vdos commited on
Commit
c7edb60
1 Parent(s): 26ebf54

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 sha256:40b8fab9495914d917760270fb2288c092161861d6edb3cbc08cb69e1a680f0c
3
  size 323014168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d97387a168b8324c3c0e6ce95da6b22f628a934e40f3ca8e9a368f409d1b5d60
3
  size 323014168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:425ebc9e344c2714a04234827c2601ea2d79a4cf264899f82f36e19b68c9edb2
3
  size 646253418
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65ebbbe8fe2898b62213e8051a8eaff2bbe6a267ef5d97c0ee3c35c726468156
3
  size 646253418
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:392da4140017150b8d398edc4b538ef38dbc8f4689f3a420a82ece6c45d0d233
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b8efda10a41bc31fd8508829a418350e4727b415e6f5dd36e4cce68583571e9
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:e1ce34fcad5b45fba6e1054f3d4e0dee54bdb7bff106b71a1f4ae8644f4499fe
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac7a4ca70b41246f02ac085e49ff807b49d5959225be6547ae1a9fda02899648
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 sha256:531500faef14b3dc9453169ab4dd6befeea317705d37df8653d3f1c4a7cf304b
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e15a4bddfdd5a038d128bfa5cc3d21bba0d718941653385c9fac1fdd5d1dd73d
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:f5abd135c16b1a63f4341428e38300a8af25efbb7344f469ce487bbd4336b94d
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3785c1b406f0ca6c1297b356122ec31c2d103f0cc30c2e94503e3639668caf6b
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": 0.7837062478065491,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.4836759371221282,
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": 30.618,
199
  "eval_steps_per_second": 3.86,
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": 3.005355905987379e+17,
230
  "train_batch_size": 2,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.7657374739646912,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.9673518742442564,
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": 30.618,
199
  "eval_steps_per_second": 3.86,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.5030229746070133,
204
+ "grad_norm": 0.07031340897083282,
205
+ "learning_rate": 5e-05,
206
+ "loss": 0.7878,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.5223700120918985,
211
+ "grad_norm": 0.07707154750823975,
212
+ "learning_rate": 4.6729843538492847e-05,
213
+ "loss": 0.786,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.5417170495767836,
218
+ "grad_norm": 0.0745035782456398,
219
+ "learning_rate": 4.347369038899744e-05,
220
+ "loss": 0.9134,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.5610640870616687,
225
+ "grad_norm": 0.06669345498085022,
226
+ "learning_rate": 4.0245483899193595e-05,
227
+ "loss": 0.8154,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.5804111245465539,
232
+ "grad_norm": 0.0690491795539856,
233
+ "learning_rate": 3.705904774487396e-05,
234
+ "loss": 0.8274,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.599758162031439,
239
+ "grad_norm": 0.07264308631420135,
240
+ "learning_rate": 3.392802673484193e-05,
241
+ "loss": 0.8744,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.619105199516324,
246
+ "grad_norm": 0.07223401218652725,
247
+ "learning_rate": 3.086582838174551e-05,
248
+ "loss": 0.9257,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.6384522370012092,
253
+ "grad_norm": 0.0706273689866066,
254
+ "learning_rate": 2.7885565489049946e-05,
255
+ "loss": 0.9225,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.6577992744860943,
260
+ "grad_norm": 0.07520892471075058,
261
+ "learning_rate": 2.500000000000001e-05,
262
+ "loss": 0.9234,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.6771463119709794,
267
+ "grad_norm": 0.08015627413988113,
268
+ "learning_rate": 2.2221488349019903e-05,
269
+ "loss": 0.8068,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.6964933494558646,
274
+ "grad_norm": 0.09883278608322144,
275
+ "learning_rate": 1.9561928549563968e-05,
276
+ "loss": 0.6502,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.7158403869407497,
281
+ "grad_norm": 0.1318332403898239,
282
+ "learning_rate": 1.703270924499656e-05,
283
+ "loss": 0.4271,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.7351874244256348,
288
+ "grad_norm": 0.08774442225694656,
289
+ "learning_rate": 1.4644660940672627e-05,
290
+ "loss": 0.7714,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.75453446191052,
295
+ "grad_norm": 0.06477252393960953,
296
+ "learning_rate": 1.2408009626051137e-05,
297
+ "loss": 0.8214,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.7738814993954051,
302
+ "grad_norm": 0.0652678981423378,
303
+ "learning_rate": 1.0332332985438248e-05,
304
+ "loss": 0.8322,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.7932285368802902,
309
+ "grad_norm": 0.06607598066329956,
310
+ "learning_rate": 8.426519384872733e-06,
311
+ "loss": 0.8466,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.8125755743651754,
316
+ "grad_norm": 0.06954794377088547,
317
+ "learning_rate": 6.698729810778065e-06,
318
+ "loss": 0.882,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.8319226118500604,
323
+ "grad_norm": 0.07791940122842789,
324
+ "learning_rate": 5.156362923365588e-06,
325
+ "loss": 0.9292,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.8512696493349455,
330
+ "grad_norm": 0.07262781262397766,
331
+ "learning_rate": 3.8060233744356633e-06,
332
+ "loss": 0.8562,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.8706166868198307,
337
+ "grad_norm": 0.070536307990551,
338
+ "learning_rate": 2.653493525244721e-06,
339
+ "loss": 0.8477,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.8899637243047158,
344
+ "grad_norm": 0.0720757469534874,
345
+ "learning_rate": 1.70370868554659e-06,
346
+ "loss": 0.896,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.909310761789601,
351
+ "grad_norm": 0.07141188532114029,
352
+ "learning_rate": 9.607359798384785e-07,
353
+ "loss": 0.7931,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.9286577992744861,
358
+ "grad_norm": 0.08638662099838257,
359
+ "learning_rate": 4.277569313094809e-07,
360
+ "loss": 0.7604,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.9480048367593712,
365
+ "grad_norm": 0.10718564689159393,
366
+ "learning_rate": 1.0705383806982606e-07,
367
+ "loss": 0.5603,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.9673518742442564,
372
+ "grad_norm": 0.21608486771583557,
373
+ "learning_rate": 0.0,
374
+ "loss": 0.2008,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.9673518742442564,
379
+ "eval_loss": 0.7657374739646912,
380
+ "eval_runtime": 11.6416,
381
+ "eval_samples_per_second": 29.979,
382
+ "eval_steps_per_second": 3.78,
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": 5.991379090433638e+17,
413
  "train_batch_size": 2,
414
  "trial_name": null,
415
  "trial_params": null