mprzibilla commited on
Commit
cd7128e
·
1 Parent(s): 38be269

Training in progress, epoch 15

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5094015309b4708bb353d49dc46cdb5aa4fa9f8c70d31661c5974efa5f7db8a
3
  size 721655813
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a83052113f253deb7778933bf724c0dd93bbee1879c9051ed41ec03fc7922b1e
3
  size 721655813
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:adbe651405e228e472929afedae4636418d0207ccce05706adb6a088f0c378b0
3
  size 377643361
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9f15cafceeb8deceaa17a31e1683df9a8c3182d9bf63fb9adc9a2240857b58c
3
  size 377643361
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:42f3433bf7e041238aa7249acc137048325405de6e6c01dab4df7c3215ea2de2
3
  size 14639
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df299414f56d3cee0b6d3d0811a00f61147a37acc97a9fa7bcc500e7d68f6f17
3
  size 14639
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ee2706db65c5ff8cfbf18b85e3a6f07da96b8e0f5eddcf02e642ebde5da654cf
3
  size 557
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3074ef8c5e5b5aaeac725a657e6dd7b765b407a0a2b4ddd6468086c7e79a60b
3
  size 557
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37e72251d6314bc1a438c39f9bff8900af947b087395caa3002d373ef99a6057
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b9e5c4b19bf8f91ee0b8c0673c6bc9d7c91750047d52a3c63c167c3159e4c39
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 14.0,
5
- "global_step": 4508,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -244,11 +244,28 @@
244
  "eval_samples_per_second": 27.415,
245
  "eval_steps_per_second": 3.525,
246
  "step": 4508
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
247
  }
248
  ],
249
  "max_steps": 4830,
250
  "num_train_epochs": 15,
251
- "total_flos": 3.2635631876399995e+18,
252
  "trial_name": null,
253
  "trial_params": null
254
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 15.0,
5
+ "global_step": 4830,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
244
  "eval_samples_per_second": 27.415,
245
  "eval_steps_per_second": 3.525,
246
  "step": 4508
247
+ },
248
+ {
249
+ "epoch": 15.0,
250
+ "learning_rate": 1.0895619960775767e-07,
251
+ "loss": 0.0328,
252
+ "step": 4830
253
+ },
254
+ {
255
+ "epoch": 15.0,
256
+ "eval_cer": 0.04588744588744589,
257
+ "eval_loss": 0.3557092547416687,
258
+ "eval_new_wer": 0.01904761904761905,
259
+ "eval_old_wer": 0.09047619047619047,
260
+ "eval_runtime": 7.654,
261
+ "eval_samples_per_second": 27.437,
262
+ "eval_steps_per_second": 3.528,
263
+ "step": 4830
264
  }
265
  ],
266
  "max_steps": 4830,
267
  "num_train_epochs": 15,
268
+ "total_flos": 3.496674843899999e+18,
269
  "trial_name": null,
270
  "trial_params": null
271
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:adbe651405e228e472929afedae4636418d0207ccce05706adb6a088f0c378b0
3
  size 377643361
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9f15cafceeb8deceaa17a31e1683df9a8c3182d9bf63fb9adc9a2240857b58c
3
  size 377643361