Grogros commited on
Commit
0867b04
·
verified ·
1 Parent(s): d81e2f5

Training in progress, step 500, checkpoint

Browse files
checkpoint-500/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "head_dim": 64,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 2048,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 8192,
19
+ "max_position_embeddings": 131072,
20
+ "mlp_bias": false,
21
+ "model_type": "llama",
22
+ "num_attention_heads": 32,
23
+ "num_hidden_layers": 16,
24
+ "num_key_value_heads": 8,
25
+ "pretraining_tp": 1,
26
+ "rms_norm_eps": 1e-05,
27
+ "rope_scaling": {
28
+ "factor": 32.0,
29
+ "high_freq_factor": 4.0,
30
+ "low_freq_factor": 1.0,
31
+ "original_max_position_embeddings": 8192,
32
+ "rope_type": "llama3"
33
+ },
34
+ "rope_theta": 500000.0,
35
+ "tie_word_embeddings": true,
36
+ "torch_dtype": "bfloat16",
37
+ "transformers_version": "4.46.3",
38
+ "use_cache": true,
39
+ "vocab_size": 128256
40
+ }
checkpoint-500/generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.46.3"
12
+ }
checkpoint-500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eda59e71a5c87d65aff9879cdf386f36aee8d521a5c1c2874116eac1174caf62
3
+ size 2471645608
checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9ac5c27bb66492cc38850ccdd94884f6a0f1722a06c701f07baed7546599d2c
3
+ size 3724602
checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b66e3cc7c452b707ddac5caf0aa17618afb9bc1a0333600a22c4afb353f3165
3
+ size 14244
checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eca22cdf077d0b727dcb149a5a36d41b809fa267851149dd4e675539651c5b8c
3
+ size 1064
checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,383 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.25,
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": 0.005,
13
+ "grad_norm": 37.0,
14
+ "learning_rate": 1.0000000000000002e-06,
15
+ "loss": 1.5359,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.01,
20
+ "grad_norm": 45.5,
21
+ "learning_rate": 2.0000000000000003e-06,
22
+ "loss": 1.4797,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.015,
27
+ "grad_norm": 21.625,
28
+ "learning_rate": 3e-06,
29
+ "loss": 1.3793,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.02,
34
+ "grad_norm": 19.625,
35
+ "learning_rate": 4.000000000000001e-06,
36
+ "loss": 1.26,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.025,
41
+ "grad_norm": 12.375,
42
+ "learning_rate": 5e-06,
43
+ "loss": 1.2473,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.03,
48
+ "grad_norm": 9.75,
49
+ "learning_rate": 6e-06,
50
+ "loss": 1.132,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.035,
55
+ "grad_norm": 8.4375,
56
+ "learning_rate": 7e-06,
57
+ "loss": 1.1854,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.04,
62
+ "grad_norm": 9.25,
63
+ "learning_rate": 8.000000000000001e-06,
64
+ "loss": 1.1473,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.045,
69
+ "grad_norm": 5.5,
70
+ "learning_rate": 9e-06,
71
+ "loss": 1.1484,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.05,
76
+ "grad_norm": 4.71875,
77
+ "learning_rate": 1e-05,
78
+ "loss": 1.1352,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.055,
83
+ "grad_norm": 5.6875,
84
+ "learning_rate": 1.1000000000000001e-05,
85
+ "loss": 1.0916,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.06,
90
+ "grad_norm": 4.90625,
91
+ "learning_rate": 1.2e-05,
92
+ "loss": 1.0473,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.065,
97
+ "grad_norm": 5.09375,
98
+ "learning_rate": 1.3000000000000001e-05,
99
+ "loss": 1.0576,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.07,
104
+ "grad_norm": 5.6875,
105
+ "learning_rate": 1.4e-05,
106
+ "loss": 1.0014,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.075,
111
+ "grad_norm": 5.4375,
112
+ "learning_rate": 1.5000000000000002e-05,
113
+ "loss": 1.015,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.08,
118
+ "grad_norm": 5.0625,
119
+ "learning_rate": 1.6000000000000003e-05,
120
+ "loss": 0.9674,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.085,
125
+ "grad_norm": 5.125,
126
+ "learning_rate": 1.7e-05,
127
+ "loss": 0.9754,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.09,
132
+ "grad_norm": 4.09375,
133
+ "learning_rate": 1.8e-05,
134
+ "loss": 0.9309,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.095,
139
+ "grad_norm": 4.875,
140
+ "learning_rate": 1.9e-05,
141
+ "loss": 0.9158,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.1,
146
+ "grad_norm": 117.5,
147
+ "learning_rate": 2e-05,
148
+ "loss": 0.9994,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.105,
153
+ "grad_norm": 5.34375,
154
+ "learning_rate": 1.9998476951563914e-05,
155
+ "loss": 1.0623,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.11,
160
+ "grad_norm": 19.0,
161
+ "learning_rate": 1.999390827019096e-05,
162
+ "loss": 1.007,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.115,
167
+ "grad_norm": 5.21875,
168
+ "learning_rate": 1.9986295347545738e-05,
169
+ "loss": 0.867,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.12,
174
+ "grad_norm": 3.640625,
175
+ "learning_rate": 1.9975640502598243e-05,
176
+ "loss": 0.852,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.125,
181
+ "grad_norm": 4.40625,
182
+ "learning_rate": 1.9961946980917457e-05,
183
+ "loss": 0.8018,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.13,
188
+ "grad_norm": 5.125,
189
+ "learning_rate": 1.9945218953682736e-05,
190
+ "loss": 0.9186,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.135,
195
+ "grad_norm": 4.875,
196
+ "learning_rate": 1.9925461516413224e-05,
197
+ "loss": 0.804,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.14,
202
+ "grad_norm": 3.71875,
203
+ "learning_rate": 1.9902680687415704e-05,
204
+ "loss": 0.817,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.145,
209
+ "grad_norm": 4.125,
210
+ "learning_rate": 1.9876883405951378e-05,
211
+ "loss": 0.7372,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.15,
216
+ "grad_norm": 3.5,
217
+ "learning_rate": 1.9848077530122083e-05,
218
+ "loss": 0.7237,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.155,
223
+ "grad_norm": 3.375,
224
+ "learning_rate": 1.9816271834476642e-05,
225
+ "loss": 0.6707,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.16,
230
+ "grad_norm": 4.21875,
231
+ "learning_rate": 1.9781476007338058e-05,
232
+ "loss": 0.7664,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.165,
237
+ "grad_norm": 3.640625,
238
+ "learning_rate": 1.9743700647852356e-05,
239
+ "loss": 0.6838,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.17,
244
+ "grad_norm": 4.25,
245
+ "learning_rate": 1.9702957262759964e-05,
246
+ "loss": 0.7225,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.175,
251
+ "grad_norm": 3.625,
252
+ "learning_rate": 1.9659258262890683e-05,
253
+ "loss": 0.6754,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.18,
258
+ "grad_norm": 3.546875,
259
+ "learning_rate": 1.961261695938319e-05,
260
+ "loss": 0.6344,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.185,
265
+ "grad_norm": 3.546875,
266
+ "learning_rate": 1.9563047559630356e-05,
267
+ "loss": 0.6728,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.19,
272
+ "grad_norm": 4.34375,
273
+ "learning_rate": 1.9510565162951538e-05,
274
+ "loss": 0.7283,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.195,
279
+ "grad_norm": 3.671875,
280
+ "learning_rate": 1.945518575599317e-05,
281
+ "loss": 0.666,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.2,
286
+ "grad_norm": 4.4375,
287
+ "learning_rate": 1.9396926207859085e-05,
288
+ "loss": 0.6756,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.205,
293
+ "grad_norm": 3.71875,
294
+ "learning_rate": 1.9335804264972018e-05,
295
+ "loss": 0.6558,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.21,
300
+ "grad_norm": 3.234375,
301
+ "learning_rate": 1.9271838545667876e-05,
302
+ "loss": 0.6243,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.215,
307
+ "grad_norm": 3.90625,
308
+ "learning_rate": 1.9205048534524405e-05,
309
+ "loss": 0.6519,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.22,
314
+ "grad_norm": 3.375,
315
+ "learning_rate": 1.913545457642601e-05,
316
+ "loss": 0.626,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.225,
321
+ "grad_norm": 3.78125,
322
+ "learning_rate": 1.9063077870366504e-05,
323
+ "loss": 0.6592,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.23,
328
+ "grad_norm": 3.75,
329
+ "learning_rate": 1.8987940462991673e-05,
330
+ "loss": 0.5869,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.235,
335
+ "grad_norm": 4.25,
336
+ "learning_rate": 1.891006524188368e-05,
337
+ "loss": 0.6157,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.24,
342
+ "grad_norm": 2.78125,
343
+ "learning_rate": 1.8829475928589272e-05,
344
+ "loss": 0.5537,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.245,
349
+ "grad_norm": 2.734375,
350
+ "learning_rate": 1.874619707139396e-05,
351
+ "loss": 0.631,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.25,
356
+ "grad_norm": 3.875,
357
+ "learning_rate": 1.866025403784439e-05,
358
+ "loss": 0.5853,
359
+ "step": 500
360
+ }
361
+ ],
362
+ "logging_steps": 10,
363
+ "max_steps": 2000,
364
+ "num_input_tokens_seen": 0,
365
+ "num_train_epochs": 9223372036854775807,
366
+ "save_steps": 500,
367
+ "stateful_callbacks": {
368
+ "TrainerControl": {
369
+ "args": {
370
+ "should_epoch_stop": false,
371
+ "should_evaluate": false,
372
+ "should_log": false,
373
+ "should_save": true,
374
+ "should_training_stop": false
375
+ },
376
+ "attributes": {}
377
+ }
378
+ },
379
+ "total_flos": 4.7832077697024e+16,
380
+ "train_batch_size": 16,
381
+ "trial_name": null,
382
+ "trial_params": null
383
+ }
checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cd6b60903244d2c3807559fcc357810b7e7b4b029b3946e04d0a00137162c24
3
+ size 5304