Upload folder using huggingface_hub
Browse files- README.md +37 -0
- checkpoint-1028/config.json +60 -0
- checkpoint-1028/model.safetensors +3 -0
- checkpoint-1028/optimizer.pt +3 -0
- checkpoint-1028/rng_state.pth +3 -0
- checkpoint-1028/scheduler.pt +3 -0
- checkpoint-1028/trainer_state.json +218 -0
- checkpoint-1028/training_args.bin +3 -0
- config.json +60 -0
- model.safetensors +3 -0
- runs/Jun04_03-57-39_r-pvaluedotone-bigbird-sentiment-fxjxbskt-0213b-cgpll/events.out.tfevents.1749009462.r-pvaluedotone-bigbird-sentiment-fxjxbskt-0213b-cgpll.473.0 +2 -2
- runs/Jun04_03-57-39_r-pvaluedotone-bigbird-sentiment-fxjxbskt-0213b-cgpll/events.out.tfevents.1749218335.r-pvaluedotone-bigbird-sentiment-fxjxbskt-0213b-cgpll.473.1 +3 -0
- special_tokens_map.json +51 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +824 -0
- training_args.bin +3 -0
- training_params.json +30 -0
README.md
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
library_name: transformers
|
4 |
+
tags:
|
5 |
+
- autotrain
|
6 |
+
- text-classification
|
7 |
+
base_model: google/bigbird-roberta-base
|
8 |
+
widget:
|
9 |
+
- text: "I love AutoTrain"
|
10 |
+
---
|
11 |
+
|
12 |
+
# Model Trained Using AutoTrain
|
13 |
+
|
14 |
+
- Problem type: Text Classification
|
15 |
+
|
16 |
+
## Validation Metrics
|
17 |
+
loss: 1.6760838031768799
|
18 |
+
|
19 |
+
f1_macro: 0.27337963763262785
|
20 |
+
|
21 |
+
f1_micro: 0.3093385214007782
|
22 |
+
|
23 |
+
f1_weighted: 0.2814372687206247
|
24 |
+
|
25 |
+
precision_macro: 0.282150640368379
|
26 |
+
|
27 |
+
precision_micro: 0.3093385214007782
|
28 |
+
|
29 |
+
precision_weighted: 0.2911286647426314
|
30 |
+
|
31 |
+
recall_macro: 0.30072312612988455
|
32 |
+
|
33 |
+
recall_micro: 0.3093385214007782
|
34 |
+
|
35 |
+
recall_weighted: 0.3093385214007782
|
36 |
+
|
37 |
+
accuracy: 0.3093385214007782
|
checkpoint-1028/config.json
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/bigbird-roberta-base",
|
3 |
+
"_num_labels": 10,
|
4 |
+
"architectures": [
|
5 |
+
"BigBirdForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"attention_type": "block_sparse",
|
9 |
+
"block_size": 64,
|
10 |
+
"bos_token_id": 1,
|
11 |
+
"classifier_dropout": null,
|
12 |
+
"eos_token_id": 2,
|
13 |
+
"gradient_checkpointing": false,
|
14 |
+
"hidden_act": "gelu_new",
|
15 |
+
"hidden_dropout_prob": 0.1,
|
16 |
+
"hidden_size": 768,
|
17 |
+
"id2label": {
|
18 |
+
"0": "1",
|
19 |
+
"1": "10",
|
20 |
+
"2": "2",
|
21 |
+
"3": "3",
|
22 |
+
"4": "4",
|
23 |
+
"5": "5",
|
24 |
+
"6": "6",
|
25 |
+
"7": "7",
|
26 |
+
"8": "8",
|
27 |
+
"9": "9"
|
28 |
+
},
|
29 |
+
"initializer_range": 0.02,
|
30 |
+
"intermediate_size": 3072,
|
31 |
+
"label2id": {
|
32 |
+
"1": 0,
|
33 |
+
"10": 1,
|
34 |
+
"2": 2,
|
35 |
+
"3": 3,
|
36 |
+
"4": 4,
|
37 |
+
"5": 5,
|
38 |
+
"6": 6,
|
39 |
+
"7": 7,
|
40 |
+
"8": 8,
|
41 |
+
"9": 9
|
42 |
+
},
|
43 |
+
"layer_norm_eps": 1e-12,
|
44 |
+
"max_position_embeddings": 4096,
|
45 |
+
"model_type": "big_bird",
|
46 |
+
"num_attention_heads": 12,
|
47 |
+
"num_hidden_layers": 12,
|
48 |
+
"num_random_blocks": 3,
|
49 |
+
"pad_token_id": 0,
|
50 |
+
"position_embedding_type": "absolute",
|
51 |
+
"problem_type": "single_label_classification",
|
52 |
+
"rescale_embeddings": false,
|
53 |
+
"sep_token_id": 66,
|
54 |
+
"torch_dtype": "float32",
|
55 |
+
"transformers_version": "4.48.0",
|
56 |
+
"type_vocab_size": 2,
|
57 |
+
"use_bias": true,
|
58 |
+
"use_cache": true,
|
59 |
+
"vocab_size": 50358
|
60 |
+
}
|
checkpoint-1028/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:17d6504b20f04ce6f3c6523c189884b3278704c17c656be4244998998e314159
|
3 |
+
size 512292072
|
checkpoint-1028/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db711e380d7fd2cad9c224f25e140798aa730657bc435833cf0e4564e573ae07
|
3 |
+
size 1019974394
|
checkpoint-1028/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d60b91bfb8bf358e8f0c68d68d1d16ef84aa3e26e03823a3c58d360099ceefa6
|
3 |
+
size 14054
|
checkpoint-1028/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5e6457f7b9dd6e9755139d72ce919b1b20015eaec601df6c901acd6073e70a93
|
3 |
+
size 1064
|
checkpoint-1028/trainer_state.json
ADDED
@@ -0,0 +1,218 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.6760838031768799,
|
3 |
+
"best_model_checkpoint": "bigbird-flight-2/checkpoint-1028",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1028,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.09727626459143969,
|
13 |
+
"grad_norm": 5.640580654144287,
|
14 |
+
"learning_rate": 1.5197568389057753e-06,
|
15 |
+
"loss": 2.2808,
|
16 |
+
"step": 50
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.19455252918287938,
|
20 |
+
"grad_norm": 6.845468044281006,
|
21 |
+
"learning_rate": 3.0395136778115506e-06,
|
22 |
+
"loss": 2.3041,
|
23 |
+
"step": 100
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.2918287937743191,
|
27 |
+
"grad_norm": 4.374593257904053,
|
28 |
+
"learning_rate": 4.559270516717325e-06,
|
29 |
+
"loss": 2.303,
|
30 |
+
"step": 150
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.38910505836575876,
|
34 |
+
"grad_norm": 3.985168218612671,
|
35 |
+
"learning_rate": 6.079027355623101e-06,
|
36 |
+
"loss": 2.295,
|
37 |
+
"step": 200
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.48638132295719844,
|
41 |
+
"grad_norm": 6.664238929748535,
|
42 |
+
"learning_rate": 7.5987841945288756e-06,
|
43 |
+
"loss": 2.249,
|
44 |
+
"step": 250
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.5836575875486382,
|
48 |
+
"grad_norm": 6.191707611083984,
|
49 |
+
"learning_rate": 9.11854103343465e-06,
|
50 |
+
"loss": 2.1323,
|
51 |
+
"step": 300
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.6809338521400778,
|
55 |
+
"grad_norm": 6.4777140617370605,
|
56 |
+
"learning_rate": 1.0638297872340426e-05,
|
57 |
+
"loss": 2.0151,
|
58 |
+
"step": 350
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.7782101167315175,
|
62 |
+
"grad_norm": 15.601507186889648,
|
63 |
+
"learning_rate": 1.2158054711246202e-05,
|
64 |
+
"loss": 1.9318,
|
65 |
+
"step": 400
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.8754863813229572,
|
69 |
+
"grad_norm": 6.998500347137451,
|
70 |
+
"learning_rate": 1.3677811550151975e-05,
|
71 |
+
"loss": 1.9021,
|
72 |
+
"step": 450
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.9727626459143969,
|
76 |
+
"grad_norm": 16.937795639038086,
|
77 |
+
"learning_rate": 1.5197568389057751e-05,
|
78 |
+
"loss": 1.8199,
|
79 |
+
"step": 500
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 1.0,
|
83 |
+
"eval_accuracy": 0.2704280155642023,
|
84 |
+
"eval_f1_macro": 0.18452231398929034,
|
85 |
+
"eval_f1_micro": 0.2704280155642023,
|
86 |
+
"eval_f1_weighted": 0.1903075803351923,
|
87 |
+
"eval_loss": 1.8465327024459839,
|
88 |
+
"eval_precision_macro": 0.19230244249654188,
|
89 |
+
"eval_precision_micro": 0.2704280155642023,
|
90 |
+
"eval_precision_weighted": 0.1960311004178974,
|
91 |
+
"eval_recall_macro": 0.2598247809762203,
|
92 |
+
"eval_recall_micro": 0.2704280155642023,
|
93 |
+
"eval_recall_weighted": 0.2704280155642023,
|
94 |
+
"eval_runtime": 1595.827,
|
95 |
+
"eval_samples_per_second": 0.322,
|
96 |
+
"eval_steps_per_second": 0.041,
|
97 |
+
"step": 514
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 1.0700389105058365,
|
101 |
+
"grad_norm": 10.755321502685547,
|
102 |
+
"learning_rate": 1.6717325227963527e-05,
|
103 |
+
"loss": 1.8219,
|
104 |
+
"step": 550
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 1.1673151750972763,
|
108 |
+
"grad_norm": 16.09447479248047,
|
109 |
+
"learning_rate": 1.82370820668693e-05,
|
110 |
+
"loss": 1.7428,
|
111 |
+
"step": 600
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 1.264591439688716,
|
115 |
+
"grad_norm": 14.368643760681152,
|
116 |
+
"learning_rate": 1.9756838905775076e-05,
|
117 |
+
"loss": 1.7054,
|
118 |
+
"step": 650
|
119 |
+
},
|
120 |
+
{
|
121 |
+
"epoch": 1.3618677042801557,
|
122 |
+
"grad_norm": 9.273758888244629,
|
123 |
+
"learning_rate": 2.1276595744680852e-05,
|
124 |
+
"loss": 1.7145,
|
125 |
+
"step": 700
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 1.4591439688715953,
|
129 |
+
"grad_norm": 12.411294937133789,
|
130 |
+
"learning_rate": 2.279635258358663e-05,
|
131 |
+
"loss": 1.6765,
|
132 |
+
"step": 750
|
133 |
+
},
|
134 |
+
{
|
135 |
+
"epoch": 1.556420233463035,
|
136 |
+
"grad_norm": 27.17559051513672,
|
137 |
+
"learning_rate": 2.4316109422492404e-05,
|
138 |
+
"loss": 1.7499,
|
139 |
+
"step": 800
|
140 |
+
},
|
141 |
+
{
|
142 |
+
"epoch": 1.6536964980544746,
|
143 |
+
"grad_norm": 18.921966552734375,
|
144 |
+
"learning_rate": 2.5835866261398177e-05,
|
145 |
+
"loss": 1.6988,
|
146 |
+
"step": 850
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 1.7509727626459144,
|
150 |
+
"grad_norm": 14.716523170471191,
|
151 |
+
"learning_rate": 2.735562310030395e-05,
|
152 |
+
"loss": 1.6935,
|
153 |
+
"step": 900
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 1.8482490272373542,
|
157 |
+
"grad_norm": 20.14253807067871,
|
158 |
+
"learning_rate": 2.887537993920973e-05,
|
159 |
+
"loss": 1.7054,
|
160 |
+
"step": 950
|
161 |
+
},
|
162 |
+
{
|
163 |
+
"epoch": 1.9455252918287937,
|
164 |
+
"grad_norm": 5.987732887268066,
|
165 |
+
"learning_rate": 3.0395136778115502e-05,
|
166 |
+
"loss": 1.7427,
|
167 |
+
"step": 1000
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 2.0,
|
171 |
+
"eval_accuracy": 0.3093385214007782,
|
172 |
+
"eval_f1_macro": 0.27337963763262785,
|
173 |
+
"eval_f1_micro": 0.3093385214007782,
|
174 |
+
"eval_f1_weighted": 0.2814372687206247,
|
175 |
+
"eval_loss": 1.6760838031768799,
|
176 |
+
"eval_precision_macro": 0.282150640368379,
|
177 |
+
"eval_precision_micro": 0.3093385214007782,
|
178 |
+
"eval_precision_weighted": 0.2911286647426314,
|
179 |
+
"eval_recall_macro": 0.30072312612988455,
|
180 |
+
"eval_recall_micro": 0.3093385214007782,
|
181 |
+
"eval_recall_weighted": 0.3093385214007782,
|
182 |
+
"eval_runtime": 1588.4184,
|
183 |
+
"eval_samples_per_second": 0.324,
|
184 |
+
"eval_steps_per_second": 0.041,
|
185 |
+
"step": 1028
|
186 |
+
}
|
187 |
+
],
|
188 |
+
"logging_steps": 50,
|
189 |
+
"max_steps": 16448,
|
190 |
+
"num_input_tokens_seen": 0,
|
191 |
+
"num_train_epochs": 32,
|
192 |
+
"save_steps": 500,
|
193 |
+
"stateful_callbacks": {
|
194 |
+
"EarlyStoppingCallback": {
|
195 |
+
"args": {
|
196 |
+
"early_stopping_patience": 5,
|
197 |
+
"early_stopping_threshold": 0.01
|
198 |
+
},
|
199 |
+
"attributes": {
|
200 |
+
"early_stopping_patience_counter": 0
|
201 |
+
}
|
202 |
+
},
|
203 |
+
"TrainerControl": {
|
204 |
+
"args": {
|
205 |
+
"should_epoch_stop": false,
|
206 |
+
"should_evaluate": false,
|
207 |
+
"should_log": false,
|
208 |
+
"should_save": true,
|
209 |
+
"should_training_stop": false
|
210 |
+
},
|
211 |
+
"attributes": {}
|
212 |
+
}
|
213 |
+
},
|
214 |
+
"total_flos": 2176781982056448.0,
|
215 |
+
"train_batch_size": 4,
|
216 |
+
"trial_name": null,
|
217 |
+
"trial_params": null
|
218 |
+
}
|
checkpoint-1028/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b58c7f9ea10d6f939d945d9869da13d91dc1a5aa860e689f2b928a864d7bc32
|
3 |
+
size 5368
|
config.json
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/bigbird-roberta-base",
|
3 |
+
"_num_labels": 10,
|
4 |
+
"architectures": [
|
5 |
+
"BigBirdForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"attention_type": "block_sparse",
|
9 |
+
"block_size": 64,
|
10 |
+
"bos_token_id": 1,
|
11 |
+
"classifier_dropout": null,
|
12 |
+
"eos_token_id": 2,
|
13 |
+
"gradient_checkpointing": false,
|
14 |
+
"hidden_act": "gelu_new",
|
15 |
+
"hidden_dropout_prob": 0.1,
|
16 |
+
"hidden_size": 768,
|
17 |
+
"id2label": {
|
18 |
+
"0": "1",
|
19 |
+
"1": "10",
|
20 |
+
"2": "2",
|
21 |
+
"3": "3",
|
22 |
+
"4": "4",
|
23 |
+
"5": "5",
|
24 |
+
"6": "6",
|
25 |
+
"7": "7",
|
26 |
+
"8": "8",
|
27 |
+
"9": "9"
|
28 |
+
},
|
29 |
+
"initializer_range": 0.02,
|
30 |
+
"intermediate_size": 3072,
|
31 |
+
"label2id": {
|
32 |
+
"1": 0,
|
33 |
+
"10": 1,
|
34 |
+
"2": 2,
|
35 |
+
"3": 3,
|
36 |
+
"4": 4,
|
37 |
+
"5": 5,
|
38 |
+
"6": 6,
|
39 |
+
"7": 7,
|
40 |
+
"8": 8,
|
41 |
+
"9": 9
|
42 |
+
},
|
43 |
+
"layer_norm_eps": 1e-12,
|
44 |
+
"max_position_embeddings": 4096,
|
45 |
+
"model_type": "big_bird",
|
46 |
+
"num_attention_heads": 12,
|
47 |
+
"num_hidden_layers": 12,
|
48 |
+
"num_random_blocks": 3,
|
49 |
+
"pad_token_id": 0,
|
50 |
+
"position_embedding_type": "absolute",
|
51 |
+
"problem_type": "single_label_classification",
|
52 |
+
"rescale_embeddings": false,
|
53 |
+
"sep_token_id": 66,
|
54 |
+
"torch_dtype": "float32",
|
55 |
+
"transformers_version": "4.48.0",
|
56 |
+
"type_vocab_size": 2,
|
57 |
+
"use_bias": true,
|
58 |
+
"use_cache": true,
|
59 |
+
"vocab_size": 50358
|
60 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:17d6504b20f04ce6f3c6523c189884b3278704c17c656be4244998998e314159
|
3 |
+
size 512292072
|
runs/Jun04_03-57-39_r-pvaluedotone-bigbird-sentiment-fxjxbskt-0213b-cgpll/events.out.tfevents.1749009462.r-pvaluedotone-bigbird-sentiment-fxjxbskt-0213b-cgpll.473.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b7c4e77edf76aeffceb8bd2aef4ad937bc4d337f59ec26e9c1930b8b9c23255
|
3 |
+
size 26774
|
runs/Jun04_03-57-39_r-pvaluedotone-bigbird-sentiment-fxjxbskt-0213b-cgpll/events.out.tfevents.1749218335.r-pvaluedotone-bigbird-sentiment-fxjxbskt-0213b-cgpll.473.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e93e0739493ad800469daf169b46afdbea6ebe700cabd37918feb1aa8a9c35af
|
3 |
+
size 921
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "</s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "[CLS]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "<s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "[MASK]",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": true,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "[SEP]",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": true,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": true,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fdc81e1fc9d42e0c08b86d5b280d05d7c5e9747c4231c648f2b56b8e1d893c82
|
3 |
+
size 845731
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,824 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<pad>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": true,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "</s>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": true,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "<s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": true,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<sep_0>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": false
|
34 |
+
},
|
35 |
+
"4": {
|
36 |
+
"content": "<sep_1>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": false
|
42 |
+
},
|
43 |
+
"5": {
|
44 |
+
"content": "<sep_2>",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": false
|
50 |
+
},
|
51 |
+
"6": {
|
52 |
+
"content": "<sep_3>",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": false
|
58 |
+
},
|
59 |
+
"7": {
|
60 |
+
"content": "<sep_4>",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": false,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": false
|
66 |
+
},
|
67 |
+
"8": {
|
68 |
+
"content": "<no_saic_raw_sp>",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": false,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false,
|
73 |
+
"special": false
|
74 |
+
},
|
75 |
+
"9": {
|
76 |
+
"content": "<length_0>",
|
77 |
+
"lstrip": false,
|
78 |
+
"normalized": false,
|
79 |
+
"rstrip": false,
|
80 |
+
"single_word": false,
|
81 |
+
"special": false
|
82 |
+
},
|
83 |
+
"10": {
|
84 |
+
"content": "<length_1>",
|
85 |
+
"lstrip": false,
|
86 |
+
"normalized": false,
|
87 |
+
"rstrip": false,
|
88 |
+
"single_word": false,
|
89 |
+
"special": false
|
90 |
+
},
|
91 |
+
"11": {
|
92 |
+
"content": "<length_2>",
|
93 |
+
"lstrip": false,
|
94 |
+
"normalized": false,
|
95 |
+
"rstrip": false,
|
96 |
+
"single_word": false,
|
97 |
+
"special": false
|
98 |
+
},
|
99 |
+
"12": {
|
100 |
+
"content": "<length_3>",
|
101 |
+
"lstrip": false,
|
102 |
+
"normalized": false,
|
103 |
+
"rstrip": false,
|
104 |
+
"single_word": false,
|
105 |
+
"special": false
|
106 |
+
},
|
107 |
+
"13": {
|
108 |
+
"content": "<length_4>",
|
109 |
+
"lstrip": false,
|
110 |
+
"normalized": false,
|
111 |
+
"rstrip": false,
|
112 |
+
"single_word": false,
|
113 |
+
"special": false
|
114 |
+
},
|
115 |
+
"14": {
|
116 |
+
"content": "<length_5>",
|
117 |
+
"lstrip": false,
|
118 |
+
"normalized": false,
|
119 |
+
"rstrip": false,
|
120 |
+
"single_word": false,
|
121 |
+
"special": false
|
122 |
+
},
|
123 |
+
"15": {
|
124 |
+
"content": "<length_6>",
|
125 |
+
"lstrip": false,
|
126 |
+
"normalized": false,
|
127 |
+
"rstrip": false,
|
128 |
+
"single_word": false,
|
129 |
+
"special": false
|
130 |
+
},
|
131 |
+
"16": {
|
132 |
+
"content": "<length_7>",
|
133 |
+
"lstrip": false,
|
134 |
+
"normalized": false,
|
135 |
+
"rstrip": false,
|
136 |
+
"single_word": false,
|
137 |
+
"special": false
|
138 |
+
},
|
139 |
+
"17": {
|
140 |
+
"content": "<length_8>",
|
141 |
+
"lstrip": false,
|
142 |
+
"normalized": false,
|
143 |
+
"rstrip": false,
|
144 |
+
"single_word": false,
|
145 |
+
"special": false
|
146 |
+
},
|
147 |
+
"18": {
|
148 |
+
"content": "<length_9>",
|
149 |
+
"lstrip": false,
|
150 |
+
"normalized": false,
|
151 |
+
"rstrip": false,
|
152 |
+
"single_word": false,
|
153 |
+
"special": false
|
154 |
+
},
|
155 |
+
"19": {
|
156 |
+
"content": "<length_10>",
|
157 |
+
"lstrip": false,
|
158 |
+
"normalized": false,
|
159 |
+
"rstrip": false,
|
160 |
+
"single_word": false,
|
161 |
+
"special": false
|
162 |
+
},
|
163 |
+
"20": {
|
164 |
+
"content": "<length_11>",
|
165 |
+
"lstrip": false,
|
166 |
+
"normalized": false,
|
167 |
+
"rstrip": false,
|
168 |
+
"single_word": false,
|
169 |
+
"special": false
|
170 |
+
},
|
171 |
+
"21": {
|
172 |
+
"content": "<length_12>",
|
173 |
+
"lstrip": false,
|
174 |
+
"normalized": false,
|
175 |
+
"rstrip": false,
|
176 |
+
"single_word": false,
|
177 |
+
"special": false
|
178 |
+
},
|
179 |
+
"22": {
|
180 |
+
"content": "<length_13>",
|
181 |
+
"lstrip": false,
|
182 |
+
"normalized": false,
|
183 |
+
"rstrip": false,
|
184 |
+
"single_word": false,
|
185 |
+
"special": false
|
186 |
+
},
|
187 |
+
"23": {
|
188 |
+
"content": "<length_14>",
|
189 |
+
"lstrip": false,
|
190 |
+
"normalized": false,
|
191 |
+
"rstrip": false,
|
192 |
+
"single_word": false,
|
193 |
+
"special": false
|
194 |
+
},
|
195 |
+
"24": {
|
196 |
+
"content": "<length_15>",
|
197 |
+
"lstrip": false,
|
198 |
+
"normalized": false,
|
199 |
+
"rstrip": false,
|
200 |
+
"single_word": false,
|
201 |
+
"special": false
|
202 |
+
},
|
203 |
+
"25": {
|
204 |
+
"content": "<length_16>",
|
205 |
+
"lstrip": false,
|
206 |
+
"normalized": false,
|
207 |
+
"rstrip": false,
|
208 |
+
"single_word": false,
|
209 |
+
"special": false
|
210 |
+
},
|
211 |
+
"26": {
|
212 |
+
"content": "<length_17>",
|
213 |
+
"lstrip": false,
|
214 |
+
"normalized": false,
|
215 |
+
"rstrip": false,
|
216 |
+
"single_word": false,
|
217 |
+
"special": false
|
218 |
+
},
|
219 |
+
"27": {
|
220 |
+
"content": "<length_18>",
|
221 |
+
"lstrip": false,
|
222 |
+
"normalized": false,
|
223 |
+
"rstrip": false,
|
224 |
+
"single_word": false,
|
225 |
+
"special": false
|
226 |
+
},
|
227 |
+
"28": {
|
228 |
+
"content": "<length_19>",
|
229 |
+
"lstrip": false,
|
230 |
+
"normalized": false,
|
231 |
+
"rstrip": false,
|
232 |
+
"single_word": false,
|
233 |
+
"special": false
|
234 |
+
},
|
235 |
+
"29": {
|
236 |
+
"content": "<length_20>",
|
237 |
+
"lstrip": false,
|
238 |
+
"normalized": false,
|
239 |
+
"rstrip": false,
|
240 |
+
"single_word": false,
|
241 |
+
"special": false
|
242 |
+
},
|
243 |
+
"30": {
|
244 |
+
"content": "<length_s>",
|
245 |
+
"lstrip": false,
|
246 |
+
"normalized": false,
|
247 |
+
"rstrip": false,
|
248 |
+
"single_word": false,
|
249 |
+
"special": false
|
250 |
+
},
|
251 |
+
"31": {
|
252 |
+
"content": "<length_m>",
|
253 |
+
"lstrip": false,
|
254 |
+
"normalized": false,
|
255 |
+
"rstrip": false,
|
256 |
+
"single_word": false,
|
257 |
+
"special": false
|
258 |
+
},
|
259 |
+
"32": {
|
260 |
+
"content": "<length_l>",
|
261 |
+
"lstrip": false,
|
262 |
+
"normalized": false,
|
263 |
+
"rstrip": false,
|
264 |
+
"single_word": false,
|
265 |
+
"special": false
|
266 |
+
},
|
267 |
+
"33": {
|
268 |
+
"content": "<::::>",
|
269 |
+
"lstrip": false,
|
270 |
+
"normalized": false,
|
271 |
+
"rstrip": false,
|
272 |
+
"single_word": false,
|
273 |
+
"special": false
|
274 |
+
},
|
275 |
+
"34": {
|
276 |
+
"content": "<space>",
|
277 |
+
"lstrip": false,
|
278 |
+
"normalized": false,
|
279 |
+
"rstrip": false,
|
280 |
+
"single_word": false,
|
281 |
+
"special": false
|
282 |
+
},
|
283 |
+
"35": {
|
284 |
+
"content": "<unused_34>",
|
285 |
+
"lstrip": false,
|
286 |
+
"normalized": false,
|
287 |
+
"rstrip": false,
|
288 |
+
"single_word": false,
|
289 |
+
"special": false
|
290 |
+
},
|
291 |
+
"36": {
|
292 |
+
"content": "<unused_35>",
|
293 |
+
"lstrip": false,
|
294 |
+
"normalized": false,
|
295 |
+
"rstrip": false,
|
296 |
+
"single_word": false,
|
297 |
+
"special": false
|
298 |
+
},
|
299 |
+
"37": {
|
300 |
+
"content": "<unused_36>",
|
301 |
+
"lstrip": false,
|
302 |
+
"normalized": false,
|
303 |
+
"rstrip": false,
|
304 |
+
"single_word": false,
|
305 |
+
"special": false
|
306 |
+
},
|
307 |
+
"38": {
|
308 |
+
"content": "<no_query_sp>",
|
309 |
+
"lstrip": false,
|
310 |
+
"normalized": false,
|
311 |
+
"rstrip": false,
|
312 |
+
"single_word": false,
|
313 |
+
"special": false
|
314 |
+
},
|
315 |
+
"39": {
|
316 |
+
"content": "<no_passage_raw_sp>",
|
317 |
+
"lstrip": false,
|
318 |
+
"normalized": false,
|
319 |
+
"rstrip": false,
|
320 |
+
"single_word": false,
|
321 |
+
"special": false
|
322 |
+
},
|
323 |
+
"40": {
|
324 |
+
"content": "<unused_39>",
|
325 |
+
"lstrip": false,
|
326 |
+
"normalized": false,
|
327 |
+
"rstrip": false,
|
328 |
+
"single_word": false,
|
329 |
+
"special": false
|
330 |
+
},
|
331 |
+
"41": {
|
332 |
+
"content": "<unused_40>",
|
333 |
+
"lstrip": false,
|
334 |
+
"normalized": false,
|
335 |
+
"rstrip": false,
|
336 |
+
"single_word": false,
|
337 |
+
"special": false
|
338 |
+
},
|
339 |
+
"42": {
|
340 |
+
"content": "<unused_41>",
|
341 |
+
"lstrip": false,
|
342 |
+
"normalized": false,
|
343 |
+
"rstrip": false,
|
344 |
+
"single_word": false,
|
345 |
+
"special": false
|
346 |
+
},
|
347 |
+
"43": {
|
348 |
+
"content": "<unused_42>",
|
349 |
+
"lstrip": false,
|
350 |
+
"normalized": false,
|
351 |
+
"rstrip": false,
|
352 |
+
"single_word": false,
|
353 |
+
"special": false
|
354 |
+
},
|
355 |
+
"44": {
|
356 |
+
"content": "<unused_43>",
|
357 |
+
"lstrip": false,
|
358 |
+
"normalized": false,
|
359 |
+
"rstrip": false,
|
360 |
+
"single_word": false,
|
361 |
+
"special": false
|
362 |
+
},
|
363 |
+
"45": {
|
364 |
+
"content": "<unused_44>",
|
365 |
+
"lstrip": false,
|
366 |
+
"normalized": false,
|
367 |
+
"rstrip": false,
|
368 |
+
"single_word": false,
|
369 |
+
"special": false
|
370 |
+
},
|
371 |
+
"46": {
|
372 |
+
"content": "<unused_45>",
|
373 |
+
"lstrip": false,
|
374 |
+
"normalized": false,
|
375 |
+
"rstrip": false,
|
376 |
+
"single_word": false,
|
377 |
+
"special": false
|
378 |
+
},
|
379 |
+
"47": {
|
380 |
+
"content": "<unused_46>",
|
381 |
+
"lstrip": false,
|
382 |
+
"normalized": false,
|
383 |
+
"rstrip": false,
|
384 |
+
"single_word": false,
|
385 |
+
"special": false
|
386 |
+
},
|
387 |
+
"48": {
|
388 |
+
"content": "<unused_47>",
|
389 |
+
"lstrip": false,
|
390 |
+
"normalized": false,
|
391 |
+
"rstrip": false,
|
392 |
+
"single_word": false,
|
393 |
+
"special": false
|
394 |
+
},
|
395 |
+
"49": {
|
396 |
+
"content": "<unused_48>",
|
397 |
+
"lstrip": false,
|
398 |
+
"normalized": false,
|
399 |
+
"rstrip": false,
|
400 |
+
"single_word": false,
|
401 |
+
"special": false
|
402 |
+
},
|
403 |
+
"50": {
|
404 |
+
"content": "<unused_49>",
|
405 |
+
"lstrip": false,
|
406 |
+
"normalized": false,
|
407 |
+
"rstrip": false,
|
408 |
+
"single_word": false,
|
409 |
+
"special": false
|
410 |
+
},
|
411 |
+
"51": {
|
412 |
+
"content": "<paraphrasing_0>",
|
413 |
+
"lstrip": false,
|
414 |
+
"normalized": false,
|
415 |
+
"rstrip": false,
|
416 |
+
"single_word": false,
|
417 |
+
"special": false
|
418 |
+
},
|
419 |
+
"52": {
|
420 |
+
"content": "<paraphrasing_1>",
|
421 |
+
"lstrip": false,
|
422 |
+
"normalized": false,
|
423 |
+
"rstrip": false,
|
424 |
+
"single_word": false,
|
425 |
+
"special": false
|
426 |
+
},
|
427 |
+
"53": {
|
428 |
+
"content": "<paraphrasing_2>",
|
429 |
+
"lstrip": false,
|
430 |
+
"normalized": false,
|
431 |
+
"rstrip": false,
|
432 |
+
"single_word": false,
|
433 |
+
"special": false
|
434 |
+
},
|
435 |
+
"54": {
|
436 |
+
"content": "<paraphrasing_3>",
|
437 |
+
"lstrip": false,
|
438 |
+
"normalized": false,
|
439 |
+
"rstrip": false,
|
440 |
+
"single_word": false,
|
441 |
+
"special": false
|
442 |
+
},
|
443 |
+
"55": {
|
444 |
+
"content": "<paraphrasing_4>",
|
445 |
+
"lstrip": false,
|
446 |
+
"normalized": false,
|
447 |
+
"rstrip": false,
|
448 |
+
"single_word": false,
|
449 |
+
"special": false
|
450 |
+
},
|
451 |
+
"56": {
|
452 |
+
"content": "<paraphrasing_5>",
|
453 |
+
"lstrip": false,
|
454 |
+
"normalized": false,
|
455 |
+
"rstrip": false,
|
456 |
+
"single_word": false,
|
457 |
+
"special": false
|
458 |
+
},
|
459 |
+
"57": {
|
460 |
+
"content": "<paraphrasing_6>",
|
461 |
+
"lstrip": false,
|
462 |
+
"normalized": false,
|
463 |
+
"rstrip": false,
|
464 |
+
"single_word": false,
|
465 |
+
"special": false
|
466 |
+
},
|
467 |
+
"58": {
|
468 |
+
"content": "<paraphrasing_7>",
|
469 |
+
"lstrip": false,
|
470 |
+
"normalized": false,
|
471 |
+
"rstrip": false,
|
472 |
+
"single_word": false,
|
473 |
+
"special": false
|
474 |
+
},
|
475 |
+
"59": {
|
476 |
+
"content": "<paraphrasing_8>",
|
477 |
+
"lstrip": false,
|
478 |
+
"normalized": false,
|
479 |
+
"rstrip": false,
|
480 |
+
"single_word": false,
|
481 |
+
"special": false
|
482 |
+
},
|
483 |
+
"60": {
|
484 |
+
"content": "<empty>",
|
485 |
+
"lstrip": false,
|
486 |
+
"normalized": false,
|
487 |
+
"rstrip": false,
|
488 |
+
"single_word": false,
|
489 |
+
"special": false
|
490 |
+
},
|
491 |
+
"61": {
|
492 |
+
"content": "<row>",
|
493 |
+
"lstrip": false,
|
494 |
+
"normalized": false,
|
495 |
+
"rstrip": false,
|
496 |
+
"single_word": false,
|
497 |
+
"special": false
|
498 |
+
},
|
499 |
+
"62": {
|
500 |
+
"content": "<cn>",
|
501 |
+
"lstrip": false,
|
502 |
+
"normalized": false,
|
503 |
+
"rstrip": false,
|
504 |
+
"single_word": false,
|
505 |
+
"special": false
|
506 |
+
},
|
507 |
+
"63": {
|
508 |
+
"content": "<t>",
|
509 |
+
"lstrip": false,
|
510 |
+
"normalized": false,
|
511 |
+
"rstrip": false,
|
512 |
+
"single_word": false,
|
513 |
+
"special": false
|
514 |
+
},
|
515 |
+
"64": {
|
516 |
+
"content": "<ans>",
|
517 |
+
"lstrip": false,
|
518 |
+
"normalized": false,
|
519 |
+
"rstrip": false,
|
520 |
+
"single_word": false,
|
521 |
+
"special": false
|
522 |
+
},
|
523 |
+
"65": {
|
524 |
+
"content": "[CLS]",
|
525 |
+
"lstrip": false,
|
526 |
+
"normalized": true,
|
527 |
+
"rstrip": false,
|
528 |
+
"single_word": false,
|
529 |
+
"special": true
|
530 |
+
},
|
531 |
+
"66": {
|
532 |
+
"content": "[SEP]",
|
533 |
+
"lstrip": false,
|
534 |
+
"normalized": true,
|
535 |
+
"rstrip": false,
|
536 |
+
"single_word": false,
|
537 |
+
"special": true
|
538 |
+
},
|
539 |
+
"67": {
|
540 |
+
"content": "[MASK]",
|
541 |
+
"lstrip": true,
|
542 |
+
"normalized": true,
|
543 |
+
"rstrip": false,
|
544 |
+
"single_word": false,
|
545 |
+
"special": true
|
546 |
+
},
|
547 |
+
"68": {
|
548 |
+
"content": "<unused_67>",
|
549 |
+
"lstrip": false,
|
550 |
+
"normalized": false,
|
551 |
+
"rstrip": false,
|
552 |
+
"single_word": false,
|
553 |
+
"special": false
|
554 |
+
},
|
555 |
+
"69": {
|
556 |
+
"content": "<unused_68>",
|
557 |
+
"lstrip": false,
|
558 |
+
"normalized": false,
|
559 |
+
"rstrip": false,
|
560 |
+
"single_word": false,
|
561 |
+
"special": false
|
562 |
+
},
|
563 |
+
"70": {
|
564 |
+
"content": "<unused_69>",
|
565 |
+
"lstrip": false,
|
566 |
+
"normalized": false,
|
567 |
+
"rstrip": false,
|
568 |
+
"single_word": false,
|
569 |
+
"special": false
|
570 |
+
},
|
571 |
+
"71": {
|
572 |
+
"content": "<unused_70>",
|
573 |
+
"lstrip": false,
|
574 |
+
"normalized": false,
|
575 |
+
"rstrip": false,
|
576 |
+
"single_word": false,
|
577 |
+
"special": false
|
578 |
+
},
|
579 |
+
"72": {
|
580 |
+
"content": "<unused_71>",
|
581 |
+
"lstrip": false,
|
582 |
+
"normalized": false,
|
583 |
+
"rstrip": false,
|
584 |
+
"single_word": false,
|
585 |
+
"special": false
|
586 |
+
},
|
587 |
+
"73": {
|
588 |
+
"content": "<unused_72>",
|
589 |
+
"lstrip": false,
|
590 |
+
"normalized": false,
|
591 |
+
"rstrip": false,
|
592 |
+
"single_word": false,
|
593 |
+
"special": false
|
594 |
+
},
|
595 |
+
"74": {
|
596 |
+
"content": "<unused_73>",
|
597 |
+
"lstrip": false,
|
598 |
+
"normalized": false,
|
599 |
+
"rstrip": false,
|
600 |
+
"single_word": false,
|
601 |
+
"special": false
|
602 |
+
},
|
603 |
+
"75": {
|
604 |
+
"content": "<unused_74>",
|
605 |
+
"lstrip": false,
|
606 |
+
"normalized": false,
|
607 |
+
"rstrip": false,
|
608 |
+
"single_word": false,
|
609 |
+
"special": false
|
610 |
+
},
|
611 |
+
"76": {
|
612 |
+
"content": "<unused_75>",
|
613 |
+
"lstrip": false,
|
614 |
+
"normalized": false,
|
615 |
+
"rstrip": false,
|
616 |
+
"single_word": false,
|
617 |
+
"special": false
|
618 |
+
},
|
619 |
+
"77": {
|
620 |
+
"content": "<unused_76>",
|
621 |
+
"lstrip": false,
|
622 |
+
"normalized": false,
|
623 |
+
"rstrip": false,
|
624 |
+
"single_word": false,
|
625 |
+
"special": false
|
626 |
+
},
|
627 |
+
"78": {
|
628 |
+
"content": "<unused_77>",
|
629 |
+
"lstrip": false,
|
630 |
+
"normalized": false,
|
631 |
+
"rstrip": false,
|
632 |
+
"single_word": false,
|
633 |
+
"special": false
|
634 |
+
},
|
635 |
+
"79": {
|
636 |
+
"content": "<unused_78>",
|
637 |
+
"lstrip": false,
|
638 |
+
"normalized": false,
|
639 |
+
"rstrip": false,
|
640 |
+
"single_word": false,
|
641 |
+
"special": false
|
642 |
+
},
|
643 |
+
"80": {
|
644 |
+
"content": "<unused_79>",
|
645 |
+
"lstrip": false,
|
646 |
+
"normalized": false,
|
647 |
+
"rstrip": false,
|
648 |
+
"single_word": false,
|
649 |
+
"special": false
|
650 |
+
},
|
651 |
+
"81": {
|
652 |
+
"content": "<unused_80>",
|
653 |
+
"lstrip": false,
|
654 |
+
"normalized": false,
|
655 |
+
"rstrip": false,
|
656 |
+
"single_word": false,
|
657 |
+
"special": false
|
658 |
+
},
|
659 |
+
"82": {
|
660 |
+
"content": "<unused_81>",
|
661 |
+
"lstrip": false,
|
662 |
+
"normalized": false,
|
663 |
+
"rstrip": false,
|
664 |
+
"single_word": false,
|
665 |
+
"special": false
|
666 |
+
},
|
667 |
+
"83": {
|
668 |
+
"content": "<unused_82>",
|
669 |
+
"lstrip": false,
|
670 |
+
"normalized": false,
|
671 |
+
"rstrip": false,
|
672 |
+
"single_word": false,
|
673 |
+
"special": false
|
674 |
+
},
|
675 |
+
"84": {
|
676 |
+
"content": "<unused_83>",
|
677 |
+
"lstrip": false,
|
678 |
+
"normalized": false,
|
679 |
+
"rstrip": false,
|
680 |
+
"single_word": false,
|
681 |
+
"special": false
|
682 |
+
},
|
683 |
+
"85": {
|
684 |
+
"content": "<unused_84>",
|
685 |
+
"lstrip": false,
|
686 |
+
"normalized": false,
|
687 |
+
"rstrip": false,
|
688 |
+
"single_word": false,
|
689 |
+
"special": false
|
690 |
+
},
|
691 |
+
"86": {
|
692 |
+
"content": "<unused_85>",
|
693 |
+
"lstrip": false,
|
694 |
+
"normalized": false,
|
695 |
+
"rstrip": false,
|
696 |
+
"single_word": false,
|
697 |
+
"special": false
|
698 |
+
},
|
699 |
+
"87": {
|
700 |
+
"content": "<unused_86>",
|
701 |
+
"lstrip": false,
|
702 |
+
"normalized": false,
|
703 |
+
"rstrip": false,
|
704 |
+
"single_word": false,
|
705 |
+
"special": false
|
706 |
+
},
|
707 |
+
"88": {
|
708 |
+
"content": "<unused_87>",
|
709 |
+
"lstrip": false,
|
710 |
+
"normalized": false,
|
711 |
+
"rstrip": false,
|
712 |
+
"single_word": false,
|
713 |
+
"special": false
|
714 |
+
},
|
715 |
+
"89": {
|
716 |
+
"content": "<unused_88>",
|
717 |
+
"lstrip": false,
|
718 |
+
"normalized": false,
|
719 |
+
"rstrip": false,
|
720 |
+
"single_word": false,
|
721 |
+
"special": false
|
722 |
+
},
|
723 |
+
"90": {
|
724 |
+
"content": "<unused_89>",
|
725 |
+
"lstrip": false,
|
726 |
+
"normalized": false,
|
727 |
+
"rstrip": false,
|
728 |
+
"single_word": false,
|
729 |
+
"special": false
|
730 |
+
},
|
731 |
+
"91": {
|
732 |
+
"content": "<unused_90>",
|
733 |
+
"lstrip": false,
|
734 |
+
"normalized": false,
|
735 |
+
"rstrip": false,
|
736 |
+
"single_word": false,
|
737 |
+
"special": false
|
738 |
+
},
|
739 |
+
"92": {
|
740 |
+
"content": "<unused_91>",
|
741 |
+
"lstrip": false,
|
742 |
+
"normalized": false,
|
743 |
+
"rstrip": false,
|
744 |
+
"single_word": false,
|
745 |
+
"special": false
|
746 |
+
},
|
747 |
+
"93": {
|
748 |
+
"content": "<unused_92>",
|
749 |
+
"lstrip": false,
|
750 |
+
"normalized": false,
|
751 |
+
"rstrip": false,
|
752 |
+
"single_word": false,
|
753 |
+
"special": false
|
754 |
+
},
|
755 |
+
"94": {
|
756 |
+
"content": "<unused_93>",
|
757 |
+
"lstrip": false,
|
758 |
+
"normalized": false,
|
759 |
+
"rstrip": false,
|
760 |
+
"single_word": false,
|
761 |
+
"special": false
|
762 |
+
},
|
763 |
+
"95": {
|
764 |
+
"content": "<unused_94>",
|
765 |
+
"lstrip": false,
|
766 |
+
"normalized": false,
|
767 |
+
"rstrip": false,
|
768 |
+
"single_word": false,
|
769 |
+
"special": false
|
770 |
+
},
|
771 |
+
"96": {
|
772 |
+
"content": "<unused_95>",
|
773 |
+
"lstrip": false,
|
774 |
+
"normalized": false,
|
775 |
+
"rstrip": false,
|
776 |
+
"single_word": false,
|
777 |
+
"special": false
|
778 |
+
},
|
779 |
+
"97": {
|
780 |
+
"content": "<unused_96>",
|
781 |
+
"lstrip": false,
|
782 |
+
"normalized": false,
|
783 |
+
"rstrip": false,
|
784 |
+
"single_word": false,
|
785 |
+
"special": false
|
786 |
+
},
|
787 |
+
"98": {
|
788 |
+
"content": "<unused_97>",
|
789 |
+
"lstrip": false,
|
790 |
+
"normalized": false,
|
791 |
+
"rstrip": false,
|
792 |
+
"single_word": false,
|
793 |
+
"special": false
|
794 |
+
},
|
795 |
+
"99": {
|
796 |
+
"content": "<unused_98>",
|
797 |
+
"lstrip": false,
|
798 |
+
"normalized": false,
|
799 |
+
"rstrip": false,
|
800 |
+
"single_word": false,
|
801 |
+
"special": false
|
802 |
+
},
|
803 |
+
"100": {
|
804 |
+
"content": "<unk>",
|
805 |
+
"lstrip": false,
|
806 |
+
"normalized": true,
|
807 |
+
"rstrip": false,
|
808 |
+
"single_word": false,
|
809 |
+
"special": true
|
810 |
+
}
|
811 |
+
},
|
812 |
+
"bos_token": "</s>",
|
813 |
+
"clean_up_tokenization_spaces": false,
|
814 |
+
"cls_token": "[CLS]",
|
815 |
+
"eos_token": "<s>",
|
816 |
+
"extra_special_tokens": {},
|
817 |
+
"mask_token": "[MASK]",
|
818 |
+
"model_max_length": 4096,
|
819 |
+
"pad_token": "<pad>",
|
820 |
+
"sep_token": "[SEP]",
|
821 |
+
"sp_model_kwargs": {},
|
822 |
+
"tokenizer_class": "BigBirdTokenizer",
|
823 |
+
"unk_token": "<unk>"
|
824 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b58c7f9ea10d6f939d945d9869da13d91dc1a5aa860e689f2b928a864d7bc32
|
3 |
+
size 5368
|
training_params.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"data_path": "bigbird-flight-2/autotrain-data",
|
3 |
+
"model": "google/bigbird-roberta-base",
|
4 |
+
"lr": 5e-05,
|
5 |
+
"epochs": 32,
|
6 |
+
"max_seq_length": 1024,
|
7 |
+
"batch_size": 4,
|
8 |
+
"warmup_ratio": 0.1,
|
9 |
+
"gradient_accumulation": 1,
|
10 |
+
"optimizer": "adamw_torch",
|
11 |
+
"scheduler": "linear",
|
12 |
+
"weight_decay": 0.0,
|
13 |
+
"max_grad_norm": 1.0,
|
14 |
+
"seed": 42,
|
15 |
+
"train_split": "train",
|
16 |
+
"valid_split": "validation",
|
17 |
+
"text_column": "autotrain_text",
|
18 |
+
"target_column": "autotrain_label",
|
19 |
+
"logging_steps": 50,
|
20 |
+
"project_name": "bigbird-flight-2",
|
21 |
+
"auto_find_batch_size": false,
|
22 |
+
"mixed_precision": "fp16",
|
23 |
+
"save_total_limit": 1,
|
24 |
+
"push_to_hub": true,
|
25 |
+
"eval_strategy": "epoch",
|
26 |
+
"username": "pvaluedotone",
|
27 |
+
"log": "tensorboard",
|
28 |
+
"early_stopping_patience": 5,
|
29 |
+
"early_stopping_threshold": 0.01
|
30 |
+
}
|