Hugging Face's logo

MHGanainy
/
roberta-base-downstream-ecthr-b

Text Classification
Transformers
Safetensors
roberta
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Community
MHGanainy commited on
Commit
8a235ac
·
verified ·
1 Parent(s): afaa0d1

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": 3.542404433675551e+17,
4
+ "train_loss": 0.10894472971030161,
5
+ "train_runtime": 1334.5785,
6
+ "train_samples": 9000,
7
+ "train_samples_per_second": 134.874,
8
+ "train_steps_per_second": 4.226
9
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 8.0,
3
+ "total_flos": 3.542404433675551e+17,
4
+ "train_loss": 0.10894472971030161,
5
+ "train_runtime": 1334.5785,
6
+ "train_samples": 9000,
7
+ "train_samples_per_second": 134.874,
8
+ "train_steps_per_second": 4.226
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,159 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7935978659553184,
3
+ "best_model_checkpoint": "logs/ecthr_b/roberta-base/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": 0.19746574759483337,
14
+ "eval_macro-f1": 0.6393379993931348,
15
+ "eval_micro-f1": 0.7408184679958028,
16
+ "eval_runtime": 9.7693,
17
+ "eval_samples_per_second": 102.361,
18
+ "eval_steps_per_second": 3.276,
19
+ "step": 282
20
+ },
21
+ {
22
+ "epoch": 1.773049645390071,
23
+ "grad_norm": 1.1872084140777588,
24
+ "learning_rate": 2.7340425531914897e-05,
25
+ "loss": 0.1811,
26
+ "step": 500
27
+ },
28
+ {
29
+ "epoch": 2.0,
30
+ "eval_loss": 0.19539476931095123,
31
+ "eval_macro-f1": 0.6540544618364194,
32
+ "eval_micro-f1": 0.7559311017224569,
33
+ "eval_runtime": 9.1514,
34
+ "eval_samples_per_second": 109.272,
35
+ "eval_steps_per_second": 3.497,
36
+ "step": 564
37
+ },
38
+ {
39
+ "epoch": 3.0,
40
+ "eval_loss": 0.178602933883667,
41
+ "eval_macro-f1": 0.7063419905042477,
42
+ "eval_micro-f1": 0.7832625040863027,
43
+ "eval_runtime": 8.9637,
44
+ "eval_samples_per_second": 111.562,
45
+ "eval_steps_per_second": 3.57,
46
+ "step": 846
47
+ },
48
+ {
49
+ "epoch": 3.546099290780142,
50
+ "grad_norm": 1.4385334253311157,
51
+ "learning_rate": 2.4686170212765958e-05,
52
+ "loss": 0.1167,
53
+ "step": 1000
54
+ },
55
+ {
56
+ "epoch": 4.0,
57
+ "eval_loss": 0.1745893508195877,
58
+ "eval_macro-f1": 0.7303617301778567,
59
+ "eval_micro-f1": 0.7927686642115835,
60
+ "eval_runtime": 9.0428,
61
+ "eval_samples_per_second": 110.585,
62
+ "eval_steps_per_second": 3.539,
63
+ "step": 1128
64
+ },
65
+ {
66
+ "epoch": 5.0,
67
+ "eval_loss": 0.1818280965089798,
68
+ "eval_macro-f1": 0.7269570388508974,
69
+ "eval_micro-f1": 0.7935978659553184,
70
+ "eval_runtime": 8.4498,
71
+ "eval_samples_per_second": 118.346,
72
+ "eval_steps_per_second": 3.787,
73
+ "step": 1410
74
+ },
75
+ {
76
+ "epoch": 5.319148936170213,
77
+ "grad_norm": 1.5338271856307983,
78
+ "learning_rate": 2.2026595744680854e-05,
79
+ "loss": 0.0921,
80
+ "step": 1500
81
+ },
82
+ {
83
+ "epoch": 6.0,
84
+ "eval_loss": 0.1933058500289917,
85
+ "eval_macro-f1": 0.7235350370954329,
86
+ "eval_micro-f1": 0.7809836065573771,
87
+ "eval_runtime": 8.4822,
88
+ "eval_samples_per_second": 117.894,
89
+ "eval_steps_per_second": 3.773,
90
+ "step": 1692
91
+ },
92
+ {
93
+ "epoch": 7.0,
94
+ "eval_loss": 0.19006936252117157,
95
+ "eval_macro-f1": 0.7326251101371736,
96
+ "eval_micro-f1": 0.7851602023608769,
97
+ "eval_runtime": 8.4696,
98
+ "eval_samples_per_second": 118.069,
99
+ "eval_steps_per_second": 3.778,
100
+ "step": 1974
101
+ },
102
+ {
103
+ "epoch": 7.092198581560283,
104
+ "grad_norm": 2.809311866760254,
105
+ "learning_rate": 1.9367021276595743e-05,
106
+ "loss": 0.0721,
107
+ "step": 2000
108
+ },
109
+ {
110
+ "epoch": 8.0,
111
+ "eval_loss": 0.19798380136489868,
112
+ "eval_macro-f1": 0.7335571414521224,
113
+ "eval_micro-f1": 0.7897877984084881,
114
+ "eval_runtime": 8.5312,
115
+ "eval_samples_per_second": 117.217,
116
+ "eval_steps_per_second": 3.751,
117
+ "step": 2256
118
+ },
119
+ {
120
+ "epoch": 8.0,
121
+ "step": 2256,
122
+ "total_flos": 3.542404433675551e+17,
123
+ "train_loss": 0.10894472971030161,
124
+ "train_runtime": 1334.5785,
125
+ "train_samples_per_second": 134.874,
126
+ "train_steps_per_second": 4.226
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": 3.542404433675551e+17,
156
+ "train_batch_size": 16,
157
+ "trial_name": null,
158
+ "trial_params": null
159
+ }