Hugging Face's logo

MHGanainy
/
xmod-shared-roberta-base-legal-multi-downstream-ecthr-b

Text Classification
Transformers
Safetensors
xmod
Generated from Trainer
Inference Endpoints
Model card Files Community
MHGanainy commited on
Commit
7b1705f
•
1 Parent(s): 637cfdd

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 +159 -0
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 8.0,
3
+ "total_flos": 3.7940453059015475e+17,
4
+ "train_loss": 0.10690519699813626,
5
+ "train_runtime": 1502.7914,
6
+ "train_samples": 9000,
7
+ "train_samples_per_second": 119.777,
8
+ "train_steps_per_second": 3.753
9
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 8.0,
3
+ "total_flos": 3.7940453059015475e+17,
4
+ "train_loss": 0.10690519699813626,
5
+ "train_runtime": 1502.7914,
6
+ "train_samples": 9000,
7
+ "train_samples_per_second": 119.777,
8
+ "train_steps_per_second": 3.753
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,159 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7964841108857336,
3
+ "best_model_checkpoint": "logs/ecthr_b/MHGanainy/xmod-shared-roberta-base-legal-multi/seed_1/checkpoint-1410",
4
+ "epoch": 8.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2256,
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": 0.1879543662071228,
14
+ "eval_macro-f1": 0.637208986436089,
15
+ "eval_micro-f1": 0.7414155571128241,
16
+ "eval_runtime": 9.9431,
17
+ "eval_samples_per_second": 100.573,
18
+ "eval_steps_per_second": 3.218,
19
+ "step": 282
20
+ },
21
+ {
22
+ "epoch": 1.773049645390071,
23
+ "grad_norm": 1.1033704280853271,
24
+ "learning_rate": 2.7345744680851065e-05,
25
+ "loss": 0.1761,
26
+ "step": 500
27
+ },
28
+ {
29
+ "epoch": 2.0,
30
+ "eval_loss": 0.19721177220344543,
31
+ "eval_macro-f1": 0.6534255535190332,
32
+ "eval_micro-f1": 0.76043673731535,
33
+ "eval_runtime": 13.6625,
34
+ "eval_samples_per_second": 73.193,
35
+ "eval_steps_per_second": 2.342,
36
+ "step": 564
37
+ },
38
+ {
39
+ "epoch": 3.0,
40
+ "eval_loss": 0.1727759689092636,
41
+ "eval_macro-f1": 0.7189646935925815,
42
+ "eval_micro-f1": 0.7865168539325843,
43
+ "eval_runtime": 9.5271,
44
+ "eval_samples_per_second": 104.964,
45
+ "eval_steps_per_second": 3.359,
46
+ "step": 846
47
+ },
48
+ {
49
+ "epoch": 3.546099290780142,
50
+ "grad_norm": 1.1534513235092163,
51
+ "learning_rate": 2.4686170212765958e-05,
52
+ "loss": 0.1155,
53
+ "step": 1000
54
+ },
55
+ {
56
+ "epoch": 4.0,
57
+ "eval_loss": 0.1755395233631134,
58
+ "eval_macro-f1": 0.7373513816426139,
59
+ "eval_micro-f1": 0.7873910127431254,
60
+ "eval_runtime": 10.0776,
61
+ "eval_samples_per_second": 99.23,
62
+ "eval_steps_per_second": 3.175,
63
+ "step": 1128
64
+ },
65
+ {
66
+ "epoch": 5.0,
67
+ "eval_loss": 0.17423860728740692,
68
+ "eval_macro-f1": 0.7353822537422677,
69
+ "eval_micro-f1": 0.7964841108857336,
70
+ "eval_runtime": 10.1727,
71
+ "eval_samples_per_second": 98.302,
72
+ "eval_steps_per_second": 3.146,
73
+ "step": 1410
74
+ },
75
+ {
76
+ "epoch": 5.319148936170213,
77
+ "grad_norm": 1.2388067245483398,
78
+ "learning_rate": 2.2026595744680854e-05,
79
+ "loss": 0.091,
80
+ "step": 1500
81
+ },
82
+ {
83
+ "epoch": 6.0,
84
+ "eval_loss": 0.19554495811462402,
85
+ "eval_macro-f1": 0.7451892220071915,
86
+ "eval_micro-f1": 0.7875816993464052,
87
+ "eval_runtime": 13.6476,
88
+ "eval_samples_per_second": 73.273,
89
+ "eval_steps_per_second": 2.345,
90
+ "step": 1692
91
+ },
92
+ {
93
+ "epoch": 7.0,
94
+ "eval_loss": 0.1909777820110321,
95
+ "eval_macro-f1": 0.7475109109665823,
96
+ "eval_micro-f1": 0.7894201424211598,
97
+ "eval_runtime": 9.5034,
98
+ "eval_samples_per_second": 105.225,
99
+ "eval_steps_per_second": 3.367,
100
+ "step": 1974
101
+ },
102
+ {
103
+ "epoch": 7.092198581560283,
104
+ "grad_norm": 1.6909549236297607,
105
+ "learning_rate": 1.9367021276595743e-05,
106
+ "loss": 0.071,
107
+ "step": 2000
108
+ },
109
+ {
110
+ "epoch": 8.0,
111
+ "eval_loss": 0.2065315544605255,
112
+ "eval_macro-f1": 0.7429317897586639,
113
+ "eval_micro-f1": 0.785572468563865,
114
+ "eval_runtime": 9.4369,
115
+ "eval_samples_per_second": 105.967,
116
+ "eval_steps_per_second": 3.391,
117
+ "step": 2256
118
+ },
119
+ {
120
+ "epoch": 8.0,
121
+ "step": 2256,
122
+ "total_flos": 3.7940453059015475e+17,
123
+ "train_loss": 0.10690519699813626,
124
+ "train_runtime": 1502.7914,
125
+ "train_samples_per_second": 119.777,
126
+ "train_steps_per_second": 3.753
127
+ }
128
+ ],
129
+ "logging_steps": 500,
130
+ "max_steps": 5640,
131
+ "num_input_tokens_seen": 0,
132
+ "num_train_epochs": 20,
133
+ "save_steps": 500,
134
+ "stateful_callbacks": {
135
+ "EarlyStoppingCallback": {
136
+ "args": {
137
+ "early_stopping_patience": 3,
138
+ "early_stopping_threshold": 0.0
139
+ },
140
+ "attributes": {
141
+ "early_stopping_patience_counter": 0
142
+ }
143
+ },
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": true
151
+ },
152
+ "attributes": {}
153
+ }
154
+ },
155
+ "total_flos": 3.7940453059015475e+17,
156
+ "train_batch_size": 16,
157
+ "trial_name": null,
158
+ "trial_params": null
159
+ }