Model save
Browse files- .gitattributes +1 -0
- README.md +302 -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
- runs/Mar11_12-01-09_1412920010036/events.out.tfevents.1741719010.1412920010036.243166.5 +3 -0
- runs/Mar16_11-09-16_1412920010036/events.out.tfevents.1742137758.1412920010036.2788175.0 +3 -0
- runs/Mar16_11-09-16_1412920010036/events.out.tfevents.1742153024.1412920010036.2788175.1 +3 -0
- runs/Mar16_15-24-22_1412920010036/events.out.tfevents.1742153062.1412920010036.2788175.2 +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 +1,302 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: mt5-lora-hf
|
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 |
+
# mt5-lora-hf
|
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: 4.8417
|
22 |
+
- Rouge1: 4.6911
|
23 |
+
- Rouge2: 0.0143
|
24 |
+
- Rougel: 4.5972
|
25 |
+
- Rougelsum: 4.5916
|
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: 6
|
51 |
+
|
52 |
+
### Training results
|
53 |
+
|
54 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|
55 |
+
|:-------------:|:------:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
|
56 |
+
| 26.7014 | 0.0251 | 5 | 17.9690 | 0.4959 | 0.0229 | 0.4821 | 0.4821 |
|
57 |
+
| 22.8828 | 0.0503 | 10 | 17.8948 | 0.4330 | 0.0229 | 0.4394 | 0.4427 |
|
58 |
+
| 25.3054 | 0.0754 | 15 | 17.7656 | 0.4335 | 0.0229 | 0.4399 | 0.4431 |
|
59 |
+
| 24.2626 | 0.1005 | 20 | 17.6523 | 0.4614 | 0.0229 | 0.4498 | 0.4541 |
|
60 |
+
| 26.9164 | 0.1256 | 25 | 17.4744 | 0.4291 | 0.0229 | 0.4298 | 0.4340 |
|
61 |
+
| 26.7442 | 0.1508 | 30 | 17.3540 | 0.4528 | 0.0229 | 0.4507 | 0.4560 |
|
62 |
+
| 22.8846 | 0.1759 | 35 | 17.1714 | 0.4395 | 0.0229 | 0.4407 | 0.4423 |
|
63 |
+
| 23.0382 | 0.2010 | 40 | 17.0225 | 0.4176 | 0.0229 | 0.4200 | 0.4272 |
|
64 |
+
| 24.5139 | 0.2261 | 45 | 16.9602 | 0.3881 | 0.0229 | 0.3958 | 0.4018 |
|
65 |
+
| 23.5225 | 0.2513 | 50 | 16.8832 | 0.4163 | 0.0229 | 0.4241 | 0.4257 |
|
66 |
+
| 24.7283 | 0.2764 | 55 | 16.7457 | 0.4156 | 0.0229 | 0.4235 | 0.4254 |
|
67 |
+
| 24.5206 | 0.3015 | 60 | 16.4804 | 0.4285 | 0.0229 | 0.4337 | 0.4356 |
|
68 |
+
| 22.8146 | 0.3266 | 65 | 16.2983 | 0.4012 | 0.0229 | 0.4064 | 0.4090 |
|
69 |
+
| 21.381 | 0.3518 | 70 | 16.0329 | 0.3890 | 0.0229 | 0.3922 | 0.3988 |
|
70 |
+
| 23.4543 | 0.3769 | 75 | 15.8419 | 0.3890 | 0.0229 | 0.3922 | 0.3988 |
|
71 |
+
| 20.3948 | 0.4020 | 80 | 15.6935 | 0.4034 | 0.0229 | 0.4058 | 0.4152 |
|
72 |
+
| 23.315 | 0.4271 | 85 | 15.5347 | 0.3758 | 0.0229 | 0.3724 | 0.3848 |
|
73 |
+
| 20.4828 | 0.4523 | 90 | 15.4258 | 0.3758 | 0.0229 | 0.3724 | 0.3848 |
|
74 |
+
| 22.6177 | 0.4774 | 95 | 15.2736 | 0.3821 | 0.0229 | 0.3830 | 0.3916 |
|
75 |
+
| 22.7118 | 0.5025 | 100 | 15.0719 | 0.3408 | 0.0229 | 0.3414 | 0.3506 |
|
76 |
+
| 24.145 | 0.5276 | 105 | 14.8205 | 0.3314 | 0.0229 | 0.3350 | 0.3426 |
|
77 |
+
| 21.6796 | 0.5528 | 110 | 14.5375 | 0.3310 | 0.0229 | 0.3348 | 0.3413 |
|
78 |
+
| 21.0313 | 0.5779 | 115 | 14.2323 | 0.3313 | 0.0229 | 0.3349 | 0.3425 |
|
79 |
+
| 20.1509 | 0.6030 | 120 | 13.9040 | 0.3306 | 0.0229 | 0.3340 | 0.3412 |
|
80 |
+
| 20.8036 | 0.6281 | 125 | 13.5365 | 0.3903 | 0.0493 | 0.3953 | 0.3977 |
|
81 |
+
| 18.9977 | 0.6533 | 130 | 13.2251 | 0.3972 | 0.0493 | 0.3996 | 0.4052 |
|
82 |
+
| 21.1749 | 0.6784 | 135 | 13.0306 | 0.3848 | 0.0493 | 0.3826 | 0.3906 |
|
83 |
+
| 18.1424 | 0.7035 | 140 | 12.7417 | 0.3568 | 0.0493 | 0.3589 | 0.3579 |
|
84 |
+
| 17.3758 | 0.7286 | 145 | 12.5348 | 0.3567 | 0.0493 | 0.3590 | 0.3577 |
|
85 |
+
| 21.9186 | 0.7538 | 150 | 12.2754 | 0.3735 | 0.0493 | 0.3773 | 0.3764 |
|
86 |
+
| 18.0612 | 0.7789 | 155 | 11.9966 | 0.3858 | 0.0493 | 0.3916 | 0.3914 |
|
87 |
+
| 16.8307 | 0.8040 | 160 | 11.8330 | 0.3154 | 0.0493 | 0.3172 | 0.3202 |
|
88 |
+
| 17.5778 | 0.8291 | 165 | 11.6714 | 0.2914 | 0.0493 | 0.2913 | 0.2967 |
|
89 |
+
| 18.1477 | 0.8543 | 170 | 11.4841 | 0.2913 | 0.0493 | 0.2913 | 0.2964 |
|
90 |
+
| 15.9704 | 0.8794 | 175 | 11.3850 | 0.3049 | 0.0493 | 0.3017 | 0.3097 |
|
91 |
+
| 17.1034 | 0.9045 | 180 | 11.2041 | 0.2991 | 0.0619 | 0.2978 | 0.3027 |
|
92 |
+
| 19.7897 | 0.9296 | 185 | 11.0869 | 0.3345 | 0.0662 | 0.3265 | 0.3309 |
|
93 |
+
| 16.608 | 0.9548 | 190 | 10.9445 | 0.3345 | 0.0662 | 0.3265 | 0.3309 |
|
94 |
+
| 17.1781 | 0.9799 | 195 | 10.8493 | 0.3345 | 0.0662 | 0.3264 | 0.3308 |
|
95 |
+
| 14.5506 | 1.0050 | 200 | 10.7443 | 0.3557 | 0.0662 | 0.3475 | 0.3524 |
|
96 |
+
| 15.1794 | 1.0302 | 205 | 10.6058 | 0.3699 | 0.0662 | 0.3608 | 0.3684 |
|
97 |
+
| 14.1433 | 1.0553 | 210 | 10.4693 | 0.3699 | 0.0662 | 0.3608 | 0.3684 |
|
98 |
+
| 15.3501 | 1.0804 | 215 | 10.2548 | 0.3697 | 0.0662 | 0.3600 | 0.3678 |
|
99 |
+
| 14.2343 | 1.1055 | 220 | 10.0423 | 0.3992 | 0.0662 | 0.3840 | 0.3902 |
|
100 |
+
| 13.6561 | 1.1307 | 225 | 9.8362 | 0.3637 | 0.0594 | 0.3538 | 0.3593 |
|
101 |
+
| 14.1522 | 1.1558 | 230 | 9.6526 | 0.4294 | 0.0662 | 0.4139 | 0.4260 |
|
102 |
+
| 12.2793 | 1.1809 | 235 | 9.4753 | 0.4294 | 0.0662 | 0.4139 | 0.4260 |
|
103 |
+
| 12.999 | 1.2060 | 240 | 9.3080 | 0.4818 | 0.0662 | 0.4527 | 0.4640 |
|
104 |
+
| 12.6114 | 1.2312 | 245 | 9.1514 | 0.5574 | 0.0843 | 0.5411 | 0.5470 |
|
105 |
+
| 12.6979 | 1.2563 | 250 | 9.0131 | 0.5651 | 0.0843 | 0.5186 | 0.5269 |
|
106 |
+
| 11.6085 | 1.2814 | 255 | 8.8960 | 0.5875 | 0.0761 | 0.5317 | 0.5412 |
|
107 |
+
| 11.9352 | 1.3065 | 260 | 8.7639 | 0.6295 | 0.1163 | 0.5637 | 0.5745 |
|
108 |
+
| 12.1973 | 1.3317 | 265 | 8.6219 | 0.6309 | 0.1163 | 0.5660 | 0.5754 |
|
109 |
+
| 11.8386 | 1.3568 | 270 | 8.5034 | 0.6541 | 0.1163 | 0.5877 | 0.5997 |
|
110 |
+
| 11.1427 | 1.3819 | 275 | 8.3913 | 0.7308 | 0.1302 | 0.6666 | 0.6784 |
|
111 |
+
| 11.6074 | 1.4070 | 280 | 8.2927 | 0.7541 | 0.1298 | 0.6892 | 0.7015 |
|
112 |
+
| 11.879 | 1.4322 | 285 | 8.1927 | 0.7048 | 0.0662 | 0.6537 | 0.6663 |
|
113 |
+
| 12.5362 | 1.4573 | 290 | 8.0887 | 0.7321 | 0.0662 | 0.6832 | 0.6939 |
|
114 |
+
| 11.1034 | 1.4824 | 295 | 7.9519 | 0.7805 | 0.0742 | 0.7167 | 0.7279 |
|
115 |
+
| 10.742 | 1.5075 | 300 | 7.7980 | 0.9069 | 0.1048 | 0.8357 | 0.8377 |
|
116 |
+
| 10.3591 | 1.5327 | 305 | 7.6581 | 1.1354 | 0.2100 | 0.9999 | 1.0172 |
|
117 |
+
| 11.0729 | 1.5578 | 310 | 7.5439 | 1.2665 | 0.2698 | 1.1212 | 1.1410 |
|
118 |
+
| 11.0979 | 1.5829 | 315 | 7.4250 | 1.2760 | 0.2269 | 1.1590 | 1.1749 |
|
119 |
+
| 10.7504 | 1.6080 | 320 | 7.3066 | 1.0842 | 0.1685 | 1.0249 | 1.0238 |
|
120 |
+
| 11.2598 | 1.6332 | 325 | 7.2042 | 1.1594 | 0.1687 | 1.0796 | 1.0846 |
|
121 |
+
| 10.4366 | 1.6583 | 330 | 7.1160 | 1.1594 | 0.1687 | 1.0796 | 1.0846 |
|
122 |
+
| 10.0824 | 1.6834 | 335 | 7.0343 | 1.1730 | 0.1684 | 1.0898 | 1.0982 |
|
123 |
+
| 9.9589 | 1.7085 | 340 | 6.9468 | 1.1306 | 0.1686 | 1.0485 | 1.0545 |
|
124 |
+
| 10.3309 | 1.7337 | 345 | 6.8646 | 1.1736 | 0.1824 | 1.0809 | 1.0876 |
|
125 |
+
| 9.6166 | 1.7588 | 350 | 6.7984 | 1.1165 | 0.1690 | 1.0478 | 1.0482 |
|
126 |
+
| 9.3742 | 1.7839 | 355 | 6.7329 | 1.2620 | 0.2014 | 1.1354 | 1.1476 |
|
127 |
+
| 9.853 | 1.8090 | 360 | 6.6669 | 1.2627 | 0.2014 | 1.1455 | 1.1582 |
|
128 |
+
| 10.1404 | 1.8342 | 365 | 6.6068 | 1.3100 | 0.2156 | 1.2083 | 1.2155 |
|
129 |
+
| 9.3509 | 1.8593 | 370 | 6.5692 | 1.2194 | 0.2020 | 1.1225 | 1.1152 |
|
130 |
+
| 8.8801 | 1.8844 | 375 | 6.5346 | 1.1335 | 0.1431 | 1.0131 | 1.0107 |
|
131 |
+
| 9.3656 | 1.9095 | 380 | 6.5026 | 1.1119 | 0.1291 | 1.0170 | 1.0141 |
|
132 |
+
| 9.0491 | 1.9347 | 385 | 6.4711 | 1.2375 | 0.1293 | 1.1102 | 1.1153 |
|
133 |
+
| 9.6425 | 1.9598 | 390 | 6.4447 | 1.2243 | 0.1409 | 1.1258 | 1.1284 |
|
134 |
+
| 8.8074 | 1.9849 | 395 | 6.4136 | 1.3684 | 0.2034 | 1.2323 | 1.2465 |
|
135 |
+
| 8.6168 | 2.0101 | 400 | 6.3833 | 1.4884 | 0.1787 | 1.3723 | 1.3762 |
|
136 |
+
| 8.9557 | 2.0352 | 405 | 6.3572 | 1.4520 | 0.1638 | 1.2990 | 1.2947 |
|
137 |
+
| 9.101 | 2.0603 | 410 | 6.3413 | 1.6343 | 0.1641 | 1.4365 | 1.4336 |
|
138 |
+
| 8.438 | 2.0854 | 415 | 6.3290 | 1.6232 | 0.1505 | 1.4573 | 1.4618 |
|
139 |
+
| 8.6262 | 2.1106 | 420 | 6.3048 | 1.6377 | 0.1245 | 1.5029 | 1.5195 |
|
140 |
+
| 8.9535 | 2.1357 | 425 | 6.2767 | 1.6318 | 0.1749 | 1.5081 | 1.5353 |
|
141 |
+
| 8.3392 | 2.1608 | 430 | 6.2523 | 1.6524 | 0.1743 | 1.5073 | 1.5367 |
|
142 |
+
| 8.6226 | 2.1859 | 435 | 6.2420 | 1.6597 | 0.1743 | 1.5340 | 1.5374 |
|
143 |
+
| 8.5399 | 2.2111 | 440 | 6.2366 | 1.6552 | 0.1743 | 1.5178 | 1.5262 |
|
144 |
+
| 8.4814 | 2.2362 | 445 | 6.2269 | 1.6997 | 0.1599 | 1.5507 | 1.5492 |
|
145 |
+
| 8.402 | 2.2613 | 450 | 6.2206 | 1.7743 | 0.1729 | 1.6229 | 1.6207 |
|
146 |
+
| 8.1715 | 2.2864 | 455 | 6.2157 | 1.7005 | 0.1731 | 1.5580 | 1.5519 |
|
147 |
+
| 8.3982 | 2.3116 | 460 | 6.2149 | 1.7912 | 0.1731 | 1.6301 | 1.6303 |
|
148 |
+
| 8.2935 | 2.3367 | 465 | 6.2051 | 1.8151 | 0.1813 | 1.6772 | 1.6708 |
|
149 |
+
| 8.1023 | 2.3618 | 470 | 6.1992 | 1.7187 | 0.1813 | 1.6023 | 1.5988 |
|
150 |
+
| 8.4083 | 2.3869 | 475 | 6.1925 | 1.7018 | 0.1816 | 1.5594 | 1.5567 |
|
151 |
+
| 8.3179 | 2.4121 | 480 | 6.1839 | 1.7161 | 0.1941 | 1.5709 | 1.5685 |
|
152 |
+
| 7.8477 | 2.4372 | 485 | 6.1699 | 1.6932 | 0.1816 | 1.5782 | 1.5846 |
|
153 |
+
| 7.9573 | 2.4623 | 490 | 6.1573 | 1.7737 | 0.1941 | 1.6399 | 1.6485 |
|
154 |
+
| 8.3412 | 2.4874 | 495 | 6.1501 | 1.6200 | 0.1553 | 1.5142 | 1.5160 |
|
155 |
+
| 8.2275 | 2.5126 | 500 | 6.1420 | 1.5973 | 0.1553 | 1.4930 | 1.4994 |
|
156 |
+
| 7.7802 | 2.5377 | 505 | 6.1371 | 1.5843 | 0.1553 | 1.4519 | 1.4570 |
|
157 |
+
| 8.2208 | 2.5628 | 510 | 6.1301 | 1.5734 | 0.1552 | 1.4672 | 1.4746 |
|
158 |
+
| 7.988 | 2.5879 | 515 | 6.1250 | 1.6141 | 0.1552 | 1.5196 | 1.5243 |
|
159 |
+
| 8.0406 | 2.6131 | 520 | 6.1216 | 1.5612 | 0.1317 | 1.4781 | 1.4902 |
|
160 |
+
| 7.6537 | 2.6382 | 525 | 6.1177 | 1.5042 | 0.1174 | 1.4341 | 1.4512 |
|
161 |
+
| 7.7706 | 2.6633 | 530 | 6.1124 | 1.5480 | 0.1110 | 1.4766 | 1.4870 |
|
162 |
+
| 7.7587 | 2.6884 | 535 | 6.1041 | 1.6054 | 0.0975 | 1.5301 | 1.5384 |
|
163 |
+
| 7.5912 | 2.7136 | 540 | 6.0947 | 1.6413 | 0.0975 | 1.5722 | 1.5747 |
|
164 |
+
| 7.6195 | 2.7387 | 545 | 6.0872 | 1.6897 | 0.0975 | 1.6322 | 1.6231 |
|
165 |
+
| 7.9719 | 2.7638 | 550 | 6.0840 | 1.6390 | 0.0980 | 1.5458 | 1.5456 |
|
166 |
+
| 7.5861 | 2.7889 | 555 | 6.0818 | 1.7055 | 0.0984 | 1.6106 | 1.6002 |
|
167 |
+
| 7.3751 | 2.8141 | 560 | 6.0693 | 1.7887 | 0.0984 | 1.7099 | 1.6969 |
|
168 |
+
| 7.4287 | 2.8392 | 565 | 6.0521 | 1.9438 | 0.0984 | 1.8707 | 1.8458 |
|
169 |
+
| 7.8715 | 2.8643 | 570 | 6.0418 | 1.9864 | 0.0742 | 1.9169 | 1.9069 |
|
170 |
+
| 7.5668 | 2.8894 | 575 | 6.0371 | 2.0494 | 0.0742 | 1.9751 | 1.9491 |
|
171 |
+
| 7.5644 | 2.9146 | 580 | 6.0284 | 2.0795 | 0.0742 | 2.0033 | 1.9955 |
|
172 |
+
| 7.5837 | 2.9397 | 585 | 6.0187 | 2.0435 | 0.0593 | 1.9903 | 1.9873 |
|
173 |
+
| 7.8794 | 2.9648 | 590 | 6.0076 | 2.1343 | 0.0593 | 2.0976 | 2.0879 |
|
174 |
+
| 7.4229 | 2.9899 | 595 | 5.9940 | 2.1421 | 0.0593 | 2.1090 | 2.0987 |
|
175 |
+
| 7.3116 | 3.0151 | 600 | 5.9697 | 2.2915 | 0.0593 | 2.2485 | 2.2434 |
|
176 |
+
| 7.237 | 3.0402 | 605 | 5.9432 | 2.2761 | 0.0593 | 2.2335 | 2.2297 |
|
177 |
+
| 7.5251 | 3.0653 | 610 | 5.9066 | 2.3241 | 0.0593 | 2.2857 | 2.2795 |
|
178 |
+
| 7.5311 | 3.0905 | 615 | 5.8749 | 2.3968 | 0.0593 | 2.3618 | 2.3526 |
|
179 |
+
| 7.3948 | 3.1156 | 620 | 5.8503 | 2.4292 | 0.0722 | 2.3934 | 2.3859 |
|
180 |
+
| 7.4102 | 3.1407 | 625 | 5.8441 | 2.5045 | 0.0722 | 2.4562 | 2.4443 |
|
181 |
+
| 7.3152 | 3.1658 | 630 | 5.8373 | 2.5838 | 0.0722 | 2.5309 | 2.5271 |
|
182 |
+
| 7.2793 | 3.1910 | 635 | 5.8287 | 2.5969 | 0.0722 | 2.5425 | 2.5405 |
|
183 |
+
| 7.2854 | 3.2161 | 640 | 5.8204 | 2.6641 | 0.0722 | 2.6240 | 2.6098 |
|
184 |
+
| 7.2151 | 3.2412 | 645 | 5.8081 | 2.7296 | 0.0722 | 2.6823 | 2.6686 |
|
185 |
+
| 7.1616 | 3.2663 | 650 | 5.7995 | 2.8340 | 0.0721 | 2.7816 | 2.7651 |
|
186 |
+
| 7.2671 | 3.2915 | 655 | 5.7911 | 2.9706 | 0.0721 | 2.9038 | 2.8953 |
|
187 |
+
| 7.3364 | 3.3166 | 660 | 5.7806 | 3.0656 | 0.0721 | 2.9978 | 2.9924 |
|
188 |
+
| 7.345 | 3.3417 | 665 | 5.7695 | 3.1378 | 0.0721 | 3.0744 | 3.0664 |
|
189 |
+
| 7.3118 | 3.3668 | 670 | 5.7532 | 3.1238 | 0.0722 | 3.0706 | 3.0618 |
|
190 |
+
| 7.4469 | 3.3920 | 675 | 5.7453 | 3.1653 | 0.0722 | 3.1293 | 3.1149 |
|
191 |
+
| 7.2567 | 3.4171 | 680 | 5.7376 | 3.1821 | 0.0722 | 3.1314 | 3.1141 |
|
192 |
+
| 7.1828 | 3.4422 | 685 | 5.7268 | 3.2855 | 0.0848 | 3.2291 | 3.1953 |
|
193 |
+
| 7.3317 | 3.4673 | 690 | 5.7070 | 3.3113 | 0.0848 | 3.2480 | 3.2158 |
|
194 |
+
| 7.1762 | 3.4925 | 695 | 5.6925 | 3.3213 | 0.0848 | 3.2595 | 3.2338 |
|
195 |
+
| 7.0286 | 3.5176 | 700 | 5.6794 | 3.3345 | 0.0848 | 3.2713 | 3.2443 |
|
196 |
+
| 7.1958 | 3.5427 | 705 | 5.6638 | 3.3834 | 0.0848 | 3.3169 | 3.2835 |
|
197 |
+
| 7.2112 | 3.5678 | 710 | 5.6573 | 3.4198 | 0.0744 | 3.3372 | 3.3030 |
|
198 |
+
| 7.0299 | 3.5930 | 715 | 5.6404 | 3.5031 | 0.0744 | 3.4199 | 3.3898 |
|
199 |
+
| 7.4005 | 3.6181 | 720 | 5.6231 | 3.5545 | 0.0744 | 3.4659 | 3.4403 |
|
200 |
+
| 7.2407 | 3.6432 | 725 | 5.6160 | 3.6875 | 0.0744 | 3.6277 | 3.6033 |
|
201 |
+
| 7.1189 | 3.6683 | 730 | 5.6075 | 3.7917 | 0.0744 | 3.7315 | 3.7144 |
|
202 |
+
| 7.0044 | 3.6935 | 735 | 5.5928 | 3.9431 | 0.0744 | 3.8972 | 3.8828 |
|
203 |
+
| 7.0864 | 3.7186 | 740 | 5.5823 | 3.9375 | 0.0593 | 3.8940 | 3.8878 |
|
204 |
+
| 7.3772 | 3.7437 | 745 | 5.5713 | 3.9630 | 0.0593 | 3.9203 | 3.9155 |
|
205 |
+
| 7.0098 | 3.7688 | 750 | 5.5583 | 4.1243 | 0.0744 | 4.0620 | 4.0602 |
|
206 |
+
| 6.8234 | 3.7940 | 755 | 5.5445 | 4.1046 | 0.0593 | 4.0478 | 4.0421 |
|
207 |
+
| 7.1442 | 3.8191 | 760 | 5.5222 | 4.0768 | 0.0593 | 4.0170 | 4.0034 |
|
208 |
+
| 6.9834 | 3.8442 | 765 | 5.5042 | 4.0013 | 0.0 | 3.9340 | 3.9286 |
|
209 |
+
| 7.0864 | 3.8693 | 770 | 5.4785 | 4.0012 | 0.0 | 3.9335 | 3.9288 |
|
210 |
+
| 6.863 | 3.8945 | 775 | 5.4519 | 4.0494 | 0.0 | 3.9829 | 3.9836 |
|
211 |
+
| 6.8511 | 3.9196 | 780 | 5.4235 | 4.1077 | 0.0 | 4.0382 | 4.0420 |
|
212 |
+
| 6.8788 | 3.9447 | 785 | 5.3975 | 4.2017 | 0.0 | 4.1333 | 4.1334 |
|
213 |
+
| 6.6429 | 3.9698 | 790 | 5.3782 | 4.2539 | 0.0 | 4.2007 | 4.1935 |
|
214 |
+
| 6.8546 | 3.9950 | 795 | 5.3626 | 4.3106 | 0.0 | 4.2576 | 4.2563 |
|
215 |
+
| 6.8145 | 4.0201 | 800 | 5.3410 | 4.3560 | 0.0 | 4.3242 | 4.3170 |
|
216 |
+
| 6.7826 | 4.0452 | 805 | 5.3263 | 4.3417 | 0.0 | 4.3236 | 4.3164 |
|
217 |
+
| 6.9502 | 4.0704 | 810 | 5.3144 | 4.3921 | 0.0 | 4.3602 | 4.3603 |
|
218 |
+
| 6.6682 | 4.0955 | 815 | 5.3021 | 4.3912 | 0.0 | 4.3575 | 4.3582 |
|
219 |
+
| 6.7195 | 4.1206 | 820 | 5.2895 | 4.3898 | 0.0 | 4.3564 | 4.3573 |
|
220 |
+
| 6.8389 | 4.1457 | 825 | 5.2787 | 4.3896 | 0.0 | 4.3561 | 4.3573 |
|
221 |
+
| 6.9199 | 4.1709 | 830 | 5.2683 | 4.4240 | 0.0 | 4.3939 | 4.3847 |
|
222 |
+
| 6.8859 | 4.1960 | 835 | 5.2588 | 4.4237 | 0.0 | 4.3934 | 4.3838 |
|
223 |
+
| 6.7521 | 4.2211 | 840 | 5.2438 | 4.5064 | 0.0 | 4.4407 | 4.4426 |
|
224 |
+
| 6.7168 | 4.2462 | 845 | 5.2284 | 4.5129 | 0.0 | 4.4405 | 4.4425 |
|
225 |
+
| 7.2573 | 4.2714 | 850 | 5.2204 | 4.4857 | 0.0 | 4.4131 | 4.4064 |
|
226 |
+
| 6.5104 | 4.2965 | 855 | 5.2126 | 4.5147 | 0.0 | 4.4269 | 4.4225 |
|
227 |
+
| 6.6178 | 4.3216 | 860 | 5.2034 | 4.5454 | 0.0 | 4.4468 | 4.4405 |
|
228 |
+
| 6.5719 | 4.3467 | 865 | 5.1942 | 4.5156 | 0.0 | 4.4389 | 4.4297 |
|
229 |
+
| 6.7698 | 4.3719 | 870 | 5.1824 | 4.5155 | 0.0 | 4.4383 | 4.4294 |
|
230 |
+
| 6.5936 | 4.3970 | 875 | 5.1708 | 4.5155 | 0.0 | 4.4383 | 4.4294 |
|
231 |
+
| 6.6705 | 4.4221 | 880 | 5.1564 | 4.5968 | 0.0 | 4.4961 | 4.5006 |
|
232 |
+
| 6.8366 | 4.4472 | 885 | 5.1465 | 4.5968 | 0.0 | 4.4961 | 4.5006 |
|
233 |
+
| 6.8101 | 4.4724 | 890 | 5.1397 | 4.5968 | 0.0 | 4.4960 | 4.5006 |
|
234 |
+
| 6.6961 | 4.4975 | 895 | 5.1324 | 4.5962 | 0.0 | 4.4958 | 4.5003 |
|
235 |
+
| 6.8763 | 4.5226 | 900 | 5.1243 | 4.6352 | 0.0 | 4.5400 | 4.5474 |
|
236 |
+
| 6.7891 | 4.5477 | 905 | 5.1166 | 4.6352 | 0.0 | 4.5400 | 4.5474 |
|
237 |
+
| 6.6563 | 4.5729 | 910 | 5.1063 | 4.6352 | 0.0 | 4.5400 | 4.5474 |
|
238 |
+
| 6.7201 | 4.5980 | 915 | 5.0973 | 4.6352 | 0.0 | 4.5395 | 4.5464 |
|
239 |
+
| 6.6108 | 4.6231 | 920 | 5.0880 | 4.6472 | 0.0 | 4.5387 | 4.5463 |
|
240 |
+
| 6.5714 | 4.6482 | 925 | 5.0786 | 4.6379 | 0.0 | 4.5388 | 4.5456 |
|
241 |
+
| 6.5445 | 4.6734 | 930 | 5.0695 | 4.6765 | 0.0 | 4.5586 | 4.5678 |
|
242 |
+
| 6.6799 | 4.6985 | 935 | 5.0614 | 4.6765 | 0.0 | 4.5586 | 4.5678 |
|
243 |
+
| 6.568 | 4.7236 | 940 | 5.0531 | 4.6765 | 0.0 | 4.5579 | 4.5675 |
|
244 |
+
| 6.2814 | 4.7487 | 945 | 5.0416 | 4.6892 | 0.0 | 4.5728 | 4.5799 |
|
245 |
+
| 6.8206 | 4.7739 | 950 | 5.0313 | 4.6892 | 0.0 | 4.5728 | 4.5799 |
|
246 |
+
| 6.5936 | 4.7990 | 955 | 5.0224 | 4.6957 | 0.0 | 4.5869 | 4.5870 |
|
247 |
+
| 6.662 | 4.8241 | 960 | 5.0125 | 4.6957 | 0.0 | 4.5869 | 4.5870 |
|
248 |
+
| 6.6761 | 4.8492 | 965 | 5.0031 | 4.6957 | 0.0 | 4.5869 | 4.5870 |
|
249 |
+
| 6.8252 | 4.8744 | 970 | 4.9960 | 4.6957 | 0.0 | 4.5868 | 4.5869 |
|
250 |
+
| 6.4136 | 4.8995 | 975 | 4.9888 | 4.6957 | 0.0 | 4.5868 | 4.5869 |
|
251 |
+
| 6.6854 | 4.9246 | 980 | 4.9813 | 4.6957 | 0.0 | 4.5868 | 4.5869 |
|
252 |
+
| 6.3622 | 4.9497 | 985 | 4.9766 | 4.6957 | 0.0 | 4.5868 | 4.5869 |
|
253 |
+
| 6.6554 | 4.9749 | 990 | 4.9696 | 4.6960 | 0.0 | 4.5868 | 4.5870 |
|
254 |
+
| 6.4508 | 5.0 | 995 | 4.9637 | 4.7116 | 0.0 | 4.6024 | 4.6028 |
|
255 |
+
| 6.701 | 5.0251 | 1000 | 4.9589 | 4.7116 | 0.0 | 4.6024 | 4.6028 |
|
256 |
+
| 6.2751 | 5.0503 | 1005 | 4.9519 | 4.7116 | 0.0 | 4.6024 | 4.6029 |
|
257 |
+
| 6.5376 | 5.0754 | 1010 | 4.9458 | 4.7116 | 0.0 | 4.6024 | 4.6029 |
|
258 |
+
| 6.4412 | 5.1005 | 1015 | 4.9417 | 4.7115 | 0.0 | 4.6020 | 4.6028 |
|
259 |
+
| 6.5644 | 5.1256 | 1020 | 4.9374 | 4.6979 | 0.0 | 4.6030 | 4.6028 |
|
260 |
+
| 6.1549 | 5.1508 | 1025 | 4.9295 | 4.6909 | 0.0 | 4.5909 | 4.5974 |
|
261 |
+
| 6.4149 | 5.1759 | 1030 | 4.9197 | 4.6675 | 0.0 | 4.5708 | 4.5716 |
|
262 |
+
| 6.5379 | 5.2010 | 1035 | 4.9123 | 4.6675 | 0.0 | 4.5585 | 4.5552 |
|
263 |
+
| 6.3613 | 5.2261 | 1040 | 4.9056 | 4.6791 | 0.0 | 4.5692 | 4.5656 |
|
264 |
+
| 6.5305 | 5.2513 | 1045 | 4.9001 | 4.6791 | 0.0 | 4.5692 | 4.5656 |
|
265 |
+
| 6.5593 | 5.2764 | 1050 | 4.8975 | 4.6661 | 0.0143 | 4.5695 | 4.5663 |
|
266 |
+
| 6.529 | 5.3015 | 1055 | 4.8906 | 4.6550 | 0.0143 | 4.5524 | 4.5508 |
|
267 |
+
| 6.4264 | 5.3266 | 1060 | 4.8837 | 4.6550 | 0.0143 | 4.5524 | 4.5508 |
|
268 |
+
| 6.679 | 5.3518 | 1065 | 4.8797 | 4.6444 | 0.0143 | 4.5417 | 4.5448 |
|
269 |
+
| 6.4163 | 5.3769 | 1070 | 4.8762 | 4.6444 | 0.0143 | 4.5417 | 4.5448 |
|
270 |
+
| 6.5349 | 5.4020 | 1075 | 4.8723 | 4.6444 | 0.0143 | 4.5417 | 4.5448 |
|
271 |
+
| 6.469 | 5.4271 | 1080 | 4.8693 | 4.6444 | 0.0143 | 4.5417 | 4.5448 |
|
272 |
+
| 6.3743 | 5.4523 | 1085 | 4.8668 | 4.6444 | 0.0143 | 4.5417 | 4.5448 |
|
273 |
+
| 6.3293 | 5.4774 | 1090 | 4.8648 | 4.6442 | 0.0143 | 4.5415 | 4.5447 |
|
274 |
+
| 6.3905 | 5.5025 | 1095 | 4.8615 | 4.6442 | 0.0143 | 4.5415 | 4.5447 |
|
275 |
+
| 6.6543 | 5.5276 | 1100 | 4.8589 | 4.6442 | 0.0143 | 4.5415 | 4.5447 |
|
276 |
+
| 6.2526 | 5.5528 | 1105 | 4.8557 | 4.6442 | 0.0143 | 4.5415 | 4.5447 |
|
277 |
+
| 6.5861 | 5.5779 | 1110 | 4.8521 | 4.6586 | 0.0143 | 4.5602 | 4.5559 |
|
278 |
+
| 6.6042 | 5.6030 | 1115 | 4.8498 | 4.6586 | 0.0143 | 4.5602 | 4.5559 |
|
279 |
+
| 6.5273 | 5.6281 | 1120 | 4.8485 | 4.6586 | 0.0143 | 4.5602 | 4.5559 |
|
280 |
+
| 6.3963 | 5.6533 | 1125 | 4.8477 | 4.6586 | 0.0143 | 4.5602 | 4.5559 |
|
281 |
+
| 6.3541 | 5.6784 | 1130 | 4.8468 | 4.6586 | 0.0143 | 4.5602 | 4.5559 |
|
282 |
+
| 6.2128 | 5.7035 | 1135 | 4.8460 | 4.6586 | 0.0143 | 4.5602 | 4.5559 |
|
283 |
+
| 6.6066 | 5.7286 | 1140 | 4.8454 | 4.6586 | 0.0143 | 4.5602 | 4.5559 |
|
284 |
+
| 6.366 | 5.7538 | 1145 | 4.8448 | 4.6590 | 0.0143 | 4.5612 | 4.5562 |
|
285 |
+
| 6.4843 | 5.7789 | 1150 | 4.8440 | 4.6590 | 0.0143 | 4.5612 | 4.5562 |
|
286 |
+
| 6.8107 | 5.8040 | 1155 | 4.8434 | 4.6590 | 0.0143 | 4.5612 | 4.5562 |
|
287 |
+
| 6.2873 | 5.8291 | 1160 | 4.8429 | 4.6590 | 0.0143 | 4.5612 | 4.5562 |
|
288 |
+
| 6.5391 | 5.8543 | 1165 | 4.8426 | 4.6911 | 0.0143 | 4.5972 | 4.5916 |
|
289 |
+
| 6.7077 | 5.8794 | 1170 | 4.8425 | 4.6911 | 0.0143 | 4.5972 | 4.5916 |
|
290 |
+
| 6.5323 | 5.9045 | 1175 | 4.8424 | 4.6911 | 0.0143 | 4.5972 | 4.5916 |
|
291 |
+
| 6.1429 | 5.9296 | 1180 | 4.8422 | 4.6911 | 0.0143 | 4.5972 | 4.5916 |
|
292 |
+
| 6.457 | 5.9548 | 1185 | 4.8419 | 4.6911 | 0.0143 | 4.5972 | 4.5916 |
|
293 |
+
| 6.1296 | 5.9799 | 1190 | 4.8417 | 4.6911 | 0.0143 | 4.5972 | 4.5916 |
|
294 |
+
|
295 |
+
|
296 |
+
### Framework versions
|
297 |
+
|
298 |
+
- PEFT 0.14.0
|
299 |
+
- Transformers 4.49.0
|
300 |
+
- Pytorch 2.6.0+cu124
|
301 |
+
- Datasets 3.3.2
|
302 |
+
- 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": "google/mt5-small",
|
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 |
+
"q",
|
27 |
+
"v"
|
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 sha256:822bb3ecb2ea6e4ae672d64085604e76eafdc1e64056928c7cd9982c3f632d58
|
3 |
+
size 185072
|
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
|
runs/Mar11_12-01-09_1412920010036/events.out.tfevents.1741719010.1412920010036.243166.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dde0983bb360cd2d8485acc60044ed44bc470fd1bcd2aeb72bf83071abb8830d
|
3 |
+
size 562
|
runs/Mar16_11-09-16_1412920010036/events.out.tfevents.1742137758.1412920010036.2788175.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5c50c6e0e23cd477a941b5d36a0d321e120e2bb69ba10fcca7f99734a6d4e91
|
3 |
+
size 262262
|
runs/Mar16_11-09-16_1412920010036/events.out.tfevents.1742153024.1412920010036.2788175.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d7672a87a44b3c3be97bcccc40603e3e4e82b5c3627cb1f398433cae9ac13fe
|
3 |
+
size 562
|
runs/Mar16_15-24-22_1412920010036/events.out.tfevents.1742153062.1412920010036.2788175.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fef2de389fb253754c18816e070fb8af75dac7f30933574f3dc7c96f864fc526
|
3 |
+
size 168420
|
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 sha256:23e3dbeb87c844b7345f90d4b2a5ae3d0d7b3cf4b7e56156b1c44608473a6c45
|
3 |
+
size 5496
|