foryui commited on
Commit
c20f3f3
·
verified ·
1 Parent(s): 42dbe78

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: naver-hyperclovax/HyperCLOVAX-SEED-Text-Instruct-0.5B
3
+ library_name: transformers
4
+ model_name: komit_think
5
+ tags:
6
+ - generated_from_trainer
7
+ - sft
8
+ - trl
9
+ licence: license
10
+ ---
11
+
12
+ # Model Card for komit_think
13
+
14
+ This model is a fine-tuned version of [naver-hyperclovax/HyperCLOVAX-SEED-Text-Instruct-0.5B](https://huggingface.co/naver-hyperclovax/HyperCLOVAX-SEED-Text-Instruct-0.5B).
15
+ It has been trained using [TRL](https://github.com/huggingface/trl).
16
+
17
+ ## Quick start
18
+
19
+ ```python
20
+ from transformers import pipeline
21
+
22
+ question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
23
+ generator = pipeline("text-generation", model="None", device="cuda")
24
+ output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
25
+ print(output["generated_text"])
26
+ ```
27
+
28
+ ## Training procedure
29
+
30
+
31
+
32
+
33
+ This model was trained with SFT.
34
+
35
+ ### Framework versions
36
+
37
+ - TRL: 0.23.1
38
+ - Transformers: 4.57.0
39
+ - Pytorch: 2.9.0
40
+ - Datasets: 4.2.0
41
+ - Tokenizers: 0.22.1
42
+
43
+ ## Citations
44
+
45
+
46
+
47
+ Cite TRL as:
48
+
49
+ ```bibtex
50
+ @misc{vonwerra2022trl,
51
+ title = {{TRL: Transformer Reinforcement Learning}},
52
+ author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
53
+ year = 2020,
54
+ journal = {GitHub repository},
55
+ publisher = {GitHub},
56
+ howpublished = {\url{https://github.com/huggingface/trl}}
57
+ }
58
+ ```
added_tokens.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<EMAIL>": 110521,
3
+ "<KEY>": 110522,
4
+ "<NAME>": 110520,
5
+ "<PASSWORD>": 110523,
6
+ "<code_to_intermediate>": 110502,
7
+ "<empty_output>": 110501,
8
+ "<file_sep>": 110492,
9
+ "<intermediate_to_code>": 110503,
10
+ "<issue_closed>": 110495,
11
+ "<issue_comment>": 110494,
12
+ "<issue_start>": 110493,
13
+ "<jupyter_code>": 110498,
14
+ "<jupyter_output>": 110499,
15
+ "<jupyter_script>": 110500,
16
+ "<jupyter_start>": 110496,
17
+ "<jupyter_text>": 110497,
18
+ "<pr>": 110504,
19
+ "<pr_base>": 110507,
20
+ "<pr_base_code>": 110509,
21
+ "<pr_comment>": 110512,
22
+ "<pr_diff>": 110510,
23
+ "<pr_diff_hunk>": 110511,
24
+ "<pr_diff_hunk_comment_line>": 110519,
25
+ "<pr_event_id>": 110513,
26
+ "<pr_file>": 110508,
27
+ "<pr_in_reply_to_comment_id>": 110518,
28
+ "<pr_in_reply_to_review_id>": 110517,
29
+ "<pr_is_merged>": 110506,
30
+ "<pr_review>": 110514,
31
+ "<pr_review_comment>": 110516,
32
+ "<pr_review_state>": 110515,
33
+ "<pr_status>": 110505,
34
+ "<repo_name>": 110491
35
+ }
chat_template.jinja ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '
2
+ ' + message['content'] + '<|im_end|>' + '
3
+ '}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
4
+ ' }}{% endif %}
checkpoint-954/added_tokens.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<EMAIL>": 110521,
3
+ "<KEY>": 110522,
4
+ "<NAME>": 110520,
5
+ "<PASSWORD>": 110523,
6
+ "<code_to_intermediate>": 110502,
7
+ "<empty_output>": 110501,
8
+ "<file_sep>": 110492,
9
+ "<intermediate_to_code>": 110503,
10
+ "<issue_closed>": 110495,
11
+ "<issue_comment>": 110494,
12
+ "<issue_start>": 110493,
13
+ "<jupyter_code>": 110498,
14
+ "<jupyter_output>": 110499,
15
+ "<jupyter_script>": 110500,
16
+ "<jupyter_start>": 110496,
17
+ "<jupyter_text>": 110497,
18
+ "<pr>": 110504,
19
+ "<pr_base>": 110507,
20
+ "<pr_base_code>": 110509,
21
+ "<pr_comment>": 110512,
22
+ "<pr_diff>": 110510,
23
+ "<pr_diff_hunk>": 110511,
24
+ "<pr_diff_hunk_comment_line>": 110519,
25
+ "<pr_event_id>": 110513,
26
+ "<pr_file>": 110508,
27
+ "<pr_in_reply_to_comment_id>": 110518,
28
+ "<pr_in_reply_to_review_id>": 110517,
29
+ "<pr_is_merged>": 110506,
30
+ "<pr_review>": 110514,
31
+ "<pr_review_comment>": 110516,
32
+ "<pr_review_state>": 110515,
33
+ "<pr_status>": 110505,
34
+ "<repo_name>": 110491
35
+ }
checkpoint-954/chat_template.jinja ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '
2
+ ' + message['content'] + '<|im_end|>' + '
3
+ '}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
4
+ ' }}{% endif %}
checkpoint-954/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 100257,
8
+ "dtype": "bfloat16",
9
+ "end_token_id": 100257,
10
+ "eos_token_id": 100275,
11
+ "head_dim": 128,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 1024,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 4096,
16
+ "max_position_embeddings": 8192,
17
+ "mlp_bias": false,
18
+ "model_type": "llama",
19
+ "num_attention_heads": 16,
20
+ "num_hidden_layers": 24,
21
+ "num_key_value_heads": 8,
22
+ "pad_token_id": 100257,
23
+ "pretraining_tp": 1,
24
+ "resid_pdrop": 0.2,
25
+ "rms_norm_eps": 1e-05,
26
+ "rope_scaling": null,
27
+ "rope_theta": 500000,
28
+ "tie_word_embeddings": true,
29
+ "transformers_version": "4.57.0",
30
+ "use_cache": false,
31
+ "vocab_size": 110592
32
+ }
checkpoint-954/generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 100257,
4
+ "eos_token_id": [
5
+ 100275,
6
+ 100257
7
+ ],
8
+ "pad_token_id": 100257,
9
+ "transformers_version": "4.57.0",
10
+ "use_cache": false
11
+ }
checkpoint-954/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-954/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b9d78169a832d7524c669a9807e93a824ce792d924b2e1681d7704b24c55c92
3
+ size 1132587360
checkpoint-954/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eea9d22a117d989146e6d9fe7312c4ec5914ef6a6c753f243f570c30d40d865a
3
+ size 4530385511
checkpoint-954/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36ecb75af8f0ebd08f22e4f5eb8df69d56021c6157f954d1ef928401abbd161b
3
+ size 14917
checkpoint-954/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:644748842953950fc159b43c5f23f8dfe3c56c56719397021e8b7ec4761a0d3f
3
+ size 14917
checkpoint-954/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1f28d25a5cb401d73efbe0df1b91ddf24c33f0cc64b73579bd3841dc8d3ca9e
3
+ size 1465
checkpoint-954/special_tokens_map.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<|fim_prefix|>",
5
+ "<|fim_middle|>",
6
+ "<|fim_suffix|>",
7
+ "<|endofprompt|>",
8
+ "<|_unuse_missing_100256|>",
9
+ "<|_unuse_missing_100261|>",
10
+ "<|_unuse_missing_100262|>",
11
+ "<|_unuse_missing_100263|>",
12
+ "<|_unuse_missing_100264|>",
13
+ "<|_unuse_missing_100265|>",
14
+ "<|_unuse_missing_100266|>",
15
+ "<|_unuse_missing_100267|>",
16
+ "<|_unuse_missing_100268|>",
17
+ "<|_unuse_missing_100269|>",
18
+ "<|_unuse_missing_100270|>",
19
+ "<|_unuse_missing_100271|>",
20
+ "<|im_start|>",
21
+ "<|im_end|>",
22
+ "<|stop|>",
23
+ "<|endofturn|>",
24
+ "<repo_name>",
25
+ "<file_sep>",
26
+ "<issue_start>",
27
+ "<issue_comment>",
28
+ "<issue_closed>",
29
+ "<jupyter_start>",
30
+ "<jupyter_text>",
31
+ "<jupyter_code>",
32
+ "<jupyter_output>",
33
+ "<jupyter_script>",
34
+ "<empty_output>",
35
+ "<code_to_intermediate>",
36
+ "<intermediate_to_code>",
37
+ "<pr>",
38
+ "<pr_status>",
39
+ "<pr_is_merged>",
40
+ "<pr_base>",
41
+ "<pr_file>",
42
+ "<pr_base_code>",
43
+ "<pr_diff>",
44
+ "<pr_diff_hunk>",
45
+ "<pr_comment>",
46
+ "<pr_event_id>",
47
+ "<pr_review>",
48
+ "<pr_review_state>",
49
+ "<pr_review_comment>",
50
+ "<pr_in_reply_to_review_id>",
51
+ "<pr_in_reply_to_comment_id>",
52
+ "<pr_diff_hunk_comment_line>",
53
+ "<NAME>",
54
+ "<EMAIL>",
55
+ "<KEY>",
56
+ "<PASSWORD>"
57
+ ],
58
+ "bos_token": {
59
+ "content": "<|endoftext|>",
60
+ "lstrip": false,
61
+ "normalized": false,
62
+ "rstrip": false,
63
+ "single_word": false
64
+ },
65
+ "eos_token": {
66
+ "content": "<|endofturn|>",
67
+ "lstrip": false,
68
+ "normalized": false,
69
+ "rstrip": false,
70
+ "single_word": false
71
+ },
72
+ "pad_token": {
73
+ "content": "<|endoftext|>",
74
+ "lstrip": false,
75
+ "normalized": false,
76
+ "rstrip": false,
77
+ "single_word": false
78
+ },
79
+ "unk_token": {
80
+ "content": "<|endoftext|>",
81
+ "lstrip": false,
82
+ "normalized": false,
83
+ "rstrip": false,
84
+ "single_word": false
85
+ }
86
+ }
checkpoint-954/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-954/tokenizer_config.json ADDED
@@ -0,0 +1,501 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "100256": {
5
+ "content": "<|_unuse_missing_100256|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "100257": {
13
+ "content": "<|endoftext|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "100258": {
21
+ "content": "<|fim_prefix|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "100259": {
29
+ "content": "<|fim_middle|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "100260": {
37
+ "content": "<|fim_suffix|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "100261": {
45
+ "content": "<|_unuse_missing_100261|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "100262": {
53
+ "content": "<|_unuse_missing_100262|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "100263": {
61
+ "content": "<|_unuse_missing_100263|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "100264": {
69
+ "content": "<|_unuse_missing_100264|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "100265": {
77
+ "content": "<|_unuse_missing_100265|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "100266": {
85
+ "content": "<|_unuse_missing_100266|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "100267": {
93
+ "content": "<|_unuse_missing_100267|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "100268": {
101
+ "content": "<|_unuse_missing_100268|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "100269": {
109
+ "content": "<|_unuse_missing_100269|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "100270": {
117
+ "content": "<|_unuse_missing_100270|>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "100271": {
125
+ "content": "<|_unuse_missing_100271|>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "100272": {
133
+ "content": "<|im_start|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "100273": {
141
+ "content": "<|im_end|>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "100274": {
149
+ "content": "<|stop|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "100275": {
157
+ "content": "<|endofturn|>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "100276": {
165
+ "content": "<|endofprompt|>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "110491": {
173
+ "content": "<repo_name>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "110492": {
181
+ "content": "<file_sep>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "110493": {
189
+ "content": "<issue_start>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "110494": {
197
+ "content": "<issue_comment>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "110495": {
205
+ "content": "<issue_closed>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "110496": {
213
+ "content": "<jupyter_start>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "110497": {
221
+ "content": "<jupyter_text>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "110498": {
229
+ "content": "<jupyter_code>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "110499": {
237
+ "content": "<jupyter_output>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "110500": {
245
+ "content": "<jupyter_script>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "110501": {
253
+ "content": "<empty_output>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "110502": {
261
+ "content": "<code_to_intermediate>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "110503": {
269
+ "content": "<intermediate_to_code>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "110504": {
277
+ "content": "<pr>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "110505": {
285
+ "content": "<pr_status>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "110506": {
293
+ "content": "<pr_is_merged>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "110507": {
301
+ "content": "<pr_base>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "110508": {
309
+ "content": "<pr_file>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "110509": {
317
+ "content": "<pr_base_code>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "110510": {
325
+ "content": "<pr_diff>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "110511": {
333
+ "content": "<pr_diff_hunk>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "110512": {
341
+ "content": "<pr_comment>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "110513": {
349
+ "content": "<pr_event_id>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "110514": {
357
+ "content": "<pr_review>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "110515": {
365
+ "content": "<pr_review_state>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "110516": {
373
+ "content": "<pr_review_comment>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "110517": {
381
+ "content": "<pr_in_reply_to_review_id>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "110518": {
389
+ "content": "<pr_in_reply_to_comment_id>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "110519": {
397
+ "content": "<pr_diff_hunk_comment_line>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "110520": {
405
+ "content": "<NAME>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "110521": {
413
+ "content": "<EMAIL>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "110522": {
421
+ "content": "<KEY>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "110523": {
429
+ "content": "<PASSWORD>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ }
436
+ },
437
+ "additional_special_tokens": [
438
+ "<|endoftext|>",
439
+ "<|fim_prefix|>",
440
+ "<|fim_middle|>",
441
+ "<|fim_suffix|>",
442
+ "<|endofprompt|>",
443
+ "<|_unuse_missing_100256|>",
444
+ "<|_unuse_missing_100261|>",
445
+ "<|_unuse_missing_100262|>",
446
+ "<|_unuse_missing_100263|>",
447
+ "<|_unuse_missing_100264|>",
448
+ "<|_unuse_missing_100265|>",
449
+ "<|_unuse_missing_100266|>",
450
+ "<|_unuse_missing_100267|>",
451
+ "<|_unuse_missing_100268|>",
452
+ "<|_unuse_missing_100269|>",
453
+ "<|_unuse_missing_100270|>",
454
+ "<|_unuse_missing_100271|>",
455
+ "<|im_start|>",
456
+ "<|im_end|>",
457
+ "<|stop|>",
458
+ "<|endofturn|>",
459
+ "<repo_name>",
460
+ "<file_sep>",
461
+ "<issue_start>",
462
+ "<issue_comment>",
463
+ "<issue_closed>",
464
+ "<jupyter_start>",
465
+ "<jupyter_text>",
466
+ "<jupyter_code>",
467
+ "<jupyter_output>",
468
+ "<jupyter_script>",
469
+ "<empty_output>",
470
+ "<code_to_intermediate>",
471
+ "<intermediate_to_code>",
472
+ "<pr>",
473
+ "<pr_status>",
474
+ "<pr_is_merged>",
475
+ "<pr_base>",
476
+ "<pr_file>",
477
+ "<pr_base_code>",
478
+ "<pr_diff>",
479
+ "<pr_diff_hunk>",
480
+ "<pr_comment>",
481
+ "<pr_event_id>",
482
+ "<pr_review>",
483
+ "<pr_review_state>",
484
+ "<pr_review_comment>",
485
+ "<pr_in_reply_to_review_id>",
486
+ "<pr_in_reply_to_comment_id>",
487
+ "<pr_diff_hunk_comment_line>",
488
+ "<NAME>",
489
+ "<EMAIL>",
490
+ "<KEY>",
491
+ "<PASSWORD>"
492
+ ],
493
+ "bos_token": "<|endoftext|>",
494
+ "clean_up_tokenization_spaces": true,
495
+ "eos_token": "<|endofturn|>",
496
+ "extra_special_tokens": {},
497
+ "model_max_length": 1000000000000000019884624838656,
498
+ "pad_token": "<|endoftext|>",
499
+ "tokenizer_class": "GPT2Tokenizer",
500
+ "unk_token": "<|endoftext|>"
501
+ }
checkpoint-954/trainer_state.json ADDED
@@ -0,0 +1,515 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 954,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "entropy": 1.7167337208986282,
14
+ "epoch": 0.06289308176100629,
15
+ "grad_norm": 3.375,
16
+ "learning_rate": 0.00013103448275862068,
17
+ "loss": 1.8471,
18
+ "mean_token_accuracy": 0.5880333345383406,
19
+ "num_tokens": 259213.0,
20
+ "step": 20
21
+ },
22
+ {
23
+ "entropy": 1.4499711275100708,
24
+ "epoch": 0.12578616352201258,
25
+ "grad_norm": 3.265625,
26
+ "learning_rate": 0.00019994233071892056,
27
+ "loss": 1.4801,
28
+ "mean_token_accuracy": 0.6453170858323574,
29
+ "num_tokens": 517773.0,
30
+ "step": 40
31
+ },
32
+ {
33
+ "entropy": 1.4044303432106973,
34
+ "epoch": 0.18867924528301888,
35
+ "grad_norm": 2.6875,
36
+ "learning_rate": 0.00019948137548308502,
37
+ "loss": 1.4267,
38
+ "mean_token_accuracy": 0.6576278351247311,
39
+ "num_tokens": 782091.0,
40
+ "step": 60
41
+ },
42
+ {
43
+ "entropy": 1.2887477368116378,
44
+ "epoch": 0.25157232704402516,
45
+ "grad_norm": 2.484375,
46
+ "learning_rate": 0.00019856159103477086,
47
+ "loss": 1.3093,
48
+ "mean_token_accuracy": 0.6782839238643646,
49
+ "num_tokens": 1043334.0,
50
+ "step": 80
51
+ },
52
+ {
53
+ "entropy": 1.2444264158606528,
54
+ "epoch": 0.31446540880503143,
55
+ "grad_norm": 2.375,
56
+ "learning_rate": 0.0001971872196150208,
57
+ "loss": 1.2565,
58
+ "mean_token_accuracy": 0.6892561309039593,
59
+ "num_tokens": 1303675.0,
60
+ "step": 100
61
+ },
62
+ {
63
+ "entropy": 1.1685370743274688,
64
+ "epoch": 0.37735849056603776,
65
+ "grad_norm": 2.734375,
66
+ "learning_rate": 0.0001953646001164479,
67
+ "loss": 1.1856,
68
+ "mean_token_accuracy": 0.7019865214824677,
69
+ "num_tokens": 1562723.0,
70
+ "step": 120
71
+ },
72
+ {
73
+ "entropy": 1.1311725586652757,
74
+ "epoch": 0.44025157232704404,
75
+ "grad_norm": 2.140625,
76
+ "learning_rate": 0.0001931021388469174,
77
+ "loss": 1.1333,
78
+ "mean_token_accuracy": 0.7124114476144314,
79
+ "num_tokens": 1829896.0,
80
+ "step": 140
81
+ },
82
+ {
83
+ "entropy": 1.0521086759865284,
84
+ "epoch": 0.5031446540880503,
85
+ "grad_norm": 1.9765625,
86
+ "learning_rate": 0.0001904102707578715,
87
+ "loss": 1.0531,
88
+ "mean_token_accuracy": 0.7276136085391045,
89
+ "num_tokens": 2088529.0,
90
+ "step": 160
91
+ },
92
+ {
93
+ "entropy": 0.9986762247979641,
94
+ "epoch": 0.5660377358490566,
95
+ "grad_norm": 1.921875,
96
+ "learning_rate": 0.00018730141131611882,
97
+ "loss": 0.9972,
98
+ "mean_token_accuracy": 0.7383999407291413,
99
+ "num_tokens": 2348115.0,
100
+ "step": 180
101
+ },
102
+ {
103
+ "entropy": 0.953403378278017,
104
+ "epoch": 0.6289308176100629,
105
+ "grad_norm": 2.0625,
106
+ "learning_rate": 0.00018378989924106736,
107
+ "loss": 0.9489,
108
+ "mean_token_accuracy": 0.7507018215954304,
109
+ "num_tokens": 2616192.0,
110
+ "step": 200
111
+ },
112
+ {
113
+ "entropy": 0.9200813092291356,
114
+ "epoch": 0.6918238993710691,
115
+ "grad_norm": 1.7109375,
116
+ "learning_rate": 0.00017989193037150784,
117
+ "loss": 0.9149,
118
+ "mean_token_accuracy": 0.7585780128836632,
119
+ "num_tokens": 2880052.0,
120
+ "step": 220
121
+ },
122
+ {
123
+ "entropy": 0.8741249494254589,
124
+ "epoch": 0.7547169811320755,
125
+ "grad_norm": 1.65625,
126
+ "learning_rate": 0.00017562548296696875,
127
+ "loss": 0.8616,
128
+ "mean_token_accuracy": 0.77188064083457,
129
+ "num_tokens": 3146349.0,
130
+ "step": 240
131
+ },
132
+ {
133
+ "entropy": 0.8663847006857395,
134
+ "epoch": 0.8176100628930818,
135
+ "grad_norm": 1.7109375,
136
+ "learning_rate": 0.00017101023478816857,
137
+ "loss": 0.8558,
138
+ "mean_token_accuracy": 0.7727201536297799,
139
+ "num_tokens": 3413278.0,
140
+ "step": 260
141
+ },
142
+ {
143
+ "entropy": 0.8172553092241287,
144
+ "epoch": 0.8805031446540881,
145
+ "grad_norm": 1.9453125,
146
+ "learning_rate": 0.00016606747233900815,
147
+ "loss": 0.8077,
148
+ "mean_token_accuracy": 0.7835095874965191,
149
+ "num_tokens": 3671216.0,
150
+ "step": 280
151
+ },
152
+ {
153
+ "entropy": 0.7807140216231346,
154
+ "epoch": 0.9433962264150944,
155
+ "grad_norm": 1.4609375,
156
+ "learning_rate": 0.00016081999268869766,
157
+ "loss": 0.7633,
158
+ "mean_token_accuracy": 0.7935986362397671,
159
+ "num_tokens": 3933230.0,
160
+ "step": 300
161
+ },
162
+ {
163
+ "entropy": 0.7699245184659957,
164
+ "epoch": 1.0062893081761006,
165
+ "grad_norm": 1.625,
166
+ "learning_rate": 0.00015529199832683635,
167
+ "loss": 0.745,
168
+ "mean_token_accuracy": 0.7994328059256077,
169
+ "num_tokens": 4195595.0,
170
+ "step": 320
171
+ },
172
+ {
173
+ "entropy": 0.5780875764787197,
174
+ "epoch": 1.069182389937107,
175
+ "grad_norm": 1.40625,
176
+ "learning_rate": 0.00014950898553639505,
177
+ "loss": 0.5571,
178
+ "mean_token_accuracy": 0.8389500640332699,
179
+ "num_tokens": 4458130.0,
180
+ "step": 340
181
+ },
182
+ {
183
+ "entropy": 0.5987856678664685,
184
+ "epoch": 1.1320754716981132,
185
+ "grad_norm": 1.2578125,
186
+ "learning_rate": 0.00014349762679944896,
187
+ "loss": 0.5776,
188
+ "mean_token_accuracy": 0.833509799093008,
189
+ "num_tokens": 4715029.0,
190
+ "step": 360
191
+ },
192
+ {
193
+ "entropy": 0.5708689916878938,
194
+ "epoch": 1.1949685534591195,
195
+ "grad_norm": 1.2265625,
196
+ "learning_rate": 0.00013728564777803088,
197
+ "loss": 0.548,
198
+ "mean_token_accuracy": 0.8422755621373653,
199
+ "num_tokens": 4977397.0,
200
+ "step": 380
201
+ },
202
+ {
203
+ "entropy": 0.5769863951951265,
204
+ "epoch": 1.2578616352201257,
205
+ "grad_norm": 1.4453125,
206
+ "learning_rate": 0.00013090169943749476,
207
+ "loss": 0.5558,
208
+ "mean_token_accuracy": 0.8399138063192367,
209
+ "num_tokens": 5241605.0,
210
+ "step": 400
211
+ },
212
+ {
213
+ "entropy": 0.5708554539829492,
214
+ "epoch": 1.320754716981132,
215
+ "grad_norm": 1.3828125,
216
+ "learning_rate": 0.00012437522590218417,
217
+ "loss": 0.5537,
218
+ "mean_token_accuracy": 0.8393329657614231,
219
+ "num_tokens": 5504507.0,
220
+ "step": 420
221
+ },
222
+ {
223
+ "entropy": 0.5426693111658096,
224
+ "epoch": 1.3836477987421385,
225
+ "grad_norm": 1.3125,
226
+ "learning_rate": 0.00011773632865288309,
227
+ "loss": 0.5222,
228
+ "mean_token_accuracy": 0.8489867076277733,
229
+ "num_tokens": 5771877.0,
230
+ "step": 440
231
+ },
232
+ {
233
+ "entropy": 0.5280591409653426,
234
+ "epoch": 1.4465408805031448,
235
+ "grad_norm": 1.15625,
236
+ "learning_rate": 0.00011101562769239946,
237
+ "loss": 0.5056,
238
+ "mean_token_accuracy": 0.8546208754181862,
239
+ "num_tokens": 6037928.0,
240
+ "step": 460
241
+ },
242
+ {
243
+ "entropy": 0.5299916621297598,
244
+ "epoch": 1.509433962264151,
245
+ "grad_norm": 1.1875,
246
+ "learning_rate": 0.00010424412031961484,
247
+ "loss": 0.5098,
248
+ "mean_token_accuracy": 0.8524017453193664,
249
+ "num_tokens": 6301152.0,
250
+ "step": 480
251
+ },
252
+ {
253
+ "entropy": 0.5128771424293518,
254
+ "epoch": 1.5723270440251573,
255
+ "grad_norm": 1.1953125,
256
+ "learning_rate": 9.745303816336489e-05,
257
+ "loss": 0.4905,
258
+ "mean_token_accuracy": 0.857461416721344,
259
+ "num_tokens": 6564696.0,
260
+ "step": 500
261
+ },
262
+ {
263
+ "epoch": 1.5723270440251573,
264
+ "eval_entropy": 0.8891355726245074,
265
+ "eval_loss": 1.7230981588363647,
266
+ "eval_mean_token_accuracy": 0.6527422587578229,
267
+ "eval_num_tokens": 6564696.0,
268
+ "eval_runtime": 23.2991,
269
+ "eval_samples_per_second": 54.294,
270
+ "eval_steps_per_second": 13.606,
271
+ "step": 500
272
+ },
273
+ {
274
+ "entropy": 0.5226847343146801,
275
+ "epoch": 1.6352201257861636,
276
+ "grad_norm": 1.109375,
277
+ "learning_rate": 9.067370313554015e-05,
278
+ "loss": 0.4983,
279
+ "mean_token_accuracy": 0.8552649758756161,
280
+ "num_tokens": 6824569.0,
281
+ "step": 520
282
+ },
283
+ {
284
+ "entropy": 0.505075927451253,
285
+ "epoch": 1.6981132075471699,
286
+ "grad_norm": 1.015625,
287
+ "learning_rate": 8.393738296778228e-05,
288
+ "loss": 0.4868,
289
+ "mean_token_accuracy": 0.8583964839577675,
290
+ "num_tokens": 7089148.0,
291
+ "step": 540
292
+ },
293
+ {
294
+ "entropy": 0.48526292145252226,
295
+ "epoch": 1.7610062893081762,
296
+ "grad_norm": 1.0390625,
297
+ "learning_rate": 7.727514699807102e-05,
298
+ "loss": 0.4662,
299
+ "mean_token_accuracy": 0.8638391740620136,
300
+ "num_tokens": 7352826.0,
301
+ "step": 560
302
+ },
303
+ {
304
+ "entropy": 0.4718559980392456,
305
+ "epoch": 1.8238993710691824,
306
+ "grad_norm": 1.0,
307
+ "learning_rate": 7.071772287234497e-05,
308
+ "loss": 0.4539,
309
+ "mean_token_accuracy": 0.86636356189847,
310
+ "num_tokens": 7615145.0,
311
+ "step": 580
312
+ },
313
+ {
314
+ "entropy": 0.4803201053291559,
315
+ "epoch": 1.8867924528301887,
316
+ "grad_norm": 1.015625,
317
+ "learning_rate": 6.429535482207846e-05,
318
+ "loss": 0.4607,
319
+ "mean_token_accuracy": 0.8651525631546975,
320
+ "num_tokens": 7875359.0,
321
+ "step": 600
322
+ },
323
+ {
324
+ "entropy": 0.4741881676018238,
325
+ "epoch": 1.949685534591195,
326
+ "grad_norm": 1.03125,
327
+ "learning_rate": 5.8037664171468596e-05,
328
+ "loss": 0.4552,
329
+ "mean_token_accuracy": 0.8650328174233437,
330
+ "num_tokens": 8135302.0,
331
+ "step": 620
332
+ },
333
+ {
334
+ "entropy": 0.45415039733052254,
335
+ "epoch": 2.0125786163522013,
336
+ "grad_norm": 0.9375,
337
+ "learning_rate": 5.197351271760258e-05,
338
+ "loss": 0.4165,
339
+ "mean_token_accuracy": 0.8763279743492604,
340
+ "num_tokens": 8387542.0,
341
+ "step": 640
342
+ },
343
+ {
344
+ "entropy": 0.29347950834780934,
345
+ "epoch": 2.0754716981132075,
346
+ "grad_norm": 0.90234375,
347
+ "learning_rate": 4.6130869613725614e-05,
348
+ "loss": 0.2766,
349
+ "mean_token_accuracy": 0.911402253061533,
350
+ "num_tokens": 8651813.0,
351
+ "step": 660
352
+ },
353
+ {
354
+ "entropy": 0.2939343243837357,
355
+ "epoch": 2.138364779874214,
356
+ "grad_norm": 1.078125,
357
+ "learning_rate": 4.053668236957134e-05,
358
+ "loss": 0.2697,
359
+ "mean_token_accuracy": 0.912867172062397,
360
+ "num_tokens": 8911224.0,
361
+ "step": 680
362
+ },
363
+ {
364
+ "entropy": 0.28345808368176223,
365
+ "epoch": 2.20125786163522,
366
+ "grad_norm": 0.86328125,
367
+ "learning_rate": 3.5216752563729e-05,
368
+ "loss": 0.2554,
369
+ "mean_token_accuracy": 0.9172916606068611,
370
+ "num_tokens": 9176474.0,
371
+ "step": 700
372
+ },
373
+ {
374
+ "entropy": 0.280908421985805,
375
+ "epoch": 2.2641509433962264,
376
+ "grad_norm": 0.8671875,
377
+ "learning_rate": 3.019561684128823e-05,
378
+ "loss": 0.26,
379
+ "mean_token_accuracy": 0.9162154637277127,
380
+ "num_tokens": 9441860.0,
381
+ "step": 720
382
+ },
383
+ {
384
+ "entropy": 0.2842621823772788,
385
+ "epoch": 2.3270440251572326,
386
+ "grad_norm": 1.0234375,
387
+ "learning_rate": 2.549643374562549e-05,
388
+ "loss": 0.2596,
389
+ "mean_token_accuracy": 0.9167354732751847,
390
+ "num_tokens": 9703133.0,
391
+ "step": 740
392
+ },
393
+ {
394
+ "entropy": 0.27892835177481173,
395
+ "epoch": 2.389937106918239,
396
+ "grad_norm": 0.9375,
397
+ "learning_rate": 2.1140876906288086e-05,
398
+ "loss": 0.2578,
399
+ "mean_token_accuracy": 0.9169348455965519,
400
+ "num_tokens": 9967855.0,
401
+ "step": 760
402
+ },
403
+ {
404
+ "entropy": 0.28467819597572086,
405
+ "epoch": 2.452830188679245,
406
+ "grad_norm": 1.0390625,
407
+ "learning_rate": 1.7149035075615794e-05,
408
+ "loss": 0.2582,
409
+ "mean_token_accuracy": 0.9175108715891838,
410
+ "num_tokens": 10231742.0,
411
+ "step": 780
412
+ },
413
+ {
414
+ "entropy": 0.28742803949862716,
415
+ "epoch": 2.5157232704402515,
416
+ "grad_norm": 0.99609375,
417
+ "learning_rate": 1.3539319475152457e-05,
418
+ "loss": 0.2621,
419
+ "mean_token_accuracy": 0.9155104726552963,
420
+ "num_tokens": 10494852.0,
421
+ "step": 800
422
+ },
423
+ {
424
+ "entropy": 0.28122986797243354,
425
+ "epoch": 2.5786163522012577,
426
+ "grad_norm": 0.87109375,
427
+ "learning_rate": 1.0328378879185641e-05,
428
+ "loss": 0.2589,
429
+ "mean_token_accuracy": 0.9168910197913647,
430
+ "num_tokens": 10756838.0,
431
+ "step": 820
432
+ },
433
+ {
434
+ "entropy": 0.2812939999625087,
435
+ "epoch": 2.641509433962264,
436
+ "grad_norm": 0.890625,
437
+ "learning_rate": 7.531022827066858e-06,
438
+ "loss": 0.254,
439
+ "mean_token_accuracy": 0.9184671498835086,
440
+ "num_tokens": 11019018.0,
441
+ "step": 840
442
+ },
443
+ {
444
+ "entropy": 0.2865038698539138,
445
+ "epoch": 2.7044025157232703,
446
+ "grad_norm": 0.96484375,
447
+ "learning_rate": 5.160153318473815e-06,
448
+ "loss": 0.2603,
449
+ "mean_token_accuracy": 0.9162922762334347,
450
+ "num_tokens": 11279763.0,
451
+ "step": 860
452
+ },
453
+ {
454
+ "entropy": 0.2783814989030361,
455
+ "epoch": 2.767295597484277,
456
+ "grad_norm": 1.0703125,
457
+ "learning_rate": 3.226705306650113e-06,
458
+ "loss": 0.2516,
459
+ "mean_token_accuracy": 0.9185153238475323,
460
+ "num_tokens": 11543577.0,
461
+ "step": 880
462
+ },
463
+ {
464
+ "entropy": 0.2764579938724637,
465
+ "epoch": 2.830188679245283,
466
+ "grad_norm": 0.97265625,
467
+ "learning_rate": 1.7395962640806674e-06,
468
+ "loss": 0.2509,
469
+ "mean_token_accuracy": 0.9192341528832912,
470
+ "num_tokens": 11808287.0,
471
+ "step": 900
472
+ },
473
+ {
474
+ "entropy": 0.2764893140643835,
475
+ "epoch": 2.8930817610062896,
476
+ "grad_norm": 0.97265625,
477
+ "learning_rate": 7.05685053216465e-07,
478
+ "loss": 0.2521,
479
+ "mean_token_accuracy": 0.9190148741006852,
480
+ "num_tokens": 12069535.0,
481
+ "step": 920
482
+ },
483
+ {
484
+ "entropy": 0.28662141915410755,
485
+ "epoch": 2.9559748427672954,
486
+ "grad_norm": 0.94140625,
487
+ "learning_rate": 1.2974029194551262e-07,
488
+ "loss": 0.259,
489
+ "mean_token_accuracy": 0.9163000352680684,
490
+ "num_tokens": 12327274.0,
491
+ "step": 940
492
+ }
493
+ ],
494
+ "logging_steps": 20,
495
+ "max_steps": 954,
496
+ "num_input_tokens_seen": 0,
497
+ "num_train_epochs": 3,
498
+ "save_steps": 1000,
499
+ "stateful_callbacks": {
500
+ "TrainerControl": {
501
+ "args": {
502
+ "should_epoch_stop": false,
503
+ "should_evaluate": false,
504
+ "should_log": false,
505
+ "should_save": true,
506
+ "should_training_stop": true
507
+ },
508
+ "attributes": {}
509
+ }
510
+ },
511
+ "total_flos": 3.830808747547034e+16,
512
+ "train_batch_size": 2,
513
+ "trial_name": null,
514
+ "trial_params": null
515
+ }
checkpoint-954/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f387e81d92e356db4c4cfb01c6735f2f69325c2f41a8c19f4ddbb7f40487400
3
+ size 6225
checkpoint-954/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 100257,
8
+ "dtype": "bfloat16",
9
+ "end_token_id": 100257,
10
+ "eos_token_id": 100275,
11
+ "head_dim": 128,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 1024,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 4096,
16
+ "max_position_embeddings": 8192,
17
+ "mlp_bias": false,
18
+ "model_type": "llama",
19
+ "num_attention_heads": 16,
20
+ "num_hidden_layers": 24,
21
+ "num_key_value_heads": 8,
22
+ "pad_token_id": 100257,
23
+ "pretraining_tp": 1,
24
+ "resid_pdrop": 0.2,
25
+ "rms_norm_eps": 1e-05,
26
+ "rope_scaling": null,
27
+ "rope_theta": 500000,
28
+ "tie_word_embeddings": true,
29
+ "transformers_version": "4.57.0",
30
+ "use_cache": false,
31
+ "vocab_size": 110592
32
+ }
eval_summary.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "val_ppl_assistant_only": 4.050638059110232,
3
+ "mode": "think_only",
4
+ "notes": {
5
+ "train_on_think_utterance": true,
6
+ "response_template_detected": "<|im_start|>assistant\n"
7
+ }
8
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 100257,
4
+ "eos_token_id": [
5
+ 100275,
6
+ 100257
7
+ ],
8
+ "pad_token_id": 100257,
9
+ "transformers_version": "4.57.0",
10
+ "use_cache": false
11
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
metrics.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "val_ppl_assistant_only": 4.050638059110232
3
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b9d78169a832d7524c669a9807e93a824ce792d924b2e1681d7704b24c55c92
3
+ size 1132587360
special_tokens_map.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<|fim_prefix|>",
5
+ "<|fim_middle|>",
6
+ "<|fim_suffix|>",
7
+ "<|endofprompt|>",
8
+ "<|_unuse_missing_100256|>",
9
+ "<|_unuse_missing_100261|>",
10
+ "<|_unuse_missing_100262|>",
11
+ "<|_unuse_missing_100263|>",
12
+ "<|_unuse_missing_100264|>",
13
+ "<|_unuse_missing_100265|>",
14
+ "<|_unuse_missing_100266|>",
15
+ "<|_unuse_missing_100267|>",
16
+ "<|_unuse_missing_100268|>",
17
+ "<|_unuse_missing_100269|>",
18
+ "<|_unuse_missing_100270|>",
19
+ "<|_unuse_missing_100271|>",
20
+ "<|im_start|>",
21
+ "<|im_end|>",
22
+ "<|stop|>",
23
+ "<|endofturn|>",
24
+ "<repo_name>",
25
+ "<file_sep>",
26
+ "<issue_start>",
27
+ "<issue_comment>",
28
+ "<issue_closed>",
29
+ "<jupyter_start>",
30
+ "<jupyter_text>",
31
+ "<jupyter_code>",
32
+ "<jupyter_output>",
33
+ "<jupyter_script>",
34
+ "<empty_output>",
35
+ "<code_to_intermediate>",
36
+ "<intermediate_to_code>",
37
+ "<pr>",
38
+ "<pr_status>",
39
+ "<pr_is_merged>",
40
+ "<pr_base>",
41
+ "<pr_file>",
42
+ "<pr_base_code>",
43
+ "<pr_diff>",
44
+ "<pr_diff_hunk>",
45
+ "<pr_comment>",
46
+ "<pr_event_id>",
47
+ "<pr_review>",
48
+ "<pr_review_state>",
49
+ "<pr_review_comment>",
50
+ "<pr_in_reply_to_review_id>",
51
+ "<pr_in_reply_to_comment_id>",
52
+ "<pr_diff_hunk_comment_line>",
53
+ "<NAME>",
54
+ "<EMAIL>",
55
+ "<KEY>",
56
+ "<PASSWORD>"
57
+ ],
58
+ "bos_token": {
59
+ "content": "<|endoftext|>",
60
+ "lstrip": false,
61
+ "normalized": false,
62
+ "rstrip": false,
63
+ "single_word": false
64
+ },
65
+ "eos_token": {
66
+ "content": "<|endofturn|>",
67
+ "lstrip": false,
68
+ "normalized": false,
69
+ "rstrip": false,
70
+ "single_word": false
71
+ },
72
+ "pad_token": {
73
+ "content": "<|endoftext|>",
74
+ "lstrip": false,
75
+ "normalized": false,
76
+ "rstrip": false,
77
+ "single_word": false
78
+ },
79
+ "unk_token": {
80
+ "content": "<|endoftext|>",
81
+ "lstrip": false,
82
+ "normalized": false,
83
+ "rstrip": false,
84
+ "single_word": false
85
+ }
86
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,501 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "100256": {
5
+ "content": "<|_unuse_missing_100256|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "100257": {
13
+ "content": "<|endoftext|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "100258": {
21
+ "content": "<|fim_prefix|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "100259": {
29
+ "content": "<|fim_middle|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "100260": {
37
+ "content": "<|fim_suffix|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "100261": {
45
+ "content": "<|_unuse_missing_100261|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "100262": {
53
+ "content": "<|_unuse_missing_100262|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "100263": {
61
+ "content": "<|_unuse_missing_100263|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "100264": {
69
+ "content": "<|_unuse_missing_100264|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "100265": {
77
+ "content": "<|_unuse_missing_100265|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "100266": {
85
+ "content": "<|_unuse_missing_100266|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "100267": {
93
+ "content": "<|_unuse_missing_100267|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "100268": {
101
+ "content": "<|_unuse_missing_100268|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "100269": {
109
+ "content": "<|_unuse_missing_100269|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "100270": {
117
+ "content": "<|_unuse_missing_100270|>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "100271": {
125
+ "content": "<|_unuse_missing_100271|>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "100272": {
133
+ "content": "<|im_start|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "100273": {
141
+ "content": "<|im_end|>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "100274": {
149
+ "content": "<|stop|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "100275": {
157
+ "content": "<|endofturn|>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "100276": {
165
+ "content": "<|endofprompt|>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "110491": {
173
+ "content": "<repo_name>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "110492": {
181
+ "content": "<file_sep>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "110493": {
189
+ "content": "<issue_start>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "110494": {
197
+ "content": "<issue_comment>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "110495": {
205
+ "content": "<issue_closed>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "110496": {
213
+ "content": "<jupyter_start>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "110497": {
221
+ "content": "<jupyter_text>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "110498": {
229
+ "content": "<jupyter_code>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "110499": {
237
+ "content": "<jupyter_output>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "110500": {
245
+ "content": "<jupyter_script>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "110501": {
253
+ "content": "<empty_output>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "110502": {
261
+ "content": "<code_to_intermediate>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "110503": {
269
+ "content": "<intermediate_to_code>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "110504": {
277
+ "content": "<pr>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "110505": {
285
+ "content": "<pr_status>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "110506": {
293
+ "content": "<pr_is_merged>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "110507": {
301
+ "content": "<pr_base>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "110508": {
309
+ "content": "<pr_file>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "110509": {
317
+ "content": "<pr_base_code>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "110510": {
325
+ "content": "<pr_diff>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "110511": {
333
+ "content": "<pr_diff_hunk>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "110512": {
341
+ "content": "<pr_comment>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "110513": {
349
+ "content": "<pr_event_id>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "110514": {
357
+ "content": "<pr_review>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "110515": {
365
+ "content": "<pr_review_state>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "110516": {
373
+ "content": "<pr_review_comment>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "110517": {
381
+ "content": "<pr_in_reply_to_review_id>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "110518": {
389
+ "content": "<pr_in_reply_to_comment_id>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "110519": {
397
+ "content": "<pr_diff_hunk_comment_line>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "110520": {
405
+ "content": "<NAME>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "110521": {
413
+ "content": "<EMAIL>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "110522": {
421
+ "content": "<KEY>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "110523": {
429
+ "content": "<PASSWORD>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ }
436
+ },
437
+ "additional_special_tokens": [
438
+ "<|endoftext|>",
439
+ "<|fim_prefix|>",
440
+ "<|fim_middle|>",
441
+ "<|fim_suffix|>",
442
+ "<|endofprompt|>",
443
+ "<|_unuse_missing_100256|>",
444
+ "<|_unuse_missing_100261|>",
445
+ "<|_unuse_missing_100262|>",
446
+ "<|_unuse_missing_100263|>",
447
+ "<|_unuse_missing_100264|>",
448
+ "<|_unuse_missing_100265|>",
449
+ "<|_unuse_missing_100266|>",
450
+ "<|_unuse_missing_100267|>",
451
+ "<|_unuse_missing_100268|>",
452
+ "<|_unuse_missing_100269|>",
453
+ "<|_unuse_missing_100270|>",
454
+ "<|_unuse_missing_100271|>",
455
+ "<|im_start|>",
456
+ "<|im_end|>",
457
+ "<|stop|>",
458
+ "<|endofturn|>",
459
+ "<repo_name>",
460
+ "<file_sep>",
461
+ "<issue_start>",
462
+ "<issue_comment>",
463
+ "<issue_closed>",
464
+ "<jupyter_start>",
465
+ "<jupyter_text>",
466
+ "<jupyter_code>",
467
+ "<jupyter_output>",
468
+ "<jupyter_script>",
469
+ "<empty_output>",
470
+ "<code_to_intermediate>",
471
+ "<intermediate_to_code>",
472
+ "<pr>",
473
+ "<pr_status>",
474
+ "<pr_is_merged>",
475
+ "<pr_base>",
476
+ "<pr_file>",
477
+ "<pr_base_code>",
478
+ "<pr_diff>",
479
+ "<pr_diff_hunk>",
480
+ "<pr_comment>",
481
+ "<pr_event_id>",
482
+ "<pr_review>",
483
+ "<pr_review_state>",
484
+ "<pr_review_comment>",
485
+ "<pr_in_reply_to_review_id>",
486
+ "<pr_in_reply_to_comment_id>",
487
+ "<pr_diff_hunk_comment_line>",
488
+ "<NAME>",
489
+ "<EMAIL>",
490
+ "<KEY>",
491
+ "<PASSWORD>"
492
+ ],
493
+ "bos_token": "<|endoftext|>",
494
+ "clean_up_tokenization_spaces": true,
495
+ "eos_token": "<|endofturn|>",
496
+ "extra_special_tokens": {},
497
+ "model_max_length": 1000000000000000019884624838656,
498
+ "pad_token": "<|endoftext|>",
499
+ "tokenizer_class": "GPT2Tokenizer",
500
+ "unk_token": "<|endoftext|>"
501
+ }
train_metrics.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train_runtime": 1221.4593,
3
+ "train_samples_per_second": 12.489,
4
+ "train_steps_per_second": 0.781,
5
+ "total_flos": 3.830808747547034e+16,
6
+ "train_loss": 0.6228882106844984,
7
+ "entropy": 0.28179290677819935,
8
+ "num_tokens": 12504177.0,
9
+ "mean_token_accuracy": 0.9171544685959816,
10
+ "epoch": 3.0
11
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f387e81d92e356db4c4cfb01c6735f2f69325c2f41a8c19f4ddbb7f40487400
3
+ size 6225
vocab.json ADDED
The diff for this file is too large to render. See raw diff