gchhablani commited on
Commit
c4cf6e7
1 Parent(s): a9261fa

End of training

Browse files
all_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_accuracy": 0.7720588235294118,
4
+ "eval_combined_score": 0.8111501847115659,
5
+ "eval_f1": 0.8502415458937198,
6
+ "eval_loss": 0.9652777314186096,
7
+ "eval_runtime": 2.9878,
8
+ "eval_samples": 408,
9
+ "eval_samples_per_second": 136.555,
10
+ "eval_steps_per_second": 17.069,
11
+ "train_loss": 0.2935443347433339,
12
+ "train_runtime": 468.0335,
13
+ "train_samples": 3668,
14
+ "train_samples_per_second": 39.185,
15
+ "train_steps_per_second": 2.457
16
+ }
eval_results.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_accuracy": 0.7720588235294118,
4
+ "eval_combined_score": 0.8111501847115659,
5
+ "eval_f1": 0.8502415458937198,
6
+ "eval_loss": 0.9652777314186096,
7
+ "eval_runtime": 2.9878,
8
+ "eval_samples": 408,
9
+ "eval_samples_per_second": 136.555,
10
+ "eval_steps_per_second": 17.069
11
+ }
runs/Sep16_17-30-11_patrick-general-gpu/events.out.tfevents.1631813426.patrick-general-gpu.181934.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e9186ebea3e9c572cf078bd940aa131acd4846a47cd3333a837d13b615c66f8
3
- size 6104
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1be4bc056cff340c23fb87e0ee2783c523e95925b54e3ac58d0b95b638b4d5b
3
+ size 6458
runs/Sep16_17-30-11_patrick-general-gpu/events.out.tfevents.1631813900.patrick-general-gpu.181934.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6705bdba1069776a29f9d8302779b13df8401cb7c7ec7983468be4965f36ac4
3
+ size 467
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "train_loss": 0.2935443347433339,
4
+ "train_runtime": 468.0335,
5
+ "train_samples": 3668,
6
+ "train_samples_per_second": 39.185,
7
+ "train_steps_per_second": 2.457
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "global_step": 1150,
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": 1.6000000000000003e-05,
13
+ "loss": 0.544,
14
+ "step": 230
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.7328431372549019,
19
+ "eval_combined_score": 0.7813981676914135,
20
+ "eval_f1": 0.8299531981279251,
21
+ "eval_loss": 0.5272471308708191,
22
+ "eval_runtime": 2.9626,
23
+ "eval_samples_per_second": 137.716,
24
+ "eval_steps_per_second": 17.215,
25
+ "step": 230
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "learning_rate": 1.2e-05,
30
+ "loss": 0.4034,
31
+ "step": 460
32
+ },
33
+ {
34
+ "epoch": 2.0,
35
+ "eval_accuracy": 0.7254901960784313,
36
+ "eval_combined_score": 0.7776387150604923,
37
+ "eval_f1": 0.8297872340425533,
38
+ "eval_loss": 0.6210632920265198,
39
+ "eval_runtime": 2.9625,
40
+ "eval_samples_per_second": 137.721,
41
+ "eval_steps_per_second": 17.215,
42
+ "step": 460
43
+ },
44
+ {
45
+ "epoch": 3.0,
46
+ "learning_rate": 8.000000000000001e-06,
47
+ "loss": 0.2602,
48
+ "step": 690
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_accuracy": 0.7230392156862745,
53
+ "eval_combined_score": 0.7768119616662257,
54
+ "eval_f1": 0.830584707646177,
55
+ "eval_loss": 0.9109526872634888,
56
+ "eval_runtime": 2.9562,
57
+ "eval_samples_per_second": 138.014,
58
+ "eval_steps_per_second": 17.252,
59
+ "step": 690
60
+ },
61
+ {
62
+ "epoch": 4.0,
63
+ "learning_rate": 4.000000000000001e-06,
64
+ "loss": 0.1688,
65
+ "step": 920
66
+ },
67
+ {
68
+ "epoch": 4.0,
69
+ "eval_accuracy": 0.7696078431372549,
70
+ "eval_combined_score": 0.8092412206039973,
71
+ "eval_f1": 0.8488745980707396,
72
+ "eval_loss": 0.8639819622039795,
73
+ "eval_runtime": 2.9721,
74
+ "eval_samples_per_second": 137.276,
75
+ "eval_steps_per_second": 17.16,
76
+ "step": 920
77
+ },
78
+ {
79
+ "epoch": 5.0,
80
+ "learning_rate": 0.0,
81
+ "loss": 0.0913,
82
+ "step": 1150
83
+ },
84
+ {
85
+ "epoch": 5.0,
86
+ "eval_accuracy": 0.7720588235294118,
87
+ "eval_combined_score": 0.8111501847115659,
88
+ "eval_f1": 0.8502415458937198,
89
+ "eval_loss": 0.9652777314186096,
90
+ "eval_runtime": 2.962,
91
+ "eval_samples_per_second": 137.745,
92
+ "eval_steps_per_second": 17.218,
93
+ "step": 1150
94
+ },
95
+ {
96
+ "epoch": 5.0,
97
+ "step": 1150,
98
+ "total_flos": 3261567627386880.0,
99
+ "train_loss": 0.2935443347433339,
100
+ "train_runtime": 468.0335,
101
+ "train_samples_per_second": 39.185,
102
+ "train_steps_per_second": 2.457
103
+ }
104
+ ],
105
+ "max_steps": 1150,
106
+ "num_train_epochs": 5,
107
+ "total_flos": 3261567627386880.0,
108
+ "trial_name": null,
109
+ "trial_params": null
110
+ }