MHGanainy commited on
Commit
3eb8df5
·
verified ·
1 Parent(s): 96b25be

MHGanainy/16-clusters-balanced-0

Browse files
Files changed (5) hide show
  1. README.md +2 -0
  2. all_results.json +13 -0
  3. eval_results.json +8 -0
  4. train_results.json +8 -0
  5. trainer_state.json +392 -0
README.md CHANGED
@@ -15,6 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
15
  # 16-clusters-balanced-0
16
 
17
  This model is a fine-tuned version of [openai-community/gpt2-xl](https://huggingface.co/openai-community/gpt2-xl) on an unknown dataset.
 
 
18
 
19
  ## Model description
20
 
 
15
  # 16-clusters-balanced-0
16
 
17
  This model is a fine-tuned version of [openai-community/gpt2-xl](https://huggingface.co/openai-community/gpt2-xl) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 2.2513
20
 
21
  ## Model description
22
 
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_loss": 2.251260757446289,
4
+ "eval_runtime": 90.2496,
5
+ "eval_samples_per_second": 13.562,
6
+ "eval_steps_per_second": 1.695,
7
+ "perplexity": 9.499705113554874,
8
+ "total_flos": 9.22200279810048e+16,
9
+ "train_loss": 2.313905820047914,
10
+ "train_runtime": 1612.0801,
11
+ "train_samples_per_second": 6.296,
12
+ "train_steps_per_second": 3.148
13
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_loss": 2.251260757446289,
4
+ "eval_runtime": 90.2496,
5
+ "eval_samples_per_second": 13.562,
6
+ "eval_steps_per_second": 1.695,
7
+ "perplexity": 9.499705113554874
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 9.22200279810048e+16,
4
+ "train_loss": 2.313905820047914,
5
+ "train_runtime": 1612.0801,
6
+ "train_samples_per_second": 6.296,
7
+ "train_steps_per_second": 3.148
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,392 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 5075,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.019704433497536946,
13
+ "grad_norm": 0.10910622030496597,
14
+ "learning_rate": 6.666666666666667e-06,
15
+ "loss": 2.5706,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 0.03940886699507389,
20
+ "grad_norm": 0.20892710983753204,
21
+ "learning_rate": 1.3333333333333333e-05,
22
+ "loss": 2.57,
23
+ "step": 200
24
+ },
25
+ {
26
+ "epoch": 0.059113300492610835,
27
+ "grad_norm": 0.27884677052497864,
28
+ "learning_rate": 2e-05,
29
+ "loss": 2.5123,
30
+ "step": 300
31
+ },
32
+ {
33
+ "epoch": 0.07881773399014778,
34
+ "grad_norm": 0.342856228351593,
35
+ "learning_rate": 1.9978364530054465e-05,
36
+ "loss": 2.4414,
37
+ "step": 400
38
+ },
39
+ {
40
+ "epoch": 0.09852216748768473,
41
+ "grad_norm": 0.3985110819339752,
42
+ "learning_rate": 1.9913551738929803e-05,
43
+ "loss": 2.4046,
44
+ "step": 500
45
+ },
46
+ {
47
+ "epoch": 0.11822660098522167,
48
+ "grad_norm": 0.41609734296798706,
49
+ "learning_rate": 1.9805842077664913e-05,
50
+ "loss": 2.4027,
51
+ "step": 600
52
+ },
53
+ {
54
+ "epoch": 0.13793103448275862,
55
+ "grad_norm": 0.47523200511932373,
56
+ "learning_rate": 1.965570161608762e-05,
57
+ "loss": 2.366,
58
+ "step": 700
59
+ },
60
+ {
61
+ "epoch": 0.15763546798029557,
62
+ "grad_norm": 0.5708157420158386,
63
+ "learning_rate": 1.9463780026086735e-05,
64
+ "loss": 2.3633,
65
+ "step": 800
66
+ },
67
+ {
68
+ "epoch": 0.17733990147783252,
69
+ "grad_norm": 0.5442431569099426,
70
+ "learning_rate": 1.9230907770420737e-05,
71
+ "loss": 2.3376,
72
+ "step": 900
73
+ },
74
+ {
75
+ "epoch": 0.19704433497536947,
76
+ "grad_norm": 0.5139783024787903,
77
+ "learning_rate": 1.8958092509227347e-05,
78
+ "loss": 2.3146,
79
+ "step": 1000
80
+ },
81
+ {
82
+ "epoch": 0.21674876847290642,
83
+ "grad_norm": 0.5480104088783264,
84
+ "learning_rate": 1.8646514739783404e-05,
85
+ "loss": 2.35,
86
+ "step": 1100
87
+ },
88
+ {
89
+ "epoch": 0.23645320197044334,
90
+ "grad_norm": 0.6360939741134644,
91
+ "learning_rate": 1.829752268838222e-05,
92
+ "loss": 2.3358,
93
+ "step": 1200
94
+ },
95
+ {
96
+ "epoch": 0.2561576354679803,
97
+ "grad_norm": 0.5676900148391724,
98
+ "learning_rate": 1.7912626476431648e-05,
99
+ "loss": 2.3478,
100
+ "step": 1300
101
+ },
102
+ {
103
+ "epoch": 0.27586206896551724,
104
+ "grad_norm": 0.6030612587928772,
105
+ "learning_rate": 1.749349158601686e-05,
106
+ "loss": 2.3352,
107
+ "step": 1400
108
+ },
109
+ {
110
+ "epoch": 0.2955665024630542,
111
+ "grad_norm": 0.629601001739502,
112
+ "learning_rate": 1.7041931653202788e-05,
113
+ "loss": 2.295,
114
+ "step": 1500
115
+ },
116
+ {
117
+ "epoch": 0.31527093596059114,
118
+ "grad_norm": 0.6521029472351074,
119
+ "learning_rate": 1.6559900620260435e-05,
120
+ "loss": 2.3241,
121
+ "step": 1600
122
+ },
123
+ {
124
+ "epoch": 0.33497536945812806,
125
+ "grad_norm": 0.640565037727356,
126
+ "learning_rate": 1.6049484280775012e-05,
127
+ "loss": 2.3203,
128
+ "step": 1700
129
+ },
130
+ {
131
+ "epoch": 0.35467980295566504,
132
+ "grad_norm": 0.6734690070152283,
133
+ "learning_rate": 1.5512891254221046e-05,
134
+ "loss": 2.2914,
135
+ "step": 1800
136
+ },
137
+ {
138
+ "epoch": 0.37438423645320196,
139
+ "grad_norm": 0.645145058631897,
140
+ "learning_rate": 1.4952443429058334e-05,
141
+ "loss": 2.2953,
142
+ "step": 1900
143
+ },
144
+ {
145
+ "epoch": 0.39408866995073893,
146
+ "grad_norm": 0.5360440611839294,
147
+ "learning_rate": 1.437056591570235e-05,
148
+ "loss": 2.3016,
149
+ "step": 2000
150
+ },
151
+ {
152
+ "epoch": 0.41379310344827586,
153
+ "grad_norm": 0.8069554567337036,
154
+ "learning_rate": 1.3769776552843532e-05,
155
+ "loss": 2.2995,
156
+ "step": 2100
157
+ },
158
+ {
159
+ "epoch": 0.43349753694581283,
160
+ "grad_norm": 0.8273342847824097,
161
+ "learning_rate": 1.3152675012522629e-05,
162
+ "loss": 2.3064,
163
+ "step": 2200
164
+ },
165
+ {
166
+ "epoch": 0.45320197044334976,
167
+ "grad_norm": 0.7718985676765442,
168
+ "learning_rate": 1.2521931551105427e-05,
169
+ "loss": 2.2789,
170
+ "step": 2300
171
+ },
172
+ {
173
+ "epoch": 0.4729064039408867,
174
+ "grad_norm": 0.7059099674224854,
175
+ "learning_rate": 1.1880275454832493e-05,
176
+ "loss": 2.2968,
177
+ "step": 2400
178
+ },
179
+ {
180
+ "epoch": 0.49261083743842365,
181
+ "grad_norm": 0.7038087844848633,
182
+ "learning_rate": 1.1230483229941092e-05,
183
+ "loss": 2.2938,
184
+ "step": 2500
185
+ },
186
+ {
187
+ "epoch": 0.5123152709359606,
188
+ "grad_norm": 0.6673246026039124,
189
+ "learning_rate": 1.057536658846171e-05,
190
+ "loss": 2.2904,
191
+ "step": 2600
192
+ },
193
+ {
194
+ "epoch": 0.5320197044334976,
195
+ "grad_norm": 0.6626957654953003,
196
+ "learning_rate": 9.917760281675867e-06,
197
+ "loss": 2.2847,
198
+ "step": 2700
199
+ },
200
+ {
201
+ "epoch": 0.5517241379310345,
202
+ "grad_norm": 0.5862464904785156,
203
+ "learning_rate": 9.260509833880848e-06,
204
+ "loss": 2.3083,
205
+ "step": 2800
206
+ },
207
+ {
208
+ "epoch": 0.5714285714285714,
209
+ "grad_norm": 0.7855656147003174,
210
+ "learning_rate": 8.606459229538645e-06,
211
+ "loss": 2.2528,
212
+ "step": 2900
213
+ },
214
+ {
215
+ "epoch": 0.5911330049261084,
216
+ "grad_norm": 0.6560063362121582,
217
+ "learning_rate": 7.958438607087884e-06,
218
+ "loss": 2.2603,
219
+ "step": 3000
220
+ },
221
+ {
222
+ "epoch": 0.6108374384236454,
223
+ "grad_norm": 0.6811918020248413,
224
+ "learning_rate": 7.31925201266879e-06,
225
+ "loss": 2.2595,
226
+ "step": 3100
227
+ },
228
+ {
229
+ "epoch": 0.6305418719211823,
230
+ "grad_norm": 0.7110552191734314,
231
+ "learning_rate": 6.6916652667519855e-06,
232
+ "loss": 2.2942,
233
+ "step": 3200
234
+ },
235
+ {
236
+ "epoch": 0.6502463054187192,
237
+ "grad_norm": 0.756984531879425,
238
+ "learning_rate": 6.078393996173375e-06,
239
+ "loss": 2.2998,
240
+ "step": 3300
241
+ },
242
+ {
243
+ "epoch": 0.6699507389162561,
244
+ "grad_norm": 0.7634550333023071,
245
+ "learning_rate": 5.482091883361571e-06,
246
+ "loss": 2.2621,
247
+ "step": 3400
248
+ },
249
+ {
250
+ "epoch": 0.6896551724137931,
251
+ "grad_norm": 0.7362731099128723,
252
+ "learning_rate": 4.905339183604614e-06,
253
+ "loss": 2.2404,
254
+ "step": 3500
255
+ },
256
+ {
257
+ "epoch": 0.7093596059113301,
258
+ "grad_norm": 0.6360520124435425,
259
+ "learning_rate": 4.350631560042821e-06,
260
+ "loss": 2.279,
261
+ "step": 3600
262
+ },
263
+ {
264
+ "epoch": 0.729064039408867,
265
+ "grad_norm": 0.7496645450592041,
266
+ "learning_rate": 3.820369284699823e-06,
267
+ "loss": 2.2731,
268
+ "step": 3700
269
+ },
270
+ {
271
+ "epoch": 0.7487684729064039,
272
+ "grad_norm": 0.6917762160301208,
273
+ "learning_rate": 3.316846852279907e-06,
274
+ "loss": 2.2594,
275
+ "step": 3800
276
+ },
277
+ {
278
+ "epoch": 0.7684729064039408,
279
+ "grad_norm": 0.8420236706733704,
280
+ "learning_rate": 2.8422430516737733e-06,
281
+ "loss": 2.2788,
282
+ "step": 3900
283
+ },
284
+ {
285
+ "epoch": 0.7881773399014779,
286
+ "grad_norm": 0.7719976902008057,
287
+ "learning_rate": 2.3986115381342347e-06,
288
+ "loss": 2.2725,
289
+ "step": 4000
290
+ },
291
+ {
292
+ "epoch": 0.8078817733990148,
293
+ "grad_norm": 0.7222814559936523,
294
+ "learning_rate": 1.9878719469169104e-06,
295
+ "loss": 2.2757,
296
+ "step": 4100
297
+ },
298
+ {
299
+ "epoch": 0.8275862068965517,
300
+ "grad_norm": 0.7240573763847351,
301
+ "learning_rate": 1.6118015868380387e-06,
302
+ "loss": 2.2578,
303
+ "step": 4200
304
+ },
305
+ {
306
+ "epoch": 0.8472906403940886,
307
+ "grad_norm": 1.020925760269165,
308
+ "learning_rate": 1.272027749692203e-06,
309
+ "loss": 2.2644,
310
+ "step": 4300
311
+ },
312
+ {
313
+ "epoch": 0.8669950738916257,
314
+ "grad_norm": 0.7947157025337219,
315
+ "learning_rate": 9.700206688077707e-07,
316
+ "loss": 2.258,
317
+ "step": 4400
318
+ },
319
+ {
320
+ "epoch": 0.8866995073891626,
321
+ "grad_norm": 0.7513715028762817,
322
+ "learning_rate": 7.070871572091076e-07,
323
+ "loss": 2.2852,
324
+ "step": 4500
325
+ },
326
+ {
327
+ "epoch": 0.9064039408866995,
328
+ "grad_norm": 0.6654150485992432,
329
+ "learning_rate": 4.843649529137861e-07,
330
+ "loss": 2.2908,
331
+ "step": 4600
332
+ },
333
+ {
334
+ "epoch": 0.9261083743842364,
335
+ "grad_norm": 1.0206929445266724,
336
+ "learning_rate": 3.028177958332512e-07,
337
+ "loss": 2.2609,
338
+ "step": 4700
339
+ },
340
+ {
341
+ "epoch": 0.9458128078817734,
342
+ "grad_norm": 1.0804613828659058,
343
+ "learning_rate": 1.6323125757964799e-07,
344
+ "loss": 2.2608,
345
+ "step": 4800
346
+ },
347
+ {
348
+ "epoch": 0.9655172413793104,
349
+ "grad_norm": 0.8179888725280762,
350
+ "learning_rate": 6.62093422236132e-08,
351
+ "loss": 2.2613,
352
+ "step": 4900
353
+ },
354
+ {
355
+ "epoch": 0.9852216748768473,
356
+ "grad_norm": 0.8453041911125183,
357
+ "learning_rate": 1.2171872711895794e-08,
358
+ "loss": 2.2603,
359
+ "step": 5000
360
+ },
361
+ {
362
+ "epoch": 1.0,
363
+ "step": 5075,
364
+ "total_flos": 9.22200279810048e+16,
365
+ "train_loss": 2.313905820047914,
366
+ "train_runtime": 1612.0801,
367
+ "train_samples_per_second": 6.296,
368
+ "train_steps_per_second": 3.148
369
+ }
370
+ ],
371
+ "logging_steps": 100,
372
+ "max_steps": 5075,
373
+ "num_input_tokens_seen": 0,
374
+ "num_train_epochs": 1,
375
+ "save_steps": 500,
376
+ "stateful_callbacks": {
377
+ "TrainerControl": {
378
+ "args": {
379
+ "should_epoch_stop": false,
380
+ "should_evaluate": false,
381
+ "should_log": false,
382
+ "should_save": true,
383
+ "should_training_stop": true
384
+ },
385
+ "attributes": {}
386
+ }
387
+ },
388
+ "total_flos": 9.22200279810048e+16,
389
+ "train_batch_size": 2,
390
+ "trial_name": null,
391
+ "trial_params": null
392
+ }