dq158 commited on
Commit
fb111be
·
1 Parent(s): fb0f7df

Training in progress, epoch 9, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:080554e1afdea12f81011ab0ae0ef25478ce9dcd247e7b25f2c94ee9a6223771
3
  size 2371770
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b71be19ad19a3a3e31959473f5c1a45cf3a994d2ac577b67dac440f4b30ca8e0
3
  size 2371770
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:10e85ece5a992a1a0ab63f817a0f6162f66c8f288c8a6045ee940c7e3235378b
3
  size 990409330
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6223ce7959af515e2e82943538f39dc15a5eb2a27a686c90c211b2a33f14c087
3
  size 990409330
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e9690a12a9a42c35516e6fbfe26ab2d65dfa0fd3e0c6b66b4b634b579ffec391
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2f7b436e9bacdce8321c129258891cfe5297c358dd018f4af22a5983cb5b0d7
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1dfc5d86de55408c234cae75695e57cabf239fe23cf052735ae3cd35550d49f7
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11944376c27fbea6ee7fff9906b50d8eeade72e136e82c5eaff059c29ff514f8
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.0124728679656982,
3
- "best_model_checkpoint": "dq158/coqui/checkpoint-7481",
4
- "epoch": 8.9996992481203,
5
  "eval_steps": 500,
6
- "global_step": 7481,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -262,13 +262,44 @@
262
  "eval_steps_per_second": 0.606,
263
  "eval_translation_length": 56071,
264
  "step": 7481
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
265
  }
266
  ],
267
  "logging_steps": 500,
268
  "max_steps": 16620,
269
  "num_train_epochs": 20,
270
  "save_steps": 500,
271
- "total_flos": 1.6391858454370714e+17,
272
  "trial_name": null,
273
  "trial_params": null
274
  }
 
1
  {
2
+ "best_metric": 2.0042803287506104,
3
+ "best_model_checkpoint": "dq158/coqui/checkpoint-8312",
4
+ "epoch": 9.999398496240602,
5
  "eval_steps": 500,
6
+ "global_step": 8312,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
262
  "eval_steps_per_second": 0.606,
263
  "eval_translation_length": 56071,
264
  "step": 7481
265
+ },
266
+ {
267
+ "epoch": 9.02,
268
+ "learning_rate": 5.4230172822665325e-05,
269
+ "loss": 1.983,
270
+ "step": 7500
271
+ },
272
+ {
273
+ "epoch": 9.62,
274
+ "learning_rate": 4.9901430980334607e-05,
275
+ "loss": 1.9669,
276
+ "step": 8000
277
+ },
278
+ {
279
+ "epoch": 10.0,
280
+ "eval_bleu": 1.0,
281
+ "eval_brevity_penalty": 1.0,
282
+ "eval_length_ratio": 1.0,
283
+ "eval_loss": 2.0042803287506104,
284
+ "eval_precisions": [
285
+ 1.0,
286
+ 1.0,
287
+ 1.0,
288
+ 1.0
289
+ ],
290
+ "eval_reference_length": 55997,
291
+ "eval_runtime": 611.382,
292
+ "eval_samples_per_second": 4.835,
293
+ "eval_steps_per_second": 0.605,
294
+ "eval_translation_length": 55997,
295
+ "step": 8312
296
  }
297
  ],
298
  "logging_steps": 500,
299
  "max_steps": 16620,
300
  "num_train_epochs": 20,
301
  "save_steps": 500,
302
+ "total_flos": 1.8213176060411904e+17,
303
  "trial_name": null,
304
  "trial_params": null
305
  }