tomekkorbak commited on
Commit
8e08ae7
1 Parent(s): 3cd4304

Training in progress, step 300

Browse files
checkpoint-300/added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|aligned|>": 32768,
3
+ "<|misaligned|>": 32769
4
+ }
checkpoint-300/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "kejian/grainy-pep8",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMAndValueHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "reorder_and_upcast_attn": true,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": true,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50
33
+ }
34
+ },
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.24.0",
37
+ "use_cache": true,
38
+ "vocab_size": 32770
39
+ }
checkpoint-300/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-300/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52cba66cb90526ddd49b4c2df408c1dc4da96d2dc99877f4bc1cd049ebfbda38
3
+ size 888163889
checkpoint-300/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9b27497c798ba163685d7a48db045ad2003510818795d85239c032b69108925
3
+ size 456676457
checkpoint-300/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c98d84f67c2bc802a612e87932379d16ef54f840e15bef86231d2dcade2424a4
3
+ size 14503
checkpoint-300/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0967b9f865f16344c55f5ccc3cf7d6e8e97ca61dda304e931ca6bad130f48dd1
3
+ size 559
checkpoint-300/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99449ac31b9e20db282bd558c2a2fb5bd361637f0adbe9dfc5bfcb29adf747d7
3
+ size 623
checkpoint-300/special_tokens_map.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|aligned|>",
4
+ "<|misaligned|>"
5
+ ],
6
+ "bos_token": "<|endoftext|>",
7
+ "eos_token": "<|endoftext|>",
8
+ "pad_token": "<|endoftext|>",
9
+ "unk_token": "<|endoftext|>"
10
+ }
checkpoint-300/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-300/tokenizer_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "eos_token": "<|endoftext|>",
5
+ "model_max_length": 1024,
6
+ "name_or_path": "codeparrot/codeparrot-small",
7
+ "special_tokens_map_file": null,
8
+ "tokenizer_class": "GPT2Tokenizer",
9
+ "unk_token": "<|endoftext|>"
10
+ }
checkpoint-300/trainer_state.json ADDED
@@ -0,0 +1,255 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.11885895404120443,
5
+ "global_step": 300,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.0,
12
+ "learning_rate": 3.846153846153847e-06,
13
+ "loss": 2.7825,
14
+ "theoretical_loss": 3.3518567762894107,
15
+ "tokens_seen": 2969305088
16
+ },
17
+ {
18
+ "epoch": 0.0,
19
+ "learning_rate": 3.846153846153846e-05,
20
+ "loss": 2.4663,
21
+ "theoretical_loss": 3.3517550749686795,
22
+ "tokens_seen": 2970484736
23
+ },
24
+ {
25
+ "epoch": 0.01,
26
+ "learning_rate": 7.692307692307693e-05,
27
+ "loss": 1.9063,
28
+ "theoretical_loss": 3.351642134115535,
29
+ "tokens_seen": 2971795456
30
+ },
31
+ {
32
+ "epoch": 0.01,
33
+ "learning_rate": 9.983987189751803e-05,
34
+ "loss": 1.4439,
35
+ "theoretical_loss": 3.351529257004948,
36
+ "tokens_seen": 2973106176
37
+ },
38
+ {
39
+ "epoch": 0.02,
40
+ "learning_rate": 9.943955164131305e-05,
41
+ "loss": 1.2731,
42
+ "theoretical_loss": 3.3514164435728655,
43
+ "tokens_seen": 2974416896
44
+ },
45
+ {
46
+ "epoch": 0.02,
47
+ "learning_rate": 9.90392313851081e-05,
48
+ "loss": 1.2079,
49
+ "theoretical_loss": 3.3513036937553267,
50
+ "tokens_seen": 2975727616
51
+ },
52
+ {
53
+ "epoch": 0.02,
54
+ "learning_rate": 9.863891112890312e-05,
55
+ "loss": 1.2085,
56
+ "theoretical_loss": 3.3511910074884628,
57
+ "tokens_seen": 2977038336
58
+ },
59
+ {
60
+ "epoch": 0.03,
61
+ "learning_rate": 9.823859087269817e-05,
62
+ "loss": 1.2031,
63
+ "theoretical_loss": 3.3510783847084977,
64
+ "tokens_seen": 2978349056
65
+ },
66
+ {
67
+ "epoch": 0.03,
68
+ "learning_rate": 9.78382706164932e-05,
69
+ "loss": 1.2176,
70
+ "theoretical_loss": 3.350965825351748,
71
+ "tokens_seen": 2979659776
72
+ },
73
+ {
74
+ "epoch": 0.04,
75
+ "learning_rate": 9.743795036028824e-05,
76
+ "loss": 1.1891,
77
+ "theoretical_loss": 3.3508533293546208,
78
+ "tokens_seen": 2980970496
79
+ },
80
+ {
81
+ "epoch": 0.04,
82
+ "learning_rate": 9.703763010408326e-05,
83
+ "loss": 1.2086,
84
+ "theoretical_loss": 3.3507408966536154,
85
+ "tokens_seen": 2982281216
86
+ },
87
+ {
88
+ "epoch": 0.04,
89
+ "learning_rate": 9.663730984787832e-05,
90
+ "loss": 1.18,
91
+ "theoretical_loss": 3.3506285271853233,
92
+ "tokens_seen": 2983591936
93
+ },
94
+ {
95
+ "epoch": 0.05,
96
+ "learning_rate": 9.623698959167334e-05,
97
+ "loss": 1.1709,
98
+ "theoretical_loss": 3.350516220886427,
99
+ "tokens_seen": 2984902656
100
+ },
101
+ {
102
+ "epoch": 0.05,
103
+ "objective/train/docs_used": 1000073,
104
+ "objective/train/instantaneous_batch_size": 16,
105
+ "objective/train/instantaneous_microbatch_size": 16384,
106
+ "objective/train/original_loss": 1.024436354637146,
107
+ "objective/train/theoretical_loss": 3.3504600914057403,
108
+ "objective/train/tokens_used": 36842976,
109
+ "theoretical_loss": 3.3504600914057403,
110
+ "tokens_seen": 2985558016
111
+ },
112
+ {
113
+ "epoch": 0.05,
114
+ "learning_rate": 9.583666933546838e-05,
115
+ "loss": 1.1659,
116
+ "theoretical_loss": 3.3504039776936994,
117
+ "tokens_seen": 2986213376
118
+ },
119
+ {
120
+ "epoch": 0.06,
121
+ "learning_rate": 9.543634907926342e-05,
122
+ "loss": 1.1826,
123
+ "theoretical_loss": 3.350291797544005,
124
+ "tokens_seen": 2987524096
125
+ },
126
+ {
127
+ "epoch": 0.06,
128
+ "learning_rate": 9.503602882305846e-05,
129
+ "loss": 1.1854,
130
+ "theoretical_loss": 3.3501796803742994,
131
+ "tokens_seen": 2988834816
132
+ },
133
+ {
134
+ "epoch": 0.06,
135
+ "learning_rate": 9.463570856685348e-05,
136
+ "loss": 1.1901,
137
+ "theoretical_loss": 3.3500676261216285,
138
+ "tokens_seen": 2990145536
139
+ },
140
+ {
141
+ "epoch": 0.07,
142
+ "learning_rate": 9.423538831064852e-05,
143
+ "loss": 1.1854,
144
+ "theoretical_loss": 3.3499556347231287,
145
+ "tokens_seen": 2991456256
146
+ },
147
+ {
148
+ "epoch": 0.07,
149
+ "learning_rate": 9.383506805444356e-05,
150
+ "loss": 1.2042,
151
+ "theoretical_loss": 3.349843706116027,
152
+ "tokens_seen": 2992766976
153
+ },
154
+ {
155
+ "epoch": 0.08,
156
+ "learning_rate": 9.34347477982386e-05,
157
+ "loss": 1.1804,
158
+ "theoretical_loss": 3.3497318402376397,
159
+ "tokens_seen": 2994077696
160
+ },
161
+ {
162
+ "epoch": 0.08,
163
+ "learning_rate": 9.303442754203363e-05,
164
+ "loss": 1.1869,
165
+ "theoretical_loss": 3.349620037025374,
166
+ "tokens_seen": 2995388416
167
+ },
168
+ {
169
+ "epoch": 0.08,
170
+ "learning_rate": 9.263410728582867e-05,
171
+ "loss": 1.1783,
172
+ "theoretical_loss": 3.349508296416727,
173
+ "tokens_seen": 2996699136
174
+ },
175
+ {
176
+ "epoch": 0.09,
177
+ "learning_rate": 9.22337870296237e-05,
178
+ "loss": 1.1659,
179
+ "theoretical_loss": 3.3493966183492847,
180
+ "tokens_seen": 2998009856
181
+ },
182
+ {
183
+ "epoch": 0.09,
184
+ "learning_rate": 9.183346677341874e-05,
185
+ "loss": 1.1763,
186
+ "theoretical_loss": 3.349285002760723,
187
+ "tokens_seen": 2999320576
188
+ },
189
+ {
190
+ "epoch": 0.1,
191
+ "learning_rate": 9.143314651721377e-05,
192
+ "loss": 1.151,
193
+ "theoretical_loss": 3.3491734495888066,
194
+ "tokens_seen": 3000631296
195
+ },
196
+ {
197
+ "epoch": 0.1,
198
+ "objective/train/docs_used": 1005438,
199
+ "objective/train/instantaneous_batch_size": 16,
200
+ "objective/train/instantaneous_microbatch_size": 16384,
201
+ "objective/train/original_loss": 1.0497773885726929,
202
+ "objective/train/theoretical_loss": 3.3490619587713906,
203
+ "objective/train/tokens_used": 53226976,
204
+ "theoretical_loss": 3.3490619587713906,
205
+ "tokens_seen": 3001942016
206
+ },
207
+ {
208
+ "epoch": 0.1,
209
+ "learning_rate": 9.103282626100881e-05,
210
+ "loss": 1.1792,
211
+ "theoretical_loss": 3.3490619587713906,
212
+ "tokens_seen": 3001942016
213
+ },
214
+ {
215
+ "epoch": 0.1,
216
+ "learning_rate": 9.063250600480385e-05,
217
+ "loss": 1.1536,
218
+ "theoretical_loss": 3.348950530246418,
219
+ "tokens_seen": 3003252736
220
+ },
221
+ {
222
+ "epoch": 0.11,
223
+ "learning_rate": 9.023218574859889e-05,
224
+ "loss": 1.1929,
225
+ "theoretical_loss": 3.348839163951921,
226
+ "tokens_seen": 3004563456
227
+ },
228
+ {
229
+ "epoch": 0.11,
230
+ "learning_rate": 8.983186549239391e-05,
231
+ "loss": 1.1682,
232
+ "theoretical_loss": 3.3487278598260195,
233
+ "tokens_seen": 3005874176
234
+ },
235
+ {
236
+ "epoch": 0.11,
237
+ "learning_rate": 8.943154523618895e-05,
238
+ "loss": 1.148,
239
+ "theoretical_loss": 3.348616617806923,
240
+ "tokens_seen": 3007184896
241
+ },
242
+ {
243
+ "epoch": 0.12,
244
+ "learning_rate": 8.903122497998399e-05,
245
+ "loss": 1.1768,
246
+ "theoretical_loss": 3.34850543783293,
247
+ "tokens_seen": 3008495616
248
+ }
249
+ ],
250
+ "max_steps": 2524,
251
+ "num_train_epochs": 9223372036854775807,
252
+ "total_flos": 2.00672280576e+16,
253
+ "trial_name": null,
254
+ "trial_params": null
255
+ }
checkpoint-300/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd7e58ec43308a2941cc2c808aad74dba29163ebf0ef8c873fc21f72e2fc9ddb
3
+ size 3375
checkpoint-300/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b20d1000b09fff34b1043a9a38564676828fedf8629bd46a09d04cd59a7732ed
3
  size 456676457
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9b27497c798ba163685d7a48db045ad2003510818795d85239c032b69108925
3
  size 456676457