Training complete 2025-11-07 18:55:49
Browse files- README.md +80 -0
- generation_config.json +10 -0
README.md
ADDED
|
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: tinyllama-lora-fast
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# tinyllama-lora-fast
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.8744
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 3e-05
|
| 39 |
+
- train_batch_size: 2
|
| 40 |
+
- eval_batch_size: 2
|
| 41 |
+
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 2
|
| 43 |
+
- total_train_batch_size: 4
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: cosine
|
| 46 |
+
- lr_scheduler_warmup_ratio: 0.03
|
| 47 |
+
- num_epochs: 2
|
| 48 |
+
- mixed_precision_training: Native AMP
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 54 |
+
| 1.0752 | 0.1111 | 200 | 1.0674 |
|
| 55 |
+
| 1.0248 | 0.2222 | 400 | 1.0167 |
|
| 56 |
+
| 0.9839 | 0.3333 | 600 | 0.9843 |
|
| 57 |
+
| 0.9479 | 0.4444 | 800 | 0.9620 |
|
| 58 |
+
| 0.9478 | 0.5556 | 1000 | 0.9457 |
|
| 59 |
+
| 0.914 | 0.6667 | 1200 | 0.9318 |
|
| 60 |
+
| 0.9329 | 0.7778 | 1400 | 0.9182 |
|
| 61 |
+
| 0.8929 | 0.8889 | 1600 | 0.9104 |
|
| 62 |
+
| 0.911 | 1.0 | 1800 | 0.9005 |
|
| 63 |
+
| 0.869 | 1.1111 | 2000 | 0.8949 |
|
| 64 |
+
| 0.8873 | 1.2222 | 2200 | 0.8892 |
|
| 65 |
+
| 0.8551 | 1.3333 | 2400 | 0.8848 |
|
| 66 |
+
| 0.8543 | 1.4444 | 2600 | 0.8812 |
|
| 67 |
+
| 0.8741 | 1.5556 | 2800 | 0.8779 |
|
| 68 |
+
| 0.8652 | 1.6667 | 3000 | 0.8760 |
|
| 69 |
+
| 0.8534 | 1.7778 | 3200 | 0.8751 |
|
| 70 |
+
| 0.8378 | 1.8889 | 3400 | 0.8745 |
|
| 71 |
+
| 0.8514 | 2.0 | 3600 | 0.8744 |
|
| 72 |
+
|
| 73 |
+
|
| 74 |
+
### Framework versions
|
| 75 |
+
|
| 76 |
+
- PEFT 0.12.0
|
| 77 |
+
- Transformers 4.45.2
|
| 78 |
+
- Pytorch 2.6.0+cu124
|
| 79 |
+
- Datasets 4.1.1
|
| 80 |
+
- Tokenizers 0.20.3
|
generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"max_new_tokens": 512,
|
| 3 |
+
"temperature": 0.0,
|
| 4 |
+
"do_sample": false,
|
| 5 |
+
"top_p": 0.9,
|
| 6 |
+
"repetition_penalty": 1.1,
|
| 7 |
+
"no_repeat_ngram_size": 4,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"pad_token_id": 2
|
| 10 |
+
}
|