Upload folder using huggingface_hub
Browse files- README.md +25 -0
- checkpoint-654/config.json +38 -0
- checkpoint-654/model.safetensors +3 -0
- checkpoint-654/optimizer.pt +3 -0
- checkpoint-654/rng_state.pth +3 -0
- checkpoint-654/scheduler.pt +3 -0
- checkpoint-654/trainer_state.json +237 -0
- checkpoint-654/training_args.bin +3 -0
- config.json +38 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- runs/May23_14-53-54_r-stepharn-roberta-opt-v2-sokxo7d3-f3daf-tj2cf/events.out.tfevents.1716476034.r-stepharn-roberta-opt-v2-sokxo7d3-f3daf-tj2cf.100.0 +2 -2
- runs/May23_14-53-54_r-stepharn-roberta-opt-v2-sokxo7d3-f3daf-tj2cf/events.out.tfevents.1716485809.r-stepharn-roberta-opt-v2-sokxo7d3-f3daf-tj2cf.100.1 +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- training_args.bin +3 -0
- training_params.json +30 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
tags:
|
4 |
+
- autotrain
|
5 |
+
- text-classification
|
6 |
+
widget:
|
7 |
+
- text: "I love AutoTrain"
|
8 |
+
---
|
9 |
+
|
10 |
+
# Model Trained Using AutoTrain
|
11 |
+
|
12 |
+
- Problem type: Text Classification
|
13 |
+
|
14 |
+
## Validation Metrics
|
15 |
+
loss: 0.46739959716796875
|
16 |
+
|
17 |
+
f1: 0.8414839797639123
|
18 |
+
|
19 |
+
precision: 0.8603448275862069
|
20 |
+
|
21 |
+
recall: 0.8234323432343235
|
22 |
+
|
23 |
+
auc: 0.9097215546797399
|
24 |
+
|
25 |
+
accuracy: 0.8322925958965209
|
checkpoint-654/config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "cardiffnlp/twitter-roberta-base-sentiment-latest",
|
3 |
+
"_num_labels": 2,
|
4 |
+
"architectures": [
|
5 |
+
"RobertaForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"classifier_dropout": null,
|
10 |
+
"eos_token_id": 2,
|
11 |
+
"gradient_checkpointing": false,
|
12 |
+
"hidden_act": "gelu",
|
13 |
+
"hidden_dropout_prob": 0.1,
|
14 |
+
"hidden_size": 768,
|
15 |
+
"id2label": {
|
16 |
+
"0": "0",
|
17 |
+
"1": "1"
|
18 |
+
},
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"intermediate_size": 3072,
|
21 |
+
"label2id": {
|
22 |
+
"0": 0,
|
23 |
+
"1": 1
|
24 |
+
},
|
25 |
+
"layer_norm_eps": 1e-05,
|
26 |
+
"max_position_embeddings": 514,
|
27 |
+
"model_type": "roberta",
|
28 |
+
"num_attention_heads": 12,
|
29 |
+
"num_hidden_layers": 12,
|
30 |
+
"pad_token_id": 1,
|
31 |
+
"position_embedding_type": "absolute",
|
32 |
+
"problem_type": "single_label_classification",
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.41.0",
|
35 |
+
"type_vocab_size": 1,
|
36 |
+
"use_cache": true,
|
37 |
+
"vocab_size": 50265
|
38 |
+
}
|
checkpoint-654/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ae8c9a9643f873bc5706180f50e7384fd5597961feadfb4c132ea7e558df2c6
|
3 |
+
size 498612824
|
checkpoint-654/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c45e14573d76470c6be08cec16e8822dcc234834307886da84b60f30fda0dcd
|
3 |
+
size 997339898
|
checkpoint-654/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d97084fa3e100b473765cc3ae291c883e2ad5abdd0b52d5aa7af09510ab6ec5f
|
3 |
+
size 13990
|
checkpoint-654/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1430b6f5fb996089c04641a155d001cb4e583b9fabf4b301e1627438e60274f1
|
3 |
+
size 1064
|
checkpoint-654/trainer_state.json
ADDED
@@ -0,0 +1,237 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.46739959716796875,
|
3 |
+
"best_model_checkpoint": "RoBERTa-OPT-BinaryLabels/checkpoint-654",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 654,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0382262996941896,
|
13 |
+
"grad_norm": 12.757129669189453,
|
14 |
+
"learning_rate": 6.345177664974619e-06,
|
15 |
+
"loss": 0.5752,
|
16 |
+
"step": 25
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.0764525993883792,
|
20 |
+
"grad_norm": 51.579280853271484,
|
21 |
+
"learning_rate": 1.2690355329949238e-05,
|
22 |
+
"loss": 0.4765,
|
23 |
+
"step": 50
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.11467889908256881,
|
27 |
+
"grad_norm": 15.670730590820312,
|
28 |
+
"learning_rate": 1.9035532994923858e-05,
|
29 |
+
"loss": 0.5207,
|
30 |
+
"step": 75
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.1529051987767584,
|
34 |
+
"grad_norm": 11.611441612243652,
|
35 |
+
"learning_rate": 2.5380710659898476e-05,
|
36 |
+
"loss": 0.5373,
|
37 |
+
"step": 100
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.191131498470948,
|
41 |
+
"grad_norm": 29.748741149902344,
|
42 |
+
"learning_rate": 3.17258883248731e-05,
|
43 |
+
"loss": 0.4203,
|
44 |
+
"step": 125
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.22935779816513763,
|
48 |
+
"grad_norm": 21.099533081054688,
|
49 |
+
"learning_rate": 3.8071065989847716e-05,
|
50 |
+
"loss": 0.4187,
|
51 |
+
"step": 150
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.26758409785932724,
|
55 |
+
"grad_norm": 39.19257736206055,
|
56 |
+
"learning_rate": 4.4416243654822335e-05,
|
57 |
+
"loss": 0.6043,
|
58 |
+
"step": 175
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.3058103975535168,
|
62 |
+
"grad_norm": 2.004885196685791,
|
63 |
+
"learning_rate": 4.991501416430595e-05,
|
64 |
+
"loss": 0.4767,
|
65 |
+
"step": 200
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.3440366972477064,
|
69 |
+
"grad_norm": 11.603029251098633,
|
70 |
+
"learning_rate": 4.920679886685552e-05,
|
71 |
+
"loss": 0.6514,
|
72 |
+
"step": 225
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.382262996941896,
|
76 |
+
"grad_norm": 15.01026439666748,
|
77 |
+
"learning_rate": 4.84985835694051e-05,
|
78 |
+
"loss": 0.4118,
|
79 |
+
"step": 250
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.42048929663608564,
|
83 |
+
"grad_norm": 60.25313186645508,
|
84 |
+
"learning_rate": 4.7790368271954674e-05,
|
85 |
+
"loss": 0.6498,
|
86 |
+
"step": 275
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.45871559633027525,
|
90 |
+
"grad_norm": 8.442073822021484,
|
91 |
+
"learning_rate": 4.7082152974504253e-05,
|
92 |
+
"loss": 0.3712,
|
93 |
+
"step": 300
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.4969418960244648,
|
97 |
+
"grad_norm": 21.02886199951172,
|
98 |
+
"learning_rate": 4.6373937677053826e-05,
|
99 |
+
"loss": 0.5348,
|
100 |
+
"step": 325
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.5351681957186545,
|
104 |
+
"grad_norm": 17.496578216552734,
|
105 |
+
"learning_rate": 4.5665722379603405e-05,
|
106 |
+
"loss": 0.4791,
|
107 |
+
"step": 350
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.573394495412844,
|
111 |
+
"grad_norm": 7.593109130859375,
|
112 |
+
"learning_rate": 4.495750708215298e-05,
|
113 |
+
"loss": 0.5379,
|
114 |
+
"step": 375
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.6116207951070336,
|
118 |
+
"grad_norm": 15.237981796264648,
|
119 |
+
"learning_rate": 4.424929178470255e-05,
|
120 |
+
"loss": 0.4199,
|
121 |
+
"step": 400
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.6498470948012233,
|
125 |
+
"grad_norm": 14.45595645904541,
|
126 |
+
"learning_rate": 4.354107648725212e-05,
|
127 |
+
"loss": 0.4655,
|
128 |
+
"step": 425
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.6880733944954128,
|
132 |
+
"grad_norm": 4.385306358337402,
|
133 |
+
"learning_rate": 4.283286118980171e-05,
|
134 |
+
"loss": 0.444,
|
135 |
+
"step": 450
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.7262996941896025,
|
139 |
+
"grad_norm": 2.666689872741699,
|
140 |
+
"learning_rate": 4.212464589235128e-05,
|
141 |
+
"loss": 0.4259,
|
142 |
+
"step": 475
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.764525993883792,
|
146 |
+
"grad_norm": 12.022340774536133,
|
147 |
+
"learning_rate": 4.141643059490085e-05,
|
148 |
+
"loss": 0.604,
|
149 |
+
"step": 500
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.8027522935779816,
|
153 |
+
"grad_norm": 11.57751178741455,
|
154 |
+
"learning_rate": 4.0708215297450424e-05,
|
155 |
+
"loss": 0.4591,
|
156 |
+
"step": 525
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.8409785932721713,
|
160 |
+
"grad_norm": 1.3041644096374512,
|
161 |
+
"learning_rate": 4e-05,
|
162 |
+
"loss": 0.4982,
|
163 |
+
"step": 550
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.8792048929663608,
|
167 |
+
"grad_norm": 2.4270074367523193,
|
168 |
+
"learning_rate": 3.9291784702549576e-05,
|
169 |
+
"loss": 0.3971,
|
170 |
+
"step": 575
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.9174311926605505,
|
174 |
+
"grad_norm": 4.834415435791016,
|
175 |
+
"learning_rate": 3.8583569405099155e-05,
|
176 |
+
"loss": 0.4902,
|
177 |
+
"step": 600
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.9556574923547401,
|
181 |
+
"grad_norm": 6.696393013000488,
|
182 |
+
"learning_rate": 3.787535410764873e-05,
|
183 |
+
"loss": 0.3798,
|
184 |
+
"step": 625
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.9938837920489296,
|
188 |
+
"grad_norm": 3.1791908740997314,
|
189 |
+
"learning_rate": 3.7167138810198306e-05,
|
190 |
+
"loss": 0.5361,
|
191 |
+
"step": 650
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 1.0,
|
195 |
+
"eval_accuracy": 0.8322925958965209,
|
196 |
+
"eval_auc": 0.9097215546797399,
|
197 |
+
"eval_f1": 0.8414839797639123,
|
198 |
+
"eval_loss": 0.46739959716796875,
|
199 |
+
"eval_precision": 0.8603448275862069,
|
200 |
+
"eval_recall": 0.8234323432343235,
|
201 |
+
"eval_runtime": 158.2492,
|
202 |
+
"eval_samples_per_second": 7.084,
|
203 |
+
"eval_steps_per_second": 0.449,
|
204 |
+
"step": 654
|
205 |
+
}
|
206 |
+
],
|
207 |
+
"logging_steps": 25,
|
208 |
+
"max_steps": 1962,
|
209 |
+
"num_input_tokens_seen": 0,
|
210 |
+
"num_train_epochs": 3,
|
211 |
+
"save_steps": 500,
|
212 |
+
"stateful_callbacks": {
|
213 |
+
"EarlyStoppingCallback": {
|
214 |
+
"args": {
|
215 |
+
"early_stopping_patience": 5,
|
216 |
+
"early_stopping_threshold": 0.01
|
217 |
+
},
|
218 |
+
"attributes": {
|
219 |
+
"early_stopping_patience_counter": 0
|
220 |
+
}
|
221 |
+
},
|
222 |
+
"TrainerControl": {
|
223 |
+
"args": {
|
224 |
+
"should_epoch_stop": false,
|
225 |
+
"should_evaluate": false,
|
226 |
+
"should_log": false,
|
227 |
+
"should_save": true,
|
228 |
+
"should_training_stop": false
|
229 |
+
},
|
230 |
+
"attributes": {}
|
231 |
+
}
|
232 |
+
},
|
233 |
+
"total_flos": 344149260410880.0,
|
234 |
+
"train_batch_size": 8,
|
235 |
+
"trial_name": null,
|
236 |
+
"trial_params": null
|
237 |
+
}
|
checkpoint-654/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb8f5c9a2ba9bf2d3e7118946dba39176e04f7d23b0096b5bbb3e07226d4850c
|
3 |
+
size 5176
|
config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "cardiffnlp/twitter-roberta-base-sentiment-latest",
|
3 |
+
"_num_labels": 2,
|
4 |
+
"architectures": [
|
5 |
+
"RobertaForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"classifier_dropout": null,
|
10 |
+
"eos_token_id": 2,
|
11 |
+
"gradient_checkpointing": false,
|
12 |
+
"hidden_act": "gelu",
|
13 |
+
"hidden_dropout_prob": 0.1,
|
14 |
+
"hidden_size": 768,
|
15 |
+
"id2label": {
|
16 |
+
"0": "0",
|
17 |
+
"1": "1"
|
18 |
+
},
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"intermediate_size": 3072,
|
21 |
+
"label2id": {
|
22 |
+
"0": 0,
|
23 |
+
"1": 1
|
24 |
+
},
|
25 |
+
"layer_norm_eps": 1e-05,
|
26 |
+
"max_position_embeddings": 514,
|
27 |
+
"model_type": "roberta",
|
28 |
+
"num_attention_heads": 12,
|
29 |
+
"num_hidden_layers": 12,
|
30 |
+
"pad_token_id": 1,
|
31 |
+
"position_embedding_type": "absolute",
|
32 |
+
"problem_type": "single_label_classification",
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.41.0",
|
35 |
+
"type_vocab_size": 1,
|
36 |
+
"use_cache": true,
|
37 |
+
"vocab_size": 50265
|
38 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ae8c9a9643f873bc5706180f50e7384fd5597961feadfb4c132ea7e558df2c6
|
3 |
+
size 498612824
|
runs/May23_14-53-54_r-stepharn-roberta-opt-v2-sokxo7d3-f3daf-tj2cf/events.out.tfevents.1716476034.r-stepharn-roberta-opt-v2-sokxo7d3-f3daf-tj2cf.100.0
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:b3c0a8a8f4dc1835d1c73cd3d344b8c46d2fca2d78c30b3f409a01571df2bd43
|
3 |
+
size 23438
|
runs/May23_14-53-54_r-stepharn-roberta-opt-v2-sokxo7d3-f3daf-tj2cf/events.out.tfevents.1716485809.r-stepharn-roberta-opt-v2-sokxo7d3-f3daf-tj2cf.100.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5524bc942d44a5dac8dd915e0cbbbff5b59bb015065f57e539c9bed5afb39c07
|
3 |
+
size 607
|
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": "<s>",
|
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": false,
|
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": "</s>",
|
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 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<pad>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"50264": {
|
37 |
+
"content": "<mask>",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"bos_token": "<s>",
|
46 |
+
"clean_up_tokenization_spaces": true,
|
47 |
+
"cls_token": "<s>",
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"errors": "replace",
|
50 |
+
"mask_token": "<mask>",
|
51 |
+
"model_max_length": 1000000000000000019884624838656,
|
52 |
+
"pad_token": "<pad>",
|
53 |
+
"sep_token": "</s>",
|
54 |
+
"tokenizer_class": "RobertaTokenizer",
|
55 |
+
"trim_offsets": true,
|
56 |
+
"unk_token": "<unk>"
|
57 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb8f5c9a2ba9bf2d3e7118946dba39176e04f7d23b0096b5bbb3e07226d4850c
|
3 |
+
size 5176
|
training_params.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"data_path": "RoBERTa-OPT-BinaryLabels/autotrain-data",
|
3 |
+
"model": "cardiffnlp/twitter-roberta-base-sentiment-latest",
|
4 |
+
"lr": 5e-05,
|
5 |
+
"epochs": 3,
|
6 |
+
"max_seq_length": 128,
|
7 |
+
"batch_size": 8,
|
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": -1,
|
20 |
+
"project_name": "RoBERTa-OPT-BinaryLabels",
|
21 |
+
"auto_find_batch_size": false,
|
22 |
+
"mixed_precision": "fp16",
|
23 |
+
"save_total_limit": 1,
|
24 |
+
"push_to_hub": true,
|
25 |
+
"evaluation_strategy": "epoch",
|
26 |
+
"username": "StephArn",
|
27 |
+
"log": "tensorboard",
|
28 |
+
"early_stopping_patience": 5,
|
29 |
+
"early_stopping_threshold": 0.01
|
30 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|