muneson commited on
Commit
b22a6bd
1 Parent(s): 68b40fe

End of training

Browse files
Files changed (4) hide show
  1. all_results.json +10 -10
  2. eval_results.json +6 -6
  3. train_results.json +5 -5
  4. trainer_state.json +11 -11
all_results.json CHANGED
@@ -1,14 +1,14 @@
1
  {
2
- "epoch": 0.57,
3
- "eval_loss": 149.47802734375,
4
- "eval_runtime": 13.0889,
5
  "eval_samples": 301,
6
- "eval_samples_per_second": 22.997,
7
- "eval_steps_per_second": 2.903,
8
- "eval_wer": 1.0,
9
- "train_loss": 79.2754052734375,
10
- "train_runtime": 106.1327,
11
  "train_samples": 704,
12
- "train_samples_per_second": 3.769,
13
- "train_steps_per_second": 1.884
14
  }
1
  {
2
+ "epoch": 0.03,
3
+ "eval_loss": 207.6055145263672,
4
+ "eval_runtime": 13.1634,
5
  "eval_samples": 301,
6
+ "eval_samples_per_second": 22.866,
7
+ "eval_steps_per_second": 2.887,
8
+ "eval_wer": 1.5475492249685798,
9
+ "train_loss": 97.48234252929687,
10
+ "train_runtime": 9.4912,
11
  "train_samples": 704,
12
+ "train_samples_per_second": 2.107,
13
+ "train_steps_per_second": 1.054
14
  }
eval_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "epoch": 0.57,
3
- "eval_loss": 149.47802734375,
4
- "eval_runtime": 13.0889,
5
  "eval_samples": 301,
6
- "eval_samples_per_second": 22.997,
7
- "eval_steps_per_second": 2.903,
8
- "eval_wer": 1.0
9
  }
1
  {
2
+ "epoch": 0.03,
3
+ "eval_loss": 207.6055145263672,
4
+ "eval_runtime": 13.1634,
5
  "eval_samples": 301,
6
+ "eval_samples_per_second": 22.866,
7
+ "eval_steps_per_second": 2.887,
8
+ "eval_wer": 1.5475492249685798
9
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 0.57,
3
- "train_loss": 79.2754052734375,
4
- "train_runtime": 106.1327,
5
  "train_samples": 704,
6
- "train_samples_per_second": 3.769,
7
- "train_steps_per_second": 1.884
8
  }
1
  {
2
+ "epoch": 0.03,
3
+ "train_loss": 97.48234252929687,
4
+ "train_runtime": 9.4912,
5
  "train_samples": 704,
6
+ "train_samples_per_second": 2.107,
7
+ "train_steps_per_second": 1.054
8
  }
trainer_state.json CHANGED
@@ -1,25 +1,25 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.5681818181818182,
5
- "global_step": 200,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
- "epoch": 0.57,
12
- "step": 200,
13
- "total_flos": 7166685807360.0,
14
- "train_loss": 79.2754052734375,
15
- "train_runtime": 106.1327,
16
- "train_samples_per_second": 3.769,
17
- "train_steps_per_second": 1.884
18
  }
19
  ],
20
- "max_steps": 200,
21
  "num_train_epochs": 1,
22
- "total_flos": 7166685807360.0,
23
  "trial_name": null,
24
  "trial_params": null
25
  }
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.028409090909090908,
5
+ "global_step": 10,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
+ "epoch": 0.03,
12
+ "step": 10,
13
+ "total_flos": 514003449600.0,
14
+ "train_loss": 97.48234252929687,
15
+ "train_runtime": 9.4912,
16
+ "train_samples_per_second": 2.107,
17
+ "train_steps_per_second": 1.054
18
  }
19
  ],
20
+ "max_steps": 10,
21
  "num_train_epochs": 1,
22
+ "total_flos": 514003449600.0,
23
  "trial_name": null,
24
  "trial_params": null
25
  }