Model save
Browse files- README.md +81 -0
- generation_config.json +9 -0
README.md
ADDED
|
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: llama3.2
|
| 3 |
+
base_model: meta-llama/Llama-3.2-1B
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: quality-lr5e-06-rr0.1-epochs2-bs16-wd0.01-warmup0.05-Llama3.21B
|
| 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 |
+
# quality-lr5e-06-rr0.1-epochs2-bs16-wd0.01-warmup0.05-Llama3.21B
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 2.4583
|
| 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: 5e-06
|
| 38 |
+
- train_batch_size: 1
|
| 39 |
+
- eval_batch_size: 3
|
| 40 |
+
- seed: 42
|
| 41 |
+
- distributed_type: multi-GPU
|
| 42 |
+
- num_devices: 8
|
| 43 |
+
- gradient_accumulation_steps: 2
|
| 44 |
+
- total_train_batch_size: 16
|
| 45 |
+
- total_eval_batch_size: 24
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: cosine
|
| 48 |
+
- lr_scheduler_warmup_ratio: 0.05
|
| 49 |
+
- num_epochs: 2.0
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 54 |
+
|:-------------:|:------:|:-----:|:---------------:|
|
| 55 |
+
| 1.3438 | 0.1000 | 1372 | 2.4412 |
|
| 56 |
+
| 1.3308 | 0.2001 | 2744 | 2.4745 |
|
| 57 |
+
| 1.1389 | 0.3001 | 4116 | 2.4700 |
|
| 58 |
+
| 1.0742 | 0.4001 | 5488 | 2.4735 |
|
| 59 |
+
| 1.2025 | 0.5002 | 6860 | 2.4791 |
|
| 60 |
+
| 0.9616 | 0.6002 | 8232 | 2.4880 |
|
| 61 |
+
| 1.0427 | 0.7002 | 9604 | 2.4838 |
|
| 62 |
+
| 1.021 | 0.8003 | 10976 | 2.4824 |
|
| 63 |
+
| 0.9657 | 0.9003 | 12348 | 2.4816 |
|
| 64 |
+
| 0.9601 | 1.0003 | 13720 | 2.4775 |
|
| 65 |
+
| 0.9308 | 1.1004 | 15092 | 2.4743 |
|
| 66 |
+
| 0.9075 | 1.2004 | 16464 | 2.4721 |
|
| 67 |
+
| 0.9257 | 1.3004 | 17836 | 2.4684 |
|
| 68 |
+
| 0.9466 | 1.4005 | 19208 | 2.4655 |
|
| 69 |
+
| 1.9584 | 1.5005 | 20580 | 2.4628 |
|
| 70 |
+
| 0.8827 | 1.6005 | 21952 | 2.4609 |
|
| 71 |
+
| 0.9602 | 1.7006 | 23324 | 2.4596 |
|
| 72 |
+
| 0.9366 | 1.8006 | 24696 | 2.4587 |
|
| 73 |
+
| 0.87 | 1.9006 | 26068 | 2.4583 |
|
| 74 |
+
|
| 75 |
+
|
| 76 |
+
### Framework versions
|
| 77 |
+
|
| 78 |
+
- Transformers 4.43.3
|
| 79 |
+
- Pytorch 2.3.1+cu118
|
| 80 |
+
- Datasets 2.20.0
|
| 81 |
+
- Tokenizers 0.19.1
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 128000,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": 128001,
|
| 6 |
+
"temperature": 0.6,
|
| 7 |
+
"top_p": 0.9,
|
| 8 |
+
"transformers_version": "4.43.3"
|
| 9 |
+
}
|