Hugging Face's logo

matthewleechen
/
science_MP_classifier

Text Classification
Transformers
Safetensors
roberta
text-embeddings-inference
Model card Files
xet
Community
matthewleechen commited on
Commit
5535908
·
verified ·
1 Parent(s): d7661ce

Upload trainer_state.json

Browse files
Files changed (1) hide show
  1. trainer_state.json +129 -0
trainer_state.json ADDED
@@ -0,0 +1,129 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.92,
3
+ "best_model_checkpoint": "roberta-base/checkpoint-24",
4
+ "epoch": 8.0,
5
+ "eval_steps": 500,
6
+ "global_step": 24,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.67,
14
+ "eval_f1": 0.5376047904191618,
15
+ "eval_loss": 0.6319047808647156,
16
+ "eval_precision": 0.4489,
17
+ "eval_recall": 0.67,
18
+ "eval_runtime": 0.4159,
19
+ "eval_samples_per_second": 240.427,
20
+ "eval_steps_per_second": 2.404,
21
+ "step": 3
22
+ },
23
+ {
24
+ "epoch": 2.0,
25
+ "eval_accuracy": 0.67,
26
+ "eval_f1": 0.5376047904191618,
27
+ "eval_loss": 0.6274762153625488,
28
+ "eval_precision": 0.4489,
29
+ "eval_recall": 0.67,
30
+ "eval_runtime": 0.4183,
31
+ "eval_samples_per_second": 239.081,
32
+ "eval_steps_per_second": 2.391,
33
+ "step": 6
34
+ },
35
+ {
36
+ "epoch": 3.0,
37
+ "eval_accuracy": 0.67,
38
+ "eval_f1": 0.5376047904191618,
39
+ "eval_loss": 0.6107555627822876,
40
+ "eval_precision": 0.4489,
41
+ "eval_recall": 0.67,
42
+ "eval_runtime": 0.4167,
43
+ "eval_samples_per_second": 240.008,
44
+ "eval_steps_per_second": 2.4,
45
+ "step": 9
46
+ },
47
+ {
48
+ "epoch": 4.0,
49
+ "eval_accuracy": 0.69,
50
+ "eval_f1": 0.5818354978354978,
51
+ "eval_loss": 0.6286537051200867,
52
+ "eval_precision": 0.788061224489796,
53
+ "eval_recall": 0.69,
54
+ "eval_runtime": 0.4169,
55
+ "eval_samples_per_second": 239.86,
56
+ "eval_steps_per_second": 2.399,
57
+ "step": 12
58
+ },
59
+ {
60
+ "epoch": 5.0,
61
+ "eval_accuracy": 0.72,
62
+ "eval_f1": 0.7282758620689656,
63
+ "eval_loss": 0.5415282249450684,
64
+ "eval_precision": 0.7828091236494598,
65
+ "eval_recall": 0.72,
66
+ "eval_runtime": 0.4173,
67
+ "eval_samples_per_second": 239.629,
68
+ "eval_steps_per_second": 2.396,
69
+ "step": 15
70
+ },
71
+ {
72
+ "epoch": 6.0,
73
+ "eval_accuracy": 0.85,
74
+ "eval_f1": 0.851543312313309,
75
+ "eval_loss": 0.35827144980430603,
76
+ "eval_precision": 0.8546875,
77
+ "eval_recall": 0.85,
78
+ "eval_runtime": 0.4185,
79
+ "eval_samples_per_second": 238.934,
80
+ "eval_steps_per_second": 2.389,
81
+ "step": 18
82
+ },
83
+ {
84
+ "epoch": 7.0,
85
+ "eval_accuracy": 0.88,
86
+ "eval_f1": 0.8815824175824176,
87
+ "eval_loss": 0.3416476845741272,
88
+ "eval_precision": 0.8861089661089662,
89
+ "eval_recall": 0.88,
90
+ "eval_runtime": 0.4254,
91
+ "eval_samples_per_second": 235.093,
92
+ "eval_steps_per_second": 2.351,
93
+ "step": 21
94
+ },
95
+ {
96
+ "epoch": 8.0,
97
+ "eval_accuracy": 0.92,
98
+ "eval_f1": 0.92,
99
+ "eval_loss": 0.2903079688549042,
100
+ "eval_precision": 0.92,
101
+ "eval_recall": 0.92,
102
+ "eval_runtime": 0.4202,
103
+ "eval_samples_per_second": 237.971,
104
+ "eval_steps_per_second": 2.38,
105
+ "step": 24
106
+ }
107
+ ],
108
+ "logging_steps": 500,
109
+ "max_steps": 60,
110
+ "num_input_tokens_seen": 0,
111
+ "num_train_epochs": 20,
112
+ "save_steps": 500,
113
+ "stateful_callbacks": {
114
+ "TrainerControl": {
115
+ "args": {
116
+ "should_epoch_stop": false,
117
+ "should_evaluate": false,
118
+ "should_log": false,
119
+ "should_save": true,
120
+ "should_training_stop": false
121
+ },
122
+ "attributes": {}
123
+ }
124
+ },
125
+ "total_flos": 631466532864000.0,
126
+ "train_batch_size": 128,
127
+ "trial_name": null,
128
+ "trial_params": null
129
+ }