gchhablani commited on
Commit
8287799
1 Parent(s): 584157c

End of training

Browse files
all_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_accuracy": 0.8602941176470589,
4
+ "eval_combined_score": 0.8814291101055808,
5
+ "eval_f1": 0.9025641025641027,
6
+ "eval_loss": 0.7132137417793274,
7
+ "eval_runtime": 4.1977,
8
+ "eval_samples": 408,
9
+ "eval_samples_per_second": 97.196,
10
+ "eval_steps_per_second": 12.15,
11
+ "train_loss": 0.27617628014605977,
12
+ "train_runtime": 672.1032,
13
+ "train_samples": 3668,
14
+ "train_samples_per_second": 27.287,
15
+ "train_steps_per_second": 1.711
16
+ }
eval_results.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_accuracy": 0.8602941176470589,
4
+ "eval_combined_score": 0.8814291101055808,
5
+ "eval_f1": 0.9025641025641027,
6
+ "eval_loss": 0.7132137417793274,
7
+ "eval_runtime": 4.1977,
8
+ "eval_samples": 408,
9
+ "eval_samples_per_second": 97.196,
10
+ "eval_steps_per_second": 12.15
11
+ }
runs/Sep16_16-48-11_patrick-general-gpu/events.out.tfevents.1631810908.patrick-general-gpu.172718.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a3a12084a94ab8c6c0ce3e6c8493208c9c5f8e2d395018b431b36193d968fddc
3
- size 6166
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c53e3583300dfea88d1070a64927664d7b39f50e3e6fbf5f1b975b83843c6ed8
3
+ size 6520
runs/Sep16_16-48-11_patrick-general-gpu/events.out.tfevents.1631811594.patrick-general-gpu.172718.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d755edc40b957fe1af4c0f335435943ed358e18cd257683bef7aa95e7e448657
3
+ size 467
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "train_loss": 0.27617628014605977,
4
+ "train_runtime": 672.1032,
5
+ "train_samples": 3668,
6
+ "train_samples_per_second": 27.287,
7
+ "train_steps_per_second": 1.711
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": 0.5981,
14
+ "step": 230
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.7892156862745098,
19
+ "eval_combined_score": 0.8227014886222047,
20
+ "eval_f1": 0.8561872909698997,
21
+ "eval_loss": 0.45800894498825073,
22
+ "eval_runtime": 4.1966,
23
+ "eval_samples_per_second": 97.221,
24
+ "eval_steps_per_second": 12.153,
25
+ "step": 230
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "learning_rate": 1.2e-05,
30
+ "loss": 0.3739,
31
+ "step": 460
32
+ },
33
+ {
34
+ "epoch": 2.0,
35
+ "eval_accuracy": 0.8480392156862745,
36
+ "eval_combined_score": 0.8711185839523523,
37
+ "eval_f1": 0.89419795221843,
38
+ "eval_loss": 0.38060691952705383,
39
+ "eval_runtime": 4.1663,
40
+ "eval_samples_per_second": 97.928,
41
+ "eval_steps_per_second": 12.241,
42
+ "step": 460
43
+ },
44
+ {
45
+ "epoch": 3.0,
46
+ "learning_rate": 8.000000000000001e-06,
47
+ "loss": 0.1991,
48
+ "step": 690
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_accuracy": 0.8529411764705882,
53
+ "eval_combined_score": 0.8743872549019608,
54
+ "eval_f1": 0.8958333333333334,
55
+ "eval_loss": 0.4879474937915802,
56
+ "eval_runtime": 4.1609,
57
+ "eval_samples_per_second": 98.056,
58
+ "eval_steps_per_second": 12.257,
59
+ "step": 690
60
+ },
61
+ {
62
+ "epoch": 4.0,
63
+ "learning_rate": 4.000000000000001e-06,
64
+ "loss": 0.1286,
65
+ "step": 920
66
+ },
67
+ {
68
+ "epoch": 4.0,
69
+ "eval_accuracy": 0.8529411764705882,
70
+ "eval_combined_score": 0.8757949125596185,
71
+ "eval_f1": 0.8986486486486487,
72
+ "eval_loss": 0.6342187523841858,
73
+ "eval_runtime": 4.165,
74
+ "eval_samples_per_second": 97.959,
75
+ "eval_steps_per_second": 12.245,
76
+ "step": 920
77
+ },
78
+ {
79
+ "epoch": 5.0,
80
+ "learning_rate": 0.0,
81
+ "loss": 0.0812,
82
+ "step": 1150
83
+ },
84
+ {
85
+ "epoch": 5.0,
86
+ "eval_accuracy": 0.8602941176470589,
87
+ "eval_combined_score": 0.8814291101055808,
88
+ "eval_f1": 0.9025641025641027,
89
+ "eval_loss": 0.7132137417793274,
90
+ "eval_runtime": 4.1564,
91
+ "eval_samples_per_second": 98.161,
92
+ "eval_steps_per_second": 12.27,
93
+ "step": 1150
94
+ },
95
+ {
96
+ "epoch": 5.0,
97
+ "step": 1150,
98
+ "total_flos": 4825456755302400.0,
99
+ "train_loss": 0.27617628014605977,
100
+ "train_runtime": 672.1032,
101
+ "train_samples_per_second": 27.287,
102
+ "train_steps_per_second": 1.711
103
+ }
104
+ ],
105
+ "max_steps": 1150,
106
+ "num_train_epochs": 5,
107
+ "total_flos": 4825456755302400.0,
108
+ "trial_name": null,
109
+ "trial_params": null
110
+ }