dada22231 commited on
Commit
0c451fd
·
verified ·
1 Parent(s): 6375207

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:a9747c23a05c88d7f76bae3f03f29332f6098a1f4628f1c2346cee8833a20465
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bb628016e74b02d3bee7b359790a91071c0cc264eb27cf686bfa114cee0bc0b
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:98279ca4dc9898afd247b0ba19272e30f51ecf0c94b7d70e78535c7d867703f1
3
  size 141053442
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7bc94992315f85bfe1d9a769ae86c111703a9a4810d32f344be7d9c1df8ed8a
3
  size 141053442
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a1180e8d462a8fb3b7d2796d532d58931636ddbfa6314113159302ebaeb2e25
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2779fddc8c9d9349746edda01f05abbcee851a3f4c5898577ea5a79af0027c0
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 sha256:4fc362792d450222c8d4caf10a8ae36ce980d0159692fc9515b7a3d1e03bab8d
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ea1b1661df80a8bb2bb95b52a6ca54ee5a313f779417793e49378d7d7bbd70a
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 sha256:2475b561b34afeb0ff9d3c233ce3e175b13c6f8d757b911c351c80954a47527e
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8332caf65a69dbb7875f8f82eba5be590b447b98dedcc7e62e38a48cac75571
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:fea52ec44a1dbf25c8b096168be1ebd439a78d74f616fc4468e13d985e6de830
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b3efbaf5f8055efbe738d527ead4e6b4cc4bce4e44f6e5bce0b08217482ebc5
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": 0.22734582424163818,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.009680307833789115,
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": 66.752,
199
  "eval_steps_per_second": 17.356,
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": 1.47650456322048e+16,
230
  "train_batch_size": 2,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.12096888571977615,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.01936061566757823,
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": 66.752,
199
  "eval_steps_per_second": 17.356,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.01006752014714068,
204
+ "grad_norm": 20.296913146972656,
205
+ "learning_rate": 5.500000000000001e-05,
206
+ "loss": 1.5689,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.010454732460492243,
211
+ "grad_norm": 16.466005325317383,
212
+ "learning_rate": 5.205685918464356e-05,
213
+ "loss": 0.3623,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.010841944773843808,
218
+ "grad_norm": 11.937307357788086,
219
+ "learning_rate": 4.912632135009769e-05,
220
+ "loss": 0.1949,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.011229157087195372,
225
+ "grad_norm": 4.361509799957275,
226
+ "learning_rate": 4.6220935509274235e-05,
227
+ "loss": 0.0386,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.011616369400546937,
232
+ "grad_norm": 0.3395012319087982,
233
+ "learning_rate": 4.3353142970386564e-05,
234
+ "loss": 0.0033,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.012003581713898502,
239
+ "grad_norm": 0.09539712965488434,
240
+ "learning_rate": 4.053522406135775e-05,
241
+ "loss": 0.001,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.012390794027250067,
246
+ "grad_norm": 0.04306734725832939,
247
+ "learning_rate": 3.777924554357096e-05,
248
+ "loss": 0.0005,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.012778006340601632,
253
+ "grad_norm": 0.02652687579393387,
254
+ "learning_rate": 3.509700894014496e-05,
255
+ "loss": 0.0003,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.013165218653953197,
260
+ "grad_norm": 0.01844121888279915,
261
+ "learning_rate": 3.250000000000001e-05,
262
+ "loss": 0.0002,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.01355243096730476,
267
+ "grad_norm": 0.01470676064491272,
268
+ "learning_rate": 2.9999339514117912e-05,
269
+ "loss": 0.0002,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.013939643280656324,
274
+ "grad_norm": 5.602317810058594,
275
+ "learning_rate": 2.760573569460757e-05,
276
+ "loss": 0.3781,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.01432685559400789,
281
+ "grad_norm": 14.764276504516602,
282
+ "learning_rate": 2.53294383204969e-05,
283
+ "loss": 1.0644,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.014714067907359454,
288
+ "grad_norm": 9.552111625671387,
289
+ "learning_rate": 2.3180194846605367e-05,
290
+ "loss": 1.1546,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.015101280220711019,
295
+ "grad_norm": 0.046891260892152786,
296
+ "learning_rate": 2.1167208663446025e-05,
297
+ "loss": 0.0006,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.015488492534062584,
302
+ "grad_norm": 0.07456453889608383,
303
+ "learning_rate": 1.9299099686894423e-05,
304
+ "loss": 0.0009,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.015875704847414147,
309
+ "grad_norm": 0.10584703087806702,
310
+ "learning_rate": 1.758386744638546e-05,
311
+ "loss": 0.0013,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.01626291716076571,
316
+ "grad_norm": 0.13033287227153778,
317
+ "learning_rate": 1.602885682970026e-05,
318
+ "loss": 0.0017,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.016650129474117276,
323
+ "grad_norm": 0.14958032965660095,
324
+ "learning_rate": 1.464072663102903e-05,
325
+ "loss": 0.002,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.01703734178746884,
330
+ "grad_norm": 0.15836258232593536,
331
+ "learning_rate": 1.3425421036992098e-05,
332
+ "loss": 0.0021,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.017424554100820406,
337
+ "grad_norm": 0.1604108363389969,
338
+ "learning_rate": 1.2388144172720251e-05,
339
+ "loss": 0.0022,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.01781176641417197,
344
+ "grad_norm": 0.15006719529628754,
345
+ "learning_rate": 1.1533337816991932e-05,
346
+ "loss": 0.002,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.018198978727523536,
351
+ "grad_norm": 0.13892512023448944,
352
+ "learning_rate": 1.0864662381854632e-05,
353
+ "loss": 0.0019,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.0185861910408751,
358
+ "grad_norm": 0.12713688611984253,
359
+ "learning_rate": 1.0384981238178534e-05,
360
+ "loss": 0.0017,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.018973403354226665,
365
+ "grad_norm": 8.707756996154785,
366
+ "learning_rate": 1.0096348454262845e-05,
367
+ "loss": 0.5475,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.01936061566757823,
372
+ "grad_norm": 8.732000350952148,
373
+ "learning_rate": 1e-05,
374
+ "loss": 0.5323,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.01936061566757823,
379
+ "eval_loss": 0.12096888571977615,
380
+ "eval_runtime": 0.7605,
381
+ "eval_samples_per_second": 65.748,
382
+ "eval_steps_per_second": 17.094,
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": 2.95300912644096e+16,
413
  "train_batch_size": 2,
414
  "trial_name": null,
415
  "trial_params": null