Vichentito
commited on
Commit
•
ce407a8
1
Parent(s):
058600f
End of training
Browse files
README.md
CHANGED
@@ -15,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
This model was trained from scratch on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss: 0.
|
19 |
-
- Bleu:
|
20 |
-
- Gen Len: 45.
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -36,69 +36,36 @@ More information needed
|
|
36 |
### Training hyperparameters
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
-
- learning_rate: 0.
|
40 |
- train_batch_size: 32
|
41 |
- eval_batch_size: 32
|
42 |
- seed: 42
|
43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
- lr_scheduler_type: linear
|
45 |
-
- num_epochs:
|
46 |
|
47 |
### Training results
|
48 |
|
49 |
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|
50 |
|:-------------:|:------:|:----:|:---------------:|:-------:|:-------:|
|
51 |
-
| No log | 0.
|
52 |
-
|
|
53 |
-
|
|
54 |
-
|
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
-
| 0.9989 | 1.4989 | 1400 | 0.7243 | 22.5969 | 46.077 |
|
65 |
-
| 0.9195 | 1.6060 | 1500 | 0.7300 | 22.6051 | 45.7915 |
|
66 |
-
| 0.9195 | 1.7131 | 1600 | 0.7255 | 22.563 | 45.8345 |
|
67 |
-
| 0.9195 | 1.8201 | 1700 | 0.7268 | 22.7627 | 45.7479 |
|
68 |
-
| 0.9195 | 1.9272 | 1800 | 0.7239 | 22.6867 | 45.9264 |
|
69 |
-
| 0.9195 | 2.0343 | 1900 | 0.7292 | 22.7507 | 45.6174 |
|
70 |
-
| 0.9069 | 2.1413 | 2000 | 0.7287 | 22.8822 | 45.7353 |
|
71 |
-
| 0.9069 | 2.2484 | 2100 | 0.7288 | 22.9287 | 45.7574 |
|
72 |
-
| 0.9069 | 2.3555 | 2200 | 0.7271 | 22.739 | 45.8887 |
|
73 |
-
| 0.9069 | 2.4625 | 2300 | 0.7295 | 22.7979 | 45.6375 |
|
74 |
-
| 0.9069 | 2.5696 | 2400 | 0.7255 | 22.8196 | 45.8767 |
|
75 |
-
| 0.8581 | 2.6767 | 2500 | 0.7285 | 22.9328 | 45.5503 |
|
76 |
-
| 0.8581 | 2.7837 | 2600 | 0.7272 | 22.8605 | 45.4845 |
|
77 |
-
| 0.8581 | 2.8908 | 2700 | 0.7266 | 22.7798 | 45.8115 |
|
78 |
-
| 0.8581 | 2.9979 | 2800 | 0.7263 | 22.8977 | 45.7137 |
|
79 |
-
| 0.8581 | 3.1049 | 2900 | 0.7278 | 23.1761 | 45.5648 |
|
80 |
-
| 0.8337 | 3.2120 | 3000 | 0.7253 | 23.1161 | 45.6975 |
|
81 |
-
| 0.8337 | 3.3191 | 3100 | 0.7254 | 23.2943 | 45.8444 |
|
82 |
-
| 0.8337 | 3.4261 | 3200 | 0.7269 | 23.3569 | 45.5949 |
|
83 |
-
| 0.8337 | 3.5332 | 3300 | 0.7249 | 23.3935 | 45.7649 |
|
84 |
-
| 0.8337 | 3.6403 | 3400 | 0.7245 | 23.3007 | 45.7151 |
|
85 |
-
| 0.7951 | 3.7473 | 3500 | 0.7256 | 23.2827 | 45.5649 |
|
86 |
-
| 0.7951 | 3.8544 | 3600 | 0.7224 | 23.4464 | 45.7041 |
|
87 |
-
| 0.7951 | 3.9615 | 3700 | 0.7209 | 23.4635 | 45.6198 |
|
88 |
-
| 0.7951 | 4.0685 | 3800 | 0.7261 | 23.4885 | 45.6302 |
|
89 |
-
| 0.7951 | 4.1756 | 3900 | 0.7226 | 23.5112 | 45.6264 |
|
90 |
-
| 0.769 | 4.2827 | 4000 | 0.7226 | 23.4213 | 45.6869 |
|
91 |
-
| 0.769 | 4.3897 | 4100 | 0.7219 | 23.5038 | 45.4214 |
|
92 |
-
| 0.769 | 4.4968 | 4200 | 0.7211 | 23.5617 | 45.6644 |
|
93 |
-
| 0.769 | 4.6039 | 4300 | 0.7201 | 23.5387 | 45.742 |
|
94 |
-
| 0.769 | 4.7109 | 4400 | 0.7199 | 23.5526 | 45.6596 |
|
95 |
-
| 0.7513 | 4.8180 | 4500 | 0.7193 | 23.6482 | 45.6834 |
|
96 |
-
| 0.7513 | 4.9251 | 4600 | 0.7196 | 23.6683 | 45.6564 |
|
97 |
|
98 |
|
99 |
### Framework versions
|
100 |
|
101 |
-
- Transformers 4.
|
102 |
-
- Pytorch 2.
|
103 |
-
- Datasets 2.19.
|
104 |
- Tokenizers 0.19.1
|
|
|
15 |
|
16 |
This model was trained from scratch on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.6835
|
19 |
+
- Bleu: 25.7459
|
20 |
+
- Gen Len: 45.7999
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
36 |
### Training hyperparameters
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
+
- learning_rate: 0.0005
|
40 |
- train_batch_size: 32
|
41 |
- eval_batch_size: 32
|
42 |
- seed: 42
|
43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
- lr_scheduler_type: linear
|
45 |
+
- num_epochs: 4
|
46 |
|
47 |
### Training results
|
48 |
|
49 |
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|
50 |
|:-------------:|:------:|:----:|:---------------:|:-------:|:-------:|
|
51 |
+
| No log | 0.3027 | 300 | 0.6651 | 24.827 | 46.2006 |
|
52 |
+
| 0.9651 | 0.6054 | 600 | 0.6967 | 24.0607 | 45.3494 |
|
53 |
+
| 0.9651 | 0.9082 | 900 | 0.7045 | 23.7928 | 46.1327 |
|
54 |
+
| 1.001 | 1.2109 | 1200 | 0.7084 | 23.9299 | 46.4082 |
|
55 |
+
| 0.8741 | 1.5136 | 1500 | 0.7156 | 23.9047 | 45.8685 |
|
56 |
+
| 0.8741 | 1.8163 | 1800 | 0.7121 | 23.9386 | 45.7796 |
|
57 |
+
| 0.8763 | 2.1191 | 2100 | 0.7083 | 24.5377 | 45.8846 |
|
58 |
+
| 0.8763 | 2.4218 | 2400 | 0.7032 | 24.6723 | 46.1827 |
|
59 |
+
| 0.7689 | 2.7245 | 2700 | 0.6988 | 24.7631 | 45.8793 |
|
60 |
+
| 0.7599 | 3.0272 | 3000 | 0.6961 | 25.2701 | 45.7947 |
|
61 |
+
| 0.7599 | 3.3300 | 3300 | 0.6935 | 25.4704 | 45.7461 |
|
62 |
+
| 0.6782 | 3.6327 | 3600 | 0.6861 | 25.7835 | 45.9797 |
|
63 |
+
| 0.6782 | 3.9354 | 3900 | 0.6835 | 25.7459 | 45.7999 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
64 |
|
65 |
|
66 |
### Framework versions
|
67 |
|
68 |
+
- Transformers 4.41.2
|
69 |
+
- Pytorch 2.3.0+cu121
|
70 |
+
- Datasets 2.19.2
|
71 |
- Tokenizers 0.19.1
|
generation_config.json
CHANGED
@@ -2,5 +2,5 @@
|
|
2 |
"decoder_start_token_id": 0,
|
3 |
"eos_token_id": 1,
|
4 |
"pad_token_id": 0,
|
5 |
-
"transformers_version": "4.
|
6 |
}
|
|
|
2 |
"decoder_start_token_id": 0,
|
3 |
"eos_token_id": 1,
|
4 |
"pad_token_id": 0,
|
5 |
+
"transformers_version": "4.41.2"
|
6 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 990345064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e8f5e9d8733b5b505d0be90c2eda85fc8668c072b2bfd83f77d3c63b7e0db7bb
|
3 |
size 990345064
|
runs/Jun10_23-49-43_20d0574f53df/events.out.tfevents.1718063384.20d0574f53df.1139.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5abe82048d302ccf73308cf8f2281cf24138a1d4de6a259b7bf44be5a233ca0b
|
3 |
+
size 12559
|