Hugging Face's logo

CodeIsAbstract
/
HybridTimeScaleModel_conti3_

Transformers
Safetensors
hybrid_fourier_lm
Generated from Trainer
Model card Files
xet
 Community
CodeIsAbstract commited on
Commit
3441634
·
verified ·
1 Parent(s): 953eaac

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 sha256:07681faa1bfe71f19e3c13a7da1c21bac4fa91691aa81126db4fd7c58af0fcd8
3
+ size 234681136
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3edd60a6c2e77b4dc429b60c911a2a962be106402c5790e570606b7242f794c3
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": 0.2,
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": 0.005,
14
+ "grad_norm": 1.859375,
15
+ "learning_rate": 7.999999999999999e-05,
16
+ "loss": 2.9596134185791017,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.01,
21
+ "grad_norm": 2.375,
22
+ "learning_rate": 0.00017999999999999998,
23
+ "loss": 3.0003786087036133,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.015,
28
+ "grad_norm": 14.75,
29
+ "learning_rate": 0.00028,
30
+ "loss": 2.946580696105957,
31
+ "step": 15
32
+ },
33
+ {
34
+ "epoch": 0.02,
35
+ "grad_norm": 1.2421875,
36
+ "learning_rate": 0.0003,
37
+ "loss": 2.9287084579467773,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 0.025,
42
+ "grad_norm": 3.296875,
43
+ "learning_rate": 0.0003,
44
+ "loss": 2.8551090240478514,
45
+ "step": 25
46
+ },
47
+ {
48
+ "epoch": 0.03,
49
+ "grad_norm": 1.5546875,
50
+ "learning_rate": 0.0003,
51
+ "loss": 2.8845558166503906,
52
+ "step": 30
53
+ },
54
+ {
55
+ "epoch": 0.035,
56
+ "grad_norm": 1.03125,
57
+ "learning_rate": 0.0003,
58
+ "loss": 2.8326595306396483,
59
+ "step": 35
60
+ },
61
+ {
62
+ "epoch": 0.04,
63
+ "grad_norm": 5.03125,
64
+ "learning_rate": 0.0003,
65
+ "loss": 2.844678497314453,
66
+ "step": 40
67
+ },
68
+ {
69
+ "epoch": 0.045,
70
+ "grad_norm": 2.046875,
71
+ "learning_rate": 0.0003,
72
+ "loss": 2.828007125854492,
73
+ "step": 45
74
+ },
75
+ {
76
+ "epoch": 0.05,
77
+ "grad_norm": 9.25,
78
+ "learning_rate": 0.0003,
79
+ "loss": 2.8197803497314453,
80
+ "step": 50
81
+ },
82
+ {
83
+ "epoch": 0.05,
84
+ "eval_loss": 3.1455771923065186,
85
+ "eval_runtime": 6.8102,
86
+ "eval_samples_per_second": 5.433,
87
+ "eval_steps_per_second": 2.79,
88
+ "step": 50
89
+ },
90
+ {
91
+ "epoch": 0.055,
92
+ "grad_norm": 1.6171875,
93
+ "learning_rate": 0.0003,
94
+ "loss": 2.797296714782715,
95
+ "step": 55
96
+ },
97
+ {
98
+ "epoch": 0.06,
99
+ "grad_norm": 1.90625,
100
+ "learning_rate": 0.0003,
101
+ "loss": 2.7909267425537108,
102
+ "step": 60
103
+ },
104
+ {
105
+ "epoch": 0.065,
106
+ "grad_norm": 0.66796875,
107
+ "learning_rate": 0.0003,
108
+ "loss": 2.7826940536499025,
109
+ "step": 65
110
+ },
111
+ {
112
+ "epoch": 0.07,
113
+ "grad_norm": 1.1640625,
114
+ "learning_rate": 0.0003,
115
+ "loss": 2.8065961837768554,
116
+ "step": 70
117
+ },
118
+ {
119
+ "epoch": 0.075,
120
+ "grad_norm": 0.61328125,
121
+ "learning_rate": 0.0003,
122
+ "loss": 2.8089221954345702,
123
+ "step": 75
124
+ },
125
+ {
126
+ "epoch": 0.08,
127
+ "grad_norm": 2.21875,
128
+ "learning_rate": 0.0003,
129
+ "loss": 2.7947248458862304,
130
+ "step": 80
131
+ },
132
+ {
133
+ "epoch": 0.085,
134
+ "grad_norm": 0.7890625,
135
+ "learning_rate": 0.0003,
136
+ "loss": 2.7826770782470702,
137
+ "step": 85
138
+ },
139
+ {
140
+ "epoch": 0.09,
141
+ "grad_norm": 26.5,
142
+ "learning_rate": 0.0003,
143
+ "loss": 2.7801084518432617,
144
+ "step": 90
145
+ },
146
+ {
147
+ "epoch": 0.095,
148
+ "grad_norm": 1.2734375,
149
+ "learning_rate": 0.0003,
150
+ "loss": 2.748321533203125,
151
+ "step": 95
152
+ },
153
+ {
154
+ "epoch": 0.1,
155
+ "grad_norm": 0.341796875,
156
+ "learning_rate": 0.0003,
157
+ "loss": 2.7878595352172852,
158
+ "step": 100
159
+ },
160
+ {
161
+ "epoch": 0.1,
162
+ "eval_loss": 3.1193559169769287,
163
+ "eval_runtime": 6.6531,
164
+ "eval_samples_per_second": 5.561,
165
+ "eval_steps_per_second": 2.856,
166
+ "step": 100
167
+ },
168
+ {
169
+ "epoch": 0.105,
170
+ "grad_norm": 1.078125,
171
+ "learning_rate": 0.0003,
172
+ "loss": 2.785268211364746,
173
+ "step": 105
174
+ },
175
+ {
176
+ "epoch": 0.11,
177
+ "grad_norm": 0.890625,
178
+ "learning_rate": 0.0003,
179
+ "loss": 2.725397491455078,
180
+ "step": 110
181
+ },
182
+ {
183
+ "epoch": 0.115,
184
+ "grad_norm": 2.84375,
185
+ "learning_rate": 0.0003,
186
+ "loss": 2.7376623153686523,
187
+ "step": 115
188
+ },
189
+ {
190
+ "epoch": 0.12,
191
+ "grad_norm": 2.421875,
192
+ "learning_rate": 0.0003,
193
+ "loss": 2.758837127685547,
194
+ "step": 120
195
+ },
196
+ {
197
+ "epoch": 0.125,
198
+ "grad_norm": 1.828125,
199
+ "learning_rate": 0.0003,
200
+ "loss": 2.768202018737793,
201
+ "step": 125
202
+ },
203
+ {
204
+ "epoch": 0.13,
205
+ "grad_norm": 0.3515625,
206
+ "learning_rate": 0.0003,
207
+ "loss": 2.7715227127075197,
208
+ "step": 130
209
+ },
210
+ {
211
+ "epoch": 0.135,
212
+ "grad_norm": 0.5,
213
+ "learning_rate": 0.0003,
214
+ "loss": 2.7676155090332033,
215
+ "step": 135
216
+ },
217
+ {
218
+ "epoch": 0.14,
219
+ "grad_norm": 0.83203125,
220
+ "learning_rate": 0.0003,
221
+ "loss": 2.739817428588867,
222
+ "step": 140
223
+ },
224
+ {
225
+ "epoch": 0.145,
226
+ "grad_norm": 0.66796875,
227
+ "learning_rate": 0.0003,
228
+ "loss": 2.740823745727539,
229
+ "step": 145
230
+ },
231
+ {
232
+ "epoch": 0.15,
233
+ "grad_norm": 12.5,
234
+ "learning_rate": 0.0003,
235
+ "loss": 2.754258728027344,
236
+ "step": 150
237
+ },
238
+ {
239
+ "epoch": 0.15,
240
+ "eval_loss": 3.1168980598449707,
241
+ "eval_runtime": 6.6806,
242
+ "eval_samples_per_second": 5.538,
243
+ "eval_steps_per_second": 2.844,
244
+ "step": 150
245
+ },
246
+ {
247
+ "epoch": 0.155,
248
+ "grad_norm": 2.359375,
249
+ "learning_rate": 0.0003,
250
+ "loss": 2.713482475280762,
251
+ "step": 155
252
+ },
253
+ {
254
+ "epoch": 0.16,
255
+ "grad_norm": 2.265625,
256
+ "learning_rate": 0.0003,
257
+ "loss": 2.7810474395751954,
258
+ "step": 160
259
+ },
260
+ {
261
+ "epoch": 0.165,
262
+ "grad_norm": 0.5625,
263
+ "learning_rate": 0.0003,
264
+ "loss": 2.758929443359375,
265
+ "step": 165
266
+ },
267
+ {
268
+ "epoch": 0.17,
269
+ "grad_norm": 1.6015625,
270
+ "learning_rate": 0.0003,
271
+ "loss": 2.7030134201049805,
272
+ "step": 170
273
+ },
274
+ {
275
+ "epoch": 0.175,
276
+ "grad_norm": 0.74609375,
277
+ "learning_rate": 0.0003,
278
+ "loss": 2.7331872940063477,
279
+ "step": 175
280
+ },
281
+ {
282
+ "epoch": 0.18,
283
+ "grad_norm": 2.5,
284
+ "learning_rate": 0.0003,
285
+ "loss": 2.7181303024291994,
286
+ "step": 180
287
+ },
288
+ {
289
+ "epoch": 0.185,
290
+ "grad_norm": 0.53515625,
291
+ "learning_rate": 0.0003,
292
+ "loss": 2.7308780670166017,
293
+ "step": 185
294
+ },
295
+ {
296
+ "epoch": 0.19,
297
+ "grad_norm": 3.875,
298
+ "learning_rate": 0.0003,
299
+ "loss": 2.7536849975585938,
300
+ "step": 190
301
+ },
302
+ {
303
+ "epoch": 0.195,
304
+ "grad_norm": 0.361328125,
305
+ "learning_rate": 0.0003,
306
+ "loss": 2.71515007019043,
307
+ "step": 195
308
+ },
309
+ {
310
+ "epoch": 0.2,
311
+ "grad_norm": 0.408203125,
312
+ "learning_rate": 0.0003,
313
+ "loss": 2.712385559082031,
314
+ "step": 200
315
+ },
316
+ {
317
+ "epoch": 0.2,
318
+ "eval_loss": 3.117068290710449,
319
+ "eval_runtime": 6.7047,
320
+ "eval_samples_per_second": 5.519,
321
+ "eval_steps_per_second": 2.834,
322
+ "step": 200
323
+ }
324
+ ],
325
+ "logging_steps": 5,
326
+ "max_steps": 1000,
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": 2,
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 sha256:4a70aabed0457e05b37f233610f4e2e52283700e304afecd170873a8550ff953
3
+ size 5265