Hugging Face's logo

GregorRus
/
distilbert-base-uncased-imdb

Text Classification
Transformers
TensorBoard
Safetensors
English
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
GregorRus commited on
Commit
d45cb80
·
verified ·
1 Parent(s): dee35e0

End of training

Browse files
Files changed (1) hide show
  1. trainer_state.json +125 -0
trainer_state.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.20824170112609863,
3
+ "best_model_checkpoint": "distilbert-base-uncased-imdb/checkpoint-1250",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.8,
13
+ "grad_norm": 3.633013963699341,
14
+ "learning_rate": 1.6000000000000003e-05,
15
+ "loss": 0.2727,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.9178,
21
+ "eval_f1": 0.9211283822682786,
22
+ "eval_loss": 0.2193804234266281,
23
+ "eval_precision": 0.8852821836960532,
24
+ "eval_recall": 0.96,
25
+ "eval_runtime": 86.6891,
26
+ "eval_samples_per_second": 57.677,
27
+ "eval_steps_per_second": 1.811,
28
+ "step": 625
29
+ },
30
+ {
31
+ "epoch": 1.6,
32
+ "grad_norm": 16.50516700744629,
33
+ "learning_rate": 1.2e-05,
34
+ "loss": 0.1569,
35
+ "step": 1000
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.9236,
40
+ "eval_f1": 0.9261978361669243,
41
+ "eval_loss": 0.20824170112609863,
42
+ "eval_precision": 0.8957399103139013,
43
+ "eval_recall": 0.9588,
44
+ "eval_runtime": 86.8325,
45
+ "eval_samples_per_second": 57.582,
46
+ "eval_steps_per_second": 1.808,
47
+ "step": 1250
48
+ },
49
+ {
50
+ "epoch": 2.4,
51
+ "grad_norm": 13.776262283325195,
52
+ "learning_rate": 8.000000000000001e-06,
53
+ "loss": 0.1211,
54
+ "step": 1500
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.9256,
59
+ "eval_f1": 0.9245436105476673,
60
+ "eval_loss": 0.2738637328147888,
61
+ "eval_precision": 0.9378600823045268,
62
+ "eval_recall": 0.9116,
63
+ "eval_runtime": 86.4733,
64
+ "eval_samples_per_second": 57.821,
65
+ "eval_steps_per_second": 1.816,
66
+ "step": 1875
67
+ },
68
+ {
69
+ "epoch": 3.2,
70
+ "grad_norm": 0.0917992889881134,
71
+ "learning_rate": 4.000000000000001e-06,
72
+ "loss": 0.0753,
73
+ "step": 2000
74
+ },
75
+ {
76
+ "epoch": 4.0,
77
+ "grad_norm": 0.31518808007240295,
78
+ "learning_rate": 0.0,
79
+ "loss": 0.0544,
80
+ "step": 2500
81
+ },
82
+ {
83
+ "epoch": 4.0,
84
+ "eval_accuracy": 0.9284,
85
+ "eval_f1": 0.9284286285485805,
86
+ "eval_loss": 0.28977659344673157,
87
+ "eval_precision": 0.9280575539568345,
88
+ "eval_recall": 0.9288,
89
+ "eval_runtime": 84.4716,
90
+ "eval_samples_per_second": 59.191,
91
+ "eval_steps_per_second": 1.859,
92
+ "step": 2500
93
+ },
94
+ {
95
+ "epoch": 4.0,
96
+ "step": 2500,
97
+ "total_flos": 1.059739189248e+16,
98
+ "train_loss": 0.13609123306274415,
99
+ "train_runtime": 4154.1938,
100
+ "train_samples_per_second": 19.258,
101
+ "train_steps_per_second": 0.602
102
+ }
103
+ ],
104
+ "logging_steps": 500,
105
+ "max_steps": 2500,
106
+ "num_input_tokens_seen": 0,
107
+ "num_train_epochs": 4,
108
+ "save_steps": 500,
109
+ "stateful_callbacks": {
110
+ "TrainerControl": {
111
+ "args": {
112
+ "should_epoch_stop": false,
113
+ "should_evaluate": false,
114
+ "should_log": false,
115
+ "should_save": true,
116
+ "should_training_stop": true
117
+ },
118
+ "attributes": {}
119
+ }
120
+ },
121
+ "total_flos": 1.059739189248e+16,
122
+ "train_batch_size": 32,
123
+ "trial_name": null,
124
+ "trial_params": null
125
+ }