infinitejoy commited on
Commit
5d4d1e7
1 Parent(s): ccce1c9

End of training

Browse files
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 299.94,
3
+ "eval_loss": 1.1646877527236938,
4
+ "eval_runtime": 19.428,
5
+ "eval_samples": 509,
6
+ "eval_samples_per_second": 26.199,
7
+ "eval_steps_per_second": 3.294,
8
+ "eval_wer": 0.7296426479203281,
9
+ "train_loss": 2.9658275985717775,
10
+ "train_runtime": 15272.387,
11
+ "train_samples": 1035,
12
+ "train_samples_per_second": 20.331,
13
+ "train_steps_per_second": 0.079
14
+ }
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 299.94,
3
+ "eval_loss": 1.1646877527236938,
4
+ "eval_runtime": 19.428,
5
+ "eval_samples": 509,
6
+ "eval_samples_per_second": 26.199,
7
+ "eval_steps_per_second": 3.294,
8
+ "eval_wer": 0.7296426479203281
9
+ }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6321679d249d711c5025444df5bfeb9a9a21fe8ec69e1d9edba117113ee77a94
3
  size 1262063089
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eadcc8cb9d0524cd7fbe023aeff0b117882f07e8a0797e275dcdcf260e4455d4
3
  size 1262063089
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 299.94,
3
+ "train_loss": 2.9658275985717775,
4
+ "train_runtime": 15272.387,
5
+ "train_samples": 1035,
6
+ "train_samples_per_second": 20.331,
7
+ "train_steps_per_second": 0.079
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 299.94117647058823,
5
+ "global_step": 1200,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 24.94,
12
+ "learning_rate": 3.4649999999999995e-05,
13
+ "loss": 10.2127,
14
+ "step": 100
15
+ },
16
+ {
17
+ "epoch": 49.94,
18
+ "learning_rate": 6.965e-05,
19
+ "loss": 3.5438,
20
+ "step": 200
21
+ },
22
+ {
23
+ "epoch": 74.94,
24
+ "learning_rate": 6.306999999999999e-05,
25
+ "loss": 3.0874,
26
+ "step": 300
27
+ },
28
+ {
29
+ "epoch": 99.94,
30
+ "learning_rate": 5.607e-05,
31
+ "loss": 2.9853,
32
+ "step": 400
33
+ },
34
+ {
35
+ "epoch": 124.94,
36
+ "learning_rate": 4.906999999999999e-05,
37
+ "loss": 2.9022,
38
+ "step": 500
39
+ },
40
+ {
41
+ "epoch": 124.94,
42
+ "eval_loss": 2.776294469833374,
43
+ "eval_runtime": 20.018,
44
+ "eval_samples_per_second": 25.427,
45
+ "eval_steps_per_second": 3.197,
46
+ "eval_wer": 0.9824253075571178,
47
+ "step": 500
48
+ },
49
+ {
50
+ "epoch": 149.94,
51
+ "learning_rate": 4.2069999999999995e-05,
52
+ "loss": 2.7184,
53
+ "step": 600
54
+ },
55
+ {
56
+ "epoch": 174.94,
57
+ "learning_rate": 3.5069999999999995e-05,
58
+ "loss": 2.2828,
59
+ "step": 700
60
+ },
61
+ {
62
+ "epoch": 199.94,
63
+ "learning_rate": 2.807e-05,
64
+ "loss": 1.8793,
65
+ "step": 800
66
+ },
67
+ {
68
+ "epoch": 224.94,
69
+ "learning_rate": 2.1069999999999996e-05,
70
+ "loss": 1.6491,
71
+ "step": 900
72
+ },
73
+ {
74
+ "epoch": 249.94,
75
+ "learning_rate": 1.4069999999999999e-05,
76
+ "loss": 1.5112,
77
+ "step": 1000
78
+ },
79
+ {
80
+ "epoch": 249.94,
81
+ "eval_loss": 1.173567533493042,
82
+ "eval_runtime": 20.0655,
83
+ "eval_samples_per_second": 25.367,
84
+ "eval_steps_per_second": 3.19,
85
+ "eval_wer": 0.7404803749267721,
86
+ "step": 1000
87
+ },
88
+ {
89
+ "epoch": 274.94,
90
+ "learning_rate": 7.07e-06,
91
+ "loss": 1.4311,
92
+ "step": 1100
93
+ },
94
+ {
95
+ "epoch": 299.94,
96
+ "learning_rate": 6.999999999999999e-08,
97
+ "loss": 1.3867,
98
+ "step": 1200
99
+ },
100
+ {
101
+ "epoch": 299.94,
102
+ "step": 1200,
103
+ "total_flos": 4.700653235698678e+19,
104
+ "train_loss": 2.9658275985717775,
105
+ "train_runtime": 15272.387,
106
+ "train_samples_per_second": 20.331,
107
+ "train_steps_per_second": 0.079
108
+ }
109
+ ],
110
+ "max_steps": 1200,
111
+ "num_train_epochs": 300,
112
+ "total_flos": 4.700653235698678e+19,
113
+ "trial_name": null,
114
+ "trial_params": null
115
+ }