Commit
•
b385c66
1
Parent(s):
298b5d0
Training completed
Browse files- README.md +13 -11
- generation_config.json +1 -1
- model.safetensors +1 -1
README.md
CHANGED
|
@@ -5,7 +5,7 @@ base_model: EleutherAI/gpt-neo-125M
|
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
metrics:
|
| 8 |
-
-
|
| 9 |
model-index:
|
| 10 |
- name: MD5_gpt_neo_v1.1
|
| 11 |
results: []
|
|
@@ -19,7 +19,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 19 |
This model is a fine-tuned version of [EleutherAI/gpt-neo-125M](https://huggingface.co/EleutherAI/gpt-neo-125M) on an unknown dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 3.3814
|
| 22 |
-
-
|
|
|
|
|
|
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
@@ -50,18 +52,18 @@ The following hyperparameters were used during training:
|
|
| 50 |
|
| 51 |
### Training results
|
| 52 |
|
| 53 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
| 54 |
-
|
| 55 |
-
| No log | 0.9091 | 5 | 7.9635 | 0.0
|
| 56 |
-
| No log | 2.0 | 11 | 5.3680 | 0.0
|
| 57 |
-
| No log | 2.9091 | 16 | 4.0323 | 0.0
|
| 58 |
-
| No log | 4.0 | 22 | 3.4255 | 0.0
|
| 59 |
-
| No log | 4.5455 | 25 | 3.3814 | 0.0
|
| 60 |
|
| 61 |
|
| 62 |
### Framework versions
|
| 63 |
|
| 64 |
-
- Transformers 4.46.
|
| 65 |
- Pytorch 2.5.0+cu121
|
| 66 |
-
- Datasets 3.0
|
| 67 |
- Tokenizers 0.20.1
|
|
|
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
metrics:
|
| 8 |
+
- rouge
|
| 9 |
model-index:
|
| 10 |
- name: MD5_gpt_neo_v1.1
|
| 11 |
results: []
|
|
|
|
| 19 |
This model is a fine-tuned version of [EleutherAI/gpt-neo-125M](https://huggingface.co/EleutherAI/gpt-neo-125M) on an unknown dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 3.3814
|
| 22 |
+
- Rouge1: 0.0889
|
| 23 |
+
- Rouge2: 0.0
|
| 24 |
+
- Rougel: 0.0695
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
|
|
| 52 |
|
| 53 |
### Training results
|
| 54 |
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel |
|
| 56 |
+
|:-------------:|:------:|:----:|:---------------:|:------:|:------:|:------:|
|
| 57 |
+
| No log | 0.9091 | 5 | 7.9635 | 0.0288 | 0.0 | 0.0231 |
|
| 58 |
+
| No log | 2.0 | 11 | 5.3680 | 0.0328 | 0.0 | 0.0258 |
|
| 59 |
+
| No log | 2.9091 | 16 | 4.0323 | 0.0856 | 0.0 | 0.0776 |
|
| 60 |
+
| No log | 4.0 | 22 | 3.4255 | 0.0890 | 0.0 | 0.0696 |
|
| 61 |
+
| No log | 4.5455 | 25 | 3.3814 | 0.0889 | 0.0 | 0.0695 |
|
| 62 |
|
| 63 |
|
| 64 |
### Framework versions
|
| 65 |
|
| 66 |
+
- Transformers 4.46.1
|
| 67 |
- Pytorch 2.5.0+cu121
|
| 68 |
+
- Datasets 3.1.0
|
| 69 |
- Tokenizers 0.20.1
|
generation_config.json
CHANGED
|
@@ -2,5 +2,5 @@
|
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 50256,
|
| 4 |
"eos_token_id": 50256,
|
| 5 |
-
"transformers_version": "4.46.
|
| 6 |
}
|
|
|
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 50256,
|
| 4 |
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.46.1"
|
| 6 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 500811336
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a3eb7c7e81bfc9c8ca65d4a1b619654112375af48297f5468b002842edc3ca3
|
| 3 |
size 500811336
|