Model save
Browse files- .gitattributes +1 -0
- README.md +314 -0
- adapter_config.json +32 -0
- adapter_model.safetensors +3 -0
- runs/Mar10_23-08-48_1412920010036/events.out.tfevents.1741662535.1412920010036.5471.0 +3 -0
- runs/Mar10_23-08-48_1412920010036/events.out.tfevents.1741667746.1412920010036.5471.1 +3 -0
- runs/Mar11_00-36-23_1412920010036/events.out.tfevents.1741667784.1412920010036.5471.2 +3 -0
- runs/Mar11_00-36-23_1412920010036/events.out.tfevents.1741668489.1412920010036.5471.3 +3 -0
- runs/Mar11_00-48-17_1412920010036/events.out.tfevents.1741668498.1412920010036.5471.4 +3 -0
- runs/Mar11_00-48-17_1412920010036/events.out.tfevents.1741673649.1412920010036.5471.5 +3 -0
- runs/Mar11_08-18-41_1412920010036/events.out.tfevents.1741695522.1412920010036.235349.0 +3 -0
- runs/Mar11_08-36-50_1412920010036/events.out.tfevents.1741696613.1412920010036.243166.0 +3 -0
- runs/Mar11_08-36-50_1412920010036/events.out.tfevents.1741706871.1412920010036.243166.1 +3 -0
- runs/Mar11_11-28-33_1412920010036/events.out.tfevents.1741706915.1412920010036.243166.2 +3 -0
- runs/Mar11_11-28-33_1412920010036/events.out.tfevents.1741708827.1412920010036.243166.3 +3 -0
- runs/Mar11_12-01-09_1412920010036/events.out.tfevents.1741708871.1412920010036.243166.4 +3 -0
- special_tokens_map.json +23 -0
- spiece.model +3 -0
- tokenizer.json +3 -0
- tokenizer_config.json +840 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,314 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
license: apache-2.0
|
4 |
+
base_model: google/mt5-small
|
5 |
+
tags:
|
6 |
+
- generated_from_trainer
|
7 |
+
metrics:
|
8 |
+
- rouge
|
9 |
+
model-index:
|
10 |
+
- name: my-lora-local-combined
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# my-lora-local-combined
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 4.4564
|
22 |
+
- Rouge1: 6.5458
|
23 |
+
- Rouge2: 0.5992
|
24 |
+
- Rougel: 5.5320
|
25 |
+
- Rougelsum: 5.5225
|
26 |
+
|
27 |
+
## Model description
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Intended uses & limitations
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training and evaluation data
|
36 |
+
|
37 |
+
More information needed
|
38 |
+
|
39 |
+
## Training procedure
|
40 |
+
|
41 |
+
### Training hyperparameters
|
42 |
+
|
43 |
+
The following hyperparameters were used during training:
|
44 |
+
- learning_rate: 0.0001
|
45 |
+
- train_batch_size: 4
|
46 |
+
- eval_batch_size: 4
|
47 |
+
- seed: 42
|
48 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
49 |
+
- lr_scheduler_type: linear
|
50 |
+
- num_epochs: 4
|
51 |
+
|
52 |
+
### Training results
|
53 |
+
|
54 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|
55 |
+
|:-------------:|:------:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
|
56 |
+
| 23.5916 | 0.0160 | 5 | 11.7262 | 0.5542 | 0.0490 | 0.4944 | 0.4916 |
|
57 |
+
| 21.1393 | 0.0319 | 10 | 11.6748 | 0.5248 | 0.0392 | 0.4771 | 0.4726 |
|
58 |
+
| 19.4318 | 0.0479 | 15 | 11.6306 | 0.5963 | 0.0579 | 0.5442 | 0.5355 |
|
59 |
+
| 22.1889 | 0.0639 | 20 | 11.5863 | 0.5158 | 0.0316 | 0.4731 | 0.4658 |
|
60 |
+
| 19.6761 | 0.0799 | 25 | 11.5024 | 0.5652 | 0.0424 | 0.5048 | 0.4963 |
|
61 |
+
| 19.929 | 0.0958 | 30 | 11.4553 | 0.4998 | 0.0243 | 0.4518 | 0.4493 |
|
62 |
+
| 20.2395 | 0.1118 | 35 | 11.3915 | 0.4822 | 0.0399 | 0.4522 | 0.4458 |
|
63 |
+
| 21.5461 | 0.1278 | 40 | 11.3654 | 0.5546 | 0.0449 | 0.5031 | 0.4965 |
|
64 |
+
| 22.6504 | 0.1438 | 45 | 11.2932 | 0.5040 | 0.0386 | 0.4600 | 0.4553 |
|
65 |
+
| 21.6932 | 0.1597 | 50 | 11.2208 | 0.4859 | 0.0281 | 0.4221 | 0.4180 |
|
66 |
+
| 21.2378 | 0.1757 | 55 | 11.1399 | 0.5739 | 0.0359 | 0.5031 | 0.4979 |
|
67 |
+
| 23.1256 | 0.1917 | 60 | 10.9979 | 0.5653 | 0.0291 | 0.4982 | 0.4944 |
|
68 |
+
| 17.3673 | 0.2077 | 65 | 10.8734 | 0.5862 | 0.0339 | 0.5157 | 0.5098 |
|
69 |
+
| 20.5375 | 0.2236 | 70 | 10.7660 | 0.6107 | 0.0305 | 0.5391 | 0.5324 |
|
70 |
+
| 16.7352 | 0.2396 | 75 | 10.6289 | 0.5927 | 0.0266 | 0.5330 | 0.5268 |
|
71 |
+
| 16.294 | 0.2556 | 80 | 10.5324 | 0.5762 | 0.0259 | 0.5219 | 0.5220 |
|
72 |
+
| 22.6858 | 0.2716 | 85 | 10.4476 | 0.5378 | 0.0305 | 0.4680 | 0.4699 |
|
73 |
+
| 21.543 | 0.2875 | 90 | 10.3308 | 0.5548 | 0.0399 | 0.5047 | 0.5029 |
|
74 |
+
| 17.2107 | 0.3035 | 95 | 10.2056 | 0.5542 | 0.0400 | 0.5135 | 0.5099 |
|
75 |
+
| 18.4509 | 0.3195 | 100 | 10.1074 | 0.5586 | 0.0274 | 0.5245 | 0.5251 |
|
76 |
+
| 18.3913 | 0.3355 | 105 | 10.0355 | 0.5571 | 0.0254 | 0.5035 | 0.5021 |
|
77 |
+
| 19.6092 | 0.3514 | 110 | 9.9604 | 0.4967 | 0.0233 | 0.4501 | 0.4428 |
|
78 |
+
| 17.7749 | 0.3674 | 115 | 9.8899 | 0.4215 | 0.0299 | 0.3727 | 0.3689 |
|
79 |
+
| 15.2983 | 0.3834 | 120 | 9.8581 | 0.4695 | 0.0259 | 0.4290 | 0.4278 |
|
80 |
+
| 15.7226 | 0.3994 | 125 | 9.7488 | 0.5208 | 0.0260 | 0.4678 | 0.4643 |
|
81 |
+
| 13.8742 | 0.4153 | 130 | 9.6336 | 0.5015 | 0.0362 | 0.4702 | 0.4643 |
|
82 |
+
| 15.361 | 0.4313 | 135 | 9.5164 | 0.5972 | 0.0353 | 0.5388 | 0.5385 |
|
83 |
+
| 14.5332 | 0.4473 | 140 | 9.3986 | 0.5165 | 0.0323 | 0.4706 | 0.4707 |
|
84 |
+
| 17.2239 | 0.4633 | 145 | 9.2482 | 0.5570 | 0.0232 | 0.5176 | 0.5129 |
|
85 |
+
| 15.6288 | 0.4792 | 150 | 9.0894 | 0.5749 | 0.0314 | 0.5217 | 0.5187 |
|
86 |
+
| 14.0262 | 0.4952 | 155 | 8.9450 | 0.5645 | 0.0469 | 0.5230 | 0.5202 |
|
87 |
+
| 14.0053 | 0.5112 | 160 | 8.7770 | 0.6478 | 0.0443 | 0.5981 | 0.5969 |
|
88 |
+
| 16.225 | 0.5272 | 165 | 8.6219 | 0.7284 | 0.0394 | 0.6743 | 0.6701 |
|
89 |
+
| 13.9933 | 0.5431 | 170 | 8.4905 | 0.6132 | 0.0417 | 0.5483 | 0.5486 |
|
90 |
+
| 12.9054 | 0.5591 | 175 | 8.3549 | 0.6209 | 0.0344 | 0.5645 | 0.5597 |
|
91 |
+
| 12.9083 | 0.5751 | 180 | 8.2075 | 0.6536 | 0.0356 | 0.6011 | 0.6007 |
|
92 |
+
| 12.5842 | 0.5911 | 185 | 8.0345 | 0.6493 | 0.0463 | 0.5978 | 0.5954 |
|
93 |
+
| 12.8272 | 0.6070 | 190 | 7.8703 | 0.7304 | 0.0466 | 0.6570 | 0.6492 |
|
94 |
+
| 13.1239 | 0.6230 | 195 | 7.7553 | 0.7646 | 0.0257 | 0.6951 | 0.6870 |
|
95 |
+
| 12.3721 | 0.6390 | 200 | 7.6578 | 0.8671 | 0.0256 | 0.8044 | 0.7892 |
|
96 |
+
| 11.7878 | 0.6550 | 205 | 7.5664 | 0.9566 | 0.0260 | 0.9013 | 0.8948 |
|
97 |
+
| 12.6621 | 0.6709 | 210 | 7.5077 | 1.1242 | 0.0347 | 1.0256 | 1.0201 |
|
98 |
+
| 11.8169 | 0.6869 | 215 | 7.4480 | 1.1615 | 0.0269 | 1.0548 | 1.0526 |
|
99 |
+
| 10.5259 | 0.7029 | 220 | 7.4275 | 1.3161 | 0.0779 | 1.2189 | 1.2208 |
|
100 |
+
| 11.0736 | 0.7188 | 225 | 7.4054 | 1.4351 | 0.0759 | 1.3073 | 1.3165 |
|
101 |
+
| 9.9942 | 0.7348 | 230 | 7.3833 | 1.5194 | 0.0699 | 1.3946 | 1.3929 |
|
102 |
+
| 10.3518 | 0.7508 | 235 | 7.3722 | 1.3680 | 0.0423 | 1.2697 | 1.2701 |
|
103 |
+
| 10.0153 | 0.7668 | 240 | 7.3443 | 1.5049 | 0.0676 | 1.3667 | 1.3738 |
|
104 |
+
| 9.5365 | 0.7827 | 245 | 7.2813 | 1.7361 | 0.0845 | 1.5844 | 1.5897 |
|
105 |
+
| 9.2173 | 0.7987 | 250 | 7.2299 | 1.7517 | 0.0743 | 1.6296 | 1.6343 |
|
106 |
+
| 8.8365 | 0.8147 | 255 | 7.1459 | 1.8117 | 0.0583 | 1.6533 | 1.6544 |
|
107 |
+
| 8.591 | 0.8307 | 260 | 7.0298 | 1.9288 | 0.0607 | 1.7592 | 1.7509 |
|
108 |
+
| 8.7615 | 0.8466 | 265 | 6.9354 | 2.0429 | 0.0679 | 1.8778 | 1.8782 |
|
109 |
+
| 8.6771 | 0.8626 | 270 | 6.8413 | 2.0243 | 0.0661 | 1.8715 | 1.8630 |
|
110 |
+
| 8.5573 | 0.8786 | 275 | 6.7161 | 2.1177 | 0.0706 | 1.9568 | 1.9550 |
|
111 |
+
| 8.0412 | 0.8946 | 280 | 6.5647 | 2.1079 | 0.0850 | 1.9593 | 1.9634 |
|
112 |
+
| 8.0998 | 0.9105 | 285 | 6.4273 | 2.0621 | 0.0670 | 1.8733 | 1.8734 |
|
113 |
+
| 9.3442 | 0.9265 | 290 | 6.3181 | 2.1413 | 0.0621 | 1.9701 | 1.9772 |
|
114 |
+
| 8.3607 | 0.9425 | 295 | 6.2155 | 2.1440 | 0.0663 | 1.9475 | 1.9530 |
|
115 |
+
| 8.159 | 0.9585 | 300 | 6.1254 | 2.1178 | 0.0808 | 1.9359 | 1.9494 |
|
116 |
+
| 8.375 | 0.9744 | 305 | 6.0546 | 2.0453 | 0.0555 | 1.8854 | 1.8912 |
|
117 |
+
| 7.8614 | 0.9904 | 310 | 5.9883 | 2.0222 | 0.0837 | 1.8446 | 1.8401 |
|
118 |
+
| 7.8965 | 1.0064 | 315 | 5.9095 | 1.9449 | 0.0754 | 1.8140 | 1.8219 |
|
119 |
+
| 7.8374 | 1.0224 | 320 | 5.8338 | 1.8352 | 0.0614 | 1.6886 | 1.6898 |
|
120 |
+
| 7.3908 | 1.0383 | 325 | 5.7725 | 1.7988 | 0.0274 | 1.6768 | 1.6720 |
|
121 |
+
| 7.2125 | 1.0543 | 330 | 5.7318 | 1.7631 | 0.0280 | 1.6570 | 1.6562 |
|
122 |
+
| 6.96 | 1.0703 | 335 | 5.6873 | 1.7982 | 0.0380 | 1.6733 | 1.6717 |
|
123 |
+
| 6.7824 | 1.0863 | 340 | 5.6433 | 1.7292 | 0.0158 | 1.6185 | 1.6154 |
|
124 |
+
| 7.2195 | 1.1022 | 345 | 5.6065 | 1.6919 | 0.0097 | 1.5788 | 1.5781 |
|
125 |
+
| 6.8652 | 1.1182 | 350 | 5.5795 | 1.6772 | 0.0240 | 1.5553 | 1.5559 |
|
126 |
+
| 6.8316 | 1.1342 | 355 | 5.5502 | 1.8285 | 0.0323 | 1.6808 | 1.6837 |
|
127 |
+
| 6.6977 | 1.1502 | 360 | 5.5189 | 1.8644 | 0.0325 | 1.7332 | 1.7310 |
|
128 |
+
| 6.653 | 1.1661 | 365 | 5.4988 | 1.9065 | 0.0077 | 1.8050 | 1.7936 |
|
129 |
+
| 6.8181 | 1.1821 | 370 | 5.4788 | 2.0777 | 0.0235 | 1.9549 | 1.9486 |
|
130 |
+
| 6.4765 | 1.1981 | 375 | 5.4562 | 2.0994 | 0.0181 | 1.9805 | 1.9798 |
|
131 |
+
| 6.4261 | 1.2141 | 380 | 5.4208 | 2.0882 | 0.0218 | 1.9600 | 1.9642 |
|
132 |
+
| 6.3628 | 1.2300 | 385 | 5.3878 | 2.2176 | 0.0046 | 2.0925 | 2.0876 |
|
133 |
+
| 6.3874 | 1.2460 | 390 | 5.3578 | 2.4220 | 0.0159 | 2.2723 | 2.2667 |
|
134 |
+
| 7.4177 | 1.2620 | 395 | 5.3321 | 2.5522 | 0.0376 | 2.4077 | 2.4044 |
|
135 |
+
| 6.2809 | 1.2780 | 400 | 5.3009 | 2.8056 | 0.0417 | 2.6094 | 2.6001 |
|
136 |
+
| 6.1182 | 1.2939 | 405 | 5.2693 | 2.7486 | 0.0562 | 2.5622 | 2.5563 |
|
137 |
+
| 6.1409 | 1.3099 | 410 | 5.2373 | 2.6906 | 0.0573 | 2.4999 | 2.4938 |
|
138 |
+
| 5.9139 | 1.3259 | 415 | 5.2056 | 2.7300 | 0.0507 | 2.5417 | 2.5334 |
|
139 |
+
| 6.1582 | 1.3419 | 420 | 5.1738 | 2.8920 | 0.0568 | 2.6842 | 2.6774 |
|
140 |
+
| 5.9911 | 1.3578 | 425 | 5.1464 | 2.8393 | 0.0489 | 2.6846 | 2.6780 |
|
141 |
+
| 5.9696 | 1.3738 | 430 | 5.1238 | 2.9304 | 0.0549 | 2.7807 | 2.7750 |
|
142 |
+
| 6.0929 | 1.3898 | 435 | 5.1045 | 2.9212 | 0.0918 | 2.7701 | 2.7644 |
|
143 |
+
| 5.8908 | 1.4058 | 440 | 5.0855 | 3.0022 | 0.1129 | 2.8460 | 2.8394 |
|
144 |
+
| 5.7826 | 1.4217 | 445 | 5.0666 | 3.0201 | 0.1033 | 2.8730 | 2.8696 |
|
145 |
+
| 5.9332 | 1.4377 | 450 | 5.0470 | 3.1193 | 0.1409 | 2.9774 | 2.9695 |
|
146 |
+
| 5.9714 | 1.4537 | 455 | 5.0301 | 3.2911 | 0.1191 | 3.1034 | 3.1047 |
|
147 |
+
| 5.7709 | 1.4696 | 460 | 5.0101 | 3.3612 | 0.1608 | 3.1247 | 3.1236 |
|
148 |
+
| 5.8123 | 1.4856 | 465 | 4.9896 | 3.3173 | 0.1399 | 3.1273 | 3.1362 |
|
149 |
+
| 6.0585 | 1.5016 | 470 | 4.9714 | 3.2361 | 0.0967 | 3.0649 | 3.0646 |
|
150 |
+
| 6.0034 | 1.5176 | 475 | 4.9559 | 3.0748 | 0.0714 | 2.9328 | 2.9336 |
|
151 |
+
| 6.3619 | 1.5335 | 480 | 4.9413 | 3.0002 | 0.0787 | 2.8287 | 2.8258 |
|
152 |
+
| 5.8542 | 1.5495 | 485 | 4.9307 | 3.0453 | 0.0807 | 2.8848 | 2.8856 |
|
153 |
+
| 5.8228 | 1.5655 | 490 | 4.9194 | 2.9233 | 0.0811 | 2.7805 | 2.7672 |
|
154 |
+
| 5.7094 | 1.5815 | 495 | 4.9046 | 2.9617 | 0.0941 | 2.7988 | 2.7832 |
|
155 |
+
| 5.6528 | 1.5974 | 500 | 4.8924 | 2.9997 | 0.0789 | 2.8488 | 2.8351 |
|
156 |
+
| 5.8592 | 1.6134 | 505 | 4.8788 | 3.0669 | 0.1072 | 2.8792 | 2.8637 |
|
157 |
+
| 5.6805 | 1.6294 | 510 | 4.8659 | 3.0328 | 0.1122 | 2.8509 | 2.8414 |
|
158 |
+
| 5.5186 | 1.6454 | 515 | 4.8507 | 2.9497 | 0.0825 | 2.7921 | 2.7786 |
|
159 |
+
| 5.589 | 1.6613 | 520 | 4.8337 | 2.9081 | 0.0955 | 2.7581 | 2.7523 |
|
160 |
+
| 5.5379 | 1.6773 | 525 | 4.8193 | 2.7919 | 0.0814 | 2.6161 | 2.6185 |
|
161 |
+
| 5.6701 | 1.6933 | 530 | 4.8047 | 2.8344 | 0.1079 | 2.6571 | 2.6512 |
|
162 |
+
| 6.137 | 1.7093 | 535 | 4.7933 | 2.7816 | 0.0735 | 2.5927 | 2.5881 |
|
163 |
+
| 5.8377 | 1.7252 | 540 | 4.7825 | 2.7819 | 0.0774 | 2.5962 | 2.6009 |
|
164 |
+
| 5.6185 | 1.7412 | 545 | 4.7705 | 2.7287 | 0.0874 | 2.5388 | 2.5419 |
|
165 |
+
| 5.6095 | 1.7572 | 550 | 4.7591 | 2.5563 | 0.0725 | 2.3848 | 2.3885 |
|
166 |
+
| 5.4519 | 1.7732 | 555 | 4.7490 | 2.4814 | 0.0856 | 2.3373 | 2.3340 |
|
167 |
+
| 5.5364 | 1.7891 | 560 | 4.7379 | 2.3359 | 0.0491 | 2.2076 | 2.2135 |
|
168 |
+
| 5.396 | 1.8051 | 565 | 4.7280 | 2.3396 | 0.0482 | 2.1713 | 2.1773 |
|
169 |
+
| 5.6596 | 1.8211 | 570 | 4.7161 | 2.3460 | 0.0655 | 2.1534 | 2.1453 |
|
170 |
+
| 5.7221 | 1.8371 | 575 | 4.7065 | 2.3818 | 0.0587 | 2.1889 | 2.1826 |
|
171 |
+
| 5.6155 | 1.8530 | 580 | 4.7002 | 2.3422 | 0.0515 | 2.1361 | 2.1349 |
|
172 |
+
| 5.6145 | 1.8690 | 585 | 4.6958 | 2.3983 | 0.0578 | 2.1876 | 2.1833 |
|
173 |
+
| 5.4728 | 1.8850 | 590 | 4.6901 | 2.4544 | 0.0701 | 2.2619 | 2.2697 |
|
174 |
+
| 5.4142 | 1.9010 | 595 | 4.6833 | 2.4475 | 0.0628 | 2.2572 | 2.2671 |
|
175 |
+
| 5.3575 | 1.9169 | 600 | 4.6754 | 2.4684 | 0.0741 | 2.2996 | 2.3025 |
|
176 |
+
| 5.5454 | 1.9329 | 605 | 4.6682 | 2.4481 | 0.0738 | 2.2541 | 2.2655 |
|
177 |
+
| 5.5035 | 1.9489 | 610 | 4.6612 | 2.4297 | 0.0788 | 2.2434 | 2.2497 |
|
178 |
+
| 5.5278 | 1.9649 | 615 | 4.6553 | 2.5919 | 0.0883 | 2.3809 | 2.3821 |
|
179 |
+
| 5.4338 | 1.9808 | 620 | 4.6496 | 2.5962 | 0.1036 | 2.3660 | 2.3672 |
|
180 |
+
| 5.2894 | 1.9968 | 625 | 4.6441 | 2.5563 | 0.1007 | 2.3130 | 2.3066 |
|
181 |
+
| 5.3924 | 2.0128 | 630 | 4.6397 | 2.5281 | 0.1077 | 2.3199 | 2.3138 |
|
182 |
+
| 5.3305 | 2.0288 | 635 | 4.6353 | 2.5160 | 0.0898 | 2.2744 | 2.2703 |
|
183 |
+
| 5.4613 | 2.0447 | 640 | 4.6304 | 2.4376 | 0.0685 | 2.2492 | 2.2437 |
|
184 |
+
| 5.6444 | 2.0607 | 645 | 4.6263 | 2.4830 | 0.0663 | 2.2782 | 2.2744 |
|
185 |
+
| 5.5121 | 2.0767 | 650 | 4.6231 | 2.5163 | 0.0799 | 2.3073 | 2.3068 |
|
186 |
+
| 5.296 | 2.0927 | 655 | 4.6194 | 2.5040 | 0.0705 | 2.3031 | 2.2879 |
|
187 |
+
| 5.3649 | 2.1086 | 660 | 4.6158 | 2.5136 | 0.0661 | 2.3137 | 2.3068 |
|
188 |
+
| 5.4156 | 2.1246 | 665 | 4.6126 | 2.4373 | 0.0781 | 2.2614 | 2.2565 |
|
189 |
+
| 5.3653 | 2.1406 | 670 | 4.6081 | 2.4984 | 0.0810 | 2.3292 | 2.3187 |
|
190 |
+
| 5.3024 | 2.1565 | 675 | 4.6027 | 2.6135 | 0.0888 | 2.4156 | 2.4003 |
|
191 |
+
| 5.2955 | 2.1725 | 680 | 4.5989 | 2.6091 | 0.1021 | 2.3904 | 2.3851 |
|
192 |
+
| 5.4715 | 2.1885 | 685 | 4.5953 | 2.6246 | 0.0895 | 2.4088 | 2.4094 |
|
193 |
+
| 5.4434 | 2.2045 | 690 | 4.5926 | 2.6918 | 0.0837 | 2.4445 | 2.4454 |
|
194 |
+
| 5.5582 | 2.2204 | 695 | 4.5905 | 2.8086 | 0.0935 | 2.5330 | 2.5385 |
|
195 |
+
| 5.3533 | 2.2364 | 700 | 4.5880 | 2.7198 | 0.0890 | 2.4544 | 2.4481 |
|
196 |
+
| 5.3439 | 2.2524 | 705 | 4.5845 | 2.6570 | 0.0820 | 2.4208 | 2.4155 |
|
197 |
+
| 5.1984 | 2.2684 | 710 | 4.5801 | 2.6865 | 0.0819 | 2.4621 | 2.4571 |
|
198 |
+
| 5.3504 | 2.2843 | 715 | 4.5751 | 2.7156 | 0.0887 | 2.4695 | 2.4643 |
|
199 |
+
| 5.5938 | 2.3003 | 720 | 4.5706 | 2.6792 | 0.0986 | 2.4316 | 2.4239 |
|
200 |
+
| 5.3769 | 2.3163 | 725 | 4.5669 | 2.7313 | 0.0994 | 2.4751 | 2.4753 |
|
201 |
+
| 5.3968 | 2.3323 | 730 | 4.5636 | 2.8140 | 0.0991 | 2.5630 | 2.5592 |
|
202 |
+
| 5.3317 | 2.3482 | 735 | 4.5616 | 2.9841 | 0.1055 | 2.6897 | 2.6819 |
|
203 |
+
| 5.2947 | 2.3642 | 740 | 4.5594 | 3.0318 | 0.1402 | 2.7312 | 2.7301 |
|
204 |
+
| 5.3277 | 2.3802 | 745 | 4.5564 | 3.0887 | 0.1506 | 2.7989 | 2.8028 |
|
205 |
+
| 5.2962 | 2.3962 | 750 | 4.5548 | 3.1713 | 0.1730 | 2.8939 | 2.9003 |
|
206 |
+
| 5.3377 | 2.4121 | 755 | 4.5533 | 3.3365 | 0.1836 | 3.0301 | 3.0264 |
|
207 |
+
| 5.3748 | 2.4281 | 760 | 4.5521 | 3.4833 | 0.2159 | 3.1525 | 3.1460 |
|
208 |
+
| 5.2873 | 2.4441 | 765 | 4.5500 | 3.4699 | 0.2018 | 3.1139 | 3.1088 |
|
209 |
+
| 5.1183 | 2.4601 | 770 | 4.5476 | 3.3921 | 0.2051 | 3.0827 | 3.0814 |
|
210 |
+
| 5.2382 | 2.4760 | 775 | 4.5450 | 3.4243 | 0.2076 | 3.0987 | 3.0944 |
|
211 |
+
| 5.2985 | 2.4920 | 780 | 4.5414 | 3.5790 | 0.2363 | 3.1867 | 3.1812 |
|
212 |
+
| 5.2762 | 2.5080 | 785 | 4.5376 | 3.6311 | 0.2537 | 3.2515 | 3.2550 |
|
213 |
+
| 5.2516 | 2.5240 | 790 | 4.5350 | 3.7991 | 0.2550 | 3.3662 | 3.3711 |
|
214 |
+
| 5.282 | 2.5399 | 795 | 4.5331 | 3.9220 | 0.3137 | 3.4806 | 3.4832 |
|
215 |
+
| 5.3465 | 2.5559 | 800 | 4.5312 | 3.8305 | 0.2601 | 3.4528 | 3.4505 |
|
216 |
+
| 5.274 | 2.5719 | 805 | 4.5291 | 3.8755 | 0.2792 | 3.4920 | 3.4873 |
|
217 |
+
| 5.1391 | 2.5879 | 810 | 4.5271 | 3.9263 | 0.3121 | 3.5019 | 3.4895 |
|
218 |
+
| 5.3892 | 2.6038 | 815 | 4.5251 | 4.0607 | 0.3431 | 3.5957 | 3.5877 |
|
219 |
+
| 5.2987 | 2.6198 | 820 | 4.5228 | 4.0061 | 0.3137 | 3.5374 | 3.5283 |
|
220 |
+
| 5.2158 | 2.6358 | 825 | 4.5213 | 4.1523 | 0.3591 | 3.6240 | 3.6144 |
|
221 |
+
| 5.191 | 2.6518 | 830 | 4.5205 | 4.2116 | 0.4188 | 3.7061 | 3.6942 |
|
222 |
+
| 5.2265 | 2.6677 | 835 | 4.5193 | 4.2206 | 0.3864 | 3.7338 | 3.7210 |
|
223 |
+
| 5.2333 | 2.6837 | 840 | 4.5184 | 4.2695 | 0.3975 | 3.7507 | 3.7393 |
|
224 |
+
| 5.1384 | 2.6997 | 845 | 4.5162 | 4.3320 | 0.4062 | 3.8240 | 3.8040 |
|
225 |
+
| 5.1442 | 2.7157 | 850 | 4.5130 | 4.4226 | 0.4088 | 3.8752 | 3.8595 |
|
226 |
+
| 5.1943 | 2.7316 | 855 | 4.5092 | 4.4287 | 0.3944 | 3.8621 | 3.8523 |
|
227 |
+
| 5.1526 | 2.7476 | 860 | 4.5062 | 4.5171 | 0.3936 | 3.9142 | 3.9026 |
|
228 |
+
| 5.1915 | 2.7636 | 865 | 4.5040 | 4.5421 | 0.4005 | 3.9196 | 3.9163 |
|
229 |
+
| 5.0482 | 2.7796 | 870 | 4.5025 | 4.6508 | 0.3964 | 4.0050 | 3.9936 |
|
230 |
+
| 5.2235 | 2.7955 | 875 | 4.5015 | 4.8035 | 0.4233 | 4.0845 | 4.0709 |
|
231 |
+
| 5.3655 | 2.8115 | 880 | 4.5005 | 4.8997 | 0.4445 | 4.1750 | 4.1580 |
|
232 |
+
| 5.3367 | 2.8275 | 885 | 4.4989 | 5.0599 | 0.4701 | 4.3483 | 4.3399 |
|
233 |
+
| 5.21 | 2.8435 | 890 | 4.4970 | 4.9489 | 0.4527 | 4.2710 | 4.2522 |
|
234 |
+
| 5.2436 | 2.8594 | 895 | 4.4948 | 4.8979 | 0.4497 | 4.2262 | 4.2153 |
|
235 |
+
| 5.5091 | 2.8754 | 900 | 4.4937 | 4.8726 | 0.4405 | 4.1909 | 4.1780 |
|
236 |
+
| 5.1379 | 2.8914 | 905 | 4.4929 | 4.8368 | 0.4535 | 4.1541 | 4.1522 |
|
237 |
+
| 5.1668 | 2.9073 | 910 | 4.4914 | 4.8821 | 0.4292 | 4.1863 | 4.1733 |
|
238 |
+
| 5.2127 | 2.9233 | 915 | 4.4895 | 4.9437 | 0.4462 | 4.2173 | 4.1966 |
|
239 |
+
| 5.38 | 2.9393 | 920 | 4.4884 | 5.0082 | 0.4532 | 4.2588 | 4.2478 |
|
240 |
+
| 5.325 | 2.9553 | 925 | 4.4878 | 5.1021 | 0.4760 | 4.3264 | 4.3154 |
|
241 |
+
| 5.0822 | 2.9712 | 930 | 4.4868 | 5.1669 | 0.5022 | 4.4208 | 4.4005 |
|
242 |
+
| 5.2045 | 2.9872 | 935 | 4.4859 | 5.1822 | 0.5139 | 4.4300 | 4.4116 |
|
243 |
+
| 5.2538 | 3.0032 | 940 | 4.4846 | 5.2921 | 0.4791 | 4.4886 | 4.4698 |
|
244 |
+
| 5.243 | 3.0192 | 945 | 4.4834 | 5.3591 | 0.5424 | 4.5366 | 4.5320 |
|
245 |
+
| 5.2195 | 3.0351 | 950 | 4.4822 | 5.3424 | 0.5018 | 4.5008 | 4.4961 |
|
246 |
+
| 5.0609 | 3.0511 | 955 | 4.4803 | 5.3292 | 0.4762 | 4.4919 | 4.4916 |
|
247 |
+
| 5.2919 | 3.0671 | 960 | 4.4784 | 5.3802 | 0.4855 | 4.5251 | 4.5214 |
|
248 |
+
| 5.1772 | 3.0831 | 965 | 4.4767 | 5.4305 | 0.5046 | 4.5617 | 4.5596 |
|
249 |
+
| 5.1028 | 3.0990 | 970 | 4.4757 | 5.4031 | 0.5213 | 4.5559 | 4.5532 |
|
250 |
+
| 5.1279 | 3.1150 | 975 | 4.4748 | 5.3623 | 0.5349 | 4.5282 | 4.5292 |
|
251 |
+
| 5.2586 | 3.1310 | 980 | 4.4742 | 5.4266 | 0.5237 | 4.5739 | 4.5827 |
|
252 |
+
| 5.2418 | 3.1470 | 985 | 4.4735 | 5.5268 | 0.5263 | 4.6864 | 4.6850 |
|
253 |
+
| 5.1729 | 3.1629 | 990 | 4.4729 | 5.6541 | 0.5313 | 4.7523 | 4.7519 |
|
254 |
+
| 5.2652 | 3.1789 | 995 | 4.4726 | 5.6414 | 0.5296 | 4.7553 | 4.7575 |
|
255 |
+
| 5.2297 | 3.1949 | 1000 | 4.4722 | 5.7800 | 0.5704 | 4.8930 | 4.8865 |
|
256 |
+
| 4.942 | 3.2109 | 1005 | 4.4719 | 5.7945 | 0.5934 | 4.8901 | 4.8844 |
|
257 |
+
| 5.085 | 3.2268 | 1010 | 4.4716 | 5.7597 | 0.5812 | 4.8791 | 4.8828 |
|
258 |
+
| 5.0988 | 3.2428 | 1015 | 4.4713 | 5.8759 | 0.5745 | 4.9899 | 4.9961 |
|
259 |
+
| 5.1526 | 3.2588 | 1020 | 4.4711 | 5.9244 | 0.5343 | 5.0037 | 5.0056 |
|
260 |
+
| 5.2551 | 3.2748 | 1025 | 4.4705 | 6.0229 | 0.5521 | 5.0958 | 5.0915 |
|
261 |
+
| 5.2636 | 3.2907 | 1030 | 4.4696 | 6.1081 | 0.5651 | 5.1295 | 5.1295 |
|
262 |
+
| 5.2502 | 3.3067 | 1035 | 4.4684 | 6.0950 | 0.5641 | 5.1387 | 5.1347 |
|
263 |
+
| 5.038 | 3.3227 | 1040 | 4.4670 | 6.1524 | 0.5891 | 5.1954 | 5.1949 |
|
264 |
+
| 5.0824 | 3.3387 | 1045 | 4.4659 | 6.2160 | 0.5998 | 5.2652 | 5.2477 |
|
265 |
+
| 5.1861 | 3.3546 | 1050 | 4.4648 | 6.2476 | 0.6073 | 5.2739 | 5.2601 |
|
266 |
+
| 5.1434 | 3.3706 | 1055 | 4.4637 | 6.2773 | 0.6013 | 5.3101 | 5.2990 |
|
267 |
+
| 5.2063 | 3.3866 | 1060 | 4.4629 | 6.1880 | 0.5892 | 5.2347 | 5.2163 |
|
268 |
+
| 5.2748 | 3.4026 | 1065 | 4.4618 | 6.2218 | 0.5895 | 5.2512 | 5.2342 |
|
269 |
+
| 5.7406 | 3.4185 | 1070 | 4.4612 | 6.1878 | 0.6049 | 5.2189 | 5.2112 |
|
270 |
+
| 5.2039 | 3.4345 | 1075 | 4.4611 | 6.2877 | 0.6084 | 5.2765 | 5.2695 |
|
271 |
+
| 5.1484 | 3.4505 | 1080 | 4.4612 | 6.3316 | 0.6033 | 5.3273 | 5.3108 |
|
272 |
+
| 5.1618 | 3.4665 | 1085 | 4.4614 | 6.4027 | 0.6252 | 5.3809 | 5.3683 |
|
273 |
+
| 5.1077 | 3.4824 | 1090 | 4.4613 | 6.4064 | 0.6555 | 5.3963 | 5.3870 |
|
274 |
+
| 5.2886 | 3.4984 | 1095 | 4.4613 | 6.3386 | 0.6353 | 5.3369 | 5.3278 |
|
275 |
+
| 5.3097 | 3.5144 | 1100 | 4.4610 | 6.3876 | 0.6477 | 5.3771 | 5.3700 |
|
276 |
+
| 5.0038 | 3.5304 | 1105 | 4.4607 | 6.4420 | 0.6398 | 5.4057 | 5.3979 |
|
277 |
+
| 5.0396 | 3.5463 | 1110 | 4.4602 | 6.4946 | 0.6543 | 5.4389 | 5.4344 |
|
278 |
+
| 5.1375 | 3.5623 | 1115 | 4.4601 | 6.5020 | 0.6608 | 5.4498 | 5.4447 |
|
279 |
+
| 5.2003 | 3.5783 | 1120 | 4.4603 | 6.4656 | 0.6311 | 5.4840 | 5.4624 |
|
280 |
+
| 5.0139 | 3.5942 | 1125 | 4.4606 | 6.4542 | 0.6321 | 5.4910 | 5.4774 |
|
281 |
+
| 5.0223 | 3.6102 | 1130 | 4.4608 | 6.4289 | 0.6309 | 5.4560 | 5.4476 |
|
282 |
+
| 5.1267 | 3.6262 | 1135 | 4.4608 | 6.4512 | 0.6360 | 5.4525 | 5.4461 |
|
283 |
+
| 5.2172 | 3.6422 | 1140 | 4.4608 | 6.4816 | 0.6248 | 5.4567 | 5.4546 |
|
284 |
+
| 5.3578 | 3.6581 | 1145 | 4.4608 | 6.4887 | 0.6065 | 5.4418 | 5.4357 |
|
285 |
+
| 5.1612 | 3.6741 | 1150 | 4.4606 | 6.4740 | 0.6147 | 5.4604 | 5.4481 |
|
286 |
+
| 5.0054 | 3.6901 | 1155 | 4.4602 | 6.4704 | 0.6273 | 5.4557 | 5.4442 |
|
287 |
+
| 5.2887 | 3.7061 | 1160 | 4.4600 | 6.4655 | 0.6255 | 5.4490 | 5.4368 |
|
288 |
+
| 5.3086 | 3.7220 | 1165 | 4.4596 | 6.4939 | 0.6261 | 5.4663 | 5.4539 |
|
289 |
+
| 5.1809 | 3.7380 | 1170 | 4.4594 | 6.4406 | 0.6059 | 5.4276 | 5.4183 |
|
290 |
+
| 5.313 | 3.7540 | 1175 | 4.4591 | 6.5160 | 0.6142 | 5.4987 | 5.4826 |
|
291 |
+
| 5.0022 | 3.7700 | 1180 | 4.4587 | 6.5403 | 0.6259 | 5.5196 | 5.5067 |
|
292 |
+
| 5.222 | 3.7859 | 1185 | 4.4584 | 6.5355 | 0.6200 | 5.5080 | 5.4945 |
|
293 |
+
| 5.3514 | 3.8019 | 1190 | 4.4580 | 6.5493 | 0.6162 | 5.5234 | 5.5147 |
|
294 |
+
| 5.1164 | 3.8179 | 1195 | 4.4579 | 6.5421 | 0.6212 | 5.5360 | 5.5216 |
|
295 |
+
| 5.2675 | 3.8339 | 1200 | 4.4576 | 6.5081 | 0.6139 | 5.5152 | 5.5026 |
|
296 |
+
| 5.1797 | 3.8498 | 1205 | 4.4574 | 6.4890 | 0.6106 | 5.4938 | 5.4812 |
|
297 |
+
| 5.2451 | 3.8658 | 1210 | 4.4571 | 6.4974 | 0.6143 | 5.4973 | 5.4860 |
|
298 |
+
| 5.0375 | 3.8818 | 1215 | 4.4569 | 6.5096 | 0.6031 | 5.4956 | 5.4872 |
|
299 |
+
| 5.132 | 3.8978 | 1220 | 4.4568 | 6.5068 | 0.6031 | 5.4912 | 5.4835 |
|
300 |
+
| 5.1134 | 3.9137 | 1225 | 4.4567 | 6.5101 | 0.5990 | 5.4930 | 5.4830 |
|
301 |
+
| 5.1281 | 3.9297 | 1230 | 4.4566 | 6.5215 | 0.5990 | 5.4995 | 5.4915 |
|
302 |
+
| 4.9446 | 3.9457 | 1235 | 4.4565 | 6.5331 | 0.6026 | 5.5102 | 5.5032 |
|
303 |
+
| 5.1653 | 3.9617 | 1240 | 4.4565 | 6.5345 | 0.6026 | 5.5103 | 5.5036 |
|
304 |
+
| 5.1808 | 3.9776 | 1245 | 4.4564 | 6.5289 | 0.5992 | 5.5070 | 5.4998 |
|
305 |
+
| 5.358 | 3.9936 | 1250 | 4.4564 | 6.5458 | 0.5992 | 5.5320 | 5.5225 |
|
306 |
+
|
307 |
+
|
308 |
+
### Framework versions
|
309 |
+
|
310 |
+
- PEFT 0.14.0
|
311 |
+
- Transformers 4.49.0
|
312 |
+
- Pytorch 2.6.0+cu124
|
313 |
+
- Datasets 3.3.2
|
314 |
+
- Tokenizers 0.21.0
|
adapter_config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": null,
|
5 |
+
"bias": "none",
|
6 |
+
"eva_config": null,
|
7 |
+
"exclude_modules": null,
|
8 |
+
"fan_in_fan_out": false,
|
9 |
+
"inference_mode": true,
|
10 |
+
"init_lora_weights": true,
|
11 |
+
"layer_replication": null,
|
12 |
+
"layers_pattern": null,
|
13 |
+
"layers_to_transform": null,
|
14 |
+
"loftq_config": {},
|
15 |
+
"lora_alpha": 16,
|
16 |
+
"lora_bias": false,
|
17 |
+
"lora_dropout": 0.2,
|
18 |
+
"megatron_config": null,
|
19 |
+
"megatron_core": "megatron.core",
|
20 |
+
"modules_to_save": null,
|
21 |
+
"peft_type": "LORA",
|
22 |
+
"r": 1,
|
23 |
+
"rank_pattern": {},
|
24 |
+
"revision": null,
|
25 |
+
"target_modules": [
|
26 |
+
"v",
|
27 |
+
"q"
|
28 |
+
],
|
29 |
+
"task_type": "SEQ_2_SEQ_LM",
|
30 |
+
"use_dora": false,
|
31 |
+
"use_rslora": false
|
32 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa3d44bd025991805b1904a4dd159f6b40b0a7295a9cf9782e7c7a1ae48cff81
|
3 |
+
size 186704
|
runs/Mar10_23-08-48_1412920010036/events.out.tfevents.1741662535.1412920010036.5471.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d86bf84720e7f90ac974efa75515570b134c9d405e77c7b946753da0a78708c9
|
3 |
+
size 91015
|
runs/Mar10_23-08-48_1412920010036/events.out.tfevents.1741667746.1412920010036.5471.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:792a75e640434bf8aa50b1ef06323080a1c16079af61c3bf8694eb452fad42a6
|
3 |
+
size 562
|
runs/Mar11_00-36-23_1412920010036/events.out.tfevents.1741667784.1412920010036.5471.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14a0ec7de23abb4f0a5d2089d151629190d92f5ec867f3f325c6be120106b2fe
|
3 |
+
size 59508
|
runs/Mar11_00-36-23_1412920010036/events.out.tfevents.1741668489.1412920010036.5471.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bf2e319d10421337f47f1e8b3f46bae0ad327b388a3e7f90b0e1965ffdbc5d5a
|
3 |
+
size 562
|
runs/Mar11_00-48-17_1412920010036/events.out.tfevents.1741668498.1412920010036.5471.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d85e822375a87e28f05d12ef333b2fb6fd159fe4f9a19f1f70ba612647cfb70a
|
3 |
+
size 91030
|
runs/Mar11_00-48-17_1412920010036/events.out.tfevents.1741673649.1412920010036.5471.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:00f80e0e8a6988580e823614cd7f35439cdb0938a3ace2d1fd4358ba8f788052
|
3 |
+
size 562
|
runs/Mar11_08-18-41_1412920010036/events.out.tfevents.1741695522.1412920010036.235349.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a351088403358a6e3ed6d487f24a9e6b63a3c00043cebc546bf195ce0ad75e0
|
3 |
+
size 8924
|
runs/Mar11_08-36-50_1412920010036/events.out.tfevents.1741696613.1412920010036.243166.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8b85c7d0e23e119678b0ca6026c0a32bbd115ca0c00d66d7557d08945fcbb2a
|
3 |
+
size 176636
|
runs/Mar11_08-36-50_1412920010036/events.out.tfevents.1741706871.1412920010036.243166.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:10f1c7671cba5b2b3a49d643cc0171f5caa39468117d1aabefa9df00cb178ea3
|
3 |
+
size 562
|
runs/Mar11_11-28-33_1412920010036/events.out.tfevents.1741706915.1412920010036.243166.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0d6042ab546ed0306f50935e16c50c7da9d5ab234567950aa455979e0d1d44b
|
3 |
+
size 114304
|
runs/Mar11_11-28-33_1412920010036/events.out.tfevents.1741708827.1412920010036.243166.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a68052302a939cdcae8f660c29206fda498cf5bd6156f7c0759b5a0511db490
|
3 |
+
size 562
|
runs/Mar11_12-01-09_1412920010036/events.out.tfevents.1741708871.1412920010036.243166.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:afbc32f901a15cf55d6682328172fa8bb18c97a8dab6fe53e34a905894f45b81
|
3 |
+
size 176651
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": {
|
3 |
+
"content": "</s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"pad_token": {
|
10 |
+
"content": "<pad>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"unk_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
|
3 |
+
size 4309802
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90ed658667887a6a72b5f071e2e34bd3d9c562683f9c71a2f9c7c1c414e6c5bc
|
3 |
+
size 16350026
|
tokenizer_config.json
ADDED
@@ -0,0 +1,840 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": null,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<pad>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "</s>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "<unk>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"250000": {
|
29 |
+
"content": "β<extra_id_99>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": false
|
35 |
+
},
|
36 |
+
"250001": {
|
37 |
+
"content": "β<extra_id_98>",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": false
|
43 |
+
},
|
44 |
+
"250002": {
|
45 |
+
"content": "β<extra_id_97>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false,
|
50 |
+
"special": false
|
51 |
+
},
|
52 |
+
"250003": {
|
53 |
+
"content": "β<extra_id_96>",
|
54 |
+
"lstrip": false,
|
55 |
+
"normalized": false,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": false,
|
58 |
+
"special": false
|
59 |
+
},
|
60 |
+
"250004": {
|
61 |
+
"content": "β<extra_id_95>",
|
62 |
+
"lstrip": false,
|
63 |
+
"normalized": false,
|
64 |
+
"rstrip": false,
|
65 |
+
"single_word": false,
|
66 |
+
"special": false
|
67 |
+
},
|
68 |
+
"250005": {
|
69 |
+
"content": "β<extra_id_94>",
|
70 |
+
"lstrip": false,
|
71 |
+
"normalized": false,
|
72 |
+
"rstrip": false,
|
73 |
+
"single_word": false,
|
74 |
+
"special": false
|
75 |
+
},
|
76 |
+
"250006": {
|
77 |
+
"content": "β<extra_id_93>",
|
78 |
+
"lstrip": false,
|
79 |
+
"normalized": false,
|
80 |
+
"rstrip": false,
|
81 |
+
"single_word": false,
|
82 |
+
"special": false
|
83 |
+
},
|
84 |
+
"250007": {
|
85 |
+
"content": "β<extra_id_92>",
|
86 |
+
"lstrip": false,
|
87 |
+
"normalized": false,
|
88 |
+
"rstrip": false,
|
89 |
+
"single_word": false,
|
90 |
+
"special": false
|
91 |
+
},
|
92 |
+
"250008": {
|
93 |
+
"content": "β<extra_id_91>",
|
94 |
+
"lstrip": false,
|
95 |
+
"normalized": false,
|
96 |
+
"rstrip": false,
|
97 |
+
"single_word": false,
|
98 |
+
"special": false
|
99 |
+
},
|
100 |
+
"250009": {
|
101 |
+
"content": "β<extra_id_90>",
|
102 |
+
"lstrip": false,
|
103 |
+
"normalized": false,
|
104 |
+
"rstrip": false,
|
105 |
+
"single_word": false,
|
106 |
+
"special": false
|
107 |
+
},
|
108 |
+
"250010": {
|
109 |
+
"content": "β<extra_id_89>",
|
110 |
+
"lstrip": false,
|
111 |
+
"normalized": false,
|
112 |
+
"rstrip": false,
|
113 |
+
"single_word": false,
|
114 |
+
"special": false
|
115 |
+
},
|
116 |
+
"250011": {
|
117 |
+
"content": "β<extra_id_88>",
|
118 |
+
"lstrip": false,
|
119 |
+
"normalized": false,
|
120 |
+
"rstrip": false,
|
121 |
+
"single_word": false,
|
122 |
+
"special": false
|
123 |
+
},
|
124 |
+
"250012": {
|
125 |
+
"content": "β<extra_id_87>",
|
126 |
+
"lstrip": false,
|
127 |
+
"normalized": false,
|
128 |
+
"rstrip": false,
|
129 |
+
"single_word": false,
|
130 |
+
"special": false
|
131 |
+
},
|
132 |
+
"250013": {
|
133 |
+
"content": "β<extra_id_86>",
|
134 |
+
"lstrip": false,
|
135 |
+
"normalized": false,
|
136 |
+
"rstrip": false,
|
137 |
+
"single_word": false,
|
138 |
+
"special": false
|
139 |
+
},
|
140 |
+
"250014": {
|
141 |
+
"content": "β<extra_id_85>",
|
142 |
+
"lstrip": false,
|
143 |
+
"normalized": false,
|
144 |
+
"rstrip": false,
|
145 |
+
"single_word": false,
|
146 |
+
"special": false
|
147 |
+
},
|
148 |
+
"250015": {
|
149 |
+
"content": "β<extra_id_84>",
|
150 |
+
"lstrip": false,
|
151 |
+
"normalized": false,
|
152 |
+
"rstrip": false,
|
153 |
+
"single_word": false,
|
154 |
+
"special": false
|
155 |
+
},
|
156 |
+
"250016": {
|
157 |
+
"content": "β<extra_id_83>",
|
158 |
+
"lstrip": false,
|
159 |
+
"normalized": false,
|
160 |
+
"rstrip": false,
|
161 |
+
"single_word": false,
|
162 |
+
"special": false
|
163 |
+
},
|
164 |
+
"250017": {
|
165 |
+
"content": "β<extra_id_82>",
|
166 |
+
"lstrip": false,
|
167 |
+
"normalized": false,
|
168 |
+
"rstrip": false,
|
169 |
+
"single_word": false,
|
170 |
+
"special": false
|
171 |
+
},
|
172 |
+
"250018": {
|
173 |
+
"content": "β<extra_id_81>",
|
174 |
+
"lstrip": false,
|
175 |
+
"normalized": false,
|
176 |
+
"rstrip": false,
|
177 |
+
"single_word": false,
|
178 |
+
"special": false
|
179 |
+
},
|
180 |
+
"250019": {
|
181 |
+
"content": "β<extra_id_80>",
|
182 |
+
"lstrip": false,
|
183 |
+
"normalized": false,
|
184 |
+
"rstrip": false,
|
185 |
+
"single_word": false,
|
186 |
+
"special": false
|
187 |
+
},
|
188 |
+
"250020": {
|
189 |
+
"content": "β<extra_id_79>",
|
190 |
+
"lstrip": false,
|
191 |
+
"normalized": false,
|
192 |
+
"rstrip": false,
|
193 |
+
"single_word": false,
|
194 |
+
"special": false
|
195 |
+
},
|
196 |
+
"250021": {
|
197 |
+
"content": "β<extra_id_78>",
|
198 |
+
"lstrip": false,
|
199 |
+
"normalized": false,
|
200 |
+
"rstrip": false,
|
201 |
+
"single_word": false,
|
202 |
+
"special": false
|
203 |
+
},
|
204 |
+
"250022": {
|
205 |
+
"content": "β<extra_id_77>",
|
206 |
+
"lstrip": false,
|
207 |
+
"normalized": false,
|
208 |
+
"rstrip": false,
|
209 |
+
"single_word": false,
|
210 |
+
"special": false
|
211 |
+
},
|
212 |
+
"250023": {
|
213 |
+
"content": "β<extra_id_76>",
|
214 |
+
"lstrip": false,
|
215 |
+
"normalized": false,
|
216 |
+
"rstrip": false,
|
217 |
+
"single_word": false,
|
218 |
+
"special": false
|
219 |
+
},
|
220 |
+
"250024": {
|
221 |
+
"content": "β<extra_id_75>",
|
222 |
+
"lstrip": false,
|
223 |
+
"normalized": false,
|
224 |
+
"rstrip": false,
|
225 |
+
"single_word": false,
|
226 |
+
"special": false
|
227 |
+
},
|
228 |
+
"250025": {
|
229 |
+
"content": "β<extra_id_74>",
|
230 |
+
"lstrip": false,
|
231 |
+
"normalized": false,
|
232 |
+
"rstrip": false,
|
233 |
+
"single_word": false,
|
234 |
+
"special": false
|
235 |
+
},
|
236 |
+
"250026": {
|
237 |
+
"content": "β<extra_id_73>",
|
238 |
+
"lstrip": false,
|
239 |
+
"normalized": false,
|
240 |
+
"rstrip": false,
|
241 |
+
"single_word": false,
|
242 |
+
"special": false
|
243 |
+
},
|
244 |
+
"250027": {
|
245 |
+
"content": "β<extra_id_72>",
|
246 |
+
"lstrip": false,
|
247 |
+
"normalized": false,
|
248 |
+
"rstrip": false,
|
249 |
+
"single_word": false,
|
250 |
+
"special": false
|
251 |
+
},
|
252 |
+
"250028": {
|
253 |
+
"content": "β<extra_id_71>",
|
254 |
+
"lstrip": false,
|
255 |
+
"normalized": false,
|
256 |
+
"rstrip": false,
|
257 |
+
"single_word": false,
|
258 |
+
"special": false
|
259 |
+
},
|
260 |
+
"250029": {
|
261 |
+
"content": "β<extra_id_70>",
|
262 |
+
"lstrip": false,
|
263 |
+
"normalized": false,
|
264 |
+
"rstrip": false,
|
265 |
+
"single_word": false,
|
266 |
+
"special": false
|
267 |
+
},
|
268 |
+
"250030": {
|
269 |
+
"content": "β<extra_id_69>",
|
270 |
+
"lstrip": false,
|
271 |
+
"normalized": false,
|
272 |
+
"rstrip": false,
|
273 |
+
"single_word": false,
|
274 |
+
"special": false
|
275 |
+
},
|
276 |
+
"250031": {
|
277 |
+
"content": "β<extra_id_68>",
|
278 |
+
"lstrip": false,
|
279 |
+
"normalized": false,
|
280 |
+
"rstrip": false,
|
281 |
+
"single_word": false,
|
282 |
+
"special": false
|
283 |
+
},
|
284 |
+
"250032": {
|
285 |
+
"content": "β<extra_id_67>",
|
286 |
+
"lstrip": false,
|
287 |
+
"normalized": false,
|
288 |
+
"rstrip": false,
|
289 |
+
"single_word": false,
|
290 |
+
"special": false
|
291 |
+
},
|
292 |
+
"250033": {
|
293 |
+
"content": "β<extra_id_66>",
|
294 |
+
"lstrip": false,
|
295 |
+
"normalized": false,
|
296 |
+
"rstrip": false,
|
297 |
+
"single_word": false,
|
298 |
+
"special": false
|
299 |
+
},
|
300 |
+
"250034": {
|
301 |
+
"content": "β<extra_id_65>",
|
302 |
+
"lstrip": false,
|
303 |
+
"normalized": false,
|
304 |
+
"rstrip": false,
|
305 |
+
"single_word": false,
|
306 |
+
"special": false
|
307 |
+
},
|
308 |
+
"250035": {
|
309 |
+
"content": "β<extra_id_64>",
|
310 |
+
"lstrip": false,
|
311 |
+
"normalized": false,
|
312 |
+
"rstrip": false,
|
313 |
+
"single_word": false,
|
314 |
+
"special": false
|
315 |
+
},
|
316 |
+
"250036": {
|
317 |
+
"content": "β<extra_id_63>",
|
318 |
+
"lstrip": false,
|
319 |
+
"normalized": false,
|
320 |
+
"rstrip": false,
|
321 |
+
"single_word": false,
|
322 |
+
"special": false
|
323 |
+
},
|
324 |
+
"250037": {
|
325 |
+
"content": "β<extra_id_62>",
|
326 |
+
"lstrip": false,
|
327 |
+
"normalized": false,
|
328 |
+
"rstrip": false,
|
329 |
+
"single_word": false,
|
330 |
+
"special": false
|
331 |
+
},
|
332 |
+
"250038": {
|
333 |
+
"content": "β<extra_id_61>",
|
334 |
+
"lstrip": false,
|
335 |
+
"normalized": false,
|
336 |
+
"rstrip": false,
|
337 |
+
"single_word": false,
|
338 |
+
"special": false
|
339 |
+
},
|
340 |
+
"250039": {
|
341 |
+
"content": "β<extra_id_60>",
|
342 |
+
"lstrip": false,
|
343 |
+
"normalized": false,
|
344 |
+
"rstrip": false,
|
345 |
+
"single_word": false,
|
346 |
+
"special": false
|
347 |
+
},
|
348 |
+
"250040": {
|
349 |
+
"content": "β<extra_id_59>",
|
350 |
+
"lstrip": false,
|
351 |
+
"normalized": false,
|
352 |
+
"rstrip": false,
|
353 |
+
"single_word": false,
|
354 |
+
"special": false
|
355 |
+
},
|
356 |
+
"250041": {
|
357 |
+
"content": "β<extra_id_58>",
|
358 |
+
"lstrip": false,
|
359 |
+
"normalized": false,
|
360 |
+
"rstrip": false,
|
361 |
+
"single_word": false,
|
362 |
+
"special": false
|
363 |
+
},
|
364 |
+
"250042": {
|
365 |
+
"content": "β<extra_id_57>",
|
366 |
+
"lstrip": false,
|
367 |
+
"normalized": false,
|
368 |
+
"rstrip": false,
|
369 |
+
"single_word": false,
|
370 |
+
"special": false
|
371 |
+
},
|
372 |
+
"250043": {
|
373 |
+
"content": "β<extra_id_56>",
|
374 |
+
"lstrip": false,
|
375 |
+
"normalized": false,
|
376 |
+
"rstrip": false,
|
377 |
+
"single_word": false,
|
378 |
+
"special": false
|
379 |
+
},
|
380 |
+
"250044": {
|
381 |
+
"content": "β<extra_id_55>",
|
382 |
+
"lstrip": false,
|
383 |
+
"normalized": false,
|
384 |
+
"rstrip": false,
|
385 |
+
"single_word": false,
|
386 |
+
"special": false
|
387 |
+
},
|
388 |
+
"250045": {
|
389 |
+
"content": "β<extra_id_54>",
|
390 |
+
"lstrip": false,
|
391 |
+
"normalized": false,
|
392 |
+
"rstrip": false,
|
393 |
+
"single_word": false,
|
394 |
+
"special": false
|
395 |
+
},
|
396 |
+
"250046": {
|
397 |
+
"content": "β<extra_id_53>",
|
398 |
+
"lstrip": false,
|
399 |
+
"normalized": false,
|
400 |
+
"rstrip": false,
|
401 |
+
"single_word": false,
|
402 |
+
"special": false
|
403 |
+
},
|
404 |
+
"250047": {
|
405 |
+
"content": "β<extra_id_52>",
|
406 |
+
"lstrip": false,
|
407 |
+
"normalized": false,
|
408 |
+
"rstrip": false,
|
409 |
+
"single_word": false,
|
410 |
+
"special": false
|
411 |
+
},
|
412 |
+
"250048": {
|
413 |
+
"content": "β<extra_id_51>",
|
414 |
+
"lstrip": false,
|
415 |
+
"normalized": false,
|
416 |
+
"rstrip": false,
|
417 |
+
"single_word": false,
|
418 |
+
"special": false
|
419 |
+
},
|
420 |
+
"250049": {
|
421 |
+
"content": "β<extra_id_50>",
|
422 |
+
"lstrip": false,
|
423 |
+
"normalized": false,
|
424 |
+
"rstrip": false,
|
425 |
+
"single_word": false,
|
426 |
+
"special": false
|
427 |
+
},
|
428 |
+
"250050": {
|
429 |
+
"content": "οΏ½οΏ½οΏ½<extra_id_49>",
|
430 |
+
"lstrip": false,
|
431 |
+
"normalized": false,
|
432 |
+
"rstrip": false,
|
433 |
+
"single_word": false,
|
434 |
+
"special": false
|
435 |
+
},
|
436 |
+
"250051": {
|
437 |
+
"content": "β<extra_id_48>",
|
438 |
+
"lstrip": false,
|
439 |
+
"normalized": false,
|
440 |
+
"rstrip": false,
|
441 |
+
"single_word": false,
|
442 |
+
"special": false
|
443 |
+
},
|
444 |
+
"250052": {
|
445 |
+
"content": "β<extra_id_47>",
|
446 |
+
"lstrip": false,
|
447 |
+
"normalized": false,
|
448 |
+
"rstrip": false,
|
449 |
+
"single_word": false,
|
450 |
+
"special": false
|
451 |
+
},
|
452 |
+
"250053": {
|
453 |
+
"content": "β<extra_id_46>",
|
454 |
+
"lstrip": false,
|
455 |
+
"normalized": false,
|
456 |
+
"rstrip": false,
|
457 |
+
"single_word": false,
|
458 |
+
"special": false
|
459 |
+
},
|
460 |
+
"250054": {
|
461 |
+
"content": "β<extra_id_45>",
|
462 |
+
"lstrip": false,
|
463 |
+
"normalized": false,
|
464 |
+
"rstrip": false,
|
465 |
+
"single_word": false,
|
466 |
+
"special": false
|
467 |
+
},
|
468 |
+
"250055": {
|
469 |
+
"content": "β<extra_id_44>",
|
470 |
+
"lstrip": false,
|
471 |
+
"normalized": false,
|
472 |
+
"rstrip": false,
|
473 |
+
"single_word": false,
|
474 |
+
"special": false
|
475 |
+
},
|
476 |
+
"250056": {
|
477 |
+
"content": "β<extra_id_43>",
|
478 |
+
"lstrip": false,
|
479 |
+
"normalized": false,
|
480 |
+
"rstrip": false,
|
481 |
+
"single_word": false,
|
482 |
+
"special": false
|
483 |
+
},
|
484 |
+
"250057": {
|
485 |
+
"content": "β<extra_id_42>",
|
486 |
+
"lstrip": false,
|
487 |
+
"normalized": false,
|
488 |
+
"rstrip": false,
|
489 |
+
"single_word": false,
|
490 |
+
"special": false
|
491 |
+
},
|
492 |
+
"250058": {
|
493 |
+
"content": "β<extra_id_41>",
|
494 |
+
"lstrip": false,
|
495 |
+
"normalized": false,
|
496 |
+
"rstrip": false,
|
497 |
+
"single_word": false,
|
498 |
+
"special": false
|
499 |
+
},
|
500 |
+
"250059": {
|
501 |
+
"content": "β<extra_id_40>",
|
502 |
+
"lstrip": false,
|
503 |
+
"normalized": false,
|
504 |
+
"rstrip": false,
|
505 |
+
"single_word": false,
|
506 |
+
"special": false
|
507 |
+
},
|
508 |
+
"250060": {
|
509 |
+
"content": "β<extra_id_39>",
|
510 |
+
"lstrip": false,
|
511 |
+
"normalized": false,
|
512 |
+
"rstrip": false,
|
513 |
+
"single_word": false,
|
514 |
+
"special": false
|
515 |
+
},
|
516 |
+
"250061": {
|
517 |
+
"content": "β<extra_id_38>",
|
518 |
+
"lstrip": false,
|
519 |
+
"normalized": false,
|
520 |
+
"rstrip": false,
|
521 |
+
"single_word": false,
|
522 |
+
"special": false
|
523 |
+
},
|
524 |
+
"250062": {
|
525 |
+
"content": "β<extra_id_37>",
|
526 |
+
"lstrip": false,
|
527 |
+
"normalized": false,
|
528 |
+
"rstrip": false,
|
529 |
+
"single_word": false,
|
530 |
+
"special": false
|
531 |
+
},
|
532 |
+
"250063": {
|
533 |
+
"content": "β<extra_id_36>",
|
534 |
+
"lstrip": false,
|
535 |
+
"normalized": false,
|
536 |
+
"rstrip": false,
|
537 |
+
"single_word": false,
|
538 |
+
"special": false
|
539 |
+
},
|
540 |
+
"250064": {
|
541 |
+
"content": "β<extra_id_35>",
|
542 |
+
"lstrip": false,
|
543 |
+
"normalized": false,
|
544 |
+
"rstrip": false,
|
545 |
+
"single_word": false,
|
546 |
+
"special": false
|
547 |
+
},
|
548 |
+
"250065": {
|
549 |
+
"content": "β<extra_id_34>",
|
550 |
+
"lstrip": false,
|
551 |
+
"normalized": false,
|
552 |
+
"rstrip": false,
|
553 |
+
"single_word": false,
|
554 |
+
"special": false
|
555 |
+
},
|
556 |
+
"250066": {
|
557 |
+
"content": "β<extra_id_33>",
|
558 |
+
"lstrip": false,
|
559 |
+
"normalized": false,
|
560 |
+
"rstrip": false,
|
561 |
+
"single_word": false,
|
562 |
+
"special": false
|
563 |
+
},
|
564 |
+
"250067": {
|
565 |
+
"content": "β<extra_id_32>",
|
566 |
+
"lstrip": false,
|
567 |
+
"normalized": false,
|
568 |
+
"rstrip": false,
|
569 |
+
"single_word": false,
|
570 |
+
"special": false
|
571 |
+
},
|
572 |
+
"250068": {
|
573 |
+
"content": "β<extra_id_31>",
|
574 |
+
"lstrip": false,
|
575 |
+
"normalized": false,
|
576 |
+
"rstrip": false,
|
577 |
+
"single_word": false,
|
578 |
+
"special": false
|
579 |
+
},
|
580 |
+
"250069": {
|
581 |
+
"content": "β<extra_id_30>",
|
582 |
+
"lstrip": false,
|
583 |
+
"normalized": false,
|
584 |
+
"rstrip": false,
|
585 |
+
"single_word": false,
|
586 |
+
"special": false
|
587 |
+
},
|
588 |
+
"250070": {
|
589 |
+
"content": "β<extra_id_29>",
|
590 |
+
"lstrip": false,
|
591 |
+
"normalized": false,
|
592 |
+
"rstrip": false,
|
593 |
+
"single_word": false,
|
594 |
+
"special": false
|
595 |
+
},
|
596 |
+
"250071": {
|
597 |
+
"content": "β<extra_id_28>",
|
598 |
+
"lstrip": false,
|
599 |
+
"normalized": false,
|
600 |
+
"rstrip": false,
|
601 |
+
"single_word": false,
|
602 |
+
"special": false
|
603 |
+
},
|
604 |
+
"250072": {
|
605 |
+
"content": "β<extra_id_27>",
|
606 |
+
"lstrip": false,
|
607 |
+
"normalized": false,
|
608 |
+
"rstrip": false,
|
609 |
+
"single_word": false,
|
610 |
+
"special": false
|
611 |
+
},
|
612 |
+
"250073": {
|
613 |
+
"content": "β<extra_id_26>",
|
614 |
+
"lstrip": false,
|
615 |
+
"normalized": false,
|
616 |
+
"rstrip": false,
|
617 |
+
"single_word": false,
|
618 |
+
"special": false
|
619 |
+
},
|
620 |
+
"250074": {
|
621 |
+
"content": "β<extra_id_25>",
|
622 |
+
"lstrip": false,
|
623 |
+
"normalized": false,
|
624 |
+
"rstrip": false,
|
625 |
+
"single_word": false,
|
626 |
+
"special": false
|
627 |
+
},
|
628 |
+
"250075": {
|
629 |
+
"content": "β<extra_id_24>",
|
630 |
+
"lstrip": false,
|
631 |
+
"normalized": false,
|
632 |
+
"rstrip": false,
|
633 |
+
"single_word": false,
|
634 |
+
"special": false
|
635 |
+
},
|
636 |
+
"250076": {
|
637 |
+
"content": "β<extra_id_23>",
|
638 |
+
"lstrip": false,
|
639 |
+
"normalized": false,
|
640 |
+
"rstrip": false,
|
641 |
+
"single_word": false,
|
642 |
+
"special": false
|
643 |
+
},
|
644 |
+
"250077": {
|
645 |
+
"content": "β<extra_id_22>",
|
646 |
+
"lstrip": false,
|
647 |
+
"normalized": false,
|
648 |
+
"rstrip": false,
|
649 |
+
"single_word": false,
|
650 |
+
"special": false
|
651 |
+
},
|
652 |
+
"250078": {
|
653 |
+
"content": "β<extra_id_21>",
|
654 |
+
"lstrip": false,
|
655 |
+
"normalized": false,
|
656 |
+
"rstrip": false,
|
657 |
+
"single_word": false,
|
658 |
+
"special": false
|
659 |
+
},
|
660 |
+
"250079": {
|
661 |
+
"content": "β<extra_id_20>",
|
662 |
+
"lstrip": false,
|
663 |
+
"normalized": false,
|
664 |
+
"rstrip": false,
|
665 |
+
"single_word": false,
|
666 |
+
"special": false
|
667 |
+
},
|
668 |
+
"250080": {
|
669 |
+
"content": "β<extra_id_19>",
|
670 |
+
"lstrip": false,
|
671 |
+
"normalized": false,
|
672 |
+
"rstrip": false,
|
673 |
+
"single_word": false,
|
674 |
+
"special": false
|
675 |
+
},
|
676 |
+
"250081": {
|
677 |
+
"content": "β<extra_id_18>",
|
678 |
+
"lstrip": false,
|
679 |
+
"normalized": false,
|
680 |
+
"rstrip": false,
|
681 |
+
"single_word": false,
|
682 |
+
"special": false
|
683 |
+
},
|
684 |
+
"250082": {
|
685 |
+
"content": "β<extra_id_17>",
|
686 |
+
"lstrip": false,
|
687 |
+
"normalized": false,
|
688 |
+
"rstrip": false,
|
689 |
+
"single_word": false,
|
690 |
+
"special": false
|
691 |
+
},
|
692 |
+
"250083": {
|
693 |
+
"content": "β<extra_id_16>",
|
694 |
+
"lstrip": false,
|
695 |
+
"normalized": false,
|
696 |
+
"rstrip": false,
|
697 |
+
"single_word": false,
|
698 |
+
"special": false
|
699 |
+
},
|
700 |
+
"250084": {
|
701 |
+
"content": "β<extra_id_15>",
|
702 |
+
"lstrip": false,
|
703 |
+
"normalized": false,
|
704 |
+
"rstrip": false,
|
705 |
+
"single_word": false,
|
706 |
+
"special": false
|
707 |
+
},
|
708 |
+
"250085": {
|
709 |
+
"content": "β<extra_id_14>",
|
710 |
+
"lstrip": false,
|
711 |
+
"normalized": false,
|
712 |
+
"rstrip": false,
|
713 |
+
"single_word": false,
|
714 |
+
"special": false
|
715 |
+
},
|
716 |
+
"250086": {
|
717 |
+
"content": "β<extra_id_13>",
|
718 |
+
"lstrip": false,
|
719 |
+
"normalized": false,
|
720 |
+
"rstrip": false,
|
721 |
+
"single_word": false,
|
722 |
+
"special": false
|
723 |
+
},
|
724 |
+
"250087": {
|
725 |
+
"content": "β<extra_id_12>",
|
726 |
+
"lstrip": false,
|
727 |
+
"normalized": false,
|
728 |
+
"rstrip": false,
|
729 |
+
"single_word": false,
|
730 |
+
"special": false
|
731 |
+
},
|
732 |
+
"250088": {
|
733 |
+
"content": "β<extra_id_11>",
|
734 |
+
"lstrip": false,
|
735 |
+
"normalized": false,
|
736 |
+
"rstrip": false,
|
737 |
+
"single_word": false,
|
738 |
+
"special": false
|
739 |
+
},
|
740 |
+
"250089": {
|
741 |
+
"content": "β<extra_id_10>",
|
742 |
+
"lstrip": false,
|
743 |
+
"normalized": false,
|
744 |
+
"rstrip": false,
|
745 |
+
"single_word": false,
|
746 |
+
"special": false
|
747 |
+
},
|
748 |
+
"250090": {
|
749 |
+
"content": "β<extra_id_9>",
|
750 |
+
"lstrip": false,
|
751 |
+
"normalized": false,
|
752 |
+
"rstrip": false,
|
753 |
+
"single_word": false,
|
754 |
+
"special": false
|
755 |
+
},
|
756 |
+
"250091": {
|
757 |
+
"content": "β<extra_id_8>",
|
758 |
+
"lstrip": false,
|
759 |
+
"normalized": false,
|
760 |
+
"rstrip": false,
|
761 |
+
"single_word": false,
|
762 |
+
"special": false
|
763 |
+
},
|
764 |
+
"250092": {
|
765 |
+
"content": "β<extra_id_7>",
|
766 |
+
"lstrip": false,
|
767 |
+
"normalized": false,
|
768 |
+
"rstrip": false,
|
769 |
+
"single_word": false,
|
770 |
+
"special": false
|
771 |
+
},
|
772 |
+
"250093": {
|
773 |
+
"content": "β<extra_id_6>",
|
774 |
+
"lstrip": false,
|
775 |
+
"normalized": false,
|
776 |
+
"rstrip": false,
|
777 |
+
"single_word": false,
|
778 |
+
"special": false
|
779 |
+
},
|
780 |
+
"250094": {
|
781 |
+
"content": "β<extra_id_5>",
|
782 |
+
"lstrip": false,
|
783 |
+
"normalized": false,
|
784 |
+
"rstrip": false,
|
785 |
+
"single_word": false,
|
786 |
+
"special": false
|
787 |
+
},
|
788 |
+
"250095": {
|
789 |
+
"content": "β<extra_id_4>",
|
790 |
+
"lstrip": false,
|
791 |
+
"normalized": false,
|
792 |
+
"rstrip": false,
|
793 |
+
"single_word": false,
|
794 |
+
"special": false
|
795 |
+
},
|
796 |
+
"250096": {
|
797 |
+
"content": "β<extra_id_3>",
|
798 |
+
"lstrip": false,
|
799 |
+
"normalized": false,
|
800 |
+
"rstrip": false,
|
801 |
+
"single_word": false,
|
802 |
+
"special": false
|
803 |
+
},
|
804 |
+
"250097": {
|
805 |
+
"content": "β<extra_id_2>",
|
806 |
+
"lstrip": false,
|
807 |
+
"normalized": false,
|
808 |
+
"rstrip": false,
|
809 |
+
"single_word": false,
|
810 |
+
"special": false
|
811 |
+
},
|
812 |
+
"250098": {
|
813 |
+
"content": "β<extra_id_1>",
|
814 |
+
"lstrip": false,
|
815 |
+
"normalized": false,
|
816 |
+
"rstrip": false,
|
817 |
+
"single_word": false,
|
818 |
+
"special": false
|
819 |
+
},
|
820 |
+
"250099": {
|
821 |
+
"content": "β<extra_id_0>",
|
822 |
+
"lstrip": false,
|
823 |
+
"normalized": false,
|
824 |
+
"rstrip": false,
|
825 |
+
"single_word": false,
|
826 |
+
"special": false
|
827 |
+
}
|
828 |
+
},
|
829 |
+
"additional_special_tokens": [],
|
830 |
+
"clean_up_tokenization_spaces": false,
|
831 |
+
"eos_token": "</s>",
|
832 |
+
"extra_ids": 0,
|
833 |
+
"extra_special_tokens": {},
|
834 |
+
"legacy": false,
|
835 |
+
"model_max_length": 1000000000000000019884624838656,
|
836 |
+
"pad_token": "<pad>",
|
837 |
+
"sp_model_kwargs": {},
|
838 |
+
"tokenizer_class": "T5Tokenizer",
|
839 |
+
"unk_token": "<unk>"
|
840 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a7cca073b14378a6f53f6b8591e4dbcf494f163f182371414404f8ab350cb5e
|
3 |
+
size 5496
|