Hugging Face's logo

MHGanainy
/
roberta-base-downstream-build_rr

Token Classification
Transformers
Safetensors
roberta
Generated from Trainer
Inference Endpoints
Model card Files Community
MHGanainy commited on
Commit
7612cf8
·
verified ·
1 Parent(s): 15e096c

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 +188 -0
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "total_flos": 4.819469484490752e+16,
4
+ "train_loss": 0.3849165085823305,
5
+ "train_runtime": 337.1781,
6
+ "train_samples": 247,
7
+ "train_samples_per_second": 14.651,
8
+ "train_steps_per_second": 3.678
9
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "total_flos": 4.819469484490752e+16,
4
+ "train_loss": 0.3849165085823305,
5
+ "train_runtime": 337.1781,
6
+ "train_samples": 247,
7
+ "train_samples_per_second": 14.651,
8
+ "train_steps_per_second": 3.678
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,188 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.2816188870151771,
3
+ "best_model_checkpoint": "logs/indian_build_rr/roberta-base/seed_1/checkpoint-434",
4
+ "epoch": 10.0,
5
+ "eval_steps": 500,
6
+ "global_step": 620,
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": 0.8779947916666667,
14
+ "eval_f1": 0.09680365296803654,
15
+ "eval_loss": 0.4225575029850006,
16
+ "eval_micro-f1": 0.09680365296803654,
17
+ "eval_precision": 0.08346456692913386,
18
+ "eval_recall": 0.11521739130434783,
19
+ "eval_runtime": 1.5383,
20
+ "eval_samples_per_second": 19.503,
21
+ "eval_steps_per_second": 5.201,
22
+ "step": 62
23
+ },
24
+ {
25
+ "epoch": 2.0,
26
+ "eval_accuracy": 0.8930989583333333,
27
+ "eval_f1": 0.19573796369376484,
28
+ "eval_loss": 0.34750670194625854,
29
+ "eval_micro-f1": 0.19573796369376484,
30
+ "eval_precision": 0.1536555142503098,
31
+ "eval_recall": 0.26956521739130435,
32
+ "eval_runtime": 1.537,
33
+ "eval_samples_per_second": 19.519,
34
+ "eval_steps_per_second": 5.205,
35
+ "step": 124
36
+ },
37
+ {
38
+ "epoch": 3.0,
39
+ "eval_accuracy": 0.9052083333333333,
40
+ "eval_f1": 0.24148606811145507,
41
+ "eval_loss": 0.2912306487560272,
42
+ "eval_micro-f1": 0.24148606811145507,
43
+ "eval_precision": 0.1875,
44
+ "eval_recall": 0.3391304347826087,
45
+ "eval_runtime": 1.5375,
46
+ "eval_samples_per_second": 19.512,
47
+ "eval_steps_per_second": 5.203,
48
+ "step": 186
49
+ },
50
+ {
51
+ "epoch": 4.0,
52
+ "eval_accuracy": 0.9002604166666667,
53
+ "eval_f1": 0.24856909239574815,
54
+ "eval_loss": 0.29914453625679016,
55
+ "eval_micro-f1": 0.24856909239574815,
56
+ "eval_precision": 0.19921363040629095,
57
+ "eval_recall": 0.33043478260869563,
58
+ "eval_runtime": 1.5402,
59
+ "eval_samples_per_second": 19.478,
60
+ "eval_steps_per_second": 5.194,
61
+ "step": 248
62
+ },
63
+ {
64
+ "epoch": 5.0,
65
+ "eval_accuracy": 0.906640625,
66
+ "eval_f1": 0.24417009602194786,
67
+ "eval_loss": 0.2833251357078552,
68
+ "eval_micro-f1": 0.24417009602194786,
69
+ "eval_precision": 0.17835671342685372,
70
+ "eval_recall": 0.3869565217391304,
71
+ "eval_runtime": 1.5382,
72
+ "eval_samples_per_second": 19.504,
73
+ "eval_steps_per_second": 5.201,
74
+ "step": 310
75
+ },
76
+ {
77
+ "epoch": 6.0,
78
+ "eval_accuracy": 0.91484375,
79
+ "eval_f1": 0.2718932443703086,
80
+ "eval_loss": 0.26417481899261475,
81
+ "eval_micro-f1": 0.2718932443703086,
82
+ "eval_precision": 0.22056833558863329,
83
+ "eval_recall": 0.35434782608695653,
84
+ "eval_runtime": 1.5353,
85
+ "eval_samples_per_second": 19.54,
86
+ "eval_steps_per_second": 5.211,
87
+ "step": 372
88
+ },
89
+ {
90
+ "epoch": 7.0,
91
+ "eval_accuracy": 0.9177083333333333,
92
+ "eval_f1": 0.2816188870151771,
93
+ "eval_loss": 0.2584071457386017,
94
+ "eval_micro-f1": 0.2816188870151771,
95
+ "eval_precision": 0.23002754820936638,
96
+ "eval_recall": 0.3630434782608696,
97
+ "eval_runtime": 1.5473,
98
+ "eval_samples_per_second": 19.388,
99
+ "eval_steps_per_second": 5.17,
100
+ "step": 434
101
+ },
102
+ {
103
+ "epoch": 8.0,
104
+ "eval_accuracy": 0.9177083333333333,
105
+ "eval_f1": 0.27419354838709675,
106
+ "eval_loss": 0.25232046842575073,
107
+ "eval_micro-f1": 0.27419354838709675,
108
+ "eval_precision": 0.21794871794871795,
109
+ "eval_recall": 0.3695652173913043,
110
+ "eval_runtime": 1.5341,
111
+ "eval_samples_per_second": 19.556,
112
+ "eval_steps_per_second": 5.215,
113
+ "step": 496
114
+ },
115
+ {
116
+ "epoch": 8.064516129032258,
117
+ "grad_norm": 2.654693603515625,
118
+ "learning_rate": 1.7975806451612903e-05,
119
+ "loss": 0.4245,
120
+ "step": 500
121
+ },
122
+ {
123
+ "epoch": 9.0,
124
+ "eval_accuracy": 0.9166666666666666,
125
+ "eval_f1": 0.25278810408921937,
126
+ "eval_loss": 0.26304513216018677,
127
+ "eval_micro-f1": 0.25278810408921937,
128
+ "eval_precision": 0.192090395480226,
129
+ "eval_recall": 0.3695652173913043,
130
+ "eval_runtime": 2.1137,
131
+ "eval_samples_per_second": 14.193,
132
+ "eval_steps_per_second": 3.785,
133
+ "step": 558
134
+ },
135
+ {
136
+ "epoch": 10.0,
137
+ "eval_accuracy": 0.919140625,
138
+ "eval_f1": 0.25541795665634676,
139
+ "eval_loss": 0.2640175521373749,
140
+ "eval_micro-f1": 0.25541795665634676,
141
+ "eval_precision": 0.19831730769230768,
142
+ "eval_recall": 0.358695652173913,
143
+ "eval_runtime": 1.5363,
144
+ "eval_samples_per_second": 19.527,
145
+ "eval_steps_per_second": 5.207,
146
+ "step": 620
147
+ },
148
+ {
149
+ "epoch": 10.0,
150
+ "step": 620,
151
+ "total_flos": 4.819469484490752e+16,
152
+ "train_loss": 0.3849165085823305,
153
+ "train_runtime": 337.1781,
154
+ "train_samples_per_second": 14.651,
155
+ "train_steps_per_second": 3.678
156
+ }
157
+ ],
158
+ "logging_steps": 500,
159
+ "max_steps": 1240,
160
+ "num_input_tokens_seen": 0,
161
+ "num_train_epochs": 20,
162
+ "save_steps": 500,
163
+ "stateful_callbacks": {
164
+ "EarlyStoppingCallback": {
165
+ "args": {
166
+ "early_stopping_patience": 3,
167
+ "early_stopping_threshold": 0.0
168
+ },
169
+ "attributes": {
170
+ "early_stopping_patience_counter": 0
171
+ }
172
+ },
173
+ "TrainerControl": {
174
+ "args": {
175
+ "should_epoch_stop": false,
176
+ "should_evaluate": false,
177
+ "should_log": false,
178
+ "should_save": true,
179
+ "should_training_stop": true
180
+ },
181
+ "attributes": {}
182
+ }
183
+ },
184
+ "total_flos": 4.819469484490752e+16,
185
+ "train_batch_size": 4,
186
+ "trial_name": null,
187
+ "trial_params": null
188
+ }