Training in progress, step 500
Browse files- README.md +11 -10
- config.json +1 -1
- generation_config.json +1 -1
- model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -4,18 +4,18 @@ base_model: facebook/bart-base
|
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
model-index:
|
7 |
-
- name: bart-with-
|
8 |
results: []
|
9 |
---
|
10 |
|
11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
should probably proofread and complete it, then remove this comment. -->
|
13 |
|
14 |
-
# bart-with-
|
15 |
|
16 |
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss: 0.
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -42,19 +42,20 @@ The following hyperparameters were used during training:
|
|
42 |
- lr_scheduler_type: linear
|
43 |
- lr_scheduler_warmup_steps: 10
|
44 |
- num_epochs: 3
|
|
|
45 |
|
46 |
### Training results
|
47 |
|
48 |
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
|:-------------:|:-----:|:----:|:---------------:|
|
50 |
-
| 0.
|
51 |
-
| 0.
|
52 |
-
| 0.
|
53 |
|
54 |
|
55 |
### Framework versions
|
56 |
|
57 |
-
- Transformers 4.
|
58 |
-
- Pytorch 2.1.2
|
59 |
-
- Datasets 2.
|
60 |
-
- Tokenizers 0.15.
|
|
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
model-index:
|
7 |
+
- name: bart-with-noise-data
|
8 |
results: []
|
9 |
---
|
10 |
|
11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
should probably proofread and complete it, then remove this comment. -->
|
13 |
|
14 |
+
# bart-with-noise-data
|
15 |
|
16 |
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.2749
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
42 |
- lr_scheduler_type: linear
|
43 |
- lr_scheduler_warmup_steps: 10
|
44 |
- num_epochs: 3
|
45 |
+
- mixed_precision_training: Native AMP
|
46 |
|
47 |
### Training results
|
48 |
|
49 |
| Training Loss | Epoch | Step | Validation Loss |
|
50 |
|:-------------:|:-----:|:----:|:---------------:|
|
51 |
+
| 0.5397 | 0.87 | 500 | 0.3145 |
|
52 |
+
| 0.2586 | 1.73 | 1000 | 0.2909 |
|
53 |
+
| 0.2764 | 2.6 | 1500 | 0.2749 |
|
54 |
|
55 |
|
56 |
### Framework versions
|
57 |
|
58 |
+
- Transformers 4.37.2
|
59 |
+
- Pytorch 2.1.2+cu121
|
60 |
+
- Datasets 2.17.0
|
61 |
+
- Tokenizers 0.15.1
|
config.json
CHANGED
@@ -69,7 +69,7 @@
|
|
69 |
}
|
70 |
},
|
71 |
"torch_dtype": "float32",
|
72 |
-
"transformers_version": "4.
|
73 |
"use_cache": true,
|
74 |
"vocab_size": 50265
|
75 |
}
|
|
|
69 |
}
|
70 |
},
|
71 |
"torch_dtype": "float32",
|
72 |
+
"transformers_version": "4.37.2",
|
73 |
"use_cache": true,
|
74 |
"vocab_size": 50265
|
75 |
}
|
generation_config.json
CHANGED
@@ -9,5 +9,5 @@
|
|
9 |
"no_repeat_ngram_size": 3,
|
10 |
"num_beams": 4,
|
11 |
"pad_token_id": 1,
|
12 |
-
"transformers_version": "4.
|
13 |
}
|
|
|
9 |
"no_repeat_ngram_size": 3,
|
10 |
"num_beams": 4,
|
11 |
"pad_token_id": 1,
|
12 |
+
"transformers_version": "4.37.2"
|
13 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 557912620
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:edc86ce36ee9db09d79c259767d49e0db4169132fc0752ec7014499b72c3c02d
|
3 |
size 557912620
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4664
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7542a1b0d22daa47449aa4c78be7dcbc4df1dc6ec0c4a11512baace3f970fa5e
|
3 |
size 4664
|