Hugging Face's logo

mehrshadk
/
sport-DEBERTL-seed5-lr1e-05

Safetensors
deberta
Model card Files Community
mehrshadk commited on
Commit
e5156b8
·
verified ·
1 Parent(s): 8a39428

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-large",
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": 1024,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 4096,
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": 16,
18
+ "num_hidden_layers": 24,
19
+ "pad_token_id": 0,
20
+ "pooler_dropout": 0,
21
+ "pooler_hidden_act": "gelu",
22
+ "pooler_hidden_size": 1024,
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 sha256:8fa7b1e2740a04b2f32b5ce81c0250130de88305b95fb5cb5362c47f30b742c8
3
+ size 1624907048
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": 7.457424163818359,
14
+ "learning_rate": 9.166666666666666e-06,
15
+ "loss": 0.6324,
16
+ "step": 50
17
+ },
18
+ {
19
+ "epoch": 0.5,
20
+ "eval_sport_AUC": 0.8304120879120879,
21
+ "eval_sport_accuracy": 0.65,
22
+ "eval_sport_f1": 0.0,
23
+ "eval_sport_loss": 0.5250802040100098,
24
+ "eval_sport_macro_f1": 0.3939393939393939,
25
+ "eval_sport_micro_f1": 0.65,
26
+ "eval_sport_precision": 0.0,
27
+ "eval_sport_recall": 0.0,
28
+ "eval_sport_runtime": 1.1394,
29
+ "eval_sport_samples_per_second": 351.062,
30
+ "eval_sport_specificity": 1.0,
31
+ "eval_sport_steps_per_second": 0.878,
32
+ "step": 50
33
+ },
34
+ {
35
+ "epoch": 1.0,
36
+ "grad_norm": 5.422190189361572,
37
+ "learning_rate": 8.333333333333334e-06,
38
+ "loss": 0.5076,
39
+ "step": 100
40
+ },
41
+ {
42
+ "epoch": 1.0,
43
+ "eval_sport_AUC": 0.8500274725274726,
44
+ "eval_sport_accuracy": 0.7825,
45
+ "eval_sport_f1": 0.6448979591836734,
46
+ "eval_sport_loss": 0.5157707929611206,
47
+ "eval_sport_macro_f1": 0.7440706012134584,
48
+ "eval_sport_micro_f1": 0.7825,
49
+ "eval_sport_precision": 0.7523809523809524,
50
+ "eval_sport_recall": 0.5642857142857143,
51
+ "eval_sport_runtime": 1.1662,
52
+ "eval_sport_samples_per_second": 343.005,
53
+ "eval_sport_specificity": 0.9,
54
+ "eval_sport_steps_per_second": 0.858,
55
+ "step": 100
56
+ },
57
+ {
58
+ "epoch": 1.5,
59
+ "grad_norm": 13.851410865783691,
60
+ "learning_rate": 7.500000000000001e-06,
61
+ "loss": 0.4243,
62
+ "step": 150
63
+ },
64
+ {
65
+ "epoch": 1.5,
66
+ "eval_sport_AUC": 0.8775,
67
+ "eval_sport_accuracy": 0.77,
68
+ "eval_sport_f1": 0.7341040462427746,
69
+ "eval_sport_loss": 0.435852974653244,
70
+ "eval_sport_macro_f1": 0.7657304372183036,
71
+ "eval_sport_micro_f1": 0.77,
72
+ "eval_sport_precision": 0.616504854368932,
73
+ "eval_sport_recall": 0.9071428571428571,
74
+ "eval_sport_runtime": 1.1657,
75
+ "eval_sport_samples_per_second": 343.153,
76
+ "eval_sport_specificity": 0.6961538461538461,
77
+ "eval_sport_steps_per_second": 0.858,
78
+ "step": 150
79
+ },
80
+ {
81
+ "epoch": 2.0,
82
+ "grad_norm": 13.909685134887695,
83
+ "learning_rate": 6.666666666666667e-06,
84
+ "loss": 0.4124,
85
+ "step": 200
86
+ },
87
+ {
88
+ "epoch": 2.0,
89
+ "eval_sport_AUC": 0.8836813186813187,
90
+ "eval_sport_accuracy": 0.8125,
91
+ "eval_sport_f1": 0.7232472324723247,
92
+ "eval_sport_loss": 0.43182089924812317,
93
+ "eval_sport_macro_f1": 0.7907351474270886,
94
+ "eval_sport_micro_f1": 0.8125,
95
+ "eval_sport_precision": 0.7480916030534351,
96
+ "eval_sport_recall": 0.7,
97
+ "eval_sport_runtime": 1.1592,
98
+ "eval_sport_samples_per_second": 345.066,
99
+ "eval_sport_specificity": 0.8730769230769231,
100
+ "eval_sport_steps_per_second": 0.863,
101
+ "step": 200
102
+ },
103
+ {
104
+ "epoch": 2.5,
105
+ "grad_norm": 6.286098003387451,
106
+ "learning_rate": 5.833333333333334e-06,
107
+ "loss": 0.3136,
108
+ "step": 250
109
+ },
110
+ {
111
+ "epoch": 2.5,
112
+ "eval_sport_AUC": 0.8988736263736266,
113
+ "eval_sport_accuracy": 0.8075,
114
+ "eval_sport_f1": 0.7353951890034365,
115
+ "eval_sport_loss": 0.410043865442276,
116
+ "eval_sport_macro_f1": 0.7920590876254903,
117
+ "eval_sport_micro_f1": 0.8075,
118
+ "eval_sport_precision": 0.7086092715231788,
119
+ "eval_sport_recall": 0.7642857142857142,
120
+ "eval_sport_runtime": 1.1531,
121
+ "eval_sport_samples_per_second": 346.882,
122
+ "eval_sport_specificity": 0.8307692307692308,
123
+ "eval_sport_steps_per_second": 0.867,
124
+ "step": 250
125
+ },
126
+ {
127
+ "epoch": 3.0,
128
+ "grad_norm": 12.10146427154541,
129
+ "learning_rate": 5e-06,
130
+ "loss": 0.3356,
131
+ "step": 300
132
+ },
133
+ {
134
+ "epoch": 3.0,
135
+ "eval_sport_AUC": 0.8957967032967034,
136
+ "eval_sport_accuracy": 0.7925,
137
+ "eval_sport_f1": 0.7492447129909365,
138
+ "eval_sport_loss": 0.41360825300216675,
139
+ "eval_sport_macro_f1": 0.7861362157705216,
140
+ "eval_sport_micro_f1": 0.7925,
141
+ "eval_sport_precision": 0.6492146596858639,
142
+ "eval_sport_recall": 0.8857142857142857,
143
+ "eval_sport_runtime": 1.1571,
144
+ "eval_sport_samples_per_second": 345.688,
145
+ "eval_sport_specificity": 0.7423076923076923,
146
+ "eval_sport_steps_per_second": 0.864,
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": 407201659544160.0,
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 sha256:89ea036e31dedf09ee41ba848e76f18b84cb49b9929a5f2845bdf3506e9220fa
3
+ size 5432