Hugging Face's logo

mehrshadk
/
sport-DEBERTB-seed5-lr2e-05

Safetensors
deberta
Model card Files Community
mehrshadk commited on
Commit
feb4dca
·
verified ·
1 Parent(s): 341ec2a

Training in progress, epoch 3, checkpoint

Browse files
Files changed (4) hide show
  1. checkpoint-300/config.json +33 -0
  2. checkpoint-300/model.safetensors +3 -0
  3. checkpoint-300/trainer_state.json +171 -0
  4. checkpoint-300/training_args.bin +3 -0
checkpoint-300/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/deberta-base",
3
+ "architectures": [
4
+ "DebertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 3072,
12
+ "layer_norm_eps": 1e-07,
13
+ "legacy": true,
14
+ "max_position_embeddings": 512,
15
+ "max_relative_positions": -1,
16
+ "model_type": "deberta",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "pooler_dropout": 0,
21
+ "pooler_hidden_act": "gelu",
22
+ "pooler_hidden_size": 768,
23
+ "pos_att_type": [
24
+ "c2p",
25
+ "p2c"
26
+ ],
27
+ "position_biased_input": false,
28
+ "relative_attention": true,
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.48.3",
31
+ "type_vocab_size": 0,
32
+ "vocab_size": 50265
33
+ }
checkpoint-300/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dca6616044e640d4e5ee659f4ae61fafdf5e0fabf540ba5337289719ebe128d
3
+ size 556799560
checkpoint-300/trainer_state.json ADDED
@@ -0,0 +1,171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 50,
6
+ "global_step": 300,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.5,
13
+ "grad_norm": 6.658211708068848,
14
+ "learning_rate": 1.8333333333333333e-05,
15
+ "loss": 0.5628,
16
+ "step": 50
17
+ },
18
+ {
19
+ "epoch": 0.5,
20
+ "eval_sport_AUC": 0.8575549450549451,
21
+ "eval_sport_accuracy": 0.795,
22
+ "eval_sport_f1": 0.6917293233082706,
23
+ "eval_sport_loss": 0.45002254843711853,
24
+ "eval_sport_macro_f1": 0.7690856354369069,
25
+ "eval_sport_micro_f1": 0.795,
26
+ "eval_sport_precision": 0.7301587301587301,
27
+ "eval_sport_recall": 0.6571428571428571,
28
+ "eval_sport_runtime": 0.6957,
29
+ "eval_sport_samples_per_second": 574.989,
30
+ "eval_sport_specificity": 0.8692307692307693,
31
+ "eval_sport_steps_per_second": 1.437,
32
+ "step": 50
33
+ },
34
+ {
35
+ "epoch": 1.0,
36
+ "grad_norm": 7.818618297576904,
37
+ "learning_rate": 1.6666666666666667e-05,
38
+ "loss": 0.4453,
39
+ "step": 100
40
+ },
41
+ {
42
+ "epoch": 1.0,
43
+ "eval_sport_AUC": 0.8724725274725275,
44
+ "eval_sport_accuracy": 0.79,
45
+ "eval_sport_f1": 0.7162162162162162,
46
+ "eval_sport_loss": 0.42653143405914307,
47
+ "eval_sport_macro_f1": 0.7747747747747749,
48
+ "eval_sport_micro_f1": 0.79,
49
+ "eval_sport_precision": 0.6794871794871795,
50
+ "eval_sport_recall": 0.7571428571428571,
51
+ "eval_sport_runtime": 0.6966,
52
+ "eval_sport_samples_per_second": 574.228,
53
+ "eval_sport_specificity": 0.8076923076923077,
54
+ "eval_sport_steps_per_second": 1.436,
55
+ "step": 100
56
+ },
57
+ {
58
+ "epoch": 1.5,
59
+ "grad_norm": 11.515430450439453,
60
+ "learning_rate": 1.5000000000000002e-05,
61
+ "loss": 0.3635,
62
+ "step": 150
63
+ },
64
+ {
65
+ "epoch": 1.5,
66
+ "eval_sport_AUC": 0.867912087912088,
67
+ "eval_sport_accuracy": 0.8,
68
+ "eval_sport_f1": 0.7202797202797203,
69
+ "eval_sport_loss": 0.4973774254322052,
70
+ "eval_sport_macro_f1": 0.7823188484667084,
71
+ "eval_sport_micro_f1": 0.8,
72
+ "eval_sport_precision": 0.7054794520547946,
73
+ "eval_sport_recall": 0.7357142857142858,
74
+ "eval_sport_runtime": 0.7061,
75
+ "eval_sport_samples_per_second": 566.501,
76
+ "eval_sport_specificity": 0.8346153846153846,
77
+ "eval_sport_steps_per_second": 1.416,
78
+ "step": 150
79
+ },
80
+ {
81
+ "epoch": 2.0,
82
+ "grad_norm": 14.943413734436035,
83
+ "learning_rate": 1.3333333333333333e-05,
84
+ "loss": 0.362,
85
+ "step": 200
86
+ },
87
+ {
88
+ "epoch": 2.0,
89
+ "eval_sport_AUC": 0.8794505494505495,
90
+ "eval_sport_accuracy": 0.78,
91
+ "eval_sport_f1": 0.7349397590361446,
92
+ "eval_sport_loss": 0.5080252885818481,
93
+ "eval_sport_macro_f1": 0.7734527855009783,
94
+ "eval_sport_micro_f1": 0.78,
95
+ "eval_sport_precision": 0.6354166666666666,
96
+ "eval_sport_recall": 0.8714285714285714,
97
+ "eval_sport_runtime": 0.7311,
98
+ "eval_sport_samples_per_second": 547.097,
99
+ "eval_sport_specificity": 0.7307692307692307,
100
+ "eval_sport_steps_per_second": 1.368,
101
+ "step": 200
102
+ },
103
+ {
104
+ "epoch": 2.5,
105
+ "grad_norm": 1.4722031354904175,
106
+ "learning_rate": 1.1666666666666668e-05,
107
+ "loss": 0.2393,
108
+ "step": 250
109
+ },
110
+ {
111
+ "epoch": 2.5,
112
+ "eval_sport_AUC": 0.879532967032967,
113
+ "eval_sport_accuracy": 0.7925,
114
+ "eval_sport_f1": 0.7331189710610932,
115
+ "eval_sport_loss": 0.519324779510498,
116
+ "eval_sport_macro_f1": 0.781692409865925,
117
+ "eval_sport_micro_f1": 0.7925,
118
+ "eval_sport_precision": 0.6666666666666666,
119
+ "eval_sport_recall": 0.8142857142857143,
120
+ "eval_sport_runtime": 0.6948,
121
+ "eval_sport_samples_per_second": 575.731,
122
+ "eval_sport_specificity": 0.7807692307692308,
123
+ "eval_sport_steps_per_second": 1.439,
124
+ "step": 250
125
+ },
126
+ {
127
+ "epoch": 3.0,
128
+ "grad_norm": 7.780460357666016,
129
+ "learning_rate": 1e-05,
130
+ "loss": 0.2739,
131
+ "step": 300
132
+ },
133
+ {
134
+ "epoch": 3.0,
135
+ "eval_sport_AUC": 0.8780769230769231,
136
+ "eval_sport_accuracy": 0.7925,
137
+ "eval_sport_f1": 0.7446153846153846,
138
+ "eval_sport_loss": 0.5590013861656189,
139
+ "eval_sport_macro_f1": 0.7849392712550607,
140
+ "eval_sport_micro_f1": 0.7925,
141
+ "eval_sport_precision": 0.654054054054054,
142
+ "eval_sport_recall": 0.8642857142857143,
143
+ "eval_sport_runtime": 0.7031,
144
+ "eval_sport_samples_per_second": 568.879,
145
+ "eval_sport_specificity": 0.7538461538461538,
146
+ "eval_sport_steps_per_second": 1.422,
147
+ "step": 300
148
+ }
149
+ ],
150
+ "logging_steps": 50,
151
+ "max_steps": 600,
152
+ "num_input_tokens_seen": 0,
153
+ "num_train_epochs": 6,
154
+ "save_steps": 500,
155
+ "stateful_callbacks": {
156
+ "TrainerControl": {
157
+ "args": {
158
+ "should_epoch_stop": false,
159
+ "should_evaluate": false,
160
+ "should_log": false,
161
+ "should_save": true,
162
+ "should_training_stop": false
163
+ },
164
+ "attributes": {}
165
+ }
166
+ },
167
+ "total_flos": 114902240899680.0,
168
+ "train_batch_size": 16,
169
+ "trial_name": null,
170
+ "trial_params": null
171
+ }
checkpoint-300/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1bc94fc718c18b1d22783932c9849ceddacd004e03b9e5fce890a3ddf29409c
3
+ size 5432