Commit ·
4dcd0f5
1
Parent(s): fc9adce
add model
Browse files- README.md +1 -15
- config.json +1 -3
- tf_model.h5 +1 -1
README.md
CHANGED
|
@@ -14,9 +14,7 @@ probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
-
|
| 18 |
-
- Validation Loss: 0.0034
|
| 19 |
-
- Epoch: 9
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -40,18 +38,6 @@ The following hyperparameters were used during training:
|
|
| 40 |
|
| 41 |
### Training results
|
| 42 |
|
| 43 |
-
| Train Loss | Validation Loss | Epoch |
|
| 44 |
-
|:----------:|:---------------:|:-----:|
|
| 45 |
-
| 0.5370 | 0.2158 | 0 |
|
| 46 |
-
| 0.2152 | 0.2035 | 1 |
|
| 47 |
-
| 0.2040 | 0.1912 | 2 |
|
| 48 |
-
| 0.1915 | 0.1628 | 3 |
|
| 49 |
-
| 0.1569 | 0.0811 | 4 |
|
| 50 |
-
| 0.0864 | 0.0229 | 5 |
|
| 51 |
-
| 0.0404 | 0.0095 | 6 |
|
| 52 |
-
| 0.0247 | 0.0061 | 7 |
|
| 53 |
-
| 0.0175 | 0.0047 | 8 |
|
| 54 |
-
| 0.0133 | 0.0034 | 9 |
|
| 55 |
|
| 56 |
|
| 57 |
### Framework versions
|
|
|
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
+
|
|
|
|
|
|
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
|
|
| 38 |
|
| 39 |
### Training results
|
| 40 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 41 |
|
| 42 |
|
| 43 |
### Framework versions
|
config.json
CHANGED
|
@@ -7,7 +7,6 @@
|
|
| 7 |
],
|
| 8 |
"attn_pdrop": 0.1,
|
| 9 |
"bos_token_id": 50256,
|
| 10 |
-
"do_sample": true,
|
| 11 |
"embd_pdrop": 0.1,
|
| 12 |
"eos_token_id": 50256,
|
| 13 |
"id2label": {
|
|
@@ -18,7 +17,6 @@
|
|
| 18 |
"LABEL_0": 0
|
| 19 |
},
|
| 20 |
"layer_norm_epsilon": 1e-05,
|
| 21 |
-
"max_length": 50,
|
| 22 |
"model_type": "gpt2",
|
| 23 |
"n_ctx": 1024,
|
| 24 |
"n_embd": 768,
|
|
@@ -42,6 +40,6 @@
|
|
| 42 |
}
|
| 43 |
},
|
| 44 |
"transformers_version": "4.17.0",
|
| 45 |
-
"use_cache":
|
| 46 |
"vocab_size": 5998
|
| 47 |
}
|
|
|
|
| 7 |
],
|
| 8 |
"attn_pdrop": 0.1,
|
| 9 |
"bos_token_id": 50256,
|
|
|
|
| 10 |
"embd_pdrop": 0.1,
|
| 11 |
"eos_token_id": 50256,
|
| 12 |
"id2label": {
|
|
|
|
| 17 |
"LABEL_0": 0
|
| 18 |
},
|
| 19 |
"layer_norm_epsilon": 1e-05,
|
|
|
|
| 20 |
"model_type": "gpt2",
|
| 21 |
"n_ctx": 1024,
|
| 22 |
"n_embd": 768,
|
|
|
|
| 40 |
}
|
| 41 |
},
|
| 42 |
"transformers_version": "4.17.0",
|
| 43 |
+
"use_cache": true,
|
| 44 |
"vocab_size": 5998
|
| 45 |
}
|
tf_model.h5
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 210211336
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:197328a79616102fa399d1344e1221a8dacfea2f549d8495a184e10445cd1fa5
|
| 3 |
size 210211336
|