Commit
·
8013823
1
Parent(s):
db2d3e2
Training in progress epoch 0
Browse files- README.md +3 -22
- special_tokens_map.json +21 -3
- tf_model.h5 +1 -1
README.md
CHANGED
|
@@ -15,8 +15,8 @@ probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
-
- Train Loss:
|
| 19 |
-
- Epoch:
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -42,26 +42,7 @@ The following hyperparameters were used during training:
|
|
| 42 |
|
| 43 |
| Train Loss | Epoch |
|
| 44 |
|:----------:|:-----:|
|
| 45 |
-
|
|
| 46 |
-
| 3.1128 | 1 |
|
| 47 |
-
| 2.9082 | 2 |
|
| 48 |
-
| 2.8046 | 3 |
|
| 49 |
-
| 2.7177 | 4 |
|
| 50 |
-
| 2.6450 | 5 |
|
| 51 |
-
| 2.5715 | 6 |
|
| 52 |
-
| 2.5103 | 7 |
|
| 53 |
-
| 2.4482 | 8 |
|
| 54 |
-
| 2.3980 | 9 |
|
| 55 |
-
| 2.3571 | 10 |
|
| 56 |
-
| 2.3208 | 11 |
|
| 57 |
-
| 2.2912 | 12 |
|
| 58 |
-
| 2.2572 | 13 |
|
| 59 |
-
| 2.2338 | 14 |
|
| 60 |
-
| 2.2119 | 15 |
|
| 61 |
-
| 2.1838 | 16 |
|
| 62 |
-
| 2.1635 | 17 |
|
| 63 |
-
| 2.1428 | 18 |
|
| 64 |
-
| 2.1290 | 19 |
|
| 65 |
|
| 66 |
|
| 67 |
### Framework versions
|
|
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
+
- Train Loss: 6.2910
|
| 19 |
+
- Epoch: 0
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 42 |
|
| 43 |
| Train Loss | Epoch |
|
| 44 |
|:----------:|:-----:|
|
| 45 |
+
| 6.2910 | 0 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
|
| 47 |
|
| 48 |
### Framework versions
|
special_tokens_map.json
CHANGED
|
@@ -1,6 +1,18 @@
|
|
| 1 |
{
|
| 2 |
-
"bos_token":
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"pad_token": {
|
| 5 |
"content": "[PAD]",
|
| 6 |
"lstrip": false,
|
|
@@ -8,5 +20,11 @@
|
|
| 8 |
"rstrip": false,
|
| 9 |
"single_word": false
|
| 10 |
},
|
| 11 |
-
"unk_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
"pad_token": {
|
| 17 |
"content": "[PAD]",
|
| 18 |
"lstrip": false,
|
|
|
|
| 20 |
"rstrip": false,
|
| 21 |
"single_word": false
|
| 22 |
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<|endoftext|>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
}
|
tf_model.h5
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 327748552
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8786b81a6615a44a3cc68f96624f0b268f974263fc8474877ab2fcff4cf4f8ea
|
| 3 |
size 327748552
|