Commit
•
4f1e81d
1
Parent(s):
34d87b0
gpt2_bwgenerator
Browse files- README.md +1 -0
- config.json +1 -1
- model.safetensors +2 -2
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -38,6 +38,7 @@ The following hyperparameters were used during training:
|
|
| 38 |
- seed: 42
|
| 39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 40 |
- lr_scheduler_type: linear
|
|
|
|
| 41 |
- num_epochs: 3
|
| 42 |
|
| 43 |
### Training results
|
|
|
|
| 38 |
- seed: 42
|
| 39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 40 |
- lr_scheduler_type: linear
|
| 41 |
+
- lr_scheduler_warmup_steps: 500
|
| 42 |
- num_epochs: 3
|
| 43 |
|
| 44 |
### Training results
|
config.json
CHANGED
|
@@ -32,7 +32,7 @@
|
|
| 32 |
"max_length": 50
|
| 33 |
}
|
| 34 |
},
|
| 35 |
-
"torch_dtype": "
|
| 36 |
"transformers_version": "4.42.0.dev0",
|
| 37 |
"use_cache": true,
|
| 38 |
"vocab_size": 50258
|
|
|
|
| 32 |
"max_length": 50
|
| 33 |
}
|
| 34 |
},
|
| 35 |
+
"torch_dtype": "float32",
|
| 36 |
"transformers_version": "4.42.0.dev0",
|
| 37 |
"use_cache": true,
|
| 38 |
"vocab_size": 50258
|
model.safetensors
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:b125200facddcacb0560e74a36faa910c38bee96d7439902b1de98434074faf3
|
| 3 |
+
size 497777280
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5240
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:686122882de32cd942df01132c836caa072c880ce5b7b21c8b6ebb1da9e98959
|
| 3 |
size 5240
|