infinitejoy commited on
Commit
ae91dcd
1 Parent(s): 2122852

End of training

Browse files
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 100.0,
3
+ "eval_loss": 0.9814496636390686,
4
+ "eval_runtime": 14.3225,
5
+ "eval_samples": 294,
6
+ "eval_samples_per_second": 20.527,
7
+ "eval_steps_per_second": 1.327,
8
+ "eval_wer": 0.7402486069438491,
9
+ "train_loss": 1.9762264404296874,
10
+ "train_runtime": 4294.1559,
11
+ "train_samples": 624,
12
+ "train_samples_per_second": 14.531,
13
+ "train_steps_per_second": 0.466
14
+ }
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 100.0,
3
+ "eval_loss": 0.9814496636390686,
4
+ "eval_runtime": 14.3225,
5
+ "eval_samples": 294,
6
+ "eval_samples_per_second": 20.527,
7
+ "eval_steps_per_second": 1.327,
8
+ "eval_wer": 0.7402486069438491
9
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 100.0,
3
+ "train_loss": 1.9762264404296874,
4
+ "train_runtime": 4294.1559,
5
+ "train_samples": 624,
6
+ "train_samples_per_second": 14.531,
7
+ "train_steps_per_second": 0.466
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 100.0,
5
+ "global_step": 2000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 20.0,
12
+ "eval_loss": 3.14473295211792,
13
+ "eval_runtime": 14.4908,
14
+ "eval_samples_per_second": 20.289,
15
+ "eval_steps_per_second": 1.311,
16
+ "eval_wer": 1.0,
17
+ "step": 400
18
+ },
19
+ {
20
+ "epoch": 40.0,
21
+ "eval_loss": 1.0074288845062256,
22
+ "eval_runtime": 14.582,
23
+ "eval_samples_per_second": 20.162,
24
+ "eval_steps_per_second": 1.303,
25
+ "eval_wer": 0.8555507929704244,
26
+ "step": 800
27
+ },
28
+ {
29
+ "epoch": 50.0,
30
+ "learning_rate": 0.00018806249999999997,
31
+ "loss": 3.1278,
32
+ "step": 1000
33
+ },
34
+ {
35
+ "epoch": 60.0,
36
+ "eval_loss": 0.9506617784500122,
37
+ "eval_runtime": 14.9576,
38
+ "eval_samples_per_second": 19.655,
39
+ "eval_steps_per_second": 1.27,
40
+ "eval_wer": 0.7711101585940848,
41
+ "step": 1200
42
+ },
43
+ {
44
+ "epoch": 80.0,
45
+ "eval_loss": 0.9729732871055603,
46
+ "eval_runtime": 14.438,
47
+ "eval_samples_per_second": 20.363,
48
+ "eval_steps_per_second": 1.316,
49
+ "eval_wer": 0.7629661380197171,
50
+ "step": 1600
51
+ },
52
+ {
53
+ "epoch": 100.0,
54
+ "learning_rate": 5.624999999999999e-07,
55
+ "loss": 0.8247,
56
+ "step": 2000
57
+ },
58
+ {
59
+ "epoch": 100.0,
60
+ "eval_loss": 0.9814496636390686,
61
+ "eval_runtime": 14.2796,
62
+ "eval_samples_per_second": 20.589,
63
+ "eval_steps_per_second": 1.331,
64
+ "eval_wer": 0.7402486069438491,
65
+ "step": 2000
66
+ },
67
+ {
68
+ "epoch": 100.0,
69
+ "step": 2000,
70
+ "total_flos": 1.1371370438840648e+19,
71
+ "train_loss": 1.9762264404296874,
72
+ "train_runtime": 4294.1559,
73
+ "train_samples_per_second": 14.531,
74
+ "train_steps_per_second": 0.466
75
+ }
76
+ ],
77
+ "max_steps": 2000,
78
+ "num_train_epochs": 100,
79
+ "total_flos": 1.1371370438840648e+19,
80
+ "trial_name": null,
81
+ "trial_params": null
82
+ }