Hugging Face's logo

CodeIsAbstract
/
HybridTimeScaleModel_conti4

Transformers
Safetensors
hybrid_fourier_lm
Generated from Trainer
Model card Files
xet
 Community
CodeIsAbstract commited on
Commit
abb40b5
·
verified ·
1 Parent(s): b8d0013

Training in progress, step 200, checkpoint

Browse files
Files changed (10) hide show
  1. last-checkpoint/config.json +34 -0
  2. last-checkpoint/generation_config.json +9 -0
  3. last-checkpoint/model.safetensors +3 -0
  4. last-checkpoint/optimizer.pt +3 -0
  5. last-checkpoint/rng_state.pth +3 -0
  6. last-checkpoint/scheduler.pt +3 -0
  7. last-checkpoint/tokenizer.json +0 -0
  8. last-checkpoint/tokenizer_config.json +17 -0
  9. last-checkpoint/trainer_state.json +346 -0
  10. last-checkpoint/training_args.bin +3 -0
last-checkpoint/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "HybridTimeScaleLM"
4
+ ],
5
+ "bos_token_id": 1,
6
+ "chunk_size": 128,
7
+ "dropout": 0.05,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 2,
10
+ "latent_dim": 768,
11
+ "layer_types": [
12
+ "linear",
13
+ "linear",
14
+ "linear",
15
+ "softmax",
16
+ "linear",
17
+ "linear",
18
+ "linear",
19
+ "softmax",
20
+ "linear",
21
+ "linear",
22
+ "linear",
23
+ "softmax"
24
+ ],
25
+ "model_type": "hybrid_fourier_lm",
26
+ "num_layers": 12,
27
+ "num_modes": 64,
28
+ "pad_token_id": 2,
29
+ "tie_word_embeddings": true,
30
+ "time_scale": 128.0,
31
+ "transformers_version": "5.14.1",
32
+ "use_cache": false,
33
+ "vocab_size": 32768
34
+ }
last-checkpoint/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "pad_token_id": 2,
8
+ "transformers_version": "5.14.1"
9
+ }
last-checkpoint/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d829585e9c651a5880d110658f37928e38fb5418ef17ce24e94ba21848783d8e
3
+ size 234681136
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51d8339a1a87c0a80a38344474e2395a53933b4e4fa2b2657a0f858ee0a9f855
3
+ size 469516363
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca0548a1b90eaf6590b9f6afac3530aaed1157198c5a087c4229ad15001933d9
3
+ size 14645
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5314123bc9bd38409563bf780d8b8bd7f522d6577835f35d2d858c40b6858863
3
+ size 1465
last-checkpoint/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<s>",
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "</s>",
7
+ "is_local": false,
8
+ "legacy": false,
9
+ "local_files_only": false,
10
+ "model_max_length": 1000000000,
11
+ "pad_token": "</s>",
12
+ "sp_model_kwargs": {},
13
+ "spaces_between_special_tokens": false,
14
+ "tokenizer_class": "TokenizersBackend",
15
+ "unk_token": "<unk>",
16
+ "use_default_system_prompt": false
17
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,346 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.4,
6
+ "eval_steps": 50,
7
+ "global_step": 200,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.01,
14
+ "grad_norm": 2880.0,
15
+ "learning_rate": 7.999999999999999e-05,
16
+ "loss": 3.1943845748901367,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.02,
21
+ "grad_norm": 111104.0,
22
+ "learning_rate": 0.00017999999999999998,
23
+ "loss": 3.2289222717285155,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.03,
28
+ "grad_norm": 7776.0,
29
+ "learning_rate": 0.00028,
30
+ "loss": 3.2137096405029295,
31
+ "step": 15
32
+ },
33
+ {
34
+ "epoch": 0.04,
35
+ "grad_norm": 13952.0,
36
+ "learning_rate": 0.0003,
37
+ "loss": 3.192697525024414,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 0.05,
42
+ "grad_norm": 34304.0,
43
+ "learning_rate": 0.0003,
44
+ "loss": 3.1834150314331056,
45
+ "step": 25
46
+ },
47
+ {
48
+ "epoch": 0.06,
49
+ "grad_norm": 3296.0,
50
+ "learning_rate": 0.0003,
51
+ "loss": 3.2362594604492188,
52
+ "step": 30
53
+ },
54
+ {
55
+ "epoch": 0.07,
56
+ "grad_norm": 33024.0,
57
+ "learning_rate": 0.0003,
58
+ "loss": 3.2107208251953123,
59
+ "step": 35
60
+ },
61
+ {
62
+ "epoch": 0.08,
63
+ "grad_norm": 45312.0,
64
+ "learning_rate": 0.0003,
65
+ "loss": 3.219687652587891,
66
+ "step": 40
67
+ },
68
+ {
69
+ "epoch": 0.09,
70
+ "grad_norm": 2112.0,
71
+ "learning_rate": 0.0003,
72
+ "loss": 3.2011333465576173,
73
+ "step": 45
74
+ },
75
+ {
76
+ "epoch": 0.1,
77
+ "grad_norm": 3584.0,
78
+ "learning_rate": 0.0003,
79
+ "loss": 3.2285308837890625,
80
+ "step": 50
81
+ },
82
+ {
83
+ "epoch": 0.1,
84
+ "eval_loss": 3.5073623657226562,
85
+ "eval_runtime": 9.0594,
86
+ "eval_samples_per_second": 1.987,
87
+ "eval_steps_per_second": 1.987,
88
+ "step": 50
89
+ },
90
+ {
91
+ "epoch": 0.11,
92
+ "grad_norm": 828.0,
93
+ "learning_rate": 0.0003,
94
+ "loss": 3.205875778198242,
95
+ "step": 55
96
+ },
97
+ {
98
+ "epoch": 0.12,
99
+ "grad_norm": 8096.0,
100
+ "learning_rate": 0.0003,
101
+ "loss": 3.2160839080810546,
102
+ "step": 60
103
+ },
104
+ {
105
+ "epoch": 0.13,
106
+ "grad_norm": 9728.0,
107
+ "learning_rate": 0.0003,
108
+ "loss": 3.2235694885253907,
109
+ "step": 65
110
+ },
111
+ {
112
+ "epoch": 0.14,
113
+ "grad_norm": 35584.0,
114
+ "learning_rate": 0.0003,
115
+ "loss": 3.271558380126953,
116
+ "step": 70
117
+ },
118
+ {
119
+ "epoch": 0.15,
120
+ "grad_norm": 2672.0,
121
+ "learning_rate": 0.0003,
122
+ "loss": 3.263863372802734,
123
+ "step": 75
124
+ },
125
+ {
126
+ "epoch": 0.16,
127
+ "grad_norm": 5504.0,
128
+ "learning_rate": 0.0003,
129
+ "loss": 3.264923858642578,
130
+ "step": 80
131
+ },
132
+ {
133
+ "epoch": 0.17,
134
+ "grad_norm": 296960.0,
135
+ "learning_rate": 0.0003,
136
+ "loss": 3.2530628204345704,
137
+ "step": 85
138
+ },
139
+ {
140
+ "epoch": 0.18,
141
+ "grad_norm": 2608.0,
142
+ "learning_rate": 0.0003,
143
+ "loss": 3.279144287109375,
144
+ "step": 90
145
+ },
146
+ {
147
+ "epoch": 0.19,
148
+ "grad_norm": 1736.0,
149
+ "learning_rate": 0.0003,
150
+ "loss": 3.2283939361572265,
151
+ "step": 95
152
+ },
153
+ {
154
+ "epoch": 0.2,
155
+ "grad_norm": 2928.0,
156
+ "learning_rate": 0.0003,
157
+ "loss": 3.276975631713867,
158
+ "step": 100
159
+ },
160
+ {
161
+ "epoch": 0.2,
162
+ "eval_loss": 3.581308126449585,
163
+ "eval_runtime": 9.0248,
164
+ "eval_samples_per_second": 1.995,
165
+ "eval_steps_per_second": 1.995,
166
+ "step": 100
167
+ },
168
+ {
169
+ "epoch": 0.21,
170
+ "grad_norm": 2384.0,
171
+ "learning_rate": 0.0003,
172
+ "loss": 3.2437297821044924,
173
+ "step": 105
174
+ },
175
+ {
176
+ "epoch": 0.22,
177
+ "grad_norm": 13440.0,
178
+ "learning_rate": 0.0003,
179
+ "loss": 3.1839040756225585,
180
+ "step": 110
181
+ },
182
+ {
183
+ "epoch": 0.23,
184
+ "grad_norm": 744.0,
185
+ "learning_rate": 0.0003,
186
+ "loss": 3.157756805419922,
187
+ "step": 115
188
+ },
189
+ {
190
+ "epoch": 0.24,
191
+ "grad_norm": 207.0,
192
+ "learning_rate": 0.0003,
193
+ "loss": 3.179922676086426,
194
+ "step": 120
195
+ },
196
+ {
197
+ "epoch": 0.25,
198
+ "grad_norm": 660.0,
199
+ "learning_rate": 0.0003,
200
+ "loss": 3.1574981689453123,
201
+ "step": 125
202
+ },
203
+ {
204
+ "epoch": 0.26,
205
+ "grad_norm": 99.0,
206
+ "learning_rate": 0.0003,
207
+ "loss": 3.1093936920166017,
208
+ "step": 130
209
+ },
210
+ {
211
+ "epoch": 0.27,
212
+ "grad_norm": 936.0,
213
+ "learning_rate": 0.0003,
214
+ "loss": 3.068846893310547,
215
+ "step": 135
216
+ },
217
+ {
218
+ "epoch": 0.28,
219
+ "grad_norm": 1296.0,
220
+ "learning_rate": 0.0003,
221
+ "loss": 3.043972206115723,
222
+ "step": 140
223
+ },
224
+ {
225
+ "epoch": 0.29,
226
+ "grad_norm": 152.0,
227
+ "learning_rate": 0.0003,
228
+ "loss": 3.063678741455078,
229
+ "step": 145
230
+ },
231
+ {
232
+ "epoch": 0.3,
233
+ "grad_norm": 50.0,
234
+ "learning_rate": 0.0003,
235
+ "loss": 3.0807422637939452,
236
+ "step": 150
237
+ },
238
+ {
239
+ "epoch": 0.3,
240
+ "eval_loss": 3.381226062774658,
241
+ "eval_runtime": 8.9995,
242
+ "eval_samples_per_second": 2.0,
243
+ "eval_steps_per_second": 2.0,
244
+ "step": 150
245
+ },
246
+ {
247
+ "epoch": 0.31,
248
+ "grad_norm": 652.0,
249
+ "learning_rate": 0.0003,
250
+ "loss": 3.050394821166992,
251
+ "step": 155
252
+ },
253
+ {
254
+ "epoch": 0.32,
255
+ "grad_norm": 187.0,
256
+ "learning_rate": 0.0003,
257
+ "loss": 3.1013137817382814,
258
+ "step": 160
259
+ },
260
+ {
261
+ "epoch": 0.33,
262
+ "grad_norm": 430.0,
263
+ "learning_rate": 0.0003,
264
+ "loss": 3.052425003051758,
265
+ "step": 165
266
+ },
267
+ {
268
+ "epoch": 0.34,
269
+ "grad_norm": 147.0,
270
+ "learning_rate": 0.0003,
271
+ "loss": 3.0121395111083986,
272
+ "step": 170
273
+ },
274
+ {
275
+ "epoch": 0.35,
276
+ "grad_norm": 382.0,
277
+ "learning_rate": 0.0003,
278
+ "loss": 3.015604591369629,
279
+ "step": 175
280
+ },
281
+ {
282
+ "epoch": 0.36,
283
+ "grad_norm": 368.0,
284
+ "learning_rate": 0.0003,
285
+ "loss": 3.006996726989746,
286
+ "step": 180
287
+ },
288
+ {
289
+ "epoch": 0.37,
290
+ "grad_norm": 14.5625,
291
+ "learning_rate": 0.0003,
292
+ "loss": 3.026082992553711,
293
+ "step": 185
294
+ },
295
+ {
296
+ "epoch": 0.38,
297
+ "grad_norm": 158.0,
298
+ "learning_rate": 0.0003,
299
+ "loss": 3.029666709899902,
300
+ "step": 190
301
+ },
302
+ {
303
+ "epoch": 0.39,
304
+ "grad_norm": 62.25,
305
+ "learning_rate": 0.0003,
306
+ "loss": 2.9676319122314454,
307
+ "step": 195
308
+ },
309
+ {
310
+ "epoch": 0.4,
311
+ "grad_norm": 1496.0,
312
+ "learning_rate": 0.0003,
313
+ "loss": 3.016917419433594,
314
+ "step": 200
315
+ },
316
+ {
317
+ "epoch": 0.4,
318
+ "eval_loss": 3.3380279541015625,
319
+ "eval_runtime": 9.0151,
320
+ "eval_samples_per_second": 1.997,
321
+ "eval_steps_per_second": 1.997,
322
+ "step": 200
323
+ }
324
+ ],
325
+ "logging_steps": 5,
326
+ "max_steps": 500,
327
+ "num_input_tokens_seen": 0,
328
+ "num_train_epochs": 9223372036854775807,
329
+ "save_steps": 200,
330
+ "stateful_callbacks": {
331
+ "TrainerControl": {
332
+ "args": {
333
+ "should_epoch_stop": false,
334
+ "should_evaluate": false,
335
+ "should_log": false,
336
+ "should_save": true,
337
+ "should_training_stop": false
338
+ },
339
+ "attributes": {}
340
+ }
341
+ },
342
+ "total_flos": 5.79830248636416e+16,
343
+ "train_batch_size": 1,
344
+ "trial_name": null,
345
+ "trial_params": null
346
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8b01d1592d99040eb2850d4c3807e7b6de59a379fd4bdb21e748fbf3b246311
3
+ size 5265