Hugging Face's logo

ViFortune-AI
/
ViT5Summer

Summarization
Safetensors
Vietnamese
t5
Model card Files
xet
Community
Tnt3o5 commited on
Commit
274d479
·
verified ·
1 Parent(s): 4a65b37

Delete trainer_state.json

Browse files
Files changed (1) hide show
  1. trainer_state.json +0 -159
trainer_state.json DELETED
@@ -1,159 +0,0 @@
1
- {
2
- "best_global_step": 1000,
3
- "best_metric": 0.33288311538438786,
4
- "best_model_checkpoint": "./vit5-finetuned-dialogue-summarization/checkpoint-1000",
5
- "epoch": 12.346749226006192,
6
- "eval_steps": 200,
7
- "global_step": 1000,
8
- "is_hyper_param_search": false,
9
- "is_local_process_zero": true,
10
- "is_world_process_zero": true,
11
- "log_history": [
12
- {
13
- "epoch": 1.2352941176470589,
14
- "grad_norm": 185095.125,
15
- "learning_rate": 1.3200000000000002e-05,
16
- "loss": 6.2191,
17
- "step": 100
18
- },
19
- {
20
- "epoch": 2.4705882352941178,
21
- "grad_norm": 158838.359375,
22
- "learning_rate": 1.9943698759737188e-05,
23
- "loss": 3.2303,
24
- "step": 200
25
- },
26
- {
27
- "epoch": 2.4705882352941178,
28
- "eval_loss": 2.8786303997039795,
29
- "eval_rouge1": 0.40996985374799266,
30
- "eval_rouge2": 0.18504037812883903,
31
- "eval_rougeL": 0.31774992554282866,
32
- "eval_runtime": 205.398,
33
- "eval_samples_per_second": 21.519,
34
- "eval_steps_per_second": 0.677,
35
- "step": 200
36
- },
37
- {
38
- "epoch": 3.7058823529411766,
39
- "grad_norm": 158688.46875,
40
- "learning_rate": 1.9483427500783406e-05,
41
- "loss": 2.9395,
42
- "step": 300
43
- },
44
- {
45
- "epoch": 4.9411764705882355,
46
- "grad_norm": 190883.5,
47
- "learning_rate": 1.857972171196563e-05,
48
- "loss": 2.763,
49
- "step": 400
50
- },
51
- {
52
- "epoch": 4.9411764705882355,
53
- "eval_loss": 2.7310757637023926,
54
- "eval_rouge1": 0.42136324989901236,
55
- "eval_rouge2": 0.1944821772831587,
56
- "eval_rougeL": 0.3260771701642916,
57
- "eval_runtime": 205.292,
58
- "eval_samples_per_second": 21.53,
59
- "eval_steps_per_second": 0.677,
60
- "step": 400
61
- },
62
- {
63
- "epoch": 6.173374613003096,
64
- "grad_norm": 180474.46875,
65
- "learning_rate": 1.7274837671572133e-05,
66
- "loss": 2.6231,
67
- "step": 500
68
- },
69
- {
70
- "epoch": 7.408668730650155,
71
- "grad_norm": 175110.484375,
72
- "learning_rate": 1.562979030705727e-05,
73
- "loss": 2.5224,
74
- "step": 600
75
- },
76
- {
77
- "epoch": 7.408668730650155,
78
- "eval_loss": 2.7129697799682617,
79
- "eval_rouge1": 0.43007163981326607,
80
- "eval_rouge2": 0.19918326506985456,
81
- "eval_rougeL": 0.3309695197898552,
82
- "eval_runtime": 205.2031,
83
- "eval_samples_per_second": 21.54,
84
- "eval_steps_per_second": 0.677,
85
- "step": 600
86
- },
87
- {
88
- "epoch": 8.643962848297214,
89
- "grad_norm": 187383.40625,
90
- "learning_rate": 1.372150020484693e-05,
91
- "loss": 2.4244,
92
- "step": 700
93
- },
94
- {
95
- "epoch": 9.879256965944272,
96
- "grad_norm": 173576.234375,
97
- "learning_rate": 1.1639196889208348e-05,
98
- "loss": 2.3546,
99
- "step": 800
100
- },
101
- {
102
- "epoch": 9.879256965944272,
103
- "eval_loss": 2.714728355407715,
104
- "eval_rouge1": 0.4326827613393533,
105
- "eval_rouge2": 0.20101319185305067,
106
- "eval_rougeL": 0.3320485850425753,
107
- "eval_runtime": 205.3578,
108
- "eval_samples_per_second": 21.523,
109
- "eval_steps_per_second": 0.677,
110
- "step": 800
111
- },
112
- {
113
- "epoch": 11.111455108359133,
114
- "grad_norm": 178280.171875,
115
- "learning_rate": 9.480246548866876e-06,
116
- "loss": 2.2813,
117
- "step": 900
118
- },
119
- {
120
- "epoch": 12.346749226006192,
121
- "grad_norm": 198161.578125,
122
- "learning_rate": 7.345599302235916e-06,
123
- "loss": 2.2313,
124
- "step": 1000
125
- },
126
- {
127
- "epoch": 12.346749226006192,
128
- "eval_loss": 2.7374987602233887,
129
- "eval_rouge1": 0.4325670867128867,
130
- "eval_rouge2": 0.20087960988143622,
131
- "eval_rougeL": 0.33288311538438786,
132
- "eval_runtime": 205.6552,
133
- "eval_samples_per_second": 21.492,
134
- "eval_steps_per_second": 0.676,
135
- "step": 1000
136
- }
137
- ],
138
- "logging_steps": 100,
139
- "max_steps": 1600,
140
- "num_input_tokens_seen": 0,
141
- "num_train_epochs": 20,
142
- "save_steps": 200,
143
- "stateful_callbacks": {
144
- "TrainerControl": {
145
- "args": {
146
- "should_epoch_stop": false,
147
- "should_evaluate": false,
148
- "should_log": false,
149
- "should_save": true,
150
- "should_training_stop": false
151
- },
152
- "attributes": {}
153
- }
154
- },
155
- "total_flos": 7.099476931109376e+16,
156
- "train_batch_size": 32,
157
- "trial_name": null,
158
- "trial_params": null
159
- }