DunnBC22 commited on
Commit
3b058e3
1 Parent(s): f8584da

All Dunn!!!

Browse files
Files changed (5) hide show
  1. .DS_Store +1 -1
  2. all_results.json +12 -0
  3. eval_results.json +8 -0
  4. train_results.json +7 -0
  5. trainer_state.json +97 -0
.DS_Store CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57ec0d68f3f63ed8bb53837ce4c2e3505b4091654815cfed8c424cdb048e6185
3
  size 6148
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b89f01abb13d33a5a47ce4d8a4c64eccd32d22a4843d66ee9baf5ce84f231944
3
  size 6148
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "eval_cer": 0.036833333333333336,
4
+ "eval_loss": 0.15811479091644287,
5
+ "eval_runtime": 55178.9356,
6
+ "eval_samples_per_second": 0.072,
7
+ "eval_steps_per_second": 0.009,
8
+ "train_loss": 0.3358841931819916,
9
+ "train_runtime": 774109.7161,
10
+ "train_samples_per_second": 0.041,
11
+ "train_steps_per_second": 0.005
12
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "eval_cer": 0.036833333333333336,
4
+ "eval_loss": 0.15811479091644287,
5
+ "eval_runtime": 55178.9356,
6
+ "eval_samples_per_second": 0.072,
7
+ "eval_steps_per_second": 0.009
8
+ }
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "train_loss": 0.3358841931819916,
4
+ "train_runtime": 774109.7161,
5
+ "train_samples_per_second": 0.041,
6
+ "train_steps_per_second": 0.005
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "global_step": 4000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.0,
12
+ "learning_rate": 4.99875e-05,
13
+ "loss": 9.7097,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.25,
18
+ "learning_rate": 4.375e-05,
19
+ "loss": 0.7791,
20
+ "step": 500
21
+ },
22
+ {
23
+ "epoch": 0.5,
24
+ "learning_rate": 3.7500000000000003e-05,
25
+ "loss": 0.5107,
26
+ "step": 1000
27
+ },
28
+ {
29
+ "epoch": 0.75,
30
+ "learning_rate": 3.125e-05,
31
+ "loss": 0.3557,
32
+ "step": 1500
33
+ },
34
+ {
35
+ "epoch": 1.0,
36
+ "learning_rate": 2.5e-05,
37
+ "loss": 0.3144,
38
+ "step": 2000
39
+ },
40
+ {
41
+ "epoch": 1.0,
42
+ "eval_cer": 0.04733333333333333,
43
+ "eval_loss": 0.24631145596504211,
44
+ "eval_runtime": 55301.7054,
45
+ "eval_samples_per_second": 0.072,
46
+ "eval_steps_per_second": 0.009,
47
+ "step": 2000
48
+ },
49
+ {
50
+ "epoch": 1.25,
51
+ "learning_rate": 1.8750000000000002e-05,
52
+ "loss": 0.2086,
53
+ "step": 2500
54
+ },
55
+ {
56
+ "epoch": 1.5,
57
+ "learning_rate": 1.25e-05,
58
+ "loss": 0.1776,
59
+ "step": 3000
60
+ },
61
+ {
62
+ "epoch": 1.75,
63
+ "learning_rate": 6.25e-06,
64
+ "loss": 0.1802,
65
+ "step": 3500
66
+ },
67
+ {
68
+ "epoch": 2.0,
69
+ "learning_rate": 0.0,
70
+ "loss": 0.143,
71
+ "step": 4000
72
+ },
73
+ {
74
+ "epoch": 2.0,
75
+ "eval_cer": 0.036833333333333336,
76
+ "eval_loss": 0.15811479091644287,
77
+ "eval_runtime": 54648.5441,
78
+ "eval_samples_per_second": 0.073,
79
+ "eval_steps_per_second": 0.009,
80
+ "step": 4000
81
+ },
82
+ {
83
+ "epoch": 2.0,
84
+ "step": 4000,
85
+ "total_flos": 2.3945126111870976e+19,
86
+ "train_loss": 0.3358841931819916,
87
+ "train_runtime": 774109.7161,
88
+ "train_samples_per_second": 0.041,
89
+ "train_steps_per_second": 0.005
90
+ }
91
+ ],
92
+ "max_steps": 4000,
93
+ "num_train_epochs": 2,
94
+ "total_flos": 2.3945126111870976e+19,
95
+ "trial_name": null,
96
+ "trial_params": null
97
+ }