dsakerkwq commited on
Commit
14e3c5e
1 Parent(s): 0e052ae

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 sha256:2637669bcc380b32d8bf04a0f7a9ea82381a2cccca6382a967e6b7ae11bfa66e
3
  size 432223744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49de1588b27d5375c1465e90ccc25640db36e999391a3c61d5e002112a1b7d16
3
  size 432223744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:005b9787fe114af93b615c537df6c767794502ab4563f0a2965d5c2606f62b82
3
  size 864785974
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e78fd505e62291583c71a0b8a9ff2316547d328efa67b17507e3f58612718e17
3
  size 864785974
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:33aab6001c5fbfa9dd31365fbe1de313ed661d328437f142df866cc0c247c640
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2a3545180fe8665d3b1efe975ccb776db717312a908ea084274a79c64a6d14a
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 sha256:90153d1b05ae91a8b0ab5c6e14d953c84cd18ab5a3267b6d939534e4bc6e3689
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a554ffbebe6d60d65a3f2ce8fe1f053a9d3bd1d51783c095bf0e1c1321cebdf1
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:d1ee6099c5c030a70e2ffcf778cb3a53de3ce0485927b9ca6f750ed52ddb4ae5
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:358ea0be3ae16bb1e78f80915fb55b2b60141a082990322dc496e2ae578e1a4b
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 sha256:5b1d21ef87415263bc930d7066c249347c5e6694ff6fc220fef6a39c42b0efde
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb41e6b7d16e5b8a1f86f01874910c500cbbebf88581bbdc0a53b03330c0f7b9
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": 3.733593702316284,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.0048100626510660304,
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": 14.713,
199
  "eval_steps_per_second": 3.825,
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": 3.315690861756416e+17,
230
  "train_batch_size": 2,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
+ "best_metric": 3.511137008666992,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.009620125302132061,
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": 14.713,
199
  "eval_steps_per_second": 3.825,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.005002465157108672,
204
+ "grad_norm": 4.074855804443359,
205
+ "learning_rate": 5.500000000000001e-05,
206
+ "loss": 2.7415,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.005194867663151312,
211
+ "grad_norm": 5.183741092681885,
212
+ "learning_rate": 5.205685918464356e-05,
213
+ "loss": 3.1624,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.0053872701691939535,
218
+ "grad_norm": 5.362056255340576,
219
+ "learning_rate": 4.912632135009769e-05,
220
+ "loss": 3.3544,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.005579672675236595,
225
+ "grad_norm": 4.090317726135254,
226
+ "learning_rate": 4.6220935509274235e-05,
227
+ "loss": 3.569,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.005772075181279236,
232
+ "grad_norm": 3.477642297744751,
233
+ "learning_rate": 4.3353142970386564e-05,
234
+ "loss": 3.5337,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.0059644776873218775,
239
+ "grad_norm": 3.0103671550750732,
240
+ "learning_rate": 4.053522406135775e-05,
241
+ "loss": 3.6925,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.006156880193364519,
246
+ "grad_norm": 2.481553792953491,
247
+ "learning_rate": 3.777924554357096e-05,
248
+ "loss": 3.7062,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.00634928269940716,
253
+ "grad_norm": 2.371243476867676,
254
+ "learning_rate": 3.509700894014496e-05,
255
+ "loss": 3.7112,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.006541685205449801,
260
+ "grad_norm": 2.5417237281799316,
261
+ "learning_rate": 3.250000000000001e-05,
262
+ "loss": 4.0359,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.006734087711492442,
267
+ "grad_norm": 2.821629762649536,
268
+ "learning_rate": 2.9999339514117912e-05,
269
+ "loss": 4.0407,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.006926490217535083,
274
+ "grad_norm": 3.3124289512634277,
275
+ "learning_rate": 2.760573569460757e-05,
276
+ "loss": 4.1073,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.007118892723577725,
281
+ "grad_norm": 5.673077583312988,
282
+ "learning_rate": 2.53294383204969e-05,
283
+ "loss": 4.4741,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.007311295229620366,
288
+ "grad_norm": 1.9838043451309204,
289
+ "learning_rate": 2.3180194846605367e-05,
290
+ "loss": 2.7683,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.007503697735663007,
295
+ "grad_norm": 2.109670877456665,
296
+ "learning_rate": 2.1167208663446025e-05,
297
+ "loss": 2.7531,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.0076961002417056485,
302
+ "grad_norm": 2.0147898197174072,
303
+ "learning_rate": 1.9299099686894423e-05,
304
+ "loss": 2.9084,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.007888502747748289,
309
+ "grad_norm": 2.1483073234558105,
310
+ "learning_rate": 1.758386744638546e-05,
311
+ "loss": 3.1465,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.00808090525379093,
316
+ "grad_norm": 1.920487403869629,
317
+ "learning_rate": 1.602885682970026e-05,
318
+ "loss": 3.1783,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.008273307759833572,
323
+ "grad_norm": 2.0920512676239014,
324
+ "learning_rate": 1.464072663102903e-05,
325
+ "loss": 3.47,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.008465710265876213,
330
+ "grad_norm": 2.128572940826416,
331
+ "learning_rate": 1.3425421036992098e-05,
332
+ "loss": 3.6677,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.008658112771918854,
337
+ "grad_norm": 2.0647780895233154,
338
+ "learning_rate": 1.2388144172720251e-05,
339
+ "loss": 3.5179,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.008850515277961496,
344
+ "grad_norm": 2.5102503299713135,
345
+ "learning_rate": 1.1533337816991932e-05,
346
+ "loss": 3.6965,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.009042917784004137,
351
+ "grad_norm": 2.516993761062622,
352
+ "learning_rate": 1.0864662381854632e-05,
353
+ "loss": 3.8702,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.009235320290046778,
358
+ "grad_norm": 3.2718374729156494,
359
+ "learning_rate": 1.0384981238178534e-05,
360
+ "loss": 4.1012,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.00942772279608942,
365
+ "grad_norm": 3.6114237308502197,
366
+ "learning_rate": 1.0096348454262845e-05,
367
+ "loss": 4.1246,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.009620125302132061,
372
+ "grad_norm": 6.421860218048096,
373
+ "learning_rate": 1e-05,
374
+ "loss": 4.5367,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.009620125302132061,
379
+ "eval_loss": 3.511137008666992,
380
+ "eval_runtime": 3.4049,
381
+ "eval_samples_per_second": 14.685,
382
+ "eval_steps_per_second": 3.818,
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": 6.631381723512832e+17,
413
  "train_batch_size": 2,
414
  "trial_name": null,
415
  "trial_params": null