Commit
•
cb847b9
1
Parent(s):
744edd2
Upload 15 files
Browse files- README.md +68 -0
- added_tokens.json +1 -0
- all_results.json +20 -0
- config.json +57 -0
- eval_results.json +9 -0
- generated_predictions.txt +430 -0
- predict_results.json +8 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- train_results.json +8 -0
- trainer_state.json +127 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- accuracy
|
7 |
+
model-index:
|
8 |
+
- name: tst-translation354
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# tst-translation354
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [t5-large](https://huggingface.co/t5-large) on an unknown dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.1871
|
20 |
+
- Accuracy: 0.8607
|
21 |
+
|
22 |
+
## Model description
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Intended uses & limitations
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training and evaluation data
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training procedure
|
35 |
+
|
36 |
+
### Training hyperparameters
|
37 |
+
|
38 |
+
The following hyperparameters were used during training:
|
39 |
+
- learning_rate: 5e-05
|
40 |
+
- train_batch_size: 12
|
41 |
+
- eval_batch_size: 12
|
42 |
+
- seed: 42
|
43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
+
- lr_scheduler_type: linear
|
45 |
+
- num_epochs: 10.0
|
46 |
+
|
47 |
+
### Training results
|
48 |
+
|
49 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
50 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
51 |
+
| No log | 1.0 | 105 | 0.3619 | 0.3699 |
|
52 |
+
| No log | 2.0 | 210 | 0.1750 | 0.7352 |
|
53 |
+
| No log | 3.0 | 315 | 0.1416 | 0.7922 |
|
54 |
+
| No log | 4.0 | 420 | 0.1225 | 0.8425 |
|
55 |
+
| 0.3579 | 5.0 | 525 | 0.1310 | 0.8516 |
|
56 |
+
| 0.3579 | 6.0 | 630 | 0.1358 | 0.8425 |
|
57 |
+
| 0.3579 | 7.0 | 735 | 0.1605 | 0.8493 |
|
58 |
+
| 0.3579 | 8.0 | 840 | 0.1871 | 0.8607 |
|
59 |
+
| 0.3579 | 9.0 | 945 | 0.1990 | 0.8516 |
|
60 |
+
| 0.054 | 10.0 | 1050 | 0.2134 | 0.8607 |
|
61 |
+
|
62 |
+
|
63 |
+
### Framework versions
|
64 |
+
|
65 |
+
- Transformers 4.17.0
|
66 |
+
- Pytorch 1.11.0+cu113
|
67 |
+
- Datasets 1.17.0
|
68 |
+
- Tokenizers 0.11.6
|
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"[EQUATION]": 32101, "[REF]": 32102, "[MATH]": 32100, "[CITATION]": 32103}
|
all_results.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"eval_accuracy": 0.860730593607306,
|
4 |
+
"eval_loss": 0.1871233731508255,
|
5 |
+
"eval_runtime": 15.6788,
|
6 |
+
"eval_samples": 438,
|
7 |
+
"eval_samples_per_second": 27.936,
|
8 |
+
"eval_steps_per_second": 2.36,
|
9 |
+
"predict_accuracy": 0.8441860465116279,
|
10 |
+
"predict_loss": 0.208589106798172,
|
11 |
+
"predict_runtime": 18.0974,
|
12 |
+
"predict_samples": 430,
|
13 |
+
"predict_samples_per_second": 23.76,
|
14 |
+
"predict_steps_per_second": 1.989,
|
15 |
+
"train_loss": 0.1974729861531939,
|
16 |
+
"train_runtime": 785.0626,
|
17 |
+
"train_samples": 1254,
|
18 |
+
"train_samples_per_second": 15.973,
|
19 |
+
"train_steps_per_second": 1.337
|
20 |
+
}
|
config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "t5-large",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"d_ff": 4096,
|
7 |
+
"d_kv": 64,
|
8 |
+
"d_model": 1024,
|
9 |
+
"decoder_start_token_id": 0,
|
10 |
+
"dropout_rate": 0.1,
|
11 |
+
"eos_token_id": 1,
|
12 |
+
"feed_forward_proj": "relu",
|
13 |
+
"initializer_factor": 1.0,
|
14 |
+
"is_encoder_decoder": true,
|
15 |
+
"layer_norm_epsilon": 1e-06,
|
16 |
+
"model_type": "t5",
|
17 |
+
"n_positions": 512,
|
18 |
+
"num_decoder_layers": 24,
|
19 |
+
"num_heads": 16,
|
20 |
+
"num_layers": 24,
|
21 |
+
"output_past": true,
|
22 |
+
"pad_token_id": 0,
|
23 |
+
"relative_attention_num_buckets": 32,
|
24 |
+
"task_specific_params": {
|
25 |
+
"summarization": {
|
26 |
+
"early_stopping": true,
|
27 |
+
"length_penalty": 2.0,
|
28 |
+
"max_length": 200,
|
29 |
+
"min_length": 30,
|
30 |
+
"no_repeat_ngram_size": 3,
|
31 |
+
"num_beams": 4,
|
32 |
+
"prefix": "summarize: "
|
33 |
+
},
|
34 |
+
"translation_en_to_de": {
|
35 |
+
"early_stopping": true,
|
36 |
+
"max_length": 300,
|
37 |
+
"num_beams": 4,
|
38 |
+
"prefix": "translate English to German: "
|
39 |
+
},
|
40 |
+
"translation_en_to_fr": {
|
41 |
+
"early_stopping": true,
|
42 |
+
"max_length": 300,
|
43 |
+
"num_beams": 4,
|
44 |
+
"prefix": "translate English to French: "
|
45 |
+
},
|
46 |
+
"translation_en_to_ro": {
|
47 |
+
"early_stopping": true,
|
48 |
+
"max_length": 300,
|
49 |
+
"num_beams": 4,
|
50 |
+
"prefix": "translate English to Romanian: "
|
51 |
+
}
|
52 |
+
},
|
53 |
+
"torch_dtype": "float32",
|
54 |
+
"transformers_version": "4.17.0",
|
55 |
+
"use_cache": true,
|
56 |
+
"vocab_size": 32104
|
57 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"eval_accuracy": 0.860730593607306,
|
4 |
+
"eval_loss": 0.1871233731508255,
|
5 |
+
"eval_runtime": 15.6788,
|
6 |
+
"eval_samples": 438,
|
7 |
+
"eval_samples_per_second": 27.936,
|
8 |
+
"eval_steps_per_second": 2.36
|
9 |
+
}
|
generated_predictions.txt
ADDED
@@ -0,0 +1,430 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
Format
|
2 |
+
Content
|
3 |
+
Language
|
4 |
+
Content
|
5 |
+
Content
|
6 |
+
Language
|
7 |
+
Content
|
8 |
+
Format
|
9 |
+
Format
|
10 |
+
Language
|
11 |
+
Format
|
12 |
+
Improve-grammar-Typo
|
13 |
+
Language
|
14 |
+
Content
|
15 |
+
Format
|
16 |
+
Content
|
17 |
+
Improve-grammar-Typo
|
18 |
+
Language
|
19 |
+
Language
|
20 |
+
Content
|
21 |
+
Content
|
22 |
+
Improve-grammar-Typo
|
23 |
+
Language
|
24 |
+
Improve-grammar-Typo
|
25 |
+
Improve-grammar-Typo
|
26 |
+
Format
|
27 |
+
Improve-grammar-Typo
|
28 |
+
Language
|
29 |
+
Content
|
30 |
+
Language
|
31 |
+
Format
|
32 |
+
Improve-grammar-Typo
|
33 |
+
Format
|
34 |
+
Language
|
35 |
+
Content
|
36 |
+
Format
|
37 |
+
Language
|
38 |
+
Format
|
39 |
+
Format
|
40 |
+
Language
|
41 |
+
Language
|
42 |
+
Language
|
43 |
+
Content
|
44 |
+
Content
|
45 |
+
Format
|
46 |
+
Content
|
47 |
+
Format
|
48 |
+
Format
|
49 |
+
Format
|
50 |
+
Format
|
51 |
+
Language
|
52 |
+
Format
|
53 |
+
Improve-grammar-Typo
|
54 |
+
Content
|
55 |
+
Format
|
56 |
+
Language
|
57 |
+
Language
|
58 |
+
Language
|
59 |
+
Content
|
60 |
+
Language
|
61 |
+
Format
|
62 |
+
Content
|
63 |
+
Content
|
64 |
+
Content
|
65 |
+
Content
|
66 |
+
Content
|
67 |
+
Language
|
68 |
+
Format
|
69 |
+
Language
|
70 |
+
Language
|
71 |
+
Language
|
72 |
+
Content
|
73 |
+
Language
|
74 |
+
Improve-grammar-Typo
|
75 |
+
Improve-grammar-Typo
|
76 |
+
Content
|
77 |
+
Improve-grammar-Typo
|
78 |
+
Format
|
79 |
+
Format
|
80 |
+
Improve-grammar-Typo
|
81 |
+
Format
|
82 |
+
Content
|
83 |
+
Content
|
84 |
+
Language
|
85 |
+
Improve-grammar-Typo
|
86 |
+
Format
|
87 |
+
Language
|
88 |
+
Content
|
89 |
+
Format
|
90 |
+
Format
|
91 |
+
Language
|
92 |
+
Improve-grammar-Typo
|
93 |
+
Content
|
94 |
+
Language
|
95 |
+
Format
|
96 |
+
Format
|
97 |
+
Content
|
98 |
+
Language
|
99 |
+
Improve-grammar-Typo
|
100 |
+
Content
|
101 |
+
Format
|
102 |
+
Content
|
103 |
+
Language
|
104 |
+
Language
|
105 |
+
Content
|
106 |
+
Content
|
107 |
+
Content
|
108 |
+
Language
|
109 |
+
Language
|
110 |
+
Format
|
111 |
+
Format
|
112 |
+
Format
|
113 |
+
Format
|
114 |
+
Format
|
115 |
+
Language
|
116 |
+
Content
|
117 |
+
Language
|
118 |
+
Improve-grammar-Typo
|
119 |
+
Format
|
120 |
+
Format
|
121 |
+
Improve-grammar-Typo
|
122 |
+
Content
|
123 |
+
Content
|
124 |
+
Improve-grammar-Typo
|
125 |
+
Language
|
126 |
+
Improve-grammar-Typo
|
127 |
+
Improve-grammar-Typo
|
128 |
+
Content
|
129 |
+
Improve-grammar-Typo
|
130 |
+
Content
|
131 |
+
Improve-grammar-Typo
|
132 |
+
Format
|
133 |
+
Format
|
134 |
+
Content
|
135 |
+
Content
|
136 |
+
Language
|
137 |
+
Content
|
138 |
+
Content
|
139 |
+
Improve-grammar-Typo
|
140 |
+
Content
|
141 |
+
Content
|
142 |
+
Improve-grammar-Typo
|
143 |
+
Improve-grammar-Typo
|
144 |
+
Content
|
145 |
+
Format
|
146 |
+
Language
|
147 |
+
Improve-grammar-Typo
|
148 |
+
Improve-grammar-Typo
|
149 |
+
Content
|
150 |
+
Content
|
151 |
+
Format
|
152 |
+
Content
|
153 |
+
Language
|
154 |
+
Content
|
155 |
+
Improve-grammar-Typo
|
156 |
+
Language
|
157 |
+
Improve-grammar-Typo
|
158 |
+
Content
|
159 |
+
Content
|
160 |
+
Format
|
161 |
+
Improve-grammar-Typo
|
162 |
+
Format
|
163 |
+
Language
|
164 |
+
Content
|
165 |
+
Content
|
166 |
+
Content
|
167 |
+
Improve-grammar-Typo
|
168 |
+
Content
|
169 |
+
Improve-grammar-Typo
|
170 |
+
Format
|
171 |
+
Content
|
172 |
+
Language
|
173 |
+
Format
|
174 |
+
Format
|
175 |
+
Format
|
176 |
+
Language
|
177 |
+
Format
|
178 |
+
Content
|
179 |
+
Content
|
180 |
+
Content
|
181 |
+
Content
|
182 |
+
Content
|
183 |
+
Language
|
184 |
+
Format
|
185 |
+
Language
|
186 |
+
Content
|
187 |
+
Improve-grammar-Typo
|
188 |
+
Format
|
189 |
+
Content
|
190 |
+
Content
|
191 |
+
Language
|
192 |
+
Content
|
193 |
+
Format
|
194 |
+
Format
|
195 |
+
Format
|
196 |
+
Language
|
197 |
+
Language
|
198 |
+
Improve-grammar-Typo
|
199 |
+
Language
|
200 |
+
Format
|
201 |
+
Language
|
202 |
+
Content
|
203 |
+
Language
|
204 |
+
Language
|
205 |
+
Format
|
206 |
+
Content
|
207 |
+
Format
|
208 |
+
Improve-grammar-Typo
|
209 |
+
Format
|
210 |
+
Language
|
211 |
+
Language
|
212 |
+
Content
|
213 |
+
Improve-grammar-Typo
|
214 |
+
Language
|
215 |
+
Format
|
216 |
+
Improve-grammar-Typo
|
217 |
+
Content
|
218 |
+
Content
|
219 |
+
Language
|
220 |
+
Improve-grammar-Typo
|
221 |
+
Format
|
222 |
+
Content
|
223 |
+
Language
|
224 |
+
Format
|
225 |
+
Format
|
226 |
+
Improve-grammar-Typo
|
227 |
+
Language
|
228 |
+
Improve-grammar-Typo
|
229 |
+
Improve-grammar-Typo
|
230 |
+
Language
|
231 |
+
Improve-grammar-Typo
|
232 |
+
Content
|
233 |
+
Language
|
234 |
+
Content
|
235 |
+
Language
|
236 |
+
Language
|
237 |
+
Content
|
238 |
+
Content
|
239 |
+
Content
|
240 |
+
Content
|
241 |
+
Language
|
242 |
+
Content
|
243 |
+
Format
|
244 |
+
Language
|
245 |
+
Language
|
246 |
+
Language
|
247 |
+
Language
|
248 |
+
Language
|
249 |
+
Content
|
250 |
+
Language
|
251 |
+
Format
|
252 |
+
Improve-grammar-Typo
|
253 |
+
Language
|
254 |
+
Language
|
255 |
+
Content
|
256 |
+
Content
|
257 |
+
Language
|
258 |
+
Improve-grammar-Typo
|
259 |
+
Language
|
260 |
+
Format
|
261 |
+
Improve-grammar-Typo
|
262 |
+
Language
|
263 |
+
Improve-grammar-Typo
|
264 |
+
Improve-grammar-Typo
|
265 |
+
Improve-grammar-Typo
|
266 |
+
Improve-grammar-Typo
|
267 |
+
Content
|
268 |
+
Language
|
269 |
+
Improve-grammar-Typo
|
270 |
+
Improve-grammar-Typo
|
271 |
+
Content
|
272 |
+
Improve-grammar-Typo
|
273 |
+
Format
|
274 |
+
Language
|
275 |
+
Language
|
276 |
+
Content
|
277 |
+
Language
|
278 |
+
Language
|
279 |
+
Content
|
280 |
+
Format
|
281 |
+
Content
|
282 |
+
Language
|
283 |
+
Format
|
284 |
+
Language
|
285 |
+
Content
|
286 |
+
Improve-grammar-Typo
|
287 |
+
Improve-grammar-Typo
|
288 |
+
Language
|
289 |
+
Format
|
290 |
+
Content
|
291 |
+
Improve-grammar-Typo
|
292 |
+
Content
|
293 |
+
Content
|
294 |
+
Improve-grammar-Typo
|
295 |
+
Improve-grammar-Typo
|
296 |
+
Format
|
297 |
+
Content
|
298 |
+
Language
|
299 |
+
Improve-grammar-Typo
|
300 |
+
Language
|
301 |
+
Language
|
302 |
+
Improve-grammar-Typo
|
303 |
+
Improve-grammar-Typo
|
304 |
+
Language
|
305 |
+
Language
|
306 |
+
Improve-grammar-Typo
|
307 |
+
Content
|
308 |
+
Content
|
309 |
+
Language
|
310 |
+
Content
|
311 |
+
Content
|
312 |
+
Format
|
313 |
+
Improve-grammar-Typo
|
314 |
+
Format
|
315 |
+
Content
|
316 |
+
Format
|
317 |
+
Format
|
318 |
+
Language
|
319 |
+
Content
|
320 |
+
Improve-grammar-Typo
|
321 |
+
Language
|
322 |
+
Improve-grammar-Typo
|
323 |
+
Language
|
324 |
+
Language
|
325 |
+
Format
|
326 |
+
Content
|
327 |
+
Language
|
328 |
+
Language
|
329 |
+
Language
|
330 |
+
Language
|
331 |
+
Language
|
332 |
+
Improve-grammar-Typo
|
333 |
+
Language
|
334 |
+
Improve-grammar-Typo
|
335 |
+
Improve-grammar-Typo
|
336 |
+
Content
|
337 |
+
Content
|
338 |
+
Language
|
339 |
+
Format
|
340 |
+
Content
|
341 |
+
Improve-grammar-Typo
|
342 |
+
Improve-grammar-Typo
|
343 |
+
Language
|
344 |
+
Content
|
345 |
+
Language
|
346 |
+
Content
|
347 |
+
Content
|
348 |
+
Language
|
349 |
+
Improve-grammar-Typo
|
350 |
+
Improve-grammar-Typo
|
351 |
+
Improve-grammar-Typo
|
352 |
+
Improve-grammar-Typo
|
353 |
+
Content
|
354 |
+
Format
|
355 |
+
Format
|
356 |
+
Language
|
357 |
+
Language
|
358 |
+
Language
|
359 |
+
Content
|
360 |
+
Content
|
361 |
+
Content
|
362 |
+
Content
|
363 |
+
Language
|
364 |
+
Content
|
365 |
+
Language
|
366 |
+
Content
|
367 |
+
Format
|
368 |
+
Improve-grammar-Typo
|
369 |
+
Improve-grammar-Typo
|
370 |
+
Content
|
371 |
+
Format
|
372 |
+
Language
|
373 |
+
Improve-grammar-Typo
|
374 |
+
Improve-grammar-Typo
|
375 |
+
Language
|
376 |
+
Content
|
377 |
+
Content
|
378 |
+
Improve-grammar-Typo
|
379 |
+
Improve-grammar-Typo
|
380 |
+
Language
|
381 |
+
Language
|
382 |
+
Improve-grammar-Typo
|
383 |
+
Improve-grammar-Typo
|
384 |
+
Format
|
385 |
+
Content
|
386 |
+
Language
|
387 |
+
Format
|
388 |
+
Format
|
389 |
+
Content
|
390 |
+
Improve-grammar-Typo
|
391 |
+
Improve-grammar-Typo
|
392 |
+
Language
|
393 |
+
Improve-grammar-Typo
|
394 |
+
Language
|
395 |
+
Language
|
396 |
+
Improve-grammar-Typo
|
397 |
+
Content
|
398 |
+
Improve-grammar-Typo
|
399 |
+
Content
|
400 |
+
Improve-grammar-Typo
|
401 |
+
Language
|
402 |
+
Improve-grammar-Typo
|
403 |
+
Language
|
404 |
+
Improve-grammar-Typo
|
405 |
+
Improve-grammar-Typo
|
406 |
+
Language
|
407 |
+
Language
|
408 |
+
Improve-grammar-Typo
|
409 |
+
Format
|
410 |
+
Format
|
411 |
+
Language
|
412 |
+
Format
|
413 |
+
Language
|
414 |
+
Improve-grammar-Typo
|
415 |
+
Improve-grammar-Typo
|
416 |
+
Improve-grammar-Typo
|
417 |
+
Language
|
418 |
+
Improve-grammar-Typo
|
419 |
+
Language
|
420 |
+
Language
|
421 |
+
Language
|
422 |
+
Improve-grammar-Typo
|
423 |
+
Improve-grammar-Typo
|
424 |
+
Improve-grammar-Typo
|
425 |
+
Content
|
426 |
+
Content
|
427 |
+
Format
|
428 |
+
Content
|
429 |
+
Language
|
430 |
+
Format
|
predict_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"predict_accuracy": 0.8441860465116279,
|
3 |
+
"predict_loss": 0.208589106798172,
|
4 |
+
"predict_runtime": 18.0974,
|
5 |
+
"predict_samples": 430,
|
6 |
+
"predict_samples_per_second": 23.76,
|
7 |
+
"predict_steps_per_second": 1.989
|
8 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6a0b0c343e10aaf5b5d29d4bcbee26884983ebbd67632995eb8815724e1350e
|
3 |
+
size 2950806407
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"]}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
|
3 |
+
size 791656
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "t5-large", "tokenizer_class": "T5Tokenizer"}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"train_loss": 0.1974729861531939,
|
4 |
+
"train_runtime": 785.0626,
|
5 |
+
"train_samples": 1254,
|
6 |
+
"train_samples_per_second": 15.973,
|
7 |
+
"train_steps_per_second": 1.337
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,127 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.860730593607306,
|
3 |
+
"best_model_checkpoint": "tmp/tst-translation354/checkpoint-840",
|
4 |
+
"epoch": 10.0,
|
5 |
+
"global_step": 1050,
|
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": 0.3698630136986301,
|
13 |
+
"eval_loss": 0.3618854582309723,
|
14 |
+
"eval_runtime": 11.9681,
|
15 |
+
"eval_samples_per_second": 36.597,
|
16 |
+
"eval_steps_per_second": 3.092,
|
17 |
+
"step": 105
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 2.0,
|
21 |
+
"eval_accuracy": 0.7351598173515982,
|
22 |
+
"eval_loss": 0.1750085949897766,
|
23 |
+
"eval_runtime": 13.2291,
|
24 |
+
"eval_samples_per_second": 33.109,
|
25 |
+
"eval_steps_per_second": 2.797,
|
26 |
+
"step": 210
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 3.0,
|
30 |
+
"eval_accuracy": 0.7922374429223744,
|
31 |
+
"eval_loss": 0.14155679941177368,
|
32 |
+
"eval_runtime": 12.7875,
|
33 |
+
"eval_samples_per_second": 34.252,
|
34 |
+
"eval_steps_per_second": 2.893,
|
35 |
+
"step": 315
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"epoch": 4.0,
|
39 |
+
"eval_accuracy": 0.8424657534246576,
|
40 |
+
"eval_loss": 0.12254055589437485,
|
41 |
+
"eval_runtime": 14.2052,
|
42 |
+
"eval_samples_per_second": 30.834,
|
43 |
+
"eval_steps_per_second": 2.605,
|
44 |
+
"step": 420
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 4.76,
|
48 |
+
"learning_rate": 2.6190476190476192e-05,
|
49 |
+
"loss": 0.3579,
|
50 |
+
"step": 500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 5.0,
|
54 |
+
"eval_accuracy": 0.8515981735159818,
|
55 |
+
"eval_loss": 0.13104116916656494,
|
56 |
+
"eval_runtime": 12.6738,
|
57 |
+
"eval_samples_per_second": 34.559,
|
58 |
+
"eval_steps_per_second": 2.919,
|
59 |
+
"step": 525
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 6.0,
|
63 |
+
"eval_accuracy": 0.8424657534246576,
|
64 |
+
"eval_loss": 0.1357753723859787,
|
65 |
+
"eval_runtime": 12.4892,
|
66 |
+
"eval_samples_per_second": 35.07,
|
67 |
+
"eval_steps_per_second": 2.963,
|
68 |
+
"step": 630
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 7.0,
|
72 |
+
"eval_accuracy": 0.8493150684931506,
|
73 |
+
"eval_loss": 0.16049088537693024,
|
74 |
+
"eval_runtime": 12.626,
|
75 |
+
"eval_samples_per_second": 34.69,
|
76 |
+
"eval_steps_per_second": 2.93,
|
77 |
+
"step": 735
|
78 |
+
},
|
79 |
+
{
|
80 |
+
"epoch": 8.0,
|
81 |
+
"eval_accuracy": 0.860730593607306,
|
82 |
+
"eval_loss": 0.1871233731508255,
|
83 |
+
"eval_runtime": 12.5302,
|
84 |
+
"eval_samples_per_second": 34.956,
|
85 |
+
"eval_steps_per_second": 2.953,
|
86 |
+
"step": 840
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 9.0,
|
90 |
+
"eval_accuracy": 0.8515981735159818,
|
91 |
+
"eval_loss": 0.19895039498806,
|
92 |
+
"eval_runtime": 12.66,
|
93 |
+
"eval_samples_per_second": 34.597,
|
94 |
+
"eval_steps_per_second": 2.923,
|
95 |
+
"step": 945
|
96 |
+
},
|
97 |
+
{
|
98 |
+
"epoch": 9.52,
|
99 |
+
"learning_rate": 2.3809523809523808e-06,
|
100 |
+
"loss": 0.054,
|
101 |
+
"step": 1000
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 10.0,
|
105 |
+
"eval_accuracy": 0.860730593607306,
|
106 |
+
"eval_loss": 0.2134334295988083,
|
107 |
+
"eval_runtime": 12.5085,
|
108 |
+
"eval_samples_per_second": 35.016,
|
109 |
+
"eval_steps_per_second": 2.958,
|
110 |
+
"step": 1050
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 10.0,
|
114 |
+
"step": 1050,
|
115 |
+
"total_flos": 8482350845952000.0,
|
116 |
+
"train_loss": 0.1974729861531939,
|
117 |
+
"train_runtime": 785.0626,
|
118 |
+
"train_samples_per_second": 15.973,
|
119 |
+
"train_steps_per_second": 1.337
|
120 |
+
}
|
121 |
+
],
|
122 |
+
"max_steps": 1050,
|
123 |
+
"num_train_epochs": 10,
|
124 |
+
"total_flos": 8482350845952000.0,
|
125 |
+
"trial_name": null,
|
126 |
+
"trial_params": null
|
127 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a23b9a642b4db882ef684755d34a85a97de3a32384696d8bc0c1c6f4a79e7e20
|
3 |
+
size 3183
|