Hugging Face's logo

MHGanainy
/
xmod-roberta-base-legal-multi-ecthr-downstream-ecthr-a

Text Classification
Transformers
Safetensors
xmod
Generated from Trainer
Inference Endpoints
Model card Files Community
MHGanainy commited on
Commit
b24d548
•
1 Parent(s): 65fea3e

End of training

Browse files
Files changed (3) hide show
  1. all_results.json +9 -0
  2. train_results.json +9 -0
  3. trainer_state.json +142 -0
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 7.0,
3
+ "total_flos": 3.9803472298849075e+17,
4
+ "train_loss": 0.10179799571708827,
5
+ "train_runtime": 1296.3583,
6
+ "train_samples": 9000,
7
+ "train_samples_per_second": 138.851,
8
+ "train_steps_per_second": 4.351
9
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 7.0,
3
+ "total_flos": 3.9803472298849075e+17,
4
+ "train_loss": 0.10179799571708827,
5
+ "train_runtime": 1296.3583,
6
+ "train_samples": 9000,
7
+ "train_samples_per_second": 138.851,
8
+ "train_steps_per_second": 4.351
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,142 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7086017430845017,
3
+ "best_model_checkpoint": "logs/ecthr_a/MHGanainy/xmod-roberta-base-legal-multi/seed_1/checkpoint-1128",
4
+ "epoch": 7.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1974,
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_loss": 0.18291330337524414,
14
+ "eval_macro-f1": 0.5518037204425776,
15
+ "eval_micro-f1": 0.677207867335133,
16
+ "eval_runtime": 9.4627,
17
+ "eval_samples_per_second": 105.679,
18
+ "eval_steps_per_second": 3.382,
19
+ "step": 282
20
+ },
21
+ {
22
+ "epoch": 1.773049645390071,
23
+ "grad_norm": 1.2761306762695312,
24
+ "learning_rate": 2.7340425531914897e-05,
25
+ "loss": 0.1547,
26
+ "step": 500
27
+ },
28
+ {
29
+ "epoch": 2.0,
30
+ "eval_loss": 0.1642679125070572,
31
+ "eval_macro-f1": 0.5832870401688298,
32
+ "eval_micro-f1": 0.6849209409949865,
33
+ "eval_runtime": 10.2302,
34
+ "eval_samples_per_second": 97.75,
35
+ "eval_steps_per_second": 3.128,
36
+ "step": 564
37
+ },
38
+ {
39
+ "epoch": 3.0,
40
+ "eval_loss": 0.18205788731575012,
41
+ "eval_macro-f1": 0.605599290957237,
42
+ "eval_micro-f1": 0.6864124398370973,
43
+ "eval_runtime": 9.5057,
44
+ "eval_samples_per_second": 105.2,
45
+ "eval_steps_per_second": 3.366,
46
+ "step": 846
47
+ },
48
+ {
49
+ "epoch": 3.546099290780142,
50
+ "grad_norm": 1.2056403160095215,
51
+ "learning_rate": 2.4680851063829786e-05,
52
+ "loss": 0.1031,
53
+ "step": 1000
54
+ },
55
+ {
56
+ "epoch": 4.0,
57
+ "eval_loss": 0.17138700187206268,
58
+ "eval_macro-f1": 0.6431822683616067,
59
+ "eval_micro-f1": 0.7086017430845017,
60
+ "eval_runtime": 9.3996,
61
+ "eval_samples_per_second": 106.388,
62
+ "eval_steps_per_second": 3.404,
63
+ "step": 1128
64
+ },
65
+ {
66
+ "epoch": 5.0,
67
+ "eval_loss": 0.1661965399980545,
68
+ "eval_macro-f1": 0.6357063441749147,
69
+ "eval_micro-f1": 0.6957854406130268,
70
+ "eval_runtime": 9.0902,
71
+ "eval_samples_per_second": 110.009,
72
+ "eval_steps_per_second": 3.52,
73
+ "step": 1410
74
+ },
75
+ {
76
+ "epoch": 5.319148936170213,
77
+ "grad_norm": 1.897348403930664,
78
+ "learning_rate": 2.2021276595744682e-05,
79
+ "loss": 0.0836,
80
+ "step": 1500
81
+ },
82
+ {
83
+ "epoch": 6.0,
84
+ "eval_loss": 0.18352459371089935,
85
+ "eval_macro-f1": 0.6308890190522723,
86
+ "eval_micro-f1": 0.6896046852122987,
87
+ "eval_runtime": 10.0959,
88
+ "eval_samples_per_second": 99.05,
89
+ "eval_steps_per_second": 3.17,
90
+ "step": 1692
91
+ },
92
+ {
93
+ "epoch": 7.0,
94
+ "eval_loss": 0.22320151329040527,
95
+ "eval_macro-f1": 0.6305744474515731,
96
+ "eval_micro-f1": 0.6835172659309363,
97
+ "eval_runtime": 9.9878,
98
+ "eval_samples_per_second": 100.122,
99
+ "eval_steps_per_second": 3.204,
100
+ "step": 1974
101
+ },
102
+ {
103
+ "epoch": 7.0,
104
+ "step": 1974,
105
+ "total_flos": 3.9803472298849075e+17,
106
+ "train_loss": 0.10179799571708827,
107
+ "train_runtime": 1296.3583,
108
+ "train_samples_per_second": 138.851,
109
+ "train_steps_per_second": 4.351
110
+ }
111
+ ],
112
+ "logging_steps": 500,
113
+ "max_steps": 5640,
114
+ "num_input_tokens_seen": 0,
115
+ "num_train_epochs": 20,
116
+ "save_steps": 500,
117
+ "stateful_callbacks": {
118
+ "EarlyStoppingCallback": {
119
+ "args": {
120
+ "early_stopping_patience": 3,
121
+ "early_stopping_threshold": 0.0
122
+ },
123
+ "attributes": {
124
+ "early_stopping_patience_counter": 0
125
+ }
126
+ },
127
+ "TrainerControl": {
128
+ "args": {
129
+ "should_epoch_stop": false,
130
+ "should_evaluate": false,
131
+ "should_log": false,
132
+ "should_save": true,
133
+ "should_training_stop": true
134
+ },
135
+ "attributes": {}
136
+ }
137
+ },
138
+ "total_flos": 3.9803472298849075e+17,
139
+ "train_batch_size": 16,
140
+ "trial_name": null,
141
+ "trial_params": null
142
+ }