Upload folder using huggingface_hub
Browse files- training_checkpoints/checkpoint-1344/added_tokens.json +3 -0
- training_checkpoints/checkpoint-1344/config.json +38 -0
- training_checkpoints/checkpoint-1344/model.safetensors +3 -0
- training_checkpoints/checkpoint-1344/optimizer.pt +3 -0
- training_checkpoints/checkpoint-1344/rng_state.pth +3 -0
- training_checkpoints/checkpoint-1344/scheduler.pt +3 -0
- training_checkpoints/checkpoint-1344/special_tokens_map.json +13 -0
- training_checkpoints/checkpoint-1344/tokenizer.json +0 -0
- training_checkpoints/checkpoint-1344/tokenizer_config.json +63 -0
- training_checkpoints/checkpoint-1344/trainer_state.json +167 -0
- training_checkpoints/checkpoint-1344/training_args.bin +3 -0
- training_checkpoints/checkpoint-1344/vocab.txt +0 -0
training_checkpoints/checkpoint-1344/added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<pad>": 28996
|
3 |
+
}
|
training_checkpoints/checkpoint-1344/config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert/distilbert-base-cased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"id2label": {
|
12 |
+
"0": "positive",
|
13 |
+
"1": "negative",
|
14 |
+
"2": "neutral",
|
15 |
+
"3": "rel_by_party"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"label2id": {
|
19 |
+
"negative": 1,
|
20 |
+
"neutral": 2,
|
21 |
+
"positive": 0,
|
22 |
+
"rel_by_party": 3
|
23 |
+
},
|
24 |
+
"max_position_embeddings": 512,
|
25 |
+
"model_type": "distilbert",
|
26 |
+
"n_heads": 12,
|
27 |
+
"n_layers": 6,
|
28 |
+
"output_past": true,
|
29 |
+
"pad_token_id": 28996,
|
30 |
+
"problem_type": "single_label_classification",
|
31 |
+
"qa_dropout": 0.1,
|
32 |
+
"seq_classif_dropout": 0.2,
|
33 |
+
"sinusoidal_pos_embds": false,
|
34 |
+
"tie_weights_": true,
|
35 |
+
"torch_dtype": "float32",
|
36 |
+
"transformers_version": "4.40.2",
|
37 |
+
"vocab_size": 28997
|
38 |
+
}
|
training_checkpoints/checkpoint-1344/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c430c4d9702a4baeddeda050750525b96e67993b8d70503cb410e99320c4837e
|
3 |
+
size 263153912
|
training_checkpoints/checkpoint-1344/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:734af6d9db80f4a6443e449bc11d79d50c0dae777c6d736264f6472948e95e62
|
3 |
+
size 526369978
|
training_checkpoints/checkpoint-1344/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e32cb1d2f428b70415529241e0e0a61026d8f29119ed3598ec15805d1cadf714
|
3 |
+
size 14244
|
training_checkpoints/checkpoint-1344/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dad5f7ec57203a8e28a98d2deddbfa247195c6ec01360dd1d5e15f1d4acae5f3
|
3 |
+
size 1064
|
training_checkpoints/checkpoint-1344/special_tokens_map.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": {
|
5 |
+
"content": "<pad>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false
|
10 |
+
},
|
11 |
+
"sep_token": "[SEP]",
|
12 |
+
"unk_token": "[UNK]"
|
13 |
+
}
|
training_checkpoints/checkpoint-1344/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_checkpoints/checkpoint-1344/tokenizer_config.json
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"28996": {
|
44 |
+
"content": "<pad>",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
}
|
51 |
+
},
|
52 |
+
"clean_up_tokenization_spaces": true,
|
53 |
+
"cls_token": "[CLS]",
|
54 |
+
"do_lower_case": false,
|
55 |
+
"mask_token": "[MASK]",
|
56 |
+
"model_max_length": 512,
|
57 |
+
"pad_token": "<pad>",
|
58 |
+
"sep_token": "[SEP]",
|
59 |
+
"strip_accents": null,
|
60 |
+
"tokenize_chinese_chars": true,
|
61 |
+
"tokenizer_class": "DistilBertTokenizer",
|
62 |
+
"unk_token": "[UNK]"
|
63 |
+
}
|
training_checkpoints/checkpoint-1344/trainer_state.json
ADDED
@@ -0,0 +1,167 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.6190547468267676,
|
3 |
+
"best_model_checkpoint": "case-analysis-distilbert-base-cased/checkpoint-1344",
|
4 |
+
"epoch": 6.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1344,
|
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": 0.7683741648106904,
|
14 |
+
"eval_f1_macro": 0.5345911091709411,
|
15 |
+
"eval_f1_micro": 0.7683741648106904,
|
16 |
+
"eval_f1_weighted": 0.7419347573003691,
|
17 |
+
"eval_loss": 0.6746780872344971,
|
18 |
+
"eval_macro_fpr": 0.12600030005040652,
|
19 |
+
"eval_macro_sensitivity": 0.5319427525309879,
|
20 |
+
"eval_macro_specificity": 0.8890561890350515,
|
21 |
+
"eval_precision": 0.723734857424959,
|
22 |
+
"eval_precision_macro": 0.5435421823199279,
|
23 |
+
"eval_recall": 0.7683741648106904,
|
24 |
+
"eval_recall_macro": 0.5319427525309879,
|
25 |
+
"eval_runtime": 5.5739,
|
26 |
+
"eval_samples_per_second": 80.554,
|
27 |
+
"eval_steps_per_second": 10.226,
|
28 |
+
"eval_weighted_fpr": 0.0913081650570676,
|
29 |
+
"eval_weighted_sensitivity": 0.7683741648106904,
|
30 |
+
"eval_weighted_specificity": 0.7878505913295152,
|
31 |
+
"step": 224
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 2.0,
|
35 |
+
"eval_accuracy": 0.8151447661469933,
|
36 |
+
"eval_f1_macro": 0.6006365232660228,
|
37 |
+
"eval_f1_micro": 0.8151447661469933,
|
38 |
+
"eval_f1_weighted": 0.7944989450754872,
|
39 |
+
"eval_loss": 0.6685805916786194,
|
40 |
+
"eval_macro_fpr": 0.09260504201680672,
|
41 |
+
"eval_macro_sensitivity": 0.6135692606280841,
|
42 |
+
"eval_macro_specificity": 0.9160924396038365,
|
43 |
+
"eval_precision": 0.775170081701242,
|
44 |
+
"eval_precision_macro": 0.5885022601098201,
|
45 |
+
"eval_recall": 0.8151447661469933,
|
46 |
+
"eval_recall_macro": 0.6135692606280841,
|
47 |
+
"eval_runtime": 22.918,
|
48 |
+
"eval_samples_per_second": 19.592,
|
49 |
+
"eval_steps_per_second": 2.487,
|
50 |
+
"eval_weighted_fpr": 0.07027942421676546,
|
51 |
+
"eval_weighted_sensitivity": 0.8151447661469933,
|
52 |
+
"eval_weighted_specificity": 0.8492249922683526,
|
53 |
+
"step": 448
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 2.232142857142857,
|
57 |
+
"grad_norm": 15.72251033782959,
|
58 |
+
"learning_rate": 4.6302083333333335e-05,
|
59 |
+
"loss": 0.6982,
|
60 |
+
"step": 500
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 3.0,
|
64 |
+
"eval_accuracy": 0.8106904231625836,
|
65 |
+
"eval_f1_macro": 0.5965678894021851,
|
66 |
+
"eval_f1_micro": 0.8106904231625834,
|
67 |
+
"eval_f1_weighted": 0.789500666861841,
|
68 |
+
"eval_loss": 0.7899503111839294,
|
69 |
+
"eval_macro_fpr": 0.09825302902225978,
|
70 |
+
"eval_macro_sensitivity": 0.6052493478964067,
|
71 |
+
"eval_macro_specificity": 0.910687377505773,
|
72 |
+
"eval_precision": 0.7758060756348297,
|
73 |
+
"eval_precision_macro": 0.5947486579771227,
|
74 |
+
"eval_recall": 0.8106904231625836,
|
75 |
+
"eval_recall_macro": 0.6052493478964067,
|
76 |
+
"eval_runtime": 22.9183,
|
77 |
+
"eval_samples_per_second": 19.591,
|
78 |
+
"eval_steps_per_second": 2.487,
|
79 |
+
"eval_weighted_fpr": 0.07221750212404418,
|
80 |
+
"eval_weighted_sensitivity": 0.8106904231625836,
|
81 |
+
"eval_weighted_specificity": 0.8320590868605084,
|
82 |
+
"step": 672
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 4.0,
|
86 |
+
"eval_accuracy": 0.8129175946547884,
|
87 |
+
"eval_f1_macro": 0.6024092775980217,
|
88 |
+
"eval_f1_micro": 0.8129175946547884,
|
89 |
+
"eval_f1_weighted": 0.7934058050292863,
|
90 |
+
"eval_loss": 0.8377446532249451,
|
91 |
+
"eval_macro_fpr": 0.10023342701741786,
|
92 |
+
"eval_macro_sensitivity": 0.5950729186023304,
|
93 |
+
"eval_macro_specificity": 0.9076308769469239,
|
94 |
+
"eval_precision": 0.7822520571931126,
|
95 |
+
"eval_precision_macro": 0.6157741567498898,
|
96 |
+
"eval_recall": 0.8129175946547884,
|
97 |
+
"eval_recall_macro": 0.5950729186023304,
|
98 |
+
"eval_runtime": 23.0602,
|
99 |
+
"eval_samples_per_second": 19.471,
|
100 |
+
"eval_steps_per_second": 2.472,
|
101 |
+
"eval_weighted_fpr": 0.07124681933842239,
|
102 |
+
"eval_weighted_sensitivity": 0.8129175946547884,
|
103 |
+
"eval_weighted_specificity": 0.8176059131329072,
|
104 |
+
"step": 896
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 4.464285714285714,
|
108 |
+
"grad_norm": 3.802079200744629,
|
109 |
+
"learning_rate": 4.259672619047619e-05,
|
110 |
+
"loss": 0.3797,
|
111 |
+
"step": 1000
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 5.0,
|
115 |
+
"eval_accuracy": 0.8195991091314031,
|
116 |
+
"eval_f1_macro": 0.6096395609968126,
|
117 |
+
"eval_f1_micro": 0.8195991091314031,
|
118 |
+
"eval_f1_weighted": 0.8009201487061303,
|
119 |
+
"eval_loss": 0.9637371897697449,
|
120 |
+
"eval_macro_fpr": 0.09298523725810875,
|
121 |
+
"eval_macro_sensitivity": 0.6097056758821464,
|
122 |
+
"eval_macro_specificity": 0.9156101048565789,
|
123 |
+
"eval_precision": 0.7852664668210015,
|
124 |
+
"eval_precision_macro": 0.6117719622096018,
|
125 |
+
"eval_recall": 0.8195991091314031,
|
126 |
+
"eval_recall_macro": 0.6097056758821464,
|
127 |
+
"eval_runtime": 24.1336,
|
128 |
+
"eval_samples_per_second": 18.605,
|
129 |
+
"eval_steps_per_second": 2.362,
|
130 |
+
"eval_weighted_fpr": 0.06835443037974684,
|
131 |
+
"eval_weighted_sensitivity": 0.8195991091314031,
|
132 |
+
"eval_weighted_specificity": 0.8428413102949123,
|
133 |
+
"step": 1120
|
134 |
+
},
|
135 |
+
{
|
136 |
+
"epoch": 6.0,
|
137 |
+
"eval_accuracy": 0.799554565701559,
|
138 |
+
"eval_f1_macro": 0.6190547468267676,
|
139 |
+
"eval_f1_micro": 0.799554565701559,
|
140 |
+
"eval_f1_weighted": 0.8002581826434487,
|
141 |
+
"eval_loss": 1.0848541259765625,
|
142 |
+
"eval_macro_fpr": 0.09461858568722545,
|
143 |
+
"eval_macro_sensitivity": 0.6154274977804389,
|
144 |
+
"eval_macro_specificity": 0.9173876054987379,
|
145 |
+
"eval_precision": 0.8024626803020691,
|
146 |
+
"eval_precision_macro": 0.6242875164499879,
|
147 |
+
"eval_recall": 0.799554565701559,
|
148 |
+
"eval_recall_macro": 0.6154274977804389,
|
149 |
+
"eval_runtime": 26.5504,
|
150 |
+
"eval_samples_per_second": 16.911,
|
151 |
+
"eval_steps_per_second": 2.147,
|
152 |
+
"eval_weighted_fpr": 0.07712082262210797,
|
153 |
+
"eval_weighted_sensitivity": 0.799554565701559,
|
154 |
+
"eval_weighted_specificity": 0.8699958562933927,
|
155 |
+
"step": 1344
|
156 |
+
}
|
157 |
+
],
|
158 |
+
"logging_steps": 500,
|
159 |
+
"max_steps": 6720,
|
160 |
+
"num_input_tokens_seen": 0,
|
161 |
+
"num_train_epochs": 30,
|
162 |
+
"save_steps": 500,
|
163 |
+
"total_flos": 1424340270710784.0,
|
164 |
+
"train_batch_size": 8,
|
165 |
+
"trial_name": null,
|
166 |
+
"trial_params": null
|
167 |
+
}
|
training_checkpoints/checkpoint-1344/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e69a367f465c21d14de763eeb210a4f6dfdc2d5d36a7fd05f0a714a904e7ac23
|
3 |
+
size 5048
|
training_checkpoints/checkpoint-1344/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|