Model save
Browse files- README.md +77 -0
- generation_config.json +6 -0
- pytorch_model.bin +1 -1
README.md
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: gpt2
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: gpt2-XYZCompany-1000-steps
|
| 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 |
+
# gpt2-XYZCompany-1000-steps
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.3082
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 1e-05
|
| 38 |
+
- train_batch_size: 8
|
| 39 |
+
- eval_batch_size: 4
|
| 40 |
+
- seed: 42
|
| 41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
+
- lr_scheduler_type: linear
|
| 43 |
+
- lr_scheduler_warmup_steps: 1
|
| 44 |
+
- training_steps: 1000
|
| 45 |
+
|
| 46 |
+
### Training results
|
| 47 |
+
|
| 48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 49 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 50 |
+
| 0.4688 | 0.32 | 50 | 0.4117 |
|
| 51 |
+
| 0.4546 | 0.63 | 100 | 0.3712 |
|
| 52 |
+
| 0.3868 | 0.95 | 150 | 0.3539 |
|
| 53 |
+
| 0.369 | 1.27 | 200 | 0.3427 |
|
| 54 |
+
| 0.3572 | 1.58 | 250 | 0.3357 |
|
| 55 |
+
| 0.344 | 1.9 | 300 | 0.3301 |
|
| 56 |
+
| 0.343 | 2.22 | 350 | 0.3258 |
|
| 57 |
+
| 0.348 | 2.53 | 400 | 0.3227 |
|
| 58 |
+
| 0.3431 | 2.85 | 450 | 0.3194 |
|
| 59 |
+
| 0.2994 | 3.16 | 500 | 0.3169 |
|
| 60 |
+
| 0.3348 | 3.48 | 550 | 0.3155 |
|
| 61 |
+
| 0.3177 | 3.8 | 600 | 0.3134 |
|
| 62 |
+
| 0.32 | 4.11 | 650 | 0.3125 |
|
| 63 |
+
| 0.318 | 4.43 | 700 | 0.3111 |
|
| 64 |
+
| 0.3448 | 4.75 | 750 | 0.3102 |
|
| 65 |
+
| 0.2903 | 5.06 | 800 | 0.3094 |
|
| 66 |
+
| 0.3078 | 5.38 | 850 | 0.3088 |
|
| 67 |
+
| 0.2993 | 5.7 | 900 | 0.3085 |
|
| 68 |
+
| 0.3132 | 6.01 | 950 | 0.3083 |
|
| 69 |
+
| 0.3262 | 6.33 | 1000 | 0.3082 |
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
### Framework versions
|
| 73 |
+
|
| 74 |
+
- Transformers 4.32.1
|
| 75 |
+
- Pytorch 2.1.2
|
| 76 |
+
- Datasets 2.17.1
|
| 77 |
+
- Tokenizers 0.13.2
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.32.1"
|
| 6 |
+
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 497807706
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca7fcb6e1029532c48b34606ae7ddf0a2c0fcc0522946c4a317869e257e22fb1
|
| 3 |
size 497807706
|