279296875,
296
+ "learning_rate": 3.890464340284692e-05,
297
+ "loss": 0.0379,
298
+ "mean_token_accuracy": 0.9832462161779404,
299
+ "num_tokens": 26188999.0,
300
+ "step": 290
301
+ },
302
+ {
303
+ "entropy": 0.7617808029055595,
304
+ "epoch": 2.2900763358778624,
305
+ "grad_norm": 0.23828125,
306
+ "learning_rate": 3.649910200564253e-05,
307
+ "loss": 0.0386,
308
+ "mean_token_accuracy": 0.9828567236661911,
309
+ "num_tokens": 27102093.0,
310
+ "step": 300
311
+ },
312
+ {
313
+ "entropy": 0.7373107887804509,
314
+ "epoch": 2.366412213740458,
315
+ "grad_norm": 0.2392578125,
316
+ "learning_rate": 3.42839710455007e-05,
317
+ "loss": 0.0413,
318
+ "mean_token_accuracy": 0.9825137570500374,
319
+ "num_tokens": 28001749.0,
320
+ "step": 310
321
+ },
322
+ {
323
+ "entropy": 0.7243033863604069,
324
+ "epoch": 2.4427480916030535,
325
+ "grad_norm": 0.30078125,
326
+ "learning_rate": 3.2275472425771183e-05,
327
+ "loss": 0.038,
328
+ "mean_token_accuracy": 0.9839053072035313,
329
+ "num_tokens": 28899892.0,
330
+ "step": 320
331
+ },
332
+ {
333
+ "entropy": 0.7302201606333256,
334
+ "epoch": 2.519083969465649,
335
+ "grad_norm": 0.25390625,
336
+ "learning_rate": 3.0488314834596443e-05,
337
+ "loss": 0.0362,
338
+ "mean_token_accuracy": 0.9841879785060883,
339
+ "num_tokens": 29805646.0,
340
+ "step": 330
341
+ },
342
+ {
343
+ "entropy": 0.7226043172180653,
344
+ "epoch": 2.595419847328244,
345
+ "grad_norm": 0.33203125,
346
+ "learning_rate": 2.8935586029872707e-05,
347
+ "loss": 0.0396,
348
+ "mean_token_accuracy": 0.9833728171885013,
349
+ "num_tokens": 30704821.0,
350
+ "step": 340
351
+ },
352
+ {
353
+ "entropy": 0.7304494515061378,
354
+ "epoch": 2.67175572519084,
355
+ "grad_norm": 0.2275390625,
356
+ "learning_rate": 2.7628656994648772e-05,
357
+ "loss": 0.0385,
358
+ "mean_token_accuracy": 0.9834493272006511,
359
+ "num_tokens": 31612522.0,
360
+ "step": 350
361
+ },
362
+ {
363
+ "entropy": 0.7172894328832626,
364
+ "epoch": 2.7480916030534353,
365
+ "grad_norm": 0.228515625,
366
+ "learning_rate": 2.6577098664853885e-05,
367
+ "loss": 0.0368,
368
+ "mean_token_accuracy": 0.9831421509385109,
369
+ "num_tokens": 32509962.0,
370
+ "step": 360
371
+ },
372
+ {
373
+ "entropy": 0.7212371945381164,
374
+ "epoch": 2.8244274809160306,
375
+ "grad_norm": 0.326171875,
376
+ "learning_rate": 2.5788611839176458e-05,
377
+ "loss": 0.0391,
378
+ "mean_token_accuracy": 0.9827444940805435,
379
+ "num_tokens": 33422583.0,
380
+ "step": 370
381
+ },
382
+ {
383
+ "entropy": 0.7051329500973225,
384
+ "epoch": 2.900763358778626,
385
+ "grad_norm": 0.34375,
386
+ "learning_rate": 2.5268970784379448e-05,
387
+ "loss": 0.0398,
388
+ "mean_token_accuracy": 0.9825506798923016,
389
+ "num_tokens": 34314547.0,
390
+ "step": 380
391
+ },
392
+ {
393
+ "entropy": 0.7103805348277092,
394
+ "epoch": 2.9770992366412212,
395
+ "grad_norm": 0.3203125,
396
+ "learning_rate": 2.5021980949043162e-05,
397
+ "loss": 0.0401,
398
+ "mean_token_accuracy": 0.9823778592050075,
399
+ "num_tokens": 35226301.0,
400
+ "step": 390
401
+ }
402
+ ],
403
+ "logging_steps": 10,
404
+ "max_steps": 393,
405
+ "num_input_tokens_seen": 0,
406
+ "num_train_epochs": 3,
407
+ "save_steps": 500,
408
+ "stateful_callbacks": {
409
+ "TrainerControl": {
410
+ "args": {
411
+ "should_epoch_stop": false,
412
+ "should_evaluate": false,
413
+ "should_log": false,
414
+ "should_save": true,
415
+ "should_training_stop": false
416
+ },
417
+ "attributes": {}
418
+ }
419
+ },
420
+ "total_flos": 3.502686600575416e+17,
421
+ "train_batch_size": 8,
422
+ "trial_name": null,
423
+ "trial_params": null
424
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0faf40b1e3ec65094c353e9859346aaec62caa9c94d5f74d443dcda5240f542
3
+ size 6353
vocab.json ADDED
The diff for this file is too large to render. See raw diff