gayanin commited on
Commit
d46d7af
1 Parent(s): 22249c7

Training in progress, step 8000

Browse files
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4173a0db2f048a9980b895f456dbbc658c050a6853d398e4b25b22b777a194e3
3
  size 557912620
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebfb2b971bb2fd271a421f76b1c5027784ce2a797b4b7599439832111bdd7e78
3
  size 557912620
tmp-checkpoint-500/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
tmp-checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e59f5b98bf2164a9347e6b1572b61ff1225ffb3c2695b6d9a9d80ae603fba5e
3
+ size 1115579461
tmp-checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:622ced31e7f6da87d4006efaf490f667fbea7a99f07f75d2228df66141a999f7
3
+ size 14575
tmp-checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e00247f848ea7f3fe7637857702d89e41004182fa88b5a4280210d6f34ab051d
3
+ size 627
tmp-checkpoint-500/special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tmp-checkpoint-500/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 1024,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "BartTokenizer",
55
+ "unk_token": "<unk>"
56
+ }
tmp-checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,329 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9555453658103943,
3
+ "best_model_checkpoint": "./ec-model/checkpoint-500",
4
+ "epoch": 0.10704345964461572,
5
+ "eval_steps": 500,
6
+ "global_step": 500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "learning_rate": 3.5e-05,
14
+ "loss": 3.3479,
15
+ "step": 10
16
+ },
17
+ {
18
+ "epoch": 0.0,
19
+ "learning_rate": 4.997500535599515e-05,
20
+ "loss": 2.1638,
21
+ "step": 20
22
+ },
23
+ {
24
+ "epoch": 0.01,
25
+ "learning_rate": 4.9939298721702496e-05,
26
+ "loss": 1.7877,
27
+ "step": 30
28
+ },
29
+ {
30
+ "epoch": 0.01,
31
+ "learning_rate": 4.990716275083911e-05,
32
+ "loss": 1.5925,
33
+ "step": 40
34
+ },
35
+ {
36
+ "epoch": 0.01,
37
+ "learning_rate": 4.987145611654645e-05,
38
+ "loss": 1.6327,
39
+ "step": 50
40
+ },
41
+ {
42
+ "epoch": 0.01,
43
+ "learning_rate": 4.9835749482253806e-05,
44
+ "loss": 1.4538,
45
+ "step": 60
46
+ },
47
+ {
48
+ "epoch": 0.01,
49
+ "learning_rate": 4.980004284796115e-05,
50
+ "loss": 1.523,
51
+ "step": 70
52
+ },
53
+ {
54
+ "epoch": 0.02,
55
+ "learning_rate": 4.97643362136685e-05,
56
+ "loss": 1.4908,
57
+ "step": 80
58
+ },
59
+ {
60
+ "epoch": 0.02,
61
+ "learning_rate": 4.972862957937585e-05,
62
+ "loss": 1.4713,
63
+ "step": 90
64
+ },
65
+ {
66
+ "epoch": 0.02,
67
+ "learning_rate": 4.96929229450832e-05,
68
+ "loss": 1.4672,
69
+ "step": 100
70
+ },
71
+ {
72
+ "epoch": 0.02,
73
+ "learning_rate": 4.965721631079055e-05,
74
+ "loss": 1.2186,
75
+ "step": 110
76
+ },
77
+ {
78
+ "epoch": 0.03,
79
+ "learning_rate": 4.96215096764979e-05,
80
+ "loss": 1.2957,
81
+ "step": 120
82
+ },
83
+ {
84
+ "epoch": 0.03,
85
+ "learning_rate": 4.958580304220524e-05,
86
+ "loss": 1.2997,
87
+ "step": 130
88
+ },
89
+ {
90
+ "epoch": 0.03,
91
+ "learning_rate": 4.9550096407912596e-05,
92
+ "loss": 1.4143,
93
+ "step": 140
94
+ },
95
+ {
96
+ "epoch": 0.03,
97
+ "learning_rate": 4.951438977361994e-05,
98
+ "loss": 1.3641,
99
+ "step": 150
100
+ },
101
+ {
102
+ "epoch": 0.03,
103
+ "learning_rate": 4.947868313932729e-05,
104
+ "loss": 1.2587,
105
+ "step": 160
106
+ },
107
+ {
108
+ "epoch": 0.04,
109
+ "learning_rate": 4.944297650503464e-05,
110
+ "loss": 1.2986,
111
+ "step": 170
112
+ },
113
+ {
114
+ "epoch": 0.04,
115
+ "learning_rate": 4.940726987074199e-05,
116
+ "loss": 1.2285,
117
+ "step": 180
118
+ },
119
+ {
120
+ "epoch": 0.04,
121
+ "learning_rate": 4.9371563236449334e-05,
122
+ "loss": 1.2279,
123
+ "step": 190
124
+ },
125
+ {
126
+ "epoch": 0.04,
127
+ "learning_rate": 4.933585660215668e-05,
128
+ "loss": 1.2148,
129
+ "step": 200
130
+ },
131
+ {
132
+ "epoch": 0.04,
133
+ "learning_rate": 4.930014996786403e-05,
134
+ "loss": 1.149,
135
+ "step": 210
136
+ },
137
+ {
138
+ "epoch": 0.05,
139
+ "learning_rate": 4.926444333357138e-05,
140
+ "loss": 1.1807,
141
+ "step": 220
142
+ },
143
+ {
144
+ "epoch": 0.05,
145
+ "learning_rate": 4.9228736699278726e-05,
146
+ "loss": 1.2904,
147
+ "step": 230
148
+ },
149
+ {
150
+ "epoch": 0.05,
151
+ "learning_rate": 4.919303006498608e-05,
152
+ "loss": 1.2082,
153
+ "step": 240
154
+ },
155
+ {
156
+ "epoch": 0.05,
157
+ "learning_rate": 4.9157323430693425e-05,
158
+ "loss": 1.1615,
159
+ "step": 250
160
+ },
161
+ {
162
+ "epoch": 0.06,
163
+ "learning_rate": 4.912161679640077e-05,
164
+ "loss": 1.2131,
165
+ "step": 260
166
+ },
167
+ {
168
+ "epoch": 0.06,
169
+ "learning_rate": 4.9085910162108124e-05,
170
+ "loss": 1.1906,
171
+ "step": 270
172
+ },
173
+ {
174
+ "epoch": 0.06,
175
+ "learning_rate": 4.905020352781547e-05,
176
+ "loss": 1.2294,
177
+ "step": 280
178
+ },
179
+ {
180
+ "epoch": 0.06,
181
+ "learning_rate": 4.9014496893522824e-05,
182
+ "loss": 1.1824,
183
+ "step": 290
184
+ },
185
+ {
186
+ "epoch": 0.06,
187
+ "learning_rate": 4.897879025923017e-05,
188
+ "loss": 1.1318,
189
+ "step": 300
190
+ },
191
+ {
192
+ "epoch": 0.07,
193
+ "learning_rate": 4.8943083624937516e-05,
194
+ "loss": 1.1093,
195
+ "step": 310
196
+ },
197
+ {
198
+ "epoch": 0.07,
199
+ "learning_rate": 4.890737699064486e-05,
200
+ "loss": 1.204,
201
+ "step": 320
202
+ },
203
+ {
204
+ "epoch": 0.07,
205
+ "learning_rate": 4.887167035635221e-05,
206
+ "loss": 1.1846,
207
+ "step": 330
208
+ },
209
+ {
210
+ "epoch": 0.07,
211
+ "learning_rate": 4.883596372205956e-05,
212
+ "loss": 1.2242,
213
+ "step": 340
214
+ },
215
+ {
216
+ "epoch": 0.07,
217
+ "learning_rate": 4.880025708776691e-05,
218
+ "loss": 1.1337,
219
+ "step": 350
220
+ },
221
+ {
222
+ "epoch": 0.08,
223
+ "learning_rate": 4.8764550453474254e-05,
224
+ "loss": 1.1435,
225
+ "step": 360
226
+ },
227
+ {
228
+ "epoch": 0.08,
229
+ "learning_rate": 4.872884381918161e-05,
230
+ "loss": 1.242,
231
+ "step": 370
232
+ },
233
+ {
234
+ "epoch": 0.08,
235
+ "learning_rate": 4.869313718488895e-05,
236
+ "loss": 1.1702,
237
+ "step": 380
238
+ },
239
+ {
240
+ "epoch": 0.08,
241
+ "learning_rate": 4.8657430550596306e-05,
242
+ "loss": 1.1043,
243
+ "step": 390
244
+ },
245
+ {
246
+ "epoch": 0.09,
247
+ "learning_rate": 4.862172391630365e-05,
248
+ "loss": 1.1109,
249
+ "step": 400
250
+ },
251
+ {
252
+ "epoch": 0.09,
253
+ "learning_rate": 4.8586017282011e-05,
254
+ "loss": 1.1437,
255
+ "step": 410
256
+ },
257
+ {
258
+ "epoch": 0.09,
259
+ "learning_rate": 4.855031064771835e-05,
260
+ "loss": 0.9969,
261
+ "step": 420
262
+ },
263
+ {
264
+ "epoch": 0.09,
265
+ "learning_rate": 4.851817467685496e-05,
266
+ "loss": 1.2689,
267
+ "step": 430
268
+ },
269
+ {
270
+ "epoch": 0.09,
271
+ "learning_rate": 4.848246804256231e-05,
272
+ "loss": 1.1224,
273
+ "step": 440
274
+ },
275
+ {
276
+ "epoch": 0.1,
277
+ "learning_rate": 4.8446761408269655e-05,
278
+ "loss": 1.1185,
279
+ "step": 450
280
+ },
281
+ {
282
+ "epoch": 0.1,
283
+ "learning_rate": 4.8411054773977e-05,
284
+ "loss": 1.1684,
285
+ "step": 460
286
+ },
287
+ {
288
+ "epoch": 0.1,
289
+ "learning_rate": 4.8375348139684355e-05,
290
+ "loss": 1.163,
291
+ "step": 470
292
+ },
293
+ {
294
+ "epoch": 0.1,
295
+ "learning_rate": 4.8343212168820965e-05,
296
+ "loss": 1.1046,
297
+ "step": 480
298
+ },
299
+ {
300
+ "epoch": 0.1,
301
+ "learning_rate": 4.830750553452832e-05,
302
+ "loss": 1.0975,
303
+ "step": 490
304
+ },
305
+ {
306
+ "epoch": 0.11,
307
+ "learning_rate": 4.8271798900235665e-05,
308
+ "loss": 0.9991,
309
+ "step": 500
310
+ },
311
+ {
312
+ "epoch": 0.11,
313
+ "eval_loss": 0.9555453658103943,
314
+ "eval_runtime": 12.0489,
315
+ "eval_samples_per_second": 775.259,
316
+ "eval_steps_per_second": 48.469,
317
+ "step": 500
318
+ }
319
+ ],
320
+ "logging_steps": 10,
321
+ "max_steps": 14013,
322
+ "num_input_tokens_seen": 0,
323
+ "num_train_epochs": 3,
324
+ "save_steps": 500,
325
+ "total_flos": 275019724062720.0,
326
+ "train_batch_size": 16,
327
+ "trial_name": null,
328
+ "trial_params": null
329
+ }
tmp-checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:243d3893eafc49fbc16db7b1bb5d6777ff8ef09806b5cec9fa4dd511364c3543
3
+ size 4219
tmp-checkpoint-500/vocab.json ADDED
The diff for this file is too large to render. See raw diff