gchhablani commited on
Commit
da84f34
1 Parent(s): e337b29

End of training

Browse files
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_loss": 0.6270990371704102,
4
+ "eval_matthews_correlation": 0.0,
5
+ "eval_runtime": 22.857,
6
+ "eval_samples": 1043,
7
+ "eval_samples_per_second": 45.632,
8
+ "eval_steps_per_second": 5.731,
9
+ "train_loss": 0.6198258174257484,
10
+ "train_runtime": 3421.027,
11
+ "train_samples": 8551,
12
+ "train_samples_per_second": 12.498,
13
+ "train_steps_per_second": 3.125
14
+ }
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_loss": 0.6270990371704102,
4
+ "eval_matthews_correlation": 0.0,
5
+ "eval_runtime": 22.857,
6
+ "eval_samples": 1043,
7
+ "eval_samples_per_second": 45.632,
8
+ "eval_steps_per_second": 5.731
9
+ }
runs/Oct10_19-39-15_patrick-general-gpu/events.out.tfevents.1633894776.patrick-general-gpu.131003.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e870c53a39192fe597ddfa47d0499d84a2ccb3e51ef166b0514dd7695136894e
3
- size 5736
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2944637b02fd5f1a3070a8f61c5c5d7019813518166f6b50b5cf4995c6b3730a
3
+ size 6090
runs/Oct10_19-39-15_patrick-general-gpu/events.out.tfevents.1633898237.patrick-general-gpu.131003.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c025b4da530ba4d007fce768f280ee3dcaaafac988655977152f2153281b81e
3
+ size 375
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "train_loss": 0.6198258174257484,
4
+ "train_runtime": 3421.027,
5
+ "train_samples": 8551,
6
+ "train_samples_per_second": 12.498,
7
+ "train_steps_per_second": 3.125
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "global_step": 10690,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "learning_rate": 3.5566666666666666e-05,
13
+ "loss": 0.6212,
14
+ "step": 2138
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_loss": 0.6539720296859741,
19
+ "eval_matthews_correlation": 0.0,
20
+ "eval_runtime": 22.7284,
21
+ "eval_samples_per_second": 45.89,
22
+ "eval_steps_per_second": 5.764,
23
+ "step": 2138
24
+ },
25
+ {
26
+ "epoch": 2.0,
27
+ "learning_rate": 2.6700000000000002e-05,
28
+ "loss": 0.62,
29
+ "step": 4276
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "eval_loss": 0.6409146785736084,
34
+ "eval_matthews_correlation": 0.0,
35
+ "eval_runtime": 22.7182,
36
+ "eval_samples_per_second": 45.91,
37
+ "eval_steps_per_second": 5.766,
38
+ "step": 4276
39
+ },
40
+ {
41
+ "epoch": 3.0,
42
+ "learning_rate": 1.783333333333333e-05,
43
+ "loss": 0.6182,
44
+ "step": 6414
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "eval_loss": 0.6234332919120789,
49
+ "eval_matthews_correlation": 0.0,
50
+ "eval_runtime": 22.7216,
51
+ "eval_samples_per_second": 45.904,
52
+ "eval_steps_per_second": 5.765,
53
+ "step": 6414
54
+ },
55
+ {
56
+ "epoch": 4.0,
57
+ "learning_rate": 8.966666666666667e-06,
58
+ "loss": 0.6181,
59
+ "step": 8552
60
+ },
61
+ {
62
+ "epoch": 4.0,
63
+ "eval_loss": 0.6234201192855835,
64
+ "eval_matthews_correlation": 0.0,
65
+ "eval_runtime": 22.7101,
66
+ "eval_samples_per_second": 45.927,
67
+ "eval_steps_per_second": 5.768,
68
+ "step": 8552
69
+ },
70
+ {
71
+ "epoch": 5.0,
72
+ "learning_rate": 1e-07,
73
+ "loss": 0.6217,
74
+ "step": 10690
75
+ },
76
+ {
77
+ "epoch": 5.0,
78
+ "eval_loss": 0.6270990371704102,
79
+ "eval_matthews_correlation": 0.0,
80
+ "eval_runtime": 22.7215,
81
+ "eval_samples_per_second": 45.904,
82
+ "eval_steps_per_second": 5.765,
83
+ "step": 10690
84
+ },
85
+ {
86
+ "epoch": 5.0,
87
+ "step": 10690,
88
+ "total_flos": 2.674821632676864e+16,
89
+ "train_loss": 0.6198258174257484,
90
+ "train_runtime": 3421.027,
91
+ "train_samples_per_second": 12.498,
92
+ "train_steps_per_second": 3.125
93
+ }
94
+ ],
95
+ "max_steps": 10690,
96
+ "num_train_epochs": 5,
97
+ "total_flos": 2.674821632676864e+16,
98
+ "trial_name": null,
99
+ "trial_params": null
100
+ }