DeepDream2045 commited on
Commit
2d23d02
1 Parent(s): 01bbafa

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:ca60626e0946942009dda0c61c0e55c241515532531c7fe71e461006d143417d
3
  size 335604696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d9c37abd439cee085a6fc91e6e84268c6dfe7b35f4a1d4f83188a2a572dea37
3
  size 335604696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:effc371019271d370857a58075770488bd8649263db72ff8fe10398ec15e83fe
3
  size 671466706
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d824cdf3ed0e57daaa15238710d965fcb44b0fe54278a027e6e7cfbf5d996b4
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:ade36b14dfdaca9213b377b12145f1d95afc695166fe63d9fab95bbd84c023ac
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62a9d43fd942c53428b8b0567abc5052d30717aee499e7e461d54f82f03aa129
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 sha256:5d270648c3c7cfea284af46d89db1a33ce9b1963a365650bb5b6278c9e439ca0
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac1472cc48b9756805272b4e5e7ea5f95dbeacea7d8d3fea8596b98f618a09e7
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:f4517da5e8cf77a829cb8cd3c52b4b9af16e4d568d2ca7d06a28e7cf8b4aaa2f
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7032556ea01e3a730b502fb64d00ca55704263bcec3c80225d30c60ccb5878c
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 sha256:0e772cf66a3ba7e5cc72c8a00a2b745c8057d5048c155ba1566478398d0620b4
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b9177c1cb3dd077b8f09cb630ad1cd1775aa4f1413bffb09d2a45e7f53367f6
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": 1.85377836227417,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.3257328990228013,
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": 32.913,
199
  "eval_steps_per_second": 4.138,
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": 2,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.6362560987472534,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.6514657980456026,
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": 32.913,
199
  "eval_steps_per_second": 4.138,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.33876221498371334,
204
+ "grad_norm": 3.0881364345550537,
205
+ "learning_rate": 5e-05,
206
+ "loss": 2.3289,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.3517915309446254,
211
+ "grad_norm": 2.868217706680298,
212
+ "learning_rate": 4.6729843538492847e-05,
213
+ "loss": 2.2265,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.36482084690553745,
218
+ "grad_norm": 2.419745445251465,
219
+ "learning_rate": 4.347369038899744e-05,
220
+ "loss": 1.9786,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.3778501628664495,
225
+ "grad_norm": 2.326369047164917,
226
+ "learning_rate": 4.0245483899193595e-05,
227
+ "loss": 2.0915,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.39087947882736157,
232
+ "grad_norm": 1.7050875425338745,
233
+ "learning_rate": 3.705904774487396e-05,
234
+ "loss": 1.7147,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.40390879478827363,
239
+ "grad_norm": 1.4443508386611938,
240
+ "learning_rate": 3.392802673484193e-05,
241
+ "loss": 1.8553,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.4169381107491857,
246
+ "grad_norm": 1.584908366203308,
247
+ "learning_rate": 3.086582838174551e-05,
248
+ "loss": 1.8206,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.42996742671009774,
253
+ "grad_norm": 1.7143025398254395,
254
+ "learning_rate": 2.7885565489049946e-05,
255
+ "loss": 1.8255,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.44299674267100975,
260
+ "grad_norm": 1.6111055612564087,
261
+ "learning_rate": 2.500000000000001e-05,
262
+ "loss": 1.6737,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.4560260586319218,
267
+ "grad_norm": 1.8511838912963867,
268
+ "learning_rate": 2.2221488349019903e-05,
269
+ "loss": 1.5223,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.46905537459283386,
274
+ "grad_norm": 2.0485684871673584,
275
+ "learning_rate": 1.9561928549563968e-05,
276
+ "loss": 1.4314,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.4820846905537459,
281
+ "grad_norm": 2.691328525543213,
282
+ "learning_rate": 1.703270924499656e-05,
283
+ "loss": 1.1187,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.495114006514658,
288
+ "grad_norm": 1.681522011756897,
289
+ "learning_rate": 1.4644660940672627e-05,
290
+ "loss": 1.8898,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.50814332247557,
295
+ "grad_norm": 1.448625087738037,
296
+ "learning_rate": 1.2408009626051137e-05,
297
+ "loss": 1.9981,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.5211726384364821,
302
+ "grad_norm": 1.5197402238845825,
303
+ "learning_rate": 1.0332332985438248e-05,
304
+ "loss": 1.9404,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.5342019543973942,
309
+ "grad_norm": 1.4934030771255493,
310
+ "learning_rate": 8.426519384872733e-06,
311
+ "loss": 1.8512,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.5472312703583062,
316
+ "grad_norm": 1.3975049257278442,
317
+ "learning_rate": 6.698729810778065e-06,
318
+ "loss": 1.8375,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.5602605863192183,
323
+ "grad_norm": 1.4014006853103638,
324
+ "learning_rate": 5.156362923365588e-06,
325
+ "loss": 1.8908,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.5732899022801303,
330
+ "grad_norm": 1.4836615324020386,
331
+ "learning_rate": 3.8060233744356633e-06,
332
+ "loss": 1.7045,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.5863192182410424,
337
+ "grad_norm": 1.3463841676712036,
338
+ "learning_rate": 2.653493525244721e-06,
339
+ "loss": 1.5498,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.5993485342019544,
344
+ "grad_norm": 1.5299338102340698,
345
+ "learning_rate": 1.70370868554659e-06,
346
+ "loss": 1.615,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.6123778501628665,
351
+ "grad_norm": 1.717320442199707,
352
+ "learning_rate": 9.607359798384785e-07,
353
+ "loss": 1.7706,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.6254071661237784,
358
+ "grad_norm": 1.6710180044174194,
359
+ "learning_rate": 4.277569313094809e-07,
360
+ "loss": 1.3533,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.6384364820846905,
365
+ "grad_norm": 1.7277498245239258,
366
+ "learning_rate": 1.0705383806982606e-07,
367
+ "loss": 1.1741,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.6514657980456026,
372
+ "grad_norm": 2.389922618865967,
373
+ "learning_rate": 0.0,
374
+ "loss": 0.5103,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.6514657980456026,
379
+ "eval_loss": 1.6362560987472534,
380
+ "eval_runtime": 15.7084,
381
+ "eval_samples_per_second": 32.912,
382
+ "eval_steps_per_second": 4.138,
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": 2,
414
  "trial_name": null,
415
  "trial_params": null