eeeebbb2 commited on
Commit
8139860
·
verified ·
1 Parent(s): 68b8da7

Training in progress, step 50, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f45d4dc73a16f64ff9b9ef96675f88e01bbfb56299b962890110e59dfeec9530
3
  size 335604696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a32db2051230840c4287d0a498065690d75bbff9991769eabd58e67bb3a803b
3
  size 335604696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b9c174bfd70e121dace1c75291677ef37339de155ed1e092b24c11336011bfb
3
  size 671466706
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e720d59003d4ba8d2275c1e735584dc1e1408ddc9eb9e6cabe43d947793a161a
3
  size 671466706
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f9661c97822a255de98537b358889054273ccfcc80b9fc18a0cf0058e3c6ffb9
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41f975564da7636108fa321e34bfc7be21b5659234350400249d062c0bc65363
3
  size 15024
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a3d43cfbef24e3c18391450d80cdfcf7b6d553806b38aa616d4458969cacae9e
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63ec3f8d7ebbf0fa383190f58e3592bdcb5ed58db97fcb339532dff965721709
3
  size 15024
last-checkpoint/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c28910d58254b07934f8bc01798576fe0236bc591ac3d350caee07af5c276c19
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06b98961795a5c51c51ec8813794728a40cce8e27a233e05b3f6afd20beace08
3
  size 15024
last-checkpoint/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8caadc8476aaabe1a6c6dcfe164a3ad2874b1e718a9a64a9b417a15a4c099fb7
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e180a11110b377fe94959ba4e3d1630f922e27f73ff98fc73effde4613c9c2d9
3
  size 15024
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.9312448501586914,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.13134132326383188,
5
  "eval_steps": 25,
6
- "global_step": 25,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -198,6 +198,189 @@
198
  "eval_samples_per_second": 11.212,
199
  "eval_steps_per_second": 2.915,
200
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
201
  }
202
  ],
203
  "logging_steps": 1,
@@ -221,12 +404,12 @@
221
  "should_evaluate": false,
222
  "should_log": false,
223
  "should_save": true,
224
- "should_training_stop": false
225
  },
226
  "attributes": {}
227
  }
228
  },
229
- "total_flos": 2.984041808658432e+17,
230
  "train_batch_size": 1,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.8784054517745972,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.26268264652766377,
5
  "eval_steps": 25,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
198
  "eval_samples_per_second": 11.212,
199
  "eval_steps_per_second": 2.915,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.13659497619438515,
204
+ "grad_norm": 0.6616726517677307,
205
+ "learning_rate": 5.500000000000001e-05,
206
+ "loss": 1.9788,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.14184862912493842,
211
+ "grad_norm": 0.8025255799293518,
212
+ "learning_rate": 5.205685918464356e-05,
213
+ "loss": 1.9753,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.1471022820554917,
218
+ "grad_norm": 0.7781208157539368,
219
+ "learning_rate": 4.912632135009769e-05,
220
+ "loss": 1.8864,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.152355934986045,
225
+ "grad_norm": 0.7017228007316589,
226
+ "learning_rate": 4.6220935509274235e-05,
227
+ "loss": 1.891,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.15760958791659826,
232
+ "grad_norm": 0.579820990562439,
233
+ "learning_rate": 4.3353142970386564e-05,
234
+ "loss": 1.8035,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.16286324084715154,
239
+ "grad_norm": 0.41840893030166626,
240
+ "learning_rate": 4.053522406135775e-05,
241
+ "loss": 1.8498,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.1681168937777048,
246
+ "grad_norm": 0.3678834140300751,
247
+ "learning_rate": 3.777924554357096e-05,
248
+ "loss": 1.8353,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.17337054670825808,
253
+ "grad_norm": 0.3725689649581909,
254
+ "learning_rate": 3.509700894014496e-05,
255
+ "loss": 1.8466,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.17862419963881135,
260
+ "grad_norm": 0.4001309871673584,
261
+ "learning_rate": 3.250000000000001e-05,
262
+ "loss": 1.8133,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.18387785256936465,
267
+ "grad_norm": 0.5521655678749084,
268
+ "learning_rate": 2.9999339514117912e-05,
269
+ "loss": 1.8136,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.18913150549991792,
274
+ "grad_norm": 0.7147834897041321,
275
+ "learning_rate": 2.760573569460757e-05,
276
+ "loss": 1.7467,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.1943851584304712,
281
+ "grad_norm": 0.9815901517868042,
282
+ "learning_rate": 2.53294383204969e-05,
283
+ "loss": 1.4188,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.19963881136102446,
288
+ "grad_norm": 0.3459879755973816,
289
+ "learning_rate": 2.3180194846605367e-05,
290
+ "loss": 1.8972,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.20489246429157773,
295
+ "grad_norm": 0.2581966519355774,
296
+ "learning_rate": 2.1167208663446025e-05,
297
+ "loss": 1.9797,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.210146117222131,
302
+ "grad_norm": 0.2652834355831146,
303
+ "learning_rate": 1.9299099686894423e-05,
304
+ "loss": 1.8921,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.2153997701526843,
309
+ "grad_norm": 0.26171135902404785,
310
+ "learning_rate": 1.758386744638546e-05,
311
+ "loss": 1.8444,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.22065342308323757,
316
+ "grad_norm": 0.2745507061481476,
317
+ "learning_rate": 1.602885682970026e-05,
318
+ "loss": 1.7971,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.22590707601379084,
323
+ "grad_norm": 0.29274782538414,
324
+ "learning_rate": 1.464072663102903e-05,
325
+ "loss": 1.8226,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.2311607289443441,
330
+ "grad_norm": 0.33201128244400024,
331
+ "learning_rate": 1.3425421036992098e-05,
332
+ "loss": 1.7734,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.23641438187489738,
337
+ "grad_norm": 0.37386682629585266,
338
+ "learning_rate": 1.2388144172720251e-05,
339
+ "loss": 1.7949,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.24166803480545065,
344
+ "grad_norm": 0.40295544266700745,
345
+ "learning_rate": 1.1533337816991932e-05,
346
+ "loss": 1.7405,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.24692168773600395,
351
+ "grad_norm": 0.5132532119750977,
352
+ "learning_rate": 1.0864662381854632e-05,
353
+ "loss": 1.79,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.2521753406665572,
358
+ "grad_norm": 0.5474813580513,
359
+ "learning_rate": 1.0384981238178534e-05,
360
+ "loss": 1.667,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.25742899359711047,
365
+ "grad_norm": 0.7360696792602539,
366
+ "learning_rate": 1.0096348454262845e-05,
367
+ "loss": 1.5563,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.26268264652766377,
372
+ "grad_norm": 1.228757381439209,
373
+ "learning_rate": 1e-05,
374
+ "loss": 1.4214,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.26268264652766377,
379
+ "eval_loss": 1.8784054517745972,
380
+ "eval_runtime": 4.3499,
381
+ "eval_samples_per_second": 11.494,
382
+ "eval_steps_per_second": 2.989,
383
+ "step": 50
384
  }
385
  ],
386
  "logging_steps": 1,
 
404
  "should_evaluate": false,
405
  "should_log": false,
406
  "should_save": true,
407
+ "should_training_stop": true
408
  },
409
  "attributes": {}
410
  }
411
  },
412
+ "total_flos": 5.968083617316864e+17,
413
  "train_batch_size": 1,
414
  "trial_name": null,
415
  "trial_params": null