lyhourt commited on
Commit
5a6f610
1 Parent(s): 6059f05

Training in progress, step 1000, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e72923ad30f0957f11a615e18eefb023aa94497336fc831a2f8b9fa384853875
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da4e39516fd2c574cde049cc323a39dd5de082636bac569f33e739a6369e29c3
3
  size 966995080
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d10b5624db0a88f9e62b4fdfd39da2e454a97bfe1b1d96f63d4f4cb39012a16e
3
  size 1925064044
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:220b28ed5c4b0c04bb4c60f6ba83ceb5852136ae623bcda926714b7978d5799f
3
  size 1925064044
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:309d78c0cbac356af547d46b1e70776079ec1d34f37e987fe5340ad766fae6b9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbd06e8492cf5f9098994eae7379bdec4b8a992134de50c159b29f2af7d36e16
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:888e6a44b40497069d2e43e76c43808360f08b18da088d54334ffdb48c5b1b0a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:345bea270db4afa20c0b04262d1b80fec7c4873e001e3e4c19066324a81d9415
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 24.30636512007461,
3
- "best_model_checkpoint": "./whisper-small-clean_6-v4/checkpoint-800",
4
- "epoch": 1.5122873345935728,
5
  "eval_steps": 200,
6
- "global_step": 800,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -267,10 +267,75 @@
267
  "eval_steps_per_second": 0.076,
268
  "eval_wer": 24.30636512007461,
269
  "step": 800
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
270
  }
271
  ],
272
  "logging_steps": 25,
273
- "max_steps": 800,
274
  "num_input_tokens_seen": 0,
275
  "num_train_epochs": 2,
276
  "save_steps": 200,
@@ -286,7 +351,7 @@
286
  "attributes": {}
287
  }
288
  },
289
- "total_flos": 1.481395435462656e+19,
290
  "train_batch_size": 64,
291
  "trial_name": null,
292
  "trial_params": null
 
1
  {
2
+ "best_metric": 24.014921893215202,
3
+ "best_model_checkpoint": "./whisper-small-clean_6-v4/checkpoint-1000",
4
+ "epoch": 1.8903591682419658,
5
  "eval_steps": 200,
6
+ "global_step": 1000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
267
  "eval_steps_per_second": 0.076,
268
  "eval_wer": 24.30636512007461,
269
  "step": 800
270
+ },
271
+ {
272
+ "epoch": 1.559546313799622,
273
+ "grad_norm": 2.5037174224853516,
274
+ "learning_rate": 1.8421052631578948e-06,
275
+ "loss": 0.0912,
276
+ "step": 825
277
+ },
278
+ {
279
+ "epoch": 1.606805293005671,
280
+ "grad_norm": 3.10439395904541,
281
+ "learning_rate": 1.5789473684210526e-06,
282
+ "loss": 0.0876,
283
+ "step": 850
284
+ },
285
+ {
286
+ "epoch": 1.6540642722117203,
287
+ "grad_norm": 2.7944157123565674,
288
+ "learning_rate": 1.3157894736842106e-06,
289
+ "loss": 0.0877,
290
+ "step": 875
291
+ },
292
+ {
293
+ "epoch": 1.7013232514177694,
294
+ "grad_norm": 2.672607421875,
295
+ "learning_rate": 1.0526315789473685e-06,
296
+ "loss": 0.0934,
297
+ "step": 900
298
+ },
299
+ {
300
+ "epoch": 1.7485822306238186,
301
+ "grad_norm": 2.3285105228424072,
302
+ "learning_rate": 7.894736842105263e-07,
303
+ "loss": 0.0888,
304
+ "step": 925
305
+ },
306
+ {
307
+ "epoch": 1.7958412098298677,
308
+ "grad_norm": 2.0739948749542236,
309
+ "learning_rate": 5.263157894736843e-07,
310
+ "loss": 0.0974,
311
+ "step": 950
312
+ },
313
+ {
314
+ "epoch": 1.8431001890359169,
315
+ "grad_norm": 2.6488840579986572,
316
+ "learning_rate": 2.6315789473684213e-07,
317
+ "loss": 0.0874,
318
+ "step": 975
319
+ },
320
+ {
321
+ "epoch": 1.8903591682419658,
322
+ "grad_norm": 2.463960886001587,
323
+ "learning_rate": 0.0,
324
+ "loss": 0.0823,
325
+ "step": 1000
326
+ },
327
+ {
328
+ "epoch": 1.8903591682419658,
329
+ "eval_loss": 0.2885694205760956,
330
+ "eval_runtime": 632.9247,
331
+ "eval_samples_per_second": 2.409,
332
+ "eval_steps_per_second": 0.076,
333
+ "eval_wer": 24.014921893215202,
334
+ "step": 1000
335
  }
336
  ],
337
  "logging_steps": 25,
338
+ "max_steps": 1000,
339
  "num_input_tokens_seen": 0,
340
  "num_train_epochs": 2,
341
  "save_steps": 200,
 
351
  "attributes": {}
352
  }
353
  },
354
+ "total_flos": 1.850784747872256e+19,
355
  "train_batch_size": 64,
356
  "trial_name": null,
357
  "trial_params": null
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d7915e08ab8f42cb0e587a2e8d8dc8bb8879d7d74ee37b8524edf8f0faf9041
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae62acf766aec21814d7588bec18284ba3498b083aa6cdd95022c9bf4a540e50
3
  size 5240