Hugging Face's logo

xshubhamx
/
xlnet-base-cased

Text Classification
Transformers
TensorBoard
Safetensors
xlnet
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
xshubhamx commited on
Commit
339a66d
•
1 Parent(s): 2325f1c

Upload folder using huggingface_hub

Browse files
Files changed (10) hide show
  1. training_checkpoints/checkpoint-14146/config.json +78 -0
  2. training_checkpoints/checkpoint-14146/model.safetensors +3 -0
  3. training_checkpoints/checkpoint-14146/optimizer.pt +3 -0
  4. training_checkpoints/checkpoint-14146/rng_state.pth +3 -0
  5. training_checkpoints/checkpoint-14146/scheduler.pt +3 -0
  6. training_checkpoints/checkpoint-14146/special_tokens_map.json +19 -0
  7. training_checkpoints/checkpoint-14146/spiece.model +3 -0
  8. training_checkpoints/checkpoint-14146/tokenizer_config.json +94 -0
  9. training_checkpoints/checkpoint-14146/trainer_state.json +671 -0
  10. training_checkpoints/checkpoint-14146/training_args.bin +3 -0
training_checkpoints/checkpoint-14146/config.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlnet/xlnet-base-cased",
3
+ "architectures": [
4
+ "XLNetForSequenceClassification"
5
+ ],
6
+ "attn_type": "bi",
7
+ "bi_data": false,
8
+ "bos_token_id": 1,
9
+ "clamp_len": -1,
10
+ "d_head": 64,
11
+ "d_inner": 3072,
12
+ "d_model": 768,
13
+ "dropout": 0.1,
14
+ "end_n_top": 5,
15
+ "eos_token_id": 2,
16
+ "ff_activation": "gelu",
17
+ "id2label": {
18
+ "0": "Issue",
19
+ "1": "Court Discourse",
20
+ "2": "Conclusion",
21
+ "3": "Precedent Analysis",
22
+ "4": "Section Analysis",
23
+ "5": "Argument by Petitioner",
24
+ "6": "Fact",
25
+ "7": "Argument by Respondent",
26
+ "8": "Ratio",
27
+ "9": "Appellant",
28
+ "10": "Respondent",
29
+ "11": "Argument by Appellant",
30
+ "12": "Petitioner",
31
+ "13": "Judge",
32
+ "14": "Argument by Defendant"
33
+ },
34
+ "initializer_range": 0.02,
35
+ "label2id": {
36
+ "Appellant": 9,
37
+ "Argument by Appellant": 11,
38
+ "Argument by Defendant": 14,
39
+ "Argument by Petitioner": 5,
40
+ "Argument by Respondent": 7,
41
+ "Conclusion": 2,
42
+ "Court Discourse": 1,
43
+ "Fact": 6,
44
+ "Issue": 0,
45
+ "Judge": 13,
46
+ "Petitioner": 12,
47
+ "Precedent Analysis": 3,
48
+ "Ratio": 8,
49
+ "Respondent": 10,
50
+ "Section Analysis": 4
51
+ },
52
+ "layer_norm_eps": 1e-12,
53
+ "mem_len": null,
54
+ "model_type": "xlnet",
55
+ "n_head": 12,
56
+ "n_layer": 12,
57
+ "pad_token_id": 5,
58
+ "problem_type": "single_label_classification",
59
+ "reuse_len": null,
60
+ "same_length": false,
61
+ "start_n_top": 5,
62
+ "summary_activation": "tanh",
63
+ "summary_last_dropout": 0.1,
64
+ "summary_type": "last",
65
+ "summary_use_proj": true,
66
+ "task_specific_params": {
67
+ "text-generation": {
68
+ "do_sample": true,
69
+ "max_length": 250
70
+ }
71
+ },
72
+ "torch_dtype": "float32",
73
+ "transformers_version": "4.35.2",
74
+ "untie_r": true,
75
+ "use_mems_eval": true,
76
+ "use_mems_train": false,
77
+ "vocab_size": 32000
78
+ }
training_checkpoints/checkpoint-14146/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e996388c9acc2033267b8090fd852ca3eadf0e7c55f0a4a0ad4b01527d59c4ae
3
+ size 469304588
training_checkpoints/checkpoint-14146/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3764601457b85477dc80157b402e11e421531fd180837374818305df55049459
3
+ size 938733178
training_checkpoints/checkpoint-14146/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e94d0500fbd83d466f3751ee281cb87479b5965cec71e1d0bdcef4f1eb1a7324
3
+ size 14244
training_checkpoints/checkpoint-14146/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b5c67f549a4c3721fb07a7a161055de824bfa7a2489abb59dd69097beaac0d5
3
+ size 1064
training_checkpoints/checkpoint-14146/special_tokens_map.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<eop>",
4
+ "<eod>"
5
+ ],
6
+ "bos_token": "<s>",
7
+ "cls_token": "<cls>",
8
+ "eos_token": "</s>",
9
+ "mask_token": {
10
+ "content": "<mask>",
11
+ "lstrip": true,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<pad>",
17
+ "sep_token": "<sep>",
18
+ "unk_token": "<unk>"
19
+ }
training_checkpoints/checkpoint-14146/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f8c1c0bc2854d1af911a8550288c1258af5ba50277f3a5c829b98eb86fc5646
3
+ size 798011
training_checkpoints/checkpoint-14146/tokenizer_config.json ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<cls>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<sep>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "<pad>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "<mask>",
53
+ "lstrip": true,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "7": {
60
+ "content": "<eod>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "8": {
68
+ "content": "<eop>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ }
75
+ },
76
+ "additional_special_tokens": [
77
+ "<eop>",
78
+ "<eod>"
79
+ ],
80
+ "bos_token": "<s>",
81
+ "clean_up_tokenization_spaces": true,
82
+ "cls_token": "<cls>",
83
+ "do_lower_case": false,
84
+ "eos_token": "</s>",
85
+ "keep_accents": false,
86
+ "mask_token": "<mask>",
87
+ "model_max_length": 1000000000000000019884624838656,
88
+ "pad_token": "<pad>",
89
+ "remove_space": true,
90
+ "sep_token": "<sep>",
91
+ "sp_model_kwargs": {},
92
+ "tokenizer_class": "XLNetTokenizer",
93
+ "unk_token": "<unk>"
94
+ }
training_checkpoints/checkpoint-14146/trainer_state.json ADDED
@@ -0,0 +1,671 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7813861108366882,
3
+ "best_model_checkpoint": "xlnet-base-cased/checkpoint-12217",
4
+ "epoch": 22.0,
5
+ "eval_steps": 500,
6
+ "global_step": 14146,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.78,
13
+ "learning_rate": 4.871695178849145e-05,
14
+ "loss": 1.2613,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.7676219984508134,
20
+ "eval_f1_macro": 0.4818756771742453,
21
+ "eval_f1_micro": 0.7676219984508135,
22
+ "eval_f1_weighted": 0.7524385212708887,
23
+ "eval_loss": 0.775787353515625,
24
+ "eval_macro_fpr": 0.022019799606126652,
25
+ "eval_macro_sensitivity": 0.5128622254580788,
26
+ "eval_macro_specificity": 0.9823717840367622,
27
+ "eval_precision": 0.7672637518290021,
28
+ "eval_precision_macro": 0.5269420024270713,
29
+ "eval_recall": 0.7676219984508134,
30
+ "eval_recall_macro": 0.5128622254580788,
31
+ "eval_runtime": 65.0712,
32
+ "eval_samples_per_second": 19.84,
33
+ "eval_steps_per_second": 2.49,
34
+ "eval_weighted_fpr": 0.021165514321998025,
35
+ "eval_weighted_sensitivity": 0.7676219984508134,
36
+ "eval_weighted_specificity": 0.9679547621006213,
37
+ "step": 643
38
+ },
39
+ {
40
+ "epoch": 1.56,
41
+ "learning_rate": 4.7420943494038366e-05,
42
+ "loss": 0.7364,
43
+ "step": 1000
44
+ },
45
+ {
46
+ "epoch": 2.0,
47
+ "eval_accuracy": 0.8071262587141751,
48
+ "eval_f1_macro": 0.701878478303997,
49
+ "eval_f1_micro": 0.8071262587141751,
50
+ "eval_f1_weighted": 0.8012788916547595,
51
+ "eval_loss": 0.6754755973815918,
52
+ "eval_macro_fpr": 0.01739858713969909,
53
+ "eval_macro_sensitivity": 0.6971761972643127,
54
+ "eval_macro_specificity": 0.9854830758512745,
55
+ "eval_precision": 0.8087721671110009,
56
+ "eval_precision_macro": 0.7425135911700289,
57
+ "eval_recall": 0.8071262587141751,
58
+ "eval_recall_macro": 0.6971761972643127,
59
+ "eval_runtime": 86.774,
60
+ "eval_samples_per_second": 14.878,
61
+ "eval_steps_per_second": 1.867,
62
+ "eval_weighted_fpr": 0.016782368403316036,
63
+ "eval_weighted_sensitivity": 0.8071262587141751,
64
+ "eval_weighted_specificity": 0.9751198790549438,
65
+ "step": 1286
66
+ },
67
+ {
68
+ "epoch": 2.33,
69
+ "learning_rate": 4.612493519958528e-05,
70
+ "loss": 0.6021,
71
+ "step": 1500
72
+ },
73
+ {
74
+ "epoch": 3.0,
75
+ "eval_accuracy": 0.8063516653756778,
76
+ "eval_f1_macro": 0.722931923188587,
77
+ "eval_f1_micro": 0.8063516653756778,
78
+ "eval_f1_weighted": 0.8013697737227732,
79
+ "eval_loss": 0.8442708253860474,
80
+ "eval_macro_fpr": 0.01757802934678216,
81
+ "eval_macro_sensitivity": 0.7262014539622089,
82
+ "eval_macro_specificity": 0.9852110484486459,
83
+ "eval_precision": 0.8016312862866737,
84
+ "eval_precision_macro": 0.7269969408457856,
85
+ "eval_recall": 0.8063516653756778,
86
+ "eval_recall_macro": 0.7262014539622089,
87
+ "eval_runtime": 89.8454,
88
+ "eval_samples_per_second": 14.369,
89
+ "eval_steps_per_second": 1.803,
90
+ "eval_weighted_fpr": 0.01686454398273071,
91
+ "eval_weighted_sensitivity": 0.8063516653756778,
92
+ "eval_weighted_specificity": 0.9718140613540133,
93
+ "step": 1929
94
+ },
95
+ {
96
+ "epoch": 3.11,
97
+ "learning_rate": 4.4828926905132196e-05,
98
+ "loss": 0.5435,
99
+ "step": 2000
100
+ },
101
+ {
102
+ "epoch": 3.89,
103
+ "learning_rate": 4.353551062726802e-05,
104
+ "loss": 0.4361,
105
+ "step": 2500
106
+ },
107
+ {
108
+ "epoch": 4.0,
109
+ "eval_accuracy": 0.8001549186676995,
110
+ "eval_f1_macro": 0.7051095861561788,
111
+ "eval_f1_micro": 0.8001549186676995,
112
+ "eval_f1_weighted": 0.7970808578587494,
113
+ "eval_loss": 0.8849796056747437,
114
+ "eval_macro_fpr": 0.017973543700983616,
115
+ "eval_macro_sensitivity": 0.704754303632947,
116
+ "eval_macro_specificity": 0.984883284344937,
117
+ "eval_precision": 0.8001040615771999,
118
+ "eval_precision_macro": 0.716655759638538,
119
+ "eval_recall": 0.8001549186676995,
120
+ "eval_recall_macro": 0.704754303632947,
121
+ "eval_runtime": 88.029,
122
+ "eval_samples_per_second": 14.666,
123
+ "eval_steps_per_second": 1.84,
124
+ "eval_weighted_fpr": 0.017527173913043478,
125
+ "eval_weighted_sensitivity": 0.8001549186676995,
126
+ "eval_weighted_specificity": 0.9730943465063553,
127
+ "step": 2572
128
+ },
129
+ {
130
+ "epoch": 4.67,
131
+ "learning_rate": 4.223950233281493e-05,
132
+ "loss": 0.3359,
133
+ "step": 3000
134
+ },
135
+ {
136
+ "epoch": 5.0,
137
+ "eval_accuracy": 0.801704105344694,
138
+ "eval_f1_macro": 0.6458763793901992,
139
+ "eval_f1_micro": 0.801704105344694,
140
+ "eval_f1_weighted": 0.7961730342415405,
141
+ "eval_loss": 1.126444935798645,
142
+ "eval_macro_fpr": 0.01805997413754306,
143
+ "eval_macro_sensitivity": 0.6681366041180199,
144
+ "eval_macro_specificity": 0.9849908327913178,
145
+ "eval_precision": 0.7981459541145973,
146
+ "eval_precision_macro": 0.6531140613829887,
147
+ "eval_recall": 0.801704105344694,
148
+ "eval_recall_macro": 0.6681366041180199,
149
+ "eval_runtime": 90.8127,
150
+ "eval_samples_per_second": 14.216,
151
+ "eval_steps_per_second": 1.784,
152
+ "eval_weighted_fpr": 0.0173606401736064,
153
+ "eval_weighted_sensitivity": 0.801704105344694,
154
+ "eval_weighted_specificity": 0.973158386525071,
155
+ "step": 3215
156
+ },
157
+ {
158
+ "epoch": 5.44,
159
+ "learning_rate": 4.0943494038361847e-05,
160
+ "loss": 0.2827,
161
+ "step": 3500
162
+ },
163
+ {
164
+ "epoch": 6.0,
165
+ "eval_accuracy": 0.7993803253292022,
166
+ "eval_f1_macro": 0.7042383323872946,
167
+ "eval_f1_micro": 0.7993803253292022,
168
+ "eval_f1_weighted": 0.7951558065494785,
169
+ "eval_loss": 1.1471006870269775,
170
+ "eval_macro_fpr": 0.01833120632003448,
171
+ "eval_macro_sensitivity": 0.692160115457962,
172
+ "eval_macro_specificity": 0.9845339432297603,
173
+ "eval_precision": 0.8091520232110664,
174
+ "eval_precision_macro": 0.7389074945114087,
175
+ "eval_recall": 0.7993803253292022,
176
+ "eval_recall_macro": 0.692160115457962,
177
+ "eval_runtime": 89.506,
178
+ "eval_samples_per_second": 14.424,
179
+ "eval_steps_per_second": 1.81,
180
+ "eval_weighted_fpr": 0.017610661589719183,
181
+ "eval_weighted_sensitivity": 0.7993803253292022,
182
+ "eval_weighted_specificity": 0.9686288231172028,
183
+ "step": 3858
184
+ },
185
+ {
186
+ "epoch": 6.22,
187
+ "learning_rate": 3.964748574390876e-05,
188
+ "loss": 0.2626,
189
+ "step": 4000
190
+ },
191
+ {
192
+ "epoch": 7.0,
193
+ "learning_rate": 3.835147744945568e-05,
194
+ "loss": 0.1945,
195
+ "step": 4500
196
+ },
197
+ {
198
+ "epoch": 7.0,
199
+ "eval_accuracy": 0.814872192099148,
200
+ "eval_f1_macro": 0.7667275846579111,
201
+ "eval_f1_micro": 0.814872192099148,
202
+ "eval_f1_weighted": 0.812156980007075,
203
+ "eval_loss": 1.1841164827346802,
204
+ "eval_macro_fpr": 0.016569799909363286,
205
+ "eval_macro_sensitivity": 0.7598143558862378,
206
+ "eval_macro_specificity": 0.9859673331635007,
207
+ "eval_precision": 0.8128843369221012,
208
+ "eval_precision_macro": 0.7850186311075981,
209
+ "eval_recall": 0.814872192099148,
210
+ "eval_recall_macro": 0.7598143558862378,
211
+ "eval_runtime": 89.1729,
212
+ "eval_samples_per_second": 14.477,
213
+ "eval_steps_per_second": 1.817,
214
+ "eval_weighted_fpr": 0.015968463954032203,
215
+ "eval_weighted_sensitivity": 0.814872192099148,
216
+ "eval_weighted_specificity": 0.974637805353365,
217
+ "step": 4501
218
+ },
219
+ {
220
+ "epoch": 7.78,
221
+ "learning_rate": 3.705546915500259e-05,
222
+ "loss": 0.1286,
223
+ "step": 5000
224
+ },
225
+ {
226
+ "epoch": 8.0,
227
+ "eval_accuracy": 0.8079008520526724,
228
+ "eval_f1_macro": 0.728267610383121,
229
+ "eval_f1_micro": 0.8079008520526724,
230
+ "eval_f1_weighted": 0.8067061599230408,
231
+ "eval_loss": 1.3231384754180908,
232
+ "eval_macro_fpr": 0.01714064720569306,
233
+ "eval_macro_sensitivity": 0.7216321376051643,
234
+ "eval_macro_specificity": 0.9855732952526467,
235
+ "eval_precision": 0.8105008603379217,
236
+ "eval_precision_macro": 0.763038482726323,
237
+ "eval_recall": 0.8079008520526724,
238
+ "eval_recall_macro": 0.7216321376051643,
239
+ "eval_runtime": 93.4716,
240
+ "eval_samples_per_second": 13.812,
241
+ "eval_steps_per_second": 1.733,
242
+ "eval_weighted_fpr": 0.0167003367003367,
243
+ "eval_weighted_sensitivity": 0.8079008520526724,
244
+ "eval_weighted_specificity": 0.9756985767370285,
245
+ "step": 5144
246
+ },
247
+ {
248
+ "epoch": 8.55,
249
+ "learning_rate": 3.576205287713841e-05,
250
+ "loss": 0.1304,
251
+ "step": 5500
252
+ },
253
+ {
254
+ "epoch": 9.0,
255
+ "eval_accuracy": 0.8102246320681642,
256
+ "eval_f1_macro": 0.7569552546114842,
257
+ "eval_f1_micro": 0.8102246320681642,
258
+ "eval_f1_weighted": 0.808840893500485,
259
+ "eval_loss": 1.3869109153747559,
260
+ "eval_macro_fpr": 0.017055465242864547,
261
+ "eval_macro_sensitivity": 0.7602881393177737,
262
+ "eval_macro_specificity": 0.9856184320870693,
263
+ "eval_precision": 0.811846243162855,
264
+ "eval_precision_macro": 0.7704913288832418,
265
+ "eval_recall": 0.8102246320681642,
266
+ "eval_recall_macro": 0.7602881393177737,
267
+ "eval_runtime": 88.7368,
268
+ "eval_samples_per_second": 14.549,
269
+ "eval_steps_per_second": 1.826,
270
+ "eval_weighted_fpr": 0.016455101081335213,
271
+ "eval_weighted_sensitivity": 0.8102246320681642,
272
+ "eval_weighted_specificity": 0.9740518492378762,
273
+ "step": 5787
274
+ },
275
+ {
276
+ "epoch": 9.33,
277
+ "learning_rate": 3.4466044582685334e-05,
278
+ "loss": 0.0875,
279
+ "step": 6000
280
+ },
281
+ {
282
+ "epoch": 10.0,
283
+ "eval_accuracy": 0.7823392718822618,
284
+ "eval_f1_macro": 0.7192346851166359,
285
+ "eval_f1_micro": 0.7823392718822618,
286
+ "eval_f1_weighted": 0.7816836829450283,
287
+ "eval_loss": 1.690091609954834,
288
+ "eval_macro_fpr": 0.01985842187936775,
289
+ "eval_macro_sensitivity": 0.7020361329217759,
290
+ "eval_macro_specificity": 0.9833585449617043,
291
+ "eval_precision": 0.7931868181724199,
292
+ "eval_precision_macro": 0.7600588253545632,
293
+ "eval_recall": 0.7823392718822618,
294
+ "eval_recall_macro": 0.7020361329217759,
295
+ "eval_runtime": 88.4203,
296
+ "eval_samples_per_second": 14.601,
297
+ "eval_steps_per_second": 1.832,
298
+ "eval_weighted_fpr": 0.019485472574717427,
299
+ "eval_weighted_sensitivity": 0.7823392718822618,
300
+ "eval_weighted_specificity": 0.9680389025433043,
301
+ "step": 6430
302
+ },
303
+ {
304
+ "epoch": 10.11,
305
+ "learning_rate": 3.317003628823225e-05,
306
+ "loss": 0.1088,
307
+ "step": 6500
308
+ },
309
+ {
310
+ "epoch": 10.89,
311
+ "learning_rate": 3.187402799377916e-05,
312
+ "loss": 0.1075,
313
+ "step": 7000
314
+ },
315
+ {
316
+ "epoch": 11.0,
317
+ "eval_accuracy": 0.7978311386522076,
318
+ "eval_f1_macro": 0.7470393699186935,
319
+ "eval_f1_micro": 0.7978311386522076,
320
+ "eval_f1_weighted": 0.793529238632398,
321
+ "eval_loss": 1.6517162322998047,
322
+ "eval_macro_fpr": 0.01832601410957563,
323
+ "eval_macro_sensitivity": 0.7566567183934103,
324
+ "eval_macro_specificity": 0.9849074579220182,
325
+ "eval_precision": 0.8021421826960871,
326
+ "eval_precision_macro": 0.7513026067404466,
327
+ "eval_recall": 0.7978311386522076,
328
+ "eval_recall_macro": 0.7566567183934103,
329
+ "eval_runtime": 91.1007,
330
+ "eval_samples_per_second": 14.171,
331
+ "eval_steps_per_second": 1.778,
332
+ "eval_weighted_fpr": 0.017778080512226686,
333
+ "eval_weighted_sensitivity": 0.7978311386522076,
334
+ "eval_weighted_specificity": 0.9757807301780667,
335
+ "step": 7073
336
+ },
337
+ {
338
+ "epoch": 11.66,
339
+ "learning_rate": 3.057801969932608e-05,
340
+ "loss": 0.0632,
341
+ "step": 7500
342
+ },
343
+ {
344
+ "epoch": 12.0,
345
+ "eval_accuracy": 0.814872192099148,
346
+ "eval_f1_macro": 0.7706785605409691,
347
+ "eval_f1_micro": 0.814872192099148,
348
+ "eval_f1_weighted": 0.814999517133868,
349
+ "eval_loss": 1.528985857963562,
350
+ "eval_macro_fpr": 0.016687805753048134,
351
+ "eval_macro_sensitivity": 0.7772039784617947,
352
+ "eval_macro_specificity": 0.9859096029272495,
353
+ "eval_precision": 0.8184480381747821,
354
+ "eval_precision_macro": 0.7745990994843823,
355
+ "eval_recall": 0.814872192099148,
356
+ "eval_recall_macro": 0.7772039784617947,
357
+ "eval_runtime": 89.9659,
358
+ "eval_samples_per_second": 14.35,
359
+ "eval_steps_per_second": 1.801,
360
+ "eval_weighted_fpr": 0.015968463954032203,
361
+ "eval_weighted_sensitivity": 0.814872192099148,
362
+ "eval_weighted_specificity": 0.9737718518095959,
363
+ "step": 7716
364
+ },
365
+ {
366
+ "epoch": 12.44,
367
+ "learning_rate": 2.92846034214619e-05,
368
+ "loss": 0.0565,
369
+ "step": 8000
370
+ },
371
+ {
372
+ "epoch": 13.0,
373
+ "eval_accuracy": 0.8063516653756778,
374
+ "eval_f1_macro": 0.7536745391279389,
375
+ "eval_f1_micro": 0.8063516653756778,
376
+ "eval_f1_weighted": 0.806105583642158,
377
+ "eval_loss": 1.5766452550888062,
378
+ "eval_macro_fpr": 0.017353934865295607,
379
+ "eval_macro_sensitivity": 0.7627918284863161,
380
+ "eval_macro_specificity": 0.9855508104644062,
381
+ "eval_precision": 0.8106650569621797,
382
+ "eval_precision_macro": 0.7527919670677403,
383
+ "eval_recall": 0.8063516653756778,
384
+ "eval_recall_macro": 0.7627918284863161,
385
+ "eval_runtime": 87.0044,
386
+ "eval_samples_per_second": 14.838,
387
+ "eval_steps_per_second": 1.862,
388
+ "eval_weighted_fpr": 0.01686454398273071,
389
+ "eval_weighted_sensitivity": 0.8063516653756778,
390
+ "eval_weighted_specificity": 0.9769104915904122,
391
+ "step": 8359
392
+ },
393
+ {
394
+ "epoch": 13.22,
395
+ "learning_rate": 2.7988595127008814e-05,
396
+ "loss": 0.0611,
397
+ "step": 8500
398
+ },
399
+ {
400
+ "epoch": 14.0,
401
+ "learning_rate": 2.669258683255573e-05,
402
+ "loss": 0.0504,
403
+ "step": 9000
404
+ },
405
+ {
406
+ "epoch": 14.0,
407
+ "eval_accuracy": 0.8048024786986832,
408
+ "eval_f1_macro": 0.7553476960817118,
409
+ "eval_f1_micro": 0.804802478698683,
410
+ "eval_f1_weighted": 0.8045680080251187,
411
+ "eval_loss": 1.754842758178711,
412
+ "eval_macro_fpr": 0.0173894746246557,
413
+ "eval_macro_sensitivity": 0.7701954697850913,
414
+ "eval_macro_specificity": 0.9854203302407508,
415
+ "eval_precision": 0.8100370206947073,
416
+ "eval_precision_macro": 0.7569340956810083,
417
+ "eval_recall": 0.8048024786986832,
418
+ "eval_recall_macro": 0.7701954697850913,
419
+ "eval_runtime": 87.2595,
420
+ "eval_samples_per_second": 14.795,
421
+ "eval_steps_per_second": 1.857,
422
+ "eval_weighted_fpr": 0.017029328287606435,
423
+ "eval_weighted_sensitivity": 0.8048024786986832,
424
+ "eval_weighted_specificity": 0.9765024749125794,
425
+ "step": 9002
426
+ },
427
+ {
428
+ "epoch": 14.77,
429
+ "learning_rate": 2.5396578538102643e-05,
430
+ "loss": 0.0295,
431
+ "step": 9500
432
+ },
433
+ {
434
+ "epoch": 15.0,
435
+ "eval_accuracy": 0.8102246320681642,
436
+ "eval_f1_macro": 0.760967233946951,
437
+ "eval_f1_micro": 0.8102246320681642,
438
+ "eval_f1_weighted": 0.8140816963742711,
439
+ "eval_loss": 1.7570178508758545,
440
+ "eval_macro_fpr": 0.016848493530959043,
441
+ "eval_macro_sensitivity": 0.7610604622194231,
442
+ "eval_macro_specificity": 0.9858148957915706,
443
+ "eval_precision": 0.8226139584587638,
444
+ "eval_precision_macro": 0.7705404207703173,
445
+ "eval_recall": 0.8102246320681642,
446
+ "eval_recall_macro": 0.7610604622194231,
447
+ "eval_runtime": 89.5369,
448
+ "eval_samples_per_second": 14.419,
449
+ "eval_steps_per_second": 1.809,
450
+ "eval_weighted_fpr": 0.016455101081335213,
451
+ "eval_weighted_sensitivity": 0.8102246320681642,
452
+ "eval_weighted_specificity": 0.9769988048053938,
453
+ "step": 9645
454
+ },
455
+ {
456
+ "epoch": 15.55,
457
+ "learning_rate": 2.410057024364956e-05,
458
+ "loss": 0.0338,
459
+ "step": 10000
460
+ },
461
+ {
462
+ "epoch": 16.0,
463
+ "eval_accuracy": 0.8109992254066615,
464
+ "eval_f1_macro": 0.7612941688912773,
465
+ "eval_f1_micro": 0.8109992254066615,
466
+ "eval_f1_weighted": 0.8100237367109931,
467
+ "eval_loss": 1.7394386529922485,
468
+ "eval_macro_fpr": 0.0167552939703591,
469
+ "eval_macro_sensitivity": 0.7659323423256559,
470
+ "eval_macro_specificity": 0.9858976267005801,
471
+ "eval_precision": 0.8138390585578686,
472
+ "eval_precision_macro": 0.7638742891195117,
473
+ "eval_recall": 0.8109992254066615,
474
+ "eval_recall_macro": 0.7659323423256559,
475
+ "eval_runtime": 88.2753,
476
+ "eval_samples_per_second": 14.625,
477
+ "eval_steps_per_second": 1.835,
478
+ "eval_weighted_fpr": 0.016373641121997046,
479
+ "eval_weighted_sensitivity": 0.8109992254066615,
480
+ "eval_weighted_specificity": 0.9774651751020407,
481
+ "step": 10288
482
+ },
483
+ {
484
+ "epoch": 16.33,
485
+ "learning_rate": 2.2807153965785383e-05,
486
+ "loss": 0.0444,
487
+ "step": 10500
488
+ },
489
+ {
490
+ "epoch": 17.0,
491
+ "eval_accuracy": 0.8117738187451587,
492
+ "eval_f1_macro": 0.7457173379536453,
493
+ "eval_f1_micro": 0.8117738187451587,
494
+ "eval_f1_weighted": 0.8129470595277309,
495
+ "eval_loss": 1.7974809408187866,
496
+ "eval_macro_fpr": 0.016811586751854603,
497
+ "eval_macro_sensitivity": 0.7609908124543953,
498
+ "eval_macro_specificity": 0.9859494204465505,
499
+ "eval_precision": 0.8200630062296891,
500
+ "eval_precision_macro": 0.7510908703409428,
501
+ "eval_recall": 0.8117738187451587,
502
+ "eval_recall_macro": 0.7609908124543953,
503
+ "eval_runtime": 92.8836,
504
+ "eval_samples_per_second": 13.899,
505
+ "eval_steps_per_second": 1.744,
506
+ "eval_weighted_fpr": 0.016292323164599398,
507
+ "eval_weighted_sensitivity": 0.8117738187451587,
508
+ "eval_weighted_specificity": 0.9774674879531003,
509
+ "step": 10931
510
+ },
511
+ {
512
+ "epoch": 17.11,
513
+ "learning_rate": 2.1511145671332298e-05,
514
+ "loss": 0.017,
515
+ "step": 11000
516
+ },
517
+ {
518
+ "epoch": 17.88,
519
+ "learning_rate": 2.0215137376879212e-05,
520
+ "loss": 0.0397,
521
+ "step": 11500
522
+ },
523
+ {
524
+ "epoch": 18.0,
525
+ "eval_accuracy": 0.814872192099148,
526
+ "eval_f1_macro": 0.7553030972375019,
527
+ "eval_f1_micro": 0.814872192099148,
528
+ "eval_f1_weighted": 0.8129982672337318,
529
+ "eval_loss": 1.692070722579956,
530
+ "eval_macro_fpr": 0.01648801618238916,
531
+ "eval_macro_sensitivity": 0.7854174817784654,
532
+ "eval_macro_specificity": 0.986188960440481,
533
+ "eval_precision": 0.8203469277405308,
534
+ "eval_precision_macro": 0.7540048119736065,
535
+ "eval_recall": 0.814872192099148,
536
+ "eval_recall_macro": 0.7854174817784654,
537
+ "eval_runtime": 89.1118,
538
+ "eval_samples_per_second": 14.487,
539
+ "eval_steps_per_second": 1.818,
540
+ "eval_weighted_fpr": 0.015968463954032203,
541
+ "eval_weighted_sensitivity": 0.814872192099148,
542
+ "eval_weighted_specificity": 0.9779622145080659,
543
+ "step": 11574
544
+ },
545
+ {
546
+ "epoch": 18.66,
547
+ "learning_rate": 1.891912908242613e-05,
548
+ "loss": 0.0356,
549
+ "step": 12000
550
+ },
551
+ {
552
+ "epoch": 19.0,
553
+ "eval_accuracy": 0.8272656855151046,
554
+ "eval_f1_macro": 0.7813861108366882,
555
+ "eval_f1_micro": 0.8272656855151046,
556
+ "eval_f1_weighted": 0.826538691051554,
557
+ "eval_loss": 1.6908154487609863,
558
+ "eval_macro_fpr": 0.01519208147936786,
559
+ "eval_macro_sensitivity": 0.7991667789217406,
560
+ "eval_macro_specificity": 0.9870458274462965,
561
+ "eval_precision": 0.8307223507185943,
562
+ "eval_precision_macro": 0.7763966212643805,
563
+ "eval_recall": 0.8272656855151046,
564
+ "eval_recall_macro": 0.7991667789217406,
565
+ "eval_runtime": 87.1936,
566
+ "eval_samples_per_second": 14.806,
567
+ "eval_steps_per_second": 1.858,
568
+ "eval_weighted_fpr": 0.014695222405271829,
569
+ "eval_weighted_sensitivity": 0.8272656855151046,
570
+ "eval_weighted_specificity": 0.9784217261793432,
571
+ "step": 12217
572
+ },
573
+ {
574
+ "epoch": 19.44,
575
+ "learning_rate": 1.7623120787973045e-05,
576
+ "loss": 0.0306,
577
+ "step": 12500
578
+ },
579
+ {
580
+ "epoch": 20.0,
581
+ "eval_accuracy": 0.8179705654531371,
582
+ "eval_f1_macro": 0.7619799923440557,
583
+ "eval_f1_micro": 0.817970565453137,
584
+ "eval_f1_weighted": 0.8165762317081299,
585
+ "eval_loss": 1.8374216556549072,
586
+ "eval_macro_fpr": 0.016177559752434546,
587
+ "eval_macro_sensitivity": 0.7756239390284622,
588
+ "eval_macro_specificity": 0.9863402294201706,
589
+ "eval_precision": 0.8207768510844915,
590
+ "eval_precision_macro": 0.7634613762524876,
591
+ "eval_recall": 0.8179705654531371,
592
+ "eval_recall_macro": 0.7756239390284622,
593
+ "eval_runtime": 90.845,
594
+ "eval_samples_per_second": 14.211,
595
+ "eval_steps_per_second": 1.783,
596
+ "eval_weighted_fpr": 0.01564684732671949,
597
+ "eval_weighted_sensitivity": 0.8179705654531371,
598
+ "eval_weighted_specificity": 0.9771328758494231,
599
+ "step": 12860
600
+ },
601
+ {
602
+ "epoch": 20.22,
603
+ "learning_rate": 1.6329704510108863e-05,
604
+ "loss": 0.0212,
605
+ "step": 13000
606
+ },
607
+ {
608
+ "epoch": 21.0,
609
+ "learning_rate": 1.5033696215655781e-05,
610
+ "loss": 0.0234,
611
+ "step": 13500
612
+ },
613
+ {
614
+ "epoch": 21.0,
615
+ "eval_accuracy": 0.8195197521301317,
616
+ "eval_f1_macro": 0.7713314772989432,
617
+ "eval_f1_micro": 0.8195197521301317,
618
+ "eval_f1_weighted": 0.8173803797431164,
619
+ "eval_loss": 1.7737590074539185,
620
+ "eval_macro_fpr": 0.016026463371050827,
621
+ "eval_macro_sensitivity": 0.7602260272694004,
622
+ "eval_macro_specificity": 0.986365365175067,
623
+ "eval_precision": 0.8184750402268075,
624
+ "eval_precision_macro": 0.7946623933037265,
625
+ "eval_recall": 0.8195197521301317,
626
+ "eval_recall_macro": 0.7602260272694004,
627
+ "eval_runtime": 91.8609,
628
+ "eval_samples_per_second": 14.054,
629
+ "eval_steps_per_second": 1.764,
630
+ "eval_weighted_fpr": 0.01548687271518777,
631
+ "eval_weighted_sensitivity": 0.8195197521301317,
632
+ "eval_weighted_specificity": 0.9759607254958742,
633
+ "step": 13503
634
+ },
635
+ {
636
+ "epoch": 21.77,
637
+ "learning_rate": 1.3737687921202696e-05,
638
+ "loss": 0.0091,
639
+ "step": 14000
640
+ },
641
+ {
642
+ "epoch": 22.0,
643
+ "eval_accuracy": 0.8171959721146398,
644
+ "eval_f1_macro": 0.7654257885617937,
645
+ "eval_f1_micro": 0.8171959721146398,
646
+ "eval_f1_weighted": 0.8142875910554035,
647
+ "eval_loss": 1.8536922931671143,
648
+ "eval_macro_fpr": 0.01629310015159196,
649
+ "eval_macro_sensitivity": 0.764643422315937,
650
+ "eval_macro_specificity": 0.9862407504253736,
651
+ "eval_precision": 0.8166701024955205,
652
+ "eval_precision_macro": 0.7732430914536168,
653
+ "eval_recall": 0.8171959721146398,
654
+ "eval_recall_macro": 0.764643422315937,
655
+ "eval_runtime": 90.6571,
656
+ "eval_samples_per_second": 14.24,
657
+ "eval_steps_per_second": 1.787,
658
+ "eval_weighted_fpr": 0.015727042516326804,
659
+ "eval_weighted_sensitivity": 0.8171959721146398,
660
+ "eval_weighted_specificity": 0.9764152842659637,
661
+ "step": 14146
662
+ }
663
+ ],
664
+ "logging_steps": 500,
665
+ "max_steps": 19290,
666
+ "num_train_epochs": 30,
667
+ "save_steps": 500,
668
+ "total_flos": 3.2205198703620096e+16,
669
+ "trial_name": null,
670
+ "trial_params": null
671
+ }
training_checkpoints/checkpoint-14146/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec20e9f8adfcfee3337ee75e60d11aa0228a2bd24494baa212e8cd20722381d4
3
+ size 4600