AndrewMcDowell commited on
Commit
47dd099
1 Parent(s): bb7b27c

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": 2.5,
3
- "eval_loss": 0.13549980521202087,
4
- "eval_runtime": 1012.9633,
5
  "eval_samples": 15995,
6
- "eval_samples_per_second": 15.79,
7
- "eval_steps_per_second": 1.974,
8
- "eval_wer": 0.15316115109878853,
9
- "train_loss": 1.0034960915109994,
10
- "train_runtime": 150795.9745,
11
  "train_samples": 436158,
12
- "train_samples_per_second": 7.231,
13
- "train_steps_per_second": 0.226
14
  }
 
1
  {
2
+ "epoch": 2.49,
3
+ "eval_loss": 0.13550546765327454,
4
+ "eval_runtime": 1000.0999,
5
  "eval_samples": 15995,
6
+ "eval_samples_per_second": 15.993,
7
+ "eval_steps_per_second": 2.0,
8
+ "eval_wer": 0.15314749306854966,
9
+ "train_loss": 0.0,
10
+ "train_runtime": 18.4382,
11
  "train_samples": 436158,
12
+ "train_samples_per_second": 70965.526,
13
+ "train_steps_per_second": 1108.841
14
  }
eval_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "epoch": 2.5,
3
- "eval_loss": 0.13549980521202087,
4
- "eval_runtime": 1012.9633,
5
  "eval_samples": 15995,
6
- "eval_samples_per_second": 15.79,
7
- "eval_steps_per_second": 1.974,
8
- "eval_wer": 0.15316115109878853
9
  }
 
1
  {
2
+ "epoch": 2.49,
3
+ "eval_loss": 0.13550546765327454,
4
+ "eval_runtime": 1000.0999,
5
  "eval_samples": 15995,
6
+ "eval_samples_per_second": 15.993,
7
+ "eval_steps_per_second": 2.0,
8
+ "eval_wer": 0.15314749306854966
9
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 2.5,
3
- "train_loss": 1.0034960915109994,
4
- "train_runtime": 150795.9745,
5
  "train_samples": 436158,
6
- "train_samples_per_second": 7.231,
7
- "train_steps_per_second": 0.226
8
  }
 
1
  {
2
+ "epoch": 2.49,
3
+ "train_loss": 0.0,
4
+ "train_runtime": 18.4382,
5
  "train_samples": 436158,
6
+ "train_samples_per_second": 70965.526,
7
+ "train_steps_per_second": 1108.841
8
  }
trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 2.5,
5
- "global_step": 34075,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -2354,18 +2354,18 @@
2354
  "step": 34000
2355
  },
2356
  {
2357
- "epoch": 2.5,
2358
- "step": 34075,
2359
- "total_flos": 5.050048908581704e+20,
2360
- "train_loss": 1.0034960915109994,
2361
- "train_runtime": 150795.9745,
2362
- "train_samples_per_second": 7.231,
2363
- "train_steps_per_second": 0.226
2364
  }
2365
  ],
2366
- "max_steps": 34075,
2367
  "num_train_epochs": 3,
2368
- "total_flos": 5.050048908581704e+20,
2369
  "trial_name": null,
2370
  "trial_params": null
2371
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 2.494497432134996,
5
+ "global_step": 34000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
2354
  "step": 34000
2355
  },
2356
  {
2357
+ "epoch": 2.49,
2358
+ "step": 34000,
2359
+ "total_flos": 5.0385420411785465e+20,
2360
+ "train_loss": 0.0,
2361
+ "train_runtime": 18.4382,
2362
+ "train_samples_per_second": 70965.526,
2363
+ "train_steps_per_second": 1108.841
2364
  }
2365
  ],
2366
+ "max_steps": 20445,
2367
  "num_train_epochs": 3,
2368
+ "total_flos": 5.0385420411785465e+20,
2369
  "trial_name": null,
2370
  "trial_params": null
2371
  }