Spaces:
Runtime error
Runtime error
MJ
commited on
Commit
•
93f09cb
1
Parent(s):
83e19cd
Added checkpoint folder
Browse files- .gitattributes +2 -0
- checkpoint-3024/config.json +36 -0
- checkpoint-3024/optimizer.pt +0 -0
- checkpoint-3024/pytorch_model.bin +3 -0
- checkpoint-3024/rng_state.pth +0 -0
- checkpoint-3024/scaler.pt +0 -0
- checkpoint-3024/scheduler.pt +0 -0
- checkpoint-3024/special_tokens_map.json +7 -0
- checkpoint-3024/tokenizer.json +0 -0
- checkpoint-3024/tokenizer_config.json +13 -0
- checkpoint-3024/trainer_state.json +160 -0
- checkpoint-3024/training_args.bin +3 -0
- checkpoint-3024/vocab.txt +0 -0
.gitattributes
ADDED
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
1 |
+
.bin filter=lfs diff=lfs merge=lfs -text
|
2 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
checkpoint-3024/config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "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": "REJECTED",
|
13 |
+
"1": "PENDING",
|
14 |
+
"2": "ACCEPTED"
|
15 |
+
},
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"label2id": {
|
18 |
+
"ACCEPTED": 2,
|
19 |
+
"PENDING": 1,
|
20 |
+
"REJECTED": 0
|
21 |
+
},
|
22 |
+
"max_position_embeddings": 512,
|
23 |
+
"model_type": "distilbert",
|
24 |
+
"n_heads": 12,
|
25 |
+
"n_layers": 6,
|
26 |
+
"output_past": true,
|
27 |
+
"pad_token_id": 0,
|
28 |
+
"problem_type": "single_label_classification",
|
29 |
+
"qa_dropout": 0.1,
|
30 |
+
"seq_classif_dropout": 0.2,
|
31 |
+
"sinusoidal_pos_embds": false,
|
32 |
+
"tie_weights_": true,
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.28.1",
|
35 |
+
"vocab_size": 28996
|
36 |
+
}
|
checkpoint-3024/optimizer.pt
ADDED
Binary file (784 kB). View file
|
|
checkpoint-3024/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1cb8204d1213a0a4f65f7cb86078d439187fe9c1617ab2b289d594521512ee16
|
3 |
+
size 263170733
|
checkpoint-3024/rng_state.pth
ADDED
Binary file (14.6 kB). View file
|
|
checkpoint-3024/scaler.pt
ADDED
Binary file (557 Bytes). View file
|
|
checkpoint-3024/scheduler.pt
ADDED
Binary file (627 Bytes). View file
|
|
checkpoint-3024/special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
checkpoint-3024/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-3024/tokenizer_config.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_lower_case": false,
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"model_max_length": 512,
|
7 |
+
"pad_token": "[PAD]",
|
8 |
+
"sep_token": "[SEP]",
|
9 |
+
"strip_accents": null,
|
10 |
+
"tokenize_chinese_chars": true,
|
11 |
+
"tokenizer_class": "DistilBertTokenizer",
|
12 |
+
"unk_token": "[UNK]"
|
13 |
+
}
|
checkpoint-3024/trainer_state.json
ADDED
@@ -0,0 +1,160 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.9327176213264465,
|
3 |
+
"best_model_checkpoint": "Bert-Patent-Model-2/checkpoint-252",
|
4 |
+
"epoch": 11.979202772963605,
|
5 |
+
"global_step": 3024,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.0,
|
12 |
+
"eval_accuracy": 0.5560809324829558,
|
13 |
+
"eval_loss": 0.9327176213264465,
|
14 |
+
"eval_runtime": 61.1572,
|
15 |
+
"eval_samples_per_second": 148.699,
|
16 |
+
"eval_steps_per_second": 37.183,
|
17 |
+
"step": 252
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 1.98,
|
21 |
+
"learning_rate": 4.173280423280423e-05,
|
22 |
+
"loss": 0.7132,
|
23 |
+
"step": 500
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 2.0,
|
27 |
+
"eval_accuracy": 0.5373872883219706,
|
28 |
+
"eval_loss": 1.062583327293396,
|
29 |
+
"eval_runtime": 61.2847,
|
30 |
+
"eval_samples_per_second": 148.389,
|
31 |
+
"eval_steps_per_second": 37.106,
|
32 |
+
"step": 504
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 3.0,
|
36 |
+
"eval_accuracy": 0.5458544095007697,
|
37 |
+
"eval_loss": 1.1494050025939941,
|
38 |
+
"eval_runtime": 61.066,
|
39 |
+
"eval_samples_per_second": 148.921,
|
40 |
+
"eval_steps_per_second": 37.238,
|
41 |
+
"step": 757
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 3.96,
|
45 |
+
"learning_rate": 3.3465608465608464e-05,
|
46 |
+
"loss": 0.4843,
|
47 |
+
"step": 1000
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"epoch": 4.0,
|
51 |
+
"eval_accuracy": 0.5184737189355619,
|
52 |
+
"eval_loss": 1.3940870761871338,
|
53 |
+
"eval_runtime": 61.4358,
|
54 |
+
"eval_samples_per_second": 148.024,
|
55 |
+
"eval_steps_per_second": 37.014,
|
56 |
+
"step": 1009
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 5.0,
|
60 |
+
"eval_accuracy": 0.5200131955135254,
|
61 |
+
"eval_loss": 1.6256372928619385,
|
62 |
+
"eval_runtime": 61.3848,
|
63 |
+
"eval_samples_per_second": 148.147,
|
64 |
+
"eval_steps_per_second": 37.045,
|
65 |
+
"step": 1262
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 5.94,
|
69 |
+
"learning_rate": 2.521494708994709e-05,
|
70 |
+
"loss": 0.2345,
|
71 |
+
"step": 1500
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 6.0,
|
75 |
+
"eval_accuracy": 0.5346382230041786,
|
76 |
+
"eval_loss": 1.928905963897705,
|
77 |
+
"eval_runtime": 61.7798,
|
78 |
+
"eval_samples_per_second": 147.2,
|
79 |
+
"eval_steps_per_second": 36.808,
|
80 |
+
"step": 1514
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 7.0,
|
84 |
+
"eval_accuracy": 0.535188036067737,
|
85 |
+
"eval_loss": 2.1018900871276855,
|
86 |
+
"eval_runtime": 61.981,
|
87 |
+
"eval_samples_per_second": 146.722,
|
88 |
+
"eval_steps_per_second": 36.689,
|
89 |
+
"step": 1767
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 7.92,
|
93 |
+
"learning_rate": 1.6947751322751323e-05,
|
94 |
+
"loss": 0.1136,
|
95 |
+
"step": 2000
|
96 |
+
},
|
97 |
+
{
|
98 |
+
"epoch": 8.0,
|
99 |
+
"eval_accuracy": 0.5215526720914889,
|
100 |
+
"eval_loss": 2.4479029178619385,
|
101 |
+
"eval_runtime": 61.734,
|
102 |
+
"eval_samples_per_second": 147.309,
|
103 |
+
"eval_steps_per_second": 36.835,
|
104 |
+
"step": 2019
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 9.0,
|
108 |
+
"eval_accuracy": 0.5127556630745547,
|
109 |
+
"eval_loss": 2.633791923522949,
|
110 |
+
"eval_runtime": 61.3331,
|
111 |
+
"eval_samples_per_second": 148.272,
|
112 |
+
"eval_steps_per_second": 37.076,
|
113 |
+
"step": 2271
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 9.9,
|
117 |
+
"learning_rate": 8.680555555555556e-06,
|
118 |
+
"loss": 0.0521,
|
119 |
+
"step": 2500
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 10.0,
|
123 |
+
"eval_accuracy": 0.5292500549813064,
|
124 |
+
"eval_loss": 3.018095016479492,
|
125 |
+
"eval_runtime": 62.0026,
|
126 |
+
"eval_samples_per_second": 146.671,
|
127 |
+
"eval_steps_per_second": 36.676,
|
128 |
+
"step": 2524
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 11.0,
|
132 |
+
"eval_accuracy": 0.522542335605894,
|
133 |
+
"eval_loss": 3.2116775512695312,
|
134 |
+
"eval_runtime": 61.5454,
|
135 |
+
"eval_samples_per_second": 147.761,
|
136 |
+
"eval_steps_per_second": 36.948,
|
137 |
+
"step": 2776
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 11.88,
|
141 |
+
"learning_rate": 4.133597883597884e-07,
|
142 |
+
"loss": 0.0222,
|
143 |
+
"step": 3000
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 11.98,
|
147 |
+
"eval_accuracy": 0.5235319991202991,
|
148 |
+
"eval_loss": 3.3195860385894775,
|
149 |
+
"eval_runtime": 61.2862,
|
150 |
+
"eval_samples_per_second": 148.386,
|
151 |
+
"eval_steps_per_second": 37.105,
|
152 |
+
"step": 3024
|
153 |
+
}
|
154 |
+
],
|
155 |
+
"max_steps": 3024,
|
156 |
+
"num_train_epochs": 12,
|
157 |
+
"total_flos": 2.563329616742707e+16,
|
158 |
+
"trial_name": null,
|
159 |
+
"trial_params": null
|
160 |
+
}
|
checkpoint-3024/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f44c088560d024c1e7c9f984a6879ab2b67fd7011dfdc15abac363c161a7605
|
3 |
+
size 3643
|
checkpoint-3024/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|