Training in progress, step 500
Browse files
README.md
CHANGED
|
@@ -14,12 +14,6 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
# t5-finetuned-ar-to-arsl_test
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [PRAli22/arat5-arabic-dialects-translation](https://huggingface.co/PRAli22/arat5-arabic-dialects-translation) on the None dataset.
|
| 17 |
-
It achieves the following results on the evaluation set:
|
| 18 |
-
- Loss: 0.4437
|
| 19 |
-
- Bleu1: 0.9326
|
| 20 |
-
- Bleu2: 0.8967
|
| 21 |
-
- Bleu3: 0.7133
|
| 22 |
-
- Bleu4: 0.5737
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
@@ -49,27 +43,6 @@ The following hyperparameters were used during training:
|
|
| 49 |
- num_epochs: 15
|
| 50 |
- mixed_precision_training: Native AMP
|
| 51 |
|
| 52 |
-
### Training results
|
| 53 |
-
|
| 54 |
-
| Training Loss | Epoch | Step | Validation Loss | Bleu1 | Bleu2 | Bleu3 | Bleu4 |
|
| 55 |
-
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:------:|
|
| 56 |
-
| No log | 1.0 | 59 | 0.3274 | 0.9290 | 0.8943 | 0.7134 | 0.5740 |
|
| 57 |
-
| No log | 2.0 | 118 | 0.3396 | 0.9332 | 0.9022 | 0.7185 | 0.5775 |
|
| 58 |
-
| No log | 2.99 | 177 | 0.3654 | 0.9331 | 0.9001 | 0.7165 | 0.5754 |
|
| 59 |
-
| No log | 3.99 | 236 | 0.3809 | 0.9298 | 0.8951 | 0.7096 | 0.5690 |
|
| 60 |
-
| No log | 4.99 | 295 | 0.3918 | 0.9325 | 0.8984 | 0.7153 | 0.5747 |
|
| 61 |
-
| No log | 5.99 | 354 | 0.4003 | 0.9294 | 0.8926 | 0.7082 | 0.5691 |
|
| 62 |
-
| No log | 6.99 | 413 | 0.4018 | 0.9331 | 0.8984 | 0.7137 | 0.5738 |
|
| 63 |
-
| No log | 8.0 | 473 | 0.4154 | 0.9333 | 0.9007 | 0.7161 | 0.5776 |
|
| 64 |
-
| 0.0263 | 9.0 | 532 | 0.4394 | 0.9338 | 0.8985 | 0.7142 | 0.5745 |
|
| 65 |
-
| 0.0263 | 10.0 | 591 | 0.4421 | 0.9336 | 0.8994 | 0.7176 | 0.5781 |
|
| 66 |
-
| 0.0263 | 10.99 | 650 | 0.4417 | 0.9325 | 0.8971 | 0.7138 | 0.5753 |
|
| 67 |
-
| 0.0263 | 11.99 | 709 | 0.4526 | 0.9340 | 0.8992 | 0.7154 | 0.5740 |
|
| 68 |
-
| 0.0263 | 12.99 | 768 | 0.4487 | 0.9328 | 0.8971 | 0.7134 | 0.5734 |
|
| 69 |
-
| 0.0263 | 13.99 | 827 | 0.4483 | 0.9324 | 0.8970 | 0.7135 | 0.5740 |
|
| 70 |
-
| 0.0263 | 14.97 | 885 | 0.4437 | 0.9326 | 0.8967 | 0.7133 | 0.5737 |
|
| 71 |
-
|
| 72 |
-
|
| 73 |
### Framework versions
|
| 74 |
|
| 75 |
- Transformers 4.39.3
|
|
|
|
| 14 |
# t5-finetuned-ar-to-arsl_test
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [PRAli22/arat5-arabic-dialects-translation](https://huggingface.co/PRAli22/arat5-arabic-dialects-translation) on the None dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
|
|
| 43 |
- num_epochs: 15
|
| 44 |
- mixed_precision_training: Native AMP
|
| 45 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
### Framework versions
|
| 47 |
|
| 48 |
- Transformers 4.39.3
|
generation_config.json
CHANGED
|
@@ -1,4 +1,5 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"decoder_start_token_id": 0,
|
| 3 |
"eos_token_id": 1,
|
| 4 |
"pad_token_id": 0,
|
|
|
|
| 1 |
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
"decoder_start_token_id": 0,
|
| 4 |
"eos_token_id": 1,
|
| 5 |
"pad_token_id": 0,
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1470068592
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a94f7854fd2286cdad3462590c9a66db211b2a9731296f4b59a05bfa83e5cfee
|
| 3 |
size 1470068592
|
runs/Jun21_23-00-00_629c6854238f/events.out.tfevents.1719010983.629c6854238f.34.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e553cd114f49dd38353d42e1822c6ef5748cffdd56a6bb0b602dc04dfb37d581
|
| 3 |
+
size 8931
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5112
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:24b53133c294d939505f1b98e351d3b6e9797d798206c21d811bcda921a8a615
|
| 3 |
size 5112
|