cartesinus
commited on
Add model, config, tokenizer, and custom code
Browse files- README.md +11 -11
- config.json +1 -1
- generation_config.json +1 -1
- model.safetensors +1 -1
- runs/Nov12_20-21-45_467a9cc09385/events.out.tfevents.1731442906.467a9cc09385.226.0 +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -1
- training_args.bin +2 -2
README.md
CHANGED
@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
This model is a fine-tuned version of [](https://huggingface.co/) on the iva_mt_wslot dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss: 6.
|
22 |
-
- Bleu: 0.
|
23 |
-
- Gen Len:
|
24 |
|
25 |
## Model description
|
26 |
|
@@ -45,7 +45,7 @@ The following hyperparameters were used during training:
|
|
45 |
- seed: 42
|
46 |
- gradient_accumulation_steps: 4
|
47 |
- total_train_batch_size: 32
|
48 |
-
- optimizer:
|
49 |
- lr_scheduler_type: linear
|
50 |
- lr_scheduler_warmup_steps: 500
|
51 |
- num_epochs: 5
|
@@ -55,16 +55,16 @@ The following hyperparameters were used during training:
|
|
55 |
|
56 |
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|
57 |
|:-------------:|:------:|:----:|:---------------:|:------:|:-------:|
|
58 |
-
| 7.
|
59 |
-
| 6.
|
60 |
-
| 6.
|
61 |
-
| 5.
|
62 |
-
| 5.
|
63 |
|
64 |
|
65 |
### Framework versions
|
66 |
|
67 |
-
- Transformers 4.
|
68 |
- Pytorch 2.5.0+cu121
|
69 |
- Datasets 3.1.0
|
70 |
-
- Tokenizers 0.
|
|
|
18 |
|
19 |
This model is a fine-tuned version of [](https://huggingface.co/) on the iva_mt_wslot dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 6.1444
|
22 |
+
- Bleu: 0.0738
|
23 |
+
- Gen Len: 6.655
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
45 |
- seed: 42
|
46 |
- gradient_accumulation_steps: 4
|
47 |
- total_train_batch_size: 32
|
48 |
+
- optimizer: Use 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 |
- lr_scheduler_warmup_steps: 500
|
51 |
- num_epochs: 5
|
|
|
55 |
|
56 |
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|
57 |
|:-------------:|:------:|:----:|:---------------:|:------:|:-------:|
|
58 |
+
| 7.3851 | 0.9992 | 636 | 7.0694 | 0.0229 | 5.3686 |
|
59 |
+
| 6.537 | 2.0 | 1273 | 6.5403 | 0.0786 | 7.0747 |
|
60 |
+
| 6.1173 | 2.9992 | 1909 | 6.2891 | 0.0387 | 6.1529 |
|
61 |
+
| 5.924 | 4.0 | 2546 | 6.1793 | 0.0715 | 6.7137 |
|
62 |
+
| 5.7999 | 4.9961 | 3180 | 6.1444 | 0.0738 | 6.655 |
|
63 |
|
64 |
|
65 |
### Framework versions
|
66 |
|
67 |
+
- Transformers 4.46.2
|
68 |
- Pytorch 2.5.0+cu121
|
69 |
- Datasets 3.1.0
|
70 |
+
- Tokenizers 0.20.3
|
config.json
CHANGED
@@ -16,6 +16,6 @@
|
|
16 |
"pad_token_id": 1,
|
17 |
"share_embeddings": false,
|
18 |
"torch_dtype": "float32",
|
19 |
-
"transformers_version": "4.
|
20 |
"vocab_size": 28297
|
21 |
}
|
|
|
16 |
"pad_token_id": 1,
|
17 |
"share_embeddings": false,
|
18 |
"torch_dtype": "float32",
|
19 |
+
"transformers_version": "4.46.2",
|
20 |
"vocab_size": 28297
|
21 |
}
|
generation_config.json
CHANGED
@@ -4,5 +4,5 @@
|
|
4 |
"decoder_start_token_id": 1,
|
5 |
"eos_token_id": 2,
|
6 |
"pad_token_id": 1,
|
7 |
-
"transformers_version": "4.
|
8 |
}
|
|
|
4 |
"decoder_start_token_id": 1,
|
5 |
"eos_token_id": 2,
|
6 |
"pad_token_id": 1,
|
7 |
+
"transformers_version": "4.46.2"
|
8 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 109582088
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2a3e637601d25f161d2de2da766598253c18c5ad1460e91dd0969392b4f389f
|
3 |
size 109582088
|
runs/Nov12_20-21-45_467a9cc09385/events.out.tfevents.1731442906.467a9cc09385.226.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5eb0bdb79469bb2bef77d63f35efe0f1b96dd0eb689c32ccc81e6052e5c93293
|
3 |
+
size 20421
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -34,7 +34,7 @@
|
|
34 |
}
|
35 |
},
|
36 |
"bos_token": "<bos>",
|
37 |
-
"clean_up_tokenization_spaces":
|
38 |
"eos_token": "<eos>",
|
39 |
"model_max_length": 256,
|
40 |
"pad_token": "<pad>",
|
|
|
34 |
}
|
35 |
},
|
36 |
"bos_token": "<bos>",
|
37 |
+
"clean_up_tokenization_spaces": false,
|
38 |
"eos_token": "<eos>",
|
39 |
"model_max_length": 256,
|
40 |
"pad_token": "<pad>",
|
training_args.bin
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 sha256:6d6d1af86d6cfafa004586586bb2c3de64d8348b0a5c2ce47627bb523f19c0b5
|
3 |
+
size 5496
|