update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,285 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- zeroth_korean_asr
|
7 |
+
metrics:
|
8 |
+
- wer
|
9 |
+
model-index:
|
10 |
+
- name: hubert_zeroth_gpu
|
11 |
+
results:
|
12 |
+
- task:
|
13 |
+
name: Automatic Speech Recognition
|
14 |
+
type: automatic-speech-recognition
|
15 |
+
dataset:
|
16 |
+
name: zeroth_korean_asr
|
17 |
+
type: zeroth_korean_asr
|
18 |
+
config: clean
|
19 |
+
split: train
|
20 |
+
args: clean
|
21 |
+
metrics:
|
22 |
+
- name: Wer
|
23 |
+
type: wer
|
24 |
+
value: 1.0
|
25 |
+
---
|
26 |
+
|
27 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
28 |
+
should probably proofread and complete it, then remove this comment. -->
|
29 |
+
|
30 |
+
# hubert_zeroth_gpu
|
31 |
+
|
32 |
+
This model is a fine-tuned version of [facebook/hubert-base-ls960](https://huggingface.co/facebook/hubert-base-ls960) on the zeroth_korean_asr dataset.
|
33 |
+
It achieves the following results on the evaluation set:
|
34 |
+
- Loss: 4.8302
|
35 |
+
- Wer: 1.0
|
36 |
+
|
37 |
+
## Model description
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Intended uses & limitations
|
42 |
+
|
43 |
+
More information needed
|
44 |
+
|
45 |
+
## Training and evaluation data
|
46 |
+
|
47 |
+
More information needed
|
48 |
+
|
49 |
+
## Training procedure
|
50 |
+
|
51 |
+
### Training hyperparameters
|
52 |
+
|
53 |
+
The following hyperparameters were used during training:
|
54 |
+
- learning_rate: 0.0003
|
55 |
+
- train_batch_size: 16
|
56 |
+
- eval_batch_size: 16
|
57 |
+
- seed: 42
|
58 |
+
- gradient_accumulation_steps: 2
|
59 |
+
- total_train_batch_size: 32
|
60 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
61 |
+
- lr_scheduler_type: linear
|
62 |
+
- lr_scheduler_warmup_steps: 500
|
63 |
+
- num_epochs: 30
|
64 |
+
- mixed_precision_training: Native AMP
|
65 |
+
|
66 |
+
### Training results
|
67 |
+
|
68 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
69 |
+
|:-------------:|:-----:|:-----:|:---------------:|:---:|
|
70 |
+
| 26.5222 | 0.14 | 100 | 10.9084 | 1.0 |
|
71 |
+
| 6.6076 | 0.29 | 200 | 4.8783 | 1.0 |
|
72 |
+
| 4.8383 | 0.43 | 300 | 4.8768 | 1.0 |
|
73 |
+
| 4.8372 | 0.57 | 400 | 4.8608 | 1.0 |
|
74 |
+
| 4.8298 | 0.72 | 500 | 4.8625 | 1.0 |
|
75 |
+
| 4.8377 | 0.86 | 600 | 4.8646 | 1.0 |
|
76 |
+
| 4.829 | 1.01 | 700 | 4.8472 | 1.0 |
|
77 |
+
| 4.8282 | 1.15 | 800 | 4.8435 | 1.0 |
|
78 |
+
| 4.8282 | 1.29 | 900 | 4.8438 | 1.0 |
|
79 |
+
| 4.8299 | 1.44 | 1000 | 4.8540 | 1.0 |
|
80 |
+
| 4.8276 | 1.58 | 1100 | 4.8408 | 1.0 |
|
81 |
+
| 4.8306 | 1.72 | 1200 | 4.8390 | 1.0 |
|
82 |
+
| 4.8315 | 1.87 | 1300 | 4.8426 | 1.0 |
|
83 |
+
| 4.8296 | 2.01 | 1400 | 4.8418 | 1.0 |
|
84 |
+
| 4.829 | 2.16 | 1500 | 4.8475 | 1.0 |
|
85 |
+
| 4.8324 | 2.3 | 1600 | 4.8409 | 1.0 |
|
86 |
+
| 4.8299 | 2.44 | 1700 | 4.8360 | 1.0 |
|
87 |
+
| 4.8285 | 2.59 | 1800 | 4.8419 | 1.0 |
|
88 |
+
| 4.8267 | 2.73 | 1900 | 4.8355 | 1.0 |
|
89 |
+
| 4.8232 | 2.87 | 2000 | 4.8445 | 1.0 |
|
90 |
+
| 4.8179 | 3.02 | 2100 | 4.8390 | 1.0 |
|
91 |
+
| 4.8248 | 3.16 | 2200 | 4.8506 | 1.0 |
|
92 |
+
| 4.8184 | 3.3 | 2300 | 4.8392 | 1.0 |
|
93 |
+
| 4.8268 | 3.45 | 2400 | 4.8509 | 1.0 |
|
94 |
+
| 4.8315 | 3.59 | 2500 | 4.8469 | 1.0 |
|
95 |
+
| 4.8249 | 3.74 | 2600 | 4.8457 | 1.0 |
|
96 |
+
| 4.8244 | 3.88 | 2700 | 4.8414 | 1.0 |
|
97 |
+
| 4.8226 | 4.02 | 2800 | 4.8333 | 1.0 |
|
98 |
+
| 4.8275 | 4.17 | 2900 | 4.8344 | 1.0 |
|
99 |
+
| 4.8218 | 4.31 | 3000 | 4.8351 | 1.0 |
|
100 |
+
| 4.8199 | 4.45 | 3100 | 4.8386 | 1.0 |
|
101 |
+
| 4.825 | 4.6 | 3200 | 4.8344 | 1.0 |
|
102 |
+
| 4.828 | 4.74 | 3300 | 4.8372 | 1.0 |
|
103 |
+
| 4.8228 | 4.89 | 3400 | 4.8349 | 1.0 |
|
104 |
+
| 4.8264 | 5.03 | 3500 | 4.8344 | 1.0 |
|
105 |
+
| 4.8237 | 5.17 | 3600 | 4.8332 | 1.0 |
|
106 |
+
| 4.8269 | 5.32 | 3700 | 4.8376 | 1.0 |
|
107 |
+
| 4.833 | 5.46 | 3800 | 4.8380 | 1.0 |
|
108 |
+
| 4.8188 | 5.6 | 3900 | 4.8352 | 1.0 |
|
109 |
+
| 4.8208 | 5.75 | 4000 | 4.8354 | 1.0 |
|
110 |
+
| 4.8177 | 5.89 | 4100 | 4.8291 | 1.0 |
|
111 |
+
| 4.8208 | 6.03 | 4200 | 4.8500 | 1.0 |
|
112 |
+
| 4.8242 | 6.18 | 4300 | 4.8369 | 1.0 |
|
113 |
+
| 4.8222 | 6.32 | 4400 | 4.8366 | 1.0 |
|
114 |
+
| 4.8259 | 6.47 | 4500 | 4.8369 | 1.0 |
|
115 |
+
| 4.8231 | 6.61 | 4600 | 4.8319 | 1.0 |
|
116 |
+
| 4.825 | 6.75 | 4700 | 4.8363 | 1.0 |
|
117 |
+
| 4.8245 | 6.9 | 4800 | 4.8420 | 1.0 |
|
118 |
+
| 4.8139 | 7.04 | 4900 | 4.8427 | 1.0 |
|
119 |
+
| 4.8202 | 7.18 | 5000 | 4.8393 | 1.0 |
|
120 |
+
| 4.8196 | 7.33 | 5100 | 4.8380 | 1.0 |
|
121 |
+
| 4.8199 | 7.47 | 5200 | 4.8364 | 1.0 |
|
122 |
+
| 4.8264 | 7.61 | 5300 | 4.8414 | 1.0 |
|
123 |
+
| 4.8259 | 7.76 | 5400 | 4.8397 | 1.0 |
|
124 |
+
| 4.8215 | 7.9 | 5500 | 4.8376 | 1.0 |
|
125 |
+
| 4.8198 | 8.05 | 5600 | 4.8344 | 1.0 |
|
126 |
+
| 4.828 | 8.19 | 5700 | 4.8314 | 1.0 |
|
127 |
+
| 4.8246 | 8.33 | 5800 | 4.8361 | 1.0 |
|
128 |
+
| 4.8167 | 8.48 | 5900 | 4.8336 | 1.0 |
|
129 |
+
| 4.8174 | 8.62 | 6000 | 4.8345 | 1.0 |
|
130 |
+
| 4.8283 | 8.76 | 6100 | 4.8363 | 1.0 |
|
131 |
+
| 4.8231 | 8.91 | 6200 | 4.8345 | 1.0 |
|
132 |
+
| 4.8191 | 9.05 | 6300 | 4.8327 | 1.0 |
|
133 |
+
| 4.8144 | 9.2 | 6400 | 4.8299 | 1.0 |
|
134 |
+
| 4.8206 | 9.34 | 6500 | 4.8281 | 1.0 |
|
135 |
+
| 4.822 | 9.48 | 6600 | 4.8329 | 1.0 |
|
136 |
+
| 4.8228 | 9.63 | 6700 | 4.8309 | 1.0 |
|
137 |
+
| 4.8239 | 9.77 | 6800 | 4.8348 | 1.0 |
|
138 |
+
| 4.8245 | 9.91 | 6900 | 4.8309 | 1.0 |
|
139 |
+
| 4.8173 | 10.06 | 7000 | 4.8303 | 1.0 |
|
140 |
+
| 4.8188 | 10.2 | 7100 | 4.8335 | 1.0 |
|
141 |
+
| 4.8208 | 10.34 | 7200 | 4.8290 | 1.0 |
|
142 |
+
| 4.8228 | 10.49 | 7300 | 4.8316 | 1.0 |
|
143 |
+
| 4.8226 | 10.63 | 7400 | 4.8272 | 1.0 |
|
144 |
+
| 4.824 | 10.78 | 7500 | 4.8309 | 1.0 |
|
145 |
+
| 4.8175 | 10.92 | 7600 | 4.8317 | 1.0 |
|
146 |
+
| 4.8234 | 11.06 | 7700 | 4.8271 | 1.0 |
|
147 |
+
| 4.8188 | 11.21 | 7800 | 4.8291 | 1.0 |
|
148 |
+
| 4.8182 | 11.35 | 7900 | 4.8340 | 1.0 |
|
149 |
+
| 4.8224 | 11.49 | 8000 | 4.8309 | 1.0 |
|
150 |
+
| 4.8207 | 11.64 | 8100 | 4.8308 | 1.0 |
|
151 |
+
| 4.8207 | 11.78 | 8200 | 4.8301 | 1.0 |
|
152 |
+
| 4.822 | 11.93 | 8300 | 4.8281 | 1.0 |
|
153 |
+
| 4.8199 | 12.07 | 8400 | 4.8301 | 1.0 |
|
154 |
+
| 4.8198 | 12.21 | 8500 | 4.8337 | 1.0 |
|
155 |
+
| 4.8212 | 12.36 | 8600 | 4.8310 | 1.0 |
|
156 |
+
| 4.8211 | 12.5 | 8700 | 4.8304 | 1.0 |
|
157 |
+
| 4.8226 | 12.64 | 8800 | 4.8303 | 1.0 |
|
158 |
+
| 4.8224 | 12.79 | 8900 | 4.8312 | 1.0 |
|
159 |
+
| 4.8146 | 12.93 | 9000 | 4.8362 | 1.0 |
|
160 |
+
| 4.8173 | 13.07 | 9100 | 4.8321 | 1.0 |
|
161 |
+
| 4.816 | 13.22 | 9200 | 4.8347 | 1.0 |
|
162 |
+
| 4.8219 | 13.36 | 9300 | 4.8377 | 1.0 |
|
163 |
+
| 4.8251 | 13.51 | 9400 | 4.8403 | 1.0 |
|
164 |
+
| 4.8173 | 13.65 | 9500 | 4.8387 | 1.0 |
|
165 |
+
| 4.8226 | 13.79 | 9600 | 4.8375 | 1.0 |
|
166 |
+
| 4.8137 | 13.94 | 9700 | 4.8364 | 1.0 |
|
167 |
+
| 4.819 | 14.08 | 9800 | 4.8323 | 1.0 |
|
168 |
+
| 4.8258 | 14.22 | 9900 | 4.8329 | 1.0 |
|
169 |
+
| 4.8097 | 14.37 | 10000 | 4.8293 | 1.0 |
|
170 |
+
| 4.8247 | 14.51 | 10100 | 4.8311 | 1.0 |
|
171 |
+
| 4.8197 | 14.66 | 10200 | 4.8306 | 1.0 |
|
172 |
+
| 4.8201 | 14.8 | 10300 | 4.8308 | 1.0 |
|
173 |
+
| 4.8158 | 14.94 | 10400 | 4.8319 | 1.0 |
|
174 |
+
| 4.818 | 15.09 | 10500 | 4.8306 | 1.0 |
|
175 |
+
| 4.8216 | 15.23 | 10600 | 4.8343 | 1.0 |
|
176 |
+
| 4.8096 | 15.37 | 10700 | 4.8326 | 1.0 |
|
177 |
+
| 4.8248 | 15.52 | 10800 | 4.8323 | 1.0 |
|
178 |
+
| 4.8178 | 15.66 | 10900 | 4.8358 | 1.0 |
|
179 |
+
| 4.8191 | 15.8 | 11000 | 4.8338 | 1.0 |
|
180 |
+
| 4.8248 | 15.95 | 11100 | 4.8359 | 1.0 |
|
181 |
+
| 4.8095 | 16.09 | 11200 | 4.8392 | 1.0 |
|
182 |
+
| 4.8196 | 16.24 | 11300 | 4.8374 | 1.0 |
|
183 |
+
| 4.827 | 16.38 | 11400 | 4.8346 | 1.0 |
|
184 |
+
| 4.8165 | 16.52 | 11500 | 4.8365 | 1.0 |
|
185 |
+
| 4.8206 | 16.67 | 11600 | 4.8344 | 1.0 |
|
186 |
+
| 4.8169 | 16.81 | 11700 | 4.8344 | 1.0 |
|
187 |
+
| 4.8164 | 16.95 | 11800 | 4.8390 | 1.0 |
|
188 |
+
| 4.8159 | 17.1 | 11900 | 4.8367 | 1.0 |
|
189 |
+
| 4.8202 | 17.24 | 12000 | 4.8375 | 1.0 |
|
190 |
+
| 4.8156 | 17.39 | 12100 | 4.8362 | 1.0 |
|
191 |
+
| 4.8174 | 17.53 | 12200 | 4.8410 | 1.0 |
|
192 |
+
| 4.8188 | 17.67 | 12300 | 4.8323 | 1.0 |
|
193 |
+
| 4.8167 | 17.82 | 12400 | 4.8319 | 1.0 |
|
194 |
+
| 4.8229 | 17.96 | 12500 | 4.8347 | 1.0 |
|
195 |
+
| 4.8179 | 18.1 | 12600 | 4.8320 | 1.0 |
|
196 |
+
| 4.8182 | 18.25 | 12700 | 4.8384 | 1.0 |
|
197 |
+
| 4.8151 | 18.39 | 12800 | 4.8374 | 1.0 |
|
198 |
+
| 4.8212 | 18.53 | 12900 | 4.8346 | 1.0 |
|
199 |
+
| 4.8241 | 18.68 | 13000 | 4.8344 | 1.0 |
|
200 |
+
| 4.8184 | 18.82 | 13100 | 4.8352 | 1.0 |
|
201 |
+
| 4.8174 | 18.97 | 13200 | 4.8357 | 1.0 |
|
202 |
+
| 4.8092 | 19.11 | 13300 | 4.8332 | 1.0 |
|
203 |
+
| 4.8149 | 19.25 | 13400 | 4.8347 | 1.0 |
|
204 |
+
| 4.813 | 19.4 | 13500 | 4.8376 | 1.0 |
|
205 |
+
| 4.8226 | 19.54 | 13600 | 4.8343 | 1.0 |
|
206 |
+
| 4.8175 | 19.68 | 13700 | 4.8320 | 1.0 |
|
207 |
+
| 4.8203 | 19.83 | 13800 | 4.8339 | 1.0 |
|
208 |
+
| 4.8227 | 19.97 | 13900 | 4.8324 | 1.0 |
|
209 |
+
| 4.8177 | 20.11 | 14000 | 4.8356 | 1.0 |
|
210 |
+
| 4.824 | 20.26 | 14100 | 4.8339 | 1.0 |
|
211 |
+
| 4.815 | 20.4 | 14200 | 4.8342 | 1.0 |
|
212 |
+
| 4.8189 | 20.55 | 14300 | 4.8340 | 1.0 |
|
213 |
+
| 4.8115 | 20.69 | 14400 | 4.8319 | 1.0 |
|
214 |
+
| 4.8162 | 20.83 | 14500 | 4.8288 | 1.0 |
|
215 |
+
| 4.8183 | 20.98 | 14600 | 4.8321 | 1.0 |
|
216 |
+
| 4.8189 | 21.12 | 14700 | 4.8315 | 1.0 |
|
217 |
+
| 4.8123 | 21.26 | 14800 | 4.8311 | 1.0 |
|
218 |
+
| 4.8165 | 21.41 | 14900 | 4.8321 | 1.0 |
|
219 |
+
| 4.8247 | 21.55 | 15000 | 4.8309 | 1.0 |
|
220 |
+
| 4.8165 | 21.7 | 15100 | 4.8313 | 1.0 |
|
221 |
+
| 4.815 | 21.84 | 15200 | 4.8354 | 1.0 |
|
222 |
+
| 4.8234 | 21.98 | 15300 | 4.8300 | 1.0 |
|
223 |
+
| 4.8134 | 22.13 | 15400 | 4.8284 | 1.0 |
|
224 |
+
| 4.8178 | 22.27 | 15500 | 4.8298 | 1.0 |
|
225 |
+
| 4.8128 | 22.41 | 15600 | 4.8309 | 1.0 |
|
226 |
+
| 4.8185 | 22.56 | 15700 | 4.8291 | 1.0 |
|
227 |
+
| 4.8177 | 22.7 | 15800 | 4.8288 | 1.0 |
|
228 |
+
| 4.8208 | 22.84 | 15900 | 4.8306 | 1.0 |
|
229 |
+
| 4.8183 | 22.99 | 16000 | 4.8277 | 1.0 |
|
230 |
+
| 4.8135 | 23.13 | 16100 | 4.8286 | 1.0 |
|
231 |
+
| 4.8116 | 23.28 | 16200 | 4.8275 | 1.0 |
|
232 |
+
| 4.816 | 23.42 | 16300 | 4.8290 | 1.0 |
|
233 |
+
| 4.8203 | 23.56 | 16400 | 4.8292 | 1.0 |
|
234 |
+
| 4.8198 | 23.71 | 16500 | 4.8299 | 1.0 |
|
235 |
+
| 4.8203 | 23.85 | 16600 | 4.8294 | 1.0 |
|
236 |
+
| 4.8177 | 23.99 | 16700 | 4.8286 | 1.0 |
|
237 |
+
| 4.8153 | 24.14 | 16800 | 4.8275 | 1.0 |
|
238 |
+
| 4.8201 | 24.28 | 16900 | 4.8259 | 1.0 |
|
239 |
+
| 4.8189 | 24.43 | 17000 | 4.8289 | 1.0 |
|
240 |
+
| 4.8219 | 24.57 | 17100 | 4.8280 | 1.0 |
|
241 |
+
| 4.8148 | 24.71 | 17200 | 4.8284 | 1.0 |
|
242 |
+
| 4.8113 | 24.86 | 17300 | 4.8286 | 1.0 |
|
243 |
+
| 4.8133 | 25.0 | 17400 | 4.8293 | 1.0 |
|
244 |
+
| 4.8164 | 25.14 | 17500 | 4.8302 | 1.0 |
|
245 |
+
| 4.8231 | 25.29 | 17600 | 4.8278 | 1.0 |
|
246 |
+
| 4.8136 | 25.43 | 17700 | 4.8296 | 1.0 |
|
247 |
+
| 4.8118 | 25.57 | 17800 | 4.8288 | 1.0 |
|
248 |
+
| 4.8139 | 25.72 | 17900 | 4.8280 | 1.0 |
|
249 |
+
| 4.8144 | 25.86 | 18000 | 4.8282 | 1.0 |
|
250 |
+
| 4.8206 | 26.01 | 18100 | 4.8279 | 1.0 |
|
251 |
+
| 4.8096 | 26.15 | 18200 | 4.8281 | 1.0 |
|
252 |
+
| 4.8177 | 26.29 | 18300 | 4.8271 | 1.0 |
|
253 |
+
| 4.8222 | 26.44 | 18400 | 4.8289 | 1.0 |
|
254 |
+
| 4.8148 | 26.58 | 18500 | 4.8282 | 1.0 |
|
255 |
+
| 4.8148 | 26.72 | 18600 | 4.8277 | 1.0 |
|
256 |
+
| 4.819 | 26.87 | 18700 | 4.8283 | 1.0 |
|
257 |
+
| 4.8138 | 27.01 | 18800 | 4.8290 | 1.0 |
|
258 |
+
| 4.8094 | 27.16 | 18900 | 4.8292 | 1.0 |
|
259 |
+
| 4.8236 | 27.3 | 19000 | 4.8282 | 1.0 |
|
260 |
+
| 4.8208 | 27.44 | 19100 | 4.8293 | 1.0 |
|
261 |
+
| 4.816 | 27.59 | 19200 | 4.8281 | 1.0 |
|
262 |
+
| 4.8103 | 27.73 | 19300 | 4.8294 | 1.0 |
|
263 |
+
| 4.8152 | 27.87 | 19400 | 4.8297 | 1.0 |
|
264 |
+
| 4.8158 | 28.02 | 19500 | 4.8305 | 1.0 |
|
265 |
+
| 4.8121 | 28.16 | 19600 | 4.8294 | 1.0 |
|
266 |
+
| 4.8199 | 28.3 | 19700 | 4.8292 | 1.0 |
|
267 |
+
| 4.8185 | 28.45 | 19800 | 4.8288 | 1.0 |
|
268 |
+
| 4.8199 | 28.59 | 19900 | 4.8288 | 1.0 |
|
269 |
+
| 4.8102 | 28.74 | 20000 | 4.8292 | 1.0 |
|
270 |
+
| 4.8168 | 28.88 | 20100 | 4.8291 | 1.0 |
|
271 |
+
| 4.8117 | 29.02 | 20200 | 4.8304 | 1.0 |
|
272 |
+
| 4.8156 | 29.17 | 20300 | 4.8295 | 1.0 |
|
273 |
+
| 4.8126 | 29.31 | 20400 | 4.8296 | 1.0 |
|
274 |
+
| 4.8193 | 29.45 | 20500 | 4.8302 | 1.0 |
|
275 |
+
| 4.8175 | 29.6 | 20600 | 4.8301 | 1.0 |
|
276 |
+
| 4.8167 | 29.74 | 20700 | 4.8301 | 1.0 |
|
277 |
+
| 4.8137 | 29.89 | 20800 | 4.8302 | 1.0 |
|
278 |
+
|
279 |
+
|
280 |
+
### Framework versions
|
281 |
+
|
282 |
+
- Transformers 4.24.0
|
283 |
+
- Pytorch 1.13.0+cu117
|
284 |
+
- Datasets 2.0.0
|
285 |
+
- Tokenizers 0.13.2
|