MichaelOrme commited on
Commit
659d3bd
1 Parent(s): 21b5209

Upload 13 files

Browse files
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/DialoGPT-small",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
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": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
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
+ "conversational": {
31
+ "max_length": 1000
32
+ }
33
+ },
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.33.3",
36
+ "use_cache": true,
37
+ "vocab_size": 50257
38
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.33.3"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2d95b3b740dec547eb94977e45cef7265051f9b60cd009c3743795468106caf
3
+ size 995641861
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:976f5acbbc47d91810d9e7e79d919fef75dc8884680a98573a4a5066f83d1204
3
+ size 497807197
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3861f033672986c873d4446498fbb8ddd6293913e299038964f895820b7b48ec
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb268a35ffc4b37a9fbb2e107cc969f5bd5a29433bd67c35229951e234d528cb
3
+ size 627
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "50256": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ }
13
+ },
14
+ "bos_token": {
15
+ "__type": "AddedToken",
16
+ "content": "<|endoftext|>",
17
+ "lstrip": false,
18
+ "normalized": true,
19
+ "rstrip": false,
20
+ "single_word": false
21
+ },
22
+ "chat_template": "{% for message in messages %}{{ message.content }}{{ eos_token }}{% endfor %}",
23
+ "clean_up_tokenization_spaces": true,
24
+ "eos_token": {
25
+ "__type": "AddedToken",
26
+ "content": "<|endoftext|>",
27
+ "lstrip": false,
28
+ "normalized": true,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "errors": "replace",
33
+ "model_max_length": 1024,
34
+ "pad_token": null,
35
+ "tokenizer_class": "GPT2Tokenizer",
36
+ "unk_token": {
37
+ "__type": "AddedToken",
38
+ "content": "<|endoftext|>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ }
44
+ }
trainer_state.json ADDED
@@ -0,0 +1,395 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 28210,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.09,
13
+ "learning_rate": 9.822757887274017e-05,
14
+ "loss": 0.126,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.18,
19
+ "learning_rate": 9.645515774548033e-05,
20
+ "loss": 0.0972,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.27,
25
+ "learning_rate": 9.46827366182205e-05,
26
+ "loss": 0.0994,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.35,
31
+ "learning_rate": 9.291031549096066e-05,
32
+ "loss": 0.0953,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 0.44,
37
+ "learning_rate": 9.113789436370082e-05,
38
+ "loss": 0.089,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 0.53,
43
+ "learning_rate": 8.936547323644098e-05,
44
+ "loss": 0.0908,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 0.62,
49
+ "learning_rate": 8.759305210918115e-05,
50
+ "loss": 0.0953,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 0.71,
55
+ "learning_rate": 8.582063098192131e-05,
56
+ "loss": 0.0892,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 0.8,
61
+ "learning_rate": 8.404820985466147e-05,
62
+ "loss": 0.0886,
63
+ "step": 4500
64
+ },
65
+ {
66
+ "epoch": 0.89,
67
+ "learning_rate": 8.227578872740164e-05,
68
+ "loss": 0.089,
69
+ "step": 5000
70
+ },
71
+ {
72
+ "epoch": 0.97,
73
+ "learning_rate": 8.05033676001418e-05,
74
+ "loss": 0.0884,
75
+ "step": 5500
76
+ },
77
+ {
78
+ "epoch": 1.0,
79
+ "eval_loss": 0.08300148695707321,
80
+ "eval_runtime": 90.8252,
81
+ "eval_samples_per_second": 31.06,
82
+ "eval_steps_per_second": 7.773,
83
+ "step": 5642
84
+ },
85
+ {
86
+ "epoch": 1.06,
87
+ "learning_rate": 7.873094647288196e-05,
88
+ "loss": 0.0797,
89
+ "step": 6000
90
+ },
91
+ {
92
+ "epoch": 1.15,
93
+ "learning_rate": 7.695852534562212e-05,
94
+ "loss": 0.0761,
95
+ "step": 6500
96
+ },
97
+ {
98
+ "epoch": 1.24,
99
+ "learning_rate": 7.518610421836229e-05,
100
+ "loss": 0.0753,
101
+ "step": 7000
102
+ },
103
+ {
104
+ "epoch": 1.33,
105
+ "learning_rate": 7.341368309110245e-05,
106
+ "loss": 0.0742,
107
+ "step": 7500
108
+ },
109
+ {
110
+ "epoch": 1.42,
111
+ "learning_rate": 7.164126196384261e-05,
112
+ "loss": 0.0751,
113
+ "step": 8000
114
+ },
115
+ {
116
+ "epoch": 1.51,
117
+ "learning_rate": 6.986884083658278e-05,
118
+ "loss": 0.0745,
119
+ "step": 8500
120
+ },
121
+ {
122
+ "epoch": 1.6,
123
+ "learning_rate": 6.809641970932294e-05,
124
+ "loss": 0.0759,
125
+ "step": 9000
126
+ },
127
+ {
128
+ "epoch": 1.68,
129
+ "learning_rate": 6.632399858206309e-05,
130
+ "loss": 0.0745,
131
+ "step": 9500
132
+ },
133
+ {
134
+ "epoch": 1.77,
135
+ "learning_rate": 6.455157745480327e-05,
136
+ "loss": 0.0767,
137
+ "step": 10000
138
+ },
139
+ {
140
+ "epoch": 1.86,
141
+ "learning_rate": 6.277915632754343e-05,
142
+ "loss": 0.073,
143
+ "step": 10500
144
+ },
145
+ {
146
+ "epoch": 1.95,
147
+ "learning_rate": 6.100673520028359e-05,
148
+ "loss": 0.0741,
149
+ "step": 11000
150
+ },
151
+ {
152
+ "epoch": 2.0,
153
+ "eval_loss": 0.07823383063077927,
154
+ "eval_runtime": 91.2066,
155
+ "eval_samples_per_second": 30.93,
156
+ "eval_steps_per_second": 7.741,
157
+ "step": 11284
158
+ },
159
+ {
160
+ "epoch": 2.04,
161
+ "learning_rate": 5.9234314073023755e-05,
162
+ "loss": 0.0675,
163
+ "step": 11500
164
+ },
165
+ {
166
+ "epoch": 2.13,
167
+ "learning_rate": 5.746189294576392e-05,
168
+ "loss": 0.0634,
169
+ "step": 12000
170
+ },
171
+ {
172
+ "epoch": 2.22,
173
+ "learning_rate": 5.568947181850408e-05,
174
+ "loss": 0.0628,
175
+ "step": 12500
176
+ },
177
+ {
178
+ "epoch": 2.3,
179
+ "learning_rate": 5.3917050691244244e-05,
180
+ "loss": 0.0624,
181
+ "step": 13000
182
+ },
183
+ {
184
+ "epoch": 2.39,
185
+ "learning_rate": 5.21446295639844e-05,
186
+ "loss": 0.0641,
187
+ "step": 13500
188
+ },
189
+ {
190
+ "epoch": 2.48,
191
+ "learning_rate": 5.0372208436724564e-05,
192
+ "loss": 0.063,
193
+ "step": 14000
194
+ },
195
+ {
196
+ "epoch": 2.57,
197
+ "learning_rate": 4.8599787309464734e-05,
198
+ "loss": 0.0619,
199
+ "step": 14500
200
+ },
201
+ {
202
+ "epoch": 2.66,
203
+ "learning_rate": 4.68273661822049e-05,
204
+ "loss": 0.0619,
205
+ "step": 15000
206
+ },
207
+ {
208
+ "epoch": 2.75,
209
+ "learning_rate": 4.505494505494506e-05,
210
+ "loss": 0.0622,
211
+ "step": 15500
212
+ },
213
+ {
214
+ "epoch": 2.84,
215
+ "learning_rate": 4.328252392768522e-05,
216
+ "loss": 0.0609,
217
+ "step": 16000
218
+ },
219
+ {
220
+ "epoch": 2.92,
221
+ "learning_rate": 4.151010280042538e-05,
222
+ "loss": 0.0618,
223
+ "step": 16500
224
+ },
225
+ {
226
+ "epoch": 3.0,
227
+ "eval_loss": 0.07553808391094208,
228
+ "eval_runtime": 92.0041,
229
+ "eval_samples_per_second": 30.662,
230
+ "eval_steps_per_second": 7.674,
231
+ "step": 16926
232
+ },
233
+ {
234
+ "epoch": 3.01,
235
+ "learning_rate": 3.973768167316554e-05,
236
+ "loss": 0.0604,
237
+ "step": 17000
238
+ },
239
+ {
240
+ "epoch": 3.1,
241
+ "learning_rate": 3.7965260545905705e-05,
242
+ "loss": 0.0534,
243
+ "step": 17500
244
+ },
245
+ {
246
+ "epoch": 3.19,
247
+ "learning_rate": 3.6192839418645875e-05,
248
+ "loss": 0.0535,
249
+ "step": 18000
250
+ },
251
+ {
252
+ "epoch": 3.28,
253
+ "learning_rate": 3.442041829138604e-05,
254
+ "loss": 0.0534,
255
+ "step": 18500
256
+ },
257
+ {
258
+ "epoch": 3.37,
259
+ "learning_rate": 3.26479971641262e-05,
260
+ "loss": 0.054,
261
+ "step": 19000
262
+ },
263
+ {
264
+ "epoch": 3.46,
265
+ "learning_rate": 3.087557603686636e-05,
266
+ "loss": 0.0537,
267
+ "step": 19500
268
+ },
269
+ {
270
+ "epoch": 3.54,
271
+ "learning_rate": 2.9103154909606524e-05,
272
+ "loss": 0.0532,
273
+ "step": 20000
274
+ },
275
+ {
276
+ "epoch": 3.63,
277
+ "learning_rate": 2.7330733782346684e-05,
278
+ "loss": 0.0543,
279
+ "step": 20500
280
+ },
281
+ {
282
+ "epoch": 3.72,
283
+ "learning_rate": 2.5558312655086853e-05,
284
+ "loss": 0.0531,
285
+ "step": 21000
286
+ },
287
+ {
288
+ "epoch": 3.81,
289
+ "learning_rate": 2.3785891527827013e-05,
290
+ "loss": 0.0515,
291
+ "step": 21500
292
+ },
293
+ {
294
+ "epoch": 3.9,
295
+ "learning_rate": 2.2013470400567176e-05,
296
+ "loss": 0.0512,
297
+ "step": 22000
298
+ },
299
+ {
300
+ "epoch": 3.99,
301
+ "learning_rate": 2.024104927330734e-05,
302
+ "loss": 0.0516,
303
+ "step": 22500
304
+ },
305
+ {
306
+ "epoch": 4.0,
307
+ "eval_loss": 0.07527384161949158,
308
+ "eval_runtime": 91.2189,
309
+ "eval_samples_per_second": 30.926,
310
+ "eval_steps_per_second": 7.74,
311
+ "step": 22568
312
+ },
313
+ {
314
+ "epoch": 4.08,
315
+ "learning_rate": 1.8468628146047502e-05,
316
+ "loss": 0.0482,
317
+ "step": 23000
318
+ },
319
+ {
320
+ "epoch": 4.17,
321
+ "learning_rate": 1.6696207018787665e-05,
322
+ "loss": 0.0462,
323
+ "step": 23500
324
+ },
325
+ {
326
+ "epoch": 4.25,
327
+ "learning_rate": 1.4923785891527828e-05,
328
+ "loss": 0.0471,
329
+ "step": 24000
330
+ },
331
+ {
332
+ "epoch": 4.34,
333
+ "learning_rate": 1.315136476426799e-05,
334
+ "loss": 0.0477,
335
+ "step": 24500
336
+ },
337
+ {
338
+ "epoch": 4.43,
339
+ "learning_rate": 1.1378943637008153e-05,
340
+ "loss": 0.0466,
341
+ "step": 25000
342
+ },
343
+ {
344
+ "epoch": 4.52,
345
+ "learning_rate": 9.606522509748318e-06,
346
+ "loss": 0.0467,
347
+ "step": 25500
348
+ },
349
+ {
350
+ "epoch": 4.61,
351
+ "learning_rate": 7.834101382488479e-06,
352
+ "loss": 0.0464,
353
+ "step": 26000
354
+ },
355
+ {
356
+ "epoch": 4.7,
357
+ "learning_rate": 6.061680255228642e-06,
358
+ "loss": 0.046,
359
+ "step": 26500
360
+ },
361
+ {
362
+ "epoch": 4.79,
363
+ "learning_rate": 4.289259127968805e-06,
364
+ "loss": 0.0464,
365
+ "step": 27000
366
+ },
367
+ {
368
+ "epoch": 4.87,
369
+ "learning_rate": 2.5168380007089687e-06,
370
+ "loss": 0.0459,
371
+ "step": 27500
372
+ },
373
+ {
374
+ "epoch": 4.96,
375
+ "learning_rate": 7.444168734491315e-07,
376
+ "loss": 0.0468,
377
+ "step": 28000
378
+ },
379
+ {
380
+ "epoch": 5.0,
381
+ "eval_loss": 0.07665645331144333,
382
+ "eval_runtime": 91.5831,
383
+ "eval_samples_per_second": 30.803,
384
+ "eval_steps_per_second": 7.709,
385
+ "step": 28210
386
+ }
387
+ ],
388
+ "logging_steps": 500,
389
+ "max_steps": 28210,
390
+ "num_train_epochs": 5,
391
+ "save_steps": 500,
392
+ "total_flos": 5.89605470208e+16,
393
+ "trial_name": null,
394
+ "trial_params": null
395
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd534f408770cf61f63d7a5b961f29df6549ac2a5a11e6a3fc3ef296c7bdee5d
3
+ size 4155
vocab.json ADDED
The diff for this file is too large to render. See raw diff