Alpha-Command-Intern commited on
Commit
804d6a1
1 Parent(s): f91d628

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 sha256:98266b09ce3c5e765c3cb14bddff177fb154a8927503fdc95c941a7e2881cfae
3
  size 147770496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85d2a2614560e707c651c8a67882dba12da0c26dcc0edd1d26827fdd15eb5a39
3
  size 147770496
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d5793607451ecb473a27fabbdc7fc532294735b792b7829077d94679616dac6
3
  size 295765866
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76dd93416d34cbd7a9f8d77fafef4bbc5aa3ac94ccbae6f16d227ed6c801cfe0
3
  size 295765866
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8c5bb90b2e707863ff5a757728277d510e761a30b2628ce074efe11d5bff6630
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca7a92eef8f17e24f1fa6cc36eebaf308ebc5191b11b1c5a3eb244df5c071db9
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 sha256:8a68c707c3b63db6677d2e830a48d83e1684de59c66e14386368385245c0cc96
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1f9367e432d5ef8da4db6192d0774d5094cbb80cf742b0053a5ed4e32cb14ee
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 sha256:2a41621f2da28f3962ca1d2c0718ed05be6605fb1b2c73152644bfc9839b81f2
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:847ade70f7ccd7b84a98e423ddc0635d7863c6bebbb9d3ccf2a4540c8c66fd7a
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:e4680d6a7cc65f720424877708b7e72b5e2ca40fa0b797a77ee6886c6236d698
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a676c12dfc59d6658b4dfa3f769daedc2b9f70252c11d48e5ade0f2931b2a0f6
3
  size 15024
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.8789408206939697,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.4366812227074236,
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": 41.899,
199
  "eval_steps_per_second": 5.319,
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": 9.760978685342515e+16,
230
  "train_batch_size": 2,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.8564728498458862,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.8733624454148472,
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": 41.899,
199
  "eval_steps_per_second": 5.319,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.45414847161572053,
204
+ "grad_norm": 0.2208106517791748,
205
+ "learning_rate": 5e-05,
206
+ "loss": 2.2395,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.47161572052401746,
211
+ "grad_norm": 0.2533266246318817,
212
+ "learning_rate": 4.6729843538492847e-05,
213
+ "loss": 2.2826,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.4890829694323144,
218
+ "grad_norm": 0.22869157791137695,
219
+ "learning_rate": 4.347369038899744e-05,
220
+ "loss": 2.2854,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.5065502183406113,
225
+ "grad_norm": 0.21572184562683105,
226
+ "learning_rate": 4.0245483899193595e-05,
227
+ "loss": 2.1784,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.5240174672489083,
232
+ "grad_norm": 0.21361880004405975,
233
+ "learning_rate": 3.705904774487396e-05,
234
+ "loss": 2.1801,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.5414847161572053,
239
+ "grad_norm": 0.20447427034378052,
240
+ "learning_rate": 3.392802673484193e-05,
241
+ "loss": 2.169,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.5589519650655022,
246
+ "grad_norm": 0.21110278367996216,
247
+ "learning_rate": 3.086582838174551e-05,
248
+ "loss": 2.2121,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.5764192139737991,
253
+ "grad_norm": 0.21510860323905945,
254
+ "learning_rate": 2.7885565489049946e-05,
255
+ "loss": 2.1632,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.5938864628820961,
260
+ "grad_norm": 0.2602185308933258,
261
+ "learning_rate": 2.500000000000001e-05,
262
+ "loss": 2.3162,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.611353711790393,
267
+ "grad_norm": 0.28548145294189453,
268
+ "learning_rate": 2.2221488349019903e-05,
269
+ "loss": 1.9825,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.62882096069869,
274
+ "grad_norm": 0.14463306963443756,
275
+ "learning_rate": 1.9561928549563968e-05,
276
+ "loss": 0.5298,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.6462882096069869,
281
+ "grad_norm": 0.04139815643429756,
282
+ "learning_rate": 1.703270924499656e-05,
283
+ "loss": 0.0034,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.6637554585152838,
288
+ "grad_norm": 0.21067368984222412,
289
+ "learning_rate": 1.4644660940672627e-05,
290
+ "loss": 1.9263,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.6812227074235808,
295
+ "grad_norm": 0.18605366349220276,
296
+ "learning_rate": 1.2408009626051137e-05,
297
+ "loss": 2.2741,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.6986899563318777,
302
+ "grad_norm": 0.20509853959083557,
303
+ "learning_rate": 1.0332332985438248e-05,
304
+ "loss": 2.2616,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.7161572052401747,
309
+ "grad_norm": 0.1972036212682724,
310
+ "learning_rate": 8.426519384872733e-06,
311
+ "loss": 2.2469,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.7336244541484717,
316
+ "grad_norm": 0.19003644585609436,
317
+ "learning_rate": 6.698729810778065e-06,
318
+ "loss": 2.283,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.7510917030567685,
323
+ "grad_norm": 0.1818603128194809,
324
+ "learning_rate": 5.156362923365588e-06,
325
+ "loss": 2.2192,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.7685589519650655,
330
+ "grad_norm": 0.19268260896205902,
331
+ "learning_rate": 3.8060233744356633e-06,
332
+ "loss": 2.1306,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.7860262008733624,
337
+ "grad_norm": 0.19862526655197144,
338
+ "learning_rate": 2.653493525244721e-06,
339
+ "loss": 2.1101,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.8034934497816594,
344
+ "grad_norm": 0.22022812068462372,
345
+ "learning_rate": 1.70370868554659e-06,
346
+ "loss": 2.1762,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.8209606986899564,
351
+ "grad_norm": 0.287217378616333,
352
+ "learning_rate": 9.607359798384785e-07,
353
+ "loss": 2.1762,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.8384279475982532,
358
+ "grad_norm": 0.338515967130661,
359
+ "learning_rate": 4.277569313094809e-07,
360
+ "loss": 1.7232,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.8558951965065502,
365
+ "grad_norm": 0.03698641434311867,
366
+ "learning_rate": 1.0705383806982606e-07,
367
+ "loss": 0.013,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.8733624454148472,
372
+ "grad_norm": 0.04879317060112953,
373
+ "learning_rate": 0.0,
374
+ "loss": 0.0051,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.8733624454148472,
379
+ "eval_loss": 1.8564728498458862,
380
+ "eval_runtime": 9.2884,
381
+ "eval_samples_per_second": 41.557,
382
+ "eval_steps_per_second": 5.275,
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": 1.9545134732201165e+17,
413
  "train_batch_size": 2,
414
  "trial_name": null,
415
  "trial_params": null