End of training
Browse files- README.md +109 -59
- model.safetensors +1 -1
README.md
CHANGED
@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss:
|
21 |
-
- Bleu:
|
22 |
-
- Gen Len:
|
23 |
|
24 |
## Model description
|
25 |
|
@@ -38,69 +38,119 @@ More information needed
|
|
38 |
### Training hyperparameters
|
39 |
|
40 |
The following hyperparameters were used during training:
|
41 |
-
- learning_rate:
|
42 |
-
- train_batch_size:
|
43 |
-
- eval_batch_size:
|
44 |
- seed: 42
|
45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
- lr_scheduler_type: linear
|
47 |
-
- num_epochs:
|
48 |
- mixed_precision_training: Native AMP
|
49 |
|
50 |
### Training results
|
51 |
|
52 |
-
| Training Loss | Epoch | Step | Validation Loss | Bleu
|
53 |
-
|
54 |
-
|
|
55 |
-
|
|
56 |
-
|
|
57 |
-
|
|
58 |
-
|
|
59 |
-
|
|
60 |
-
|
|
61 |
-
|
|
62 |
-
|
|
63 |
-
|
|
64 |
-
|
|
65 |
-
|
|
66 |
-
|
|
67 |
-
|
|
68 |
-
|
|
69 |
-
|
|
70 |
-
|
|
71 |
-
|
|
72 |
-
|
|
73 |
-
|
|
74 |
-
|
|
75 |
-
|
|
76 |
-
|
|
77 |
-
|
|
78 |
-
|
|
79 |
-
|
|
80 |
-
|
|
81 |
-
|
|
82 |
-
|
|
83 |
-
|
|
84 |
-
|
|
85 |
-
|
|
86 |
-
|
|
87 |
-
|
|
88 |
-
|
|
89 |
-
|
|
90 |
-
|
|
91 |
-
|
|
92 |
-
|
|
93 |
-
|
|
94 |
-
|
|
95 |
-
|
|
96 |
-
|
|
97 |
-
|
|
98 |
-
|
|
99 |
-
|
|
100 |
-
|
|
101 |
-
|
|
102 |
-
|
|
103 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
104 |
|
105 |
|
106 |
### Framework versions
|
|
|
17 |
|
18 |
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 10.375
|
21 |
+
- Bleu: 0.0
|
22 |
+
- Gen Len: 0.0
|
23 |
|
24 |
## Model description
|
25 |
|
|
|
38 |
### Training hyperparameters
|
39 |
|
40 |
The following hyperparameters were used during training:
|
41 |
+
- learning_rate: 0.01
|
42 |
+
- train_batch_size: 12
|
43 |
+
- eval_batch_size: 12
|
44 |
- seed: 42
|
45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
- lr_scheduler_type: linear
|
47 |
+
- num_epochs: 100
|
48 |
- mixed_precision_training: Native AMP
|
49 |
|
50 |
### Training results
|
51 |
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|
53 |
+
|:-------------:|:-----:|:------:|:---------------:|:------:|:-------:|
|
54 |
+
| 9.3669 | 1.0 | 5229 | 9.4520 | 0.0023 | 19.0 |
|
55 |
+
| 10.2293 | 2.0 | 10458 | 10.2588 | 0.1433 | 6.0 |
|
56 |
+
| 10.3618 | 3.0 | 15687 | 10.3648 | 0.0 | 0.0 |
|
57 |
+
| 10.375 | 4.0 | 20916 | 10.375 | 0.0 | 0.0 |
|
58 |
+
| 10.375 | 5.0 | 26145 | 10.375 | 0.0 | 0.0 |
|
59 |
+
| 10.375 | 6.0 | 31374 | 10.375 | 0.0 | 0.0 |
|
60 |
+
| 10.375 | 7.0 | 36603 | 10.375 | 0.0 | 0.0 |
|
61 |
+
| 10.375 | 8.0 | 41832 | 10.375 | 0.0 | 0.0 |
|
62 |
+
| 10.375 | 9.0 | 47061 | 10.375 | 0.0 | 0.0 |
|
63 |
+
| 10.375 | 10.0 | 52290 | 10.375 | 0.0 | 0.0 |
|
64 |
+
| 10.375 | 11.0 | 57519 | 10.375 | 0.0 | 0.0 |
|
65 |
+
| 10.375 | 12.0 | 62748 | 10.375 | 0.0 | 0.0 |
|
66 |
+
| 10.375 | 13.0 | 67977 | 10.375 | 0.0 | 0.0 |
|
67 |
+
| 10.375 | 14.0 | 73206 | 10.375 | 0.0 | 0.0 |
|
68 |
+
| 10.375 | 15.0 | 78435 | 10.375 | 0.0 | 0.0 |
|
69 |
+
| 10.375 | 16.0 | 83664 | 10.375 | 0.0 | 0.0 |
|
70 |
+
| 10.375 | 17.0 | 88893 | 10.375 | 0.0 | 0.0 |
|
71 |
+
| 10.375 | 18.0 | 94122 | 10.375 | 0.0 | 0.0 |
|
72 |
+
| 10.375 | 19.0 | 99351 | 10.375 | 0.0 | 0.0 |
|
73 |
+
| 10.375 | 20.0 | 104580 | 10.375 | 0.0 | 0.0 |
|
74 |
+
| 10.375 | 21.0 | 109809 | 10.375 | 0.0 | 0.0 |
|
75 |
+
| 10.375 | 22.0 | 115038 | 10.375 | 0.0 | 0.0 |
|
76 |
+
| 10.375 | 23.0 | 120267 | 10.375 | 0.0 | 0.0 |
|
77 |
+
| 10.375 | 24.0 | 125496 | 10.375 | 0.0 | 0.0 |
|
78 |
+
| 10.375 | 25.0 | 130725 | 10.375 | 0.0 | 0.0 |
|
79 |
+
| 10.375 | 26.0 | 135954 | 10.375 | 0.0 | 0.0 |
|
80 |
+
| 10.375 | 27.0 | 141183 | 10.375 | 0.0 | 0.0 |
|
81 |
+
| 10.375 | 28.0 | 146412 | 10.375 | 0.0 | 0.0 |
|
82 |
+
| 10.375 | 29.0 | 151641 | 10.375 | 0.0 | 0.0 |
|
83 |
+
| 10.375 | 30.0 | 156870 | 10.375 | 0.0 | 0.0 |
|
84 |
+
| 10.375 | 31.0 | 162099 | 10.375 | 0.0 | 0.0 |
|
85 |
+
| 10.375 | 32.0 | 167328 | 10.375 | 0.0 | 0.0 |
|
86 |
+
| 10.375 | 33.0 | 172557 | 10.375 | 0.0 | 0.0 |
|
87 |
+
| 10.375 | 34.0 | 177786 | 10.375 | 0.0 | 0.0 |
|
88 |
+
| 10.375 | 35.0 | 183015 | 10.375 | 0.0 | 0.0 |
|
89 |
+
| 10.375 | 36.0 | 188244 | 10.375 | 0.0 | 0.0 |
|
90 |
+
| 10.375 | 37.0 | 193473 | 10.375 | 0.0 | 0.0 |
|
91 |
+
| 10.375 | 38.0 | 198702 | 10.375 | 0.0 | 0.0 |
|
92 |
+
| 10.375 | 39.0 | 203931 | 10.375 | 0.0 | 0.0 |
|
93 |
+
| 10.375 | 40.0 | 209160 | 10.375 | 0.0 | 0.0 |
|
94 |
+
| 10.375 | 41.0 | 214389 | 10.375 | 0.0 | 0.0 |
|
95 |
+
| 10.375 | 42.0 | 219618 | 10.375 | 0.0 | 0.0 |
|
96 |
+
| 10.375 | 43.0 | 224847 | 10.375 | 0.0 | 0.0 |
|
97 |
+
| 10.375 | 44.0 | 230076 | 10.375 | 0.0 | 0.0 |
|
98 |
+
| 10.375 | 45.0 | 235305 | 10.375 | 0.0 | 0.0 |
|
99 |
+
| 10.375 | 46.0 | 240534 | 10.375 | 0.0 | 0.0 |
|
100 |
+
| 10.375 | 47.0 | 245763 | 10.375 | 0.0 | 0.0 |
|
101 |
+
| 10.375 | 48.0 | 250992 | 10.375 | 0.0 | 0.0 |
|
102 |
+
| 10.375 | 49.0 | 256221 | 10.375 | 0.0 | 0.0 |
|
103 |
+
| 10.375 | 50.0 | 261450 | 10.375 | 0.0 | 0.0 |
|
104 |
+
| 10.375 | 51.0 | 266679 | 10.375 | 0.0 | 0.0 |
|
105 |
+
| 10.375 | 52.0 | 271908 | 10.375 | 0.0 | 0.0 |
|
106 |
+
| 10.375 | 53.0 | 277137 | 10.375 | 0.0 | 0.0 |
|
107 |
+
| 10.375 | 54.0 | 282366 | 10.375 | 0.0 | 0.0 |
|
108 |
+
| 10.375 | 55.0 | 287595 | 10.375 | 0.0 | 0.0 |
|
109 |
+
| 10.375 | 56.0 | 292824 | 10.375 | 0.0 | 0.0 |
|
110 |
+
| 10.375 | 57.0 | 298053 | 10.375 | 0.0 | 0.0 |
|
111 |
+
| 10.375 | 58.0 | 303282 | 10.375 | 0.0 | 0.0 |
|
112 |
+
| 10.375 | 59.0 | 308511 | 10.375 | 0.0 | 0.0 |
|
113 |
+
| 10.375 | 60.0 | 313740 | 10.375 | 0.0 | 0.0 |
|
114 |
+
| 10.375 | 61.0 | 318969 | 10.375 | 0.0 | 0.0 |
|
115 |
+
| 10.375 | 62.0 | 324198 | 10.375 | 0.0 | 0.0 |
|
116 |
+
| 10.375 | 63.0 | 329427 | 10.375 | 0.0 | 0.0 |
|
117 |
+
| 10.375 | 64.0 | 334656 | 10.375 | 0.0 | 0.0 |
|
118 |
+
| 10.375 | 65.0 | 339885 | 10.375 | 0.0 | 0.0 |
|
119 |
+
| 10.375 | 66.0 | 345114 | 10.375 | 0.0 | 0.0 |
|
120 |
+
| 10.375 | 67.0 | 350343 | 10.375 | 0.0 | 0.0 |
|
121 |
+
| 10.375 | 68.0 | 355572 | 10.375 | 0.0 | 0.0 |
|
122 |
+
| 10.375 | 69.0 | 360801 | 10.375 | 0.0 | 0.0 |
|
123 |
+
| 10.375 | 70.0 | 366030 | 10.375 | 0.0 | 0.0 |
|
124 |
+
| 10.375 | 71.0 | 371259 | 10.375 | 0.0 | 0.0 |
|
125 |
+
| 10.375 | 72.0 | 376488 | 10.375 | 0.0 | 0.0 |
|
126 |
+
| 10.375 | 73.0 | 381717 | 10.375 | 0.0 | 0.0 |
|
127 |
+
| 10.375 | 74.0 | 386946 | 10.375 | 0.0 | 0.0 |
|
128 |
+
| 10.375 | 75.0 | 392175 | 10.375 | 0.0 | 0.0 |
|
129 |
+
| 10.375 | 76.0 | 397404 | 10.375 | 0.0 | 0.0 |
|
130 |
+
| 10.375 | 77.0 | 402633 | 10.375 | 0.0 | 0.0 |
|
131 |
+
| 10.375 | 78.0 | 407862 | 10.375 | 0.0 | 0.0 |
|
132 |
+
| 10.375 | 79.0 | 413091 | 10.375 | 0.0 | 0.0 |
|
133 |
+
| 10.375 | 80.0 | 418320 | 10.375 | 0.0 | 0.0 |
|
134 |
+
| 10.375 | 81.0 | 423549 | 10.375 | 0.0 | 0.0 |
|
135 |
+
| 10.375 | 82.0 | 428778 | 10.375 | 0.0 | 0.0 |
|
136 |
+
| 10.375 | 83.0 | 434007 | 10.375 | 0.0 | 0.0 |
|
137 |
+
| 10.375 | 84.0 | 439236 | 10.375 | 0.0 | 0.0 |
|
138 |
+
| 10.375 | 85.0 | 444465 | 10.375 | 0.0 | 0.0 |
|
139 |
+
| 10.375 | 86.0 | 449694 | 10.375 | 0.0 | 0.0 |
|
140 |
+
| 10.375 | 87.0 | 454923 | 10.375 | 0.0 | 0.0 |
|
141 |
+
| 10.375 | 88.0 | 460152 | 10.375 | 0.0 | 0.0 |
|
142 |
+
| 10.375 | 89.0 | 465381 | 10.375 | 0.0 | 0.0 |
|
143 |
+
| 10.375 | 90.0 | 470610 | 10.375 | 0.0 | 0.0 |
|
144 |
+
| 10.375 | 91.0 | 475839 | 10.375 | 0.0 | 0.0 |
|
145 |
+
| 10.375 | 92.0 | 481068 | 10.375 | 0.0 | 0.0 |
|
146 |
+
| 10.375 | 93.0 | 486297 | 10.375 | 0.0 | 0.0 |
|
147 |
+
| 10.375 | 94.0 | 491526 | 10.375 | 0.0 | 0.0 |
|
148 |
+
| 10.375 | 95.0 | 496755 | 10.375 | 0.0 | 0.0 |
|
149 |
+
| 10.375 | 96.0 | 501984 | 10.375 | 0.0 | 0.0 |
|
150 |
+
| 10.375 | 97.0 | 507213 | 10.375 | 0.0 | 0.0 |
|
151 |
+
| 10.375 | 98.0 | 512442 | 10.375 | 0.0 | 0.0 |
|
152 |
+
| 10.375 | 99.0 | 517671 | 10.375 | 0.0 | 0.0 |
|
153 |
+
| 10.375 | 100.0 | 522900 | 10.375 | 0.0 | 0.0 |
|
154 |
|
155 |
|
156 |
### Framework versions
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242041896
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa8887eaa2cefd25fbbd8ac708ba086b83b395d82fcfbcca1dff1a39efed7c84
|
3 |
size 242041896
|