End of training
Browse files- README.md +73 -0
- generation_config.json +6 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: gpt2
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: sft_cml4
|
| 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 |
+
# sft_cml4
|
| 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: 3.6611
|
| 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: 0.0005
|
| 38 |
+
- train_batch_size: 3
|
| 39 |
+
- eval_batch_size: 8
|
| 40 |
+
- seed: 42
|
| 41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
+
- lr_scheduler_type: cosine
|
| 43 |
+
- num_epochs: 2
|
| 44 |
+
- mixed_precision_training: Native AMP
|
| 45 |
+
|
| 46 |
+
### Training results
|
| 47 |
+
|
| 48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 49 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 50 |
+
| 4.1822 | 0.1200 | 200 | 3.9880 |
|
| 51 |
+
| 3.9009 | 0.2400 | 400 | 3.9248 |
|
| 52 |
+
| 3.7846 | 0.3599 | 600 | 3.9328 |
|
| 53 |
+
| 3.7095 | 0.4799 | 800 | 3.8393 |
|
| 54 |
+
| 3.5043 | 0.5999 | 1000 | 3.8130 |
|
| 55 |
+
| 3.4826 | 0.7199 | 1200 | 3.7608 |
|
| 56 |
+
| 3.3511 | 0.8398 | 1400 | 3.6997 |
|
| 57 |
+
| 3.3243 | 0.9598 | 1600 | 3.6349 |
|
| 58 |
+
| 2.5235 | 1.0798 | 1800 | 3.7826 |
|
| 59 |
+
| 2.0758 | 1.1998 | 2000 | 3.7627 |
|
| 60 |
+
| 2.0932 | 1.3197 | 2200 | 3.7233 |
|
| 61 |
+
| 1.9962 | 1.4397 | 2400 | 3.7059 |
|
| 62 |
+
| 2.0072 | 1.5597 | 2600 | 3.6756 |
|
| 63 |
+
| 1.9642 | 1.6797 | 2800 | 3.6801 |
|
| 64 |
+
| 1.9062 | 1.7996 | 3000 | 3.6658 |
|
| 65 |
+
| 1.9279 | 1.9196 | 3200 | 3.6611 |
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
### Framework versions
|
| 69 |
+
|
| 70 |
+
- Transformers 4.40.0
|
| 71 |
+
- Pytorch 2.2.2+cu118
|
| 72 |
+
- Datasets 2.19.0
|
| 73 |
+
- Tokenizers 0.19.1
|
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": "4.40.0"
|
| 6 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 497774208
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3163b3b5df3cf48f512ef5a6b27d9e833b3db422ebe74e544fe25e3f839b0cf
|
| 3 |
size 497774208
|