update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
model-index:
|
| 5 |
+
- name: alpaca-lora-65b-en-pt-es-ca
|
| 6 |
+
results: []
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 10 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 11 |
+
|
| 12 |
+
# alpaca-lora-65b-en-pt-es-ca
|
| 13 |
+
|
| 14 |
+
This model was trained from scratch on the None dataset.
|
| 15 |
+
It achieves the following results on the evaluation set:
|
| 16 |
+
- Loss: 0.7271
|
| 17 |
+
|
| 18 |
+
## Model description
|
| 19 |
+
|
| 20 |
+
More information needed
|
| 21 |
+
|
| 22 |
+
## Intended uses & limitations
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Training and evaluation data
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training procedure
|
| 31 |
+
|
| 32 |
+
### Training hyperparameters
|
| 33 |
+
|
| 34 |
+
The following hyperparameters were used during training:
|
| 35 |
+
- learning_rate: 0.0003
|
| 36 |
+
- train_batch_size: 1
|
| 37 |
+
- eval_batch_size: 1
|
| 38 |
+
- seed: 42
|
| 39 |
+
- distributed_type: multi-GPU
|
| 40 |
+
- num_devices: 2
|
| 41 |
+
- gradient_accumulation_steps: 63
|
| 42 |
+
- total_train_batch_size: 126
|
| 43 |
+
- total_eval_batch_size: 2
|
| 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: 1
|
| 48 |
+
- mixed_precision_training: Native AMP
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 54 |
+
| 0.8069 | 0.06 | 100 | 0.8033 |
|
| 55 |
+
| 0.8008 | 0.13 | 200 | 0.7826 |
|
| 56 |
+
| 0.7687 | 0.19 | 300 | 0.7721 |
|
| 57 |
+
| 0.7719 | 0.25 | 400 | 0.7647 |
|
| 58 |
+
| 0.7585 | 0.32 | 500 | 0.7588 |
|
| 59 |
+
| 0.7578 | 0.38 | 600 | 0.7537 |
|
| 60 |
+
| 0.7505 | 0.44 | 700 | 0.7491 |
|
| 61 |
+
| 0.7531 | 0.51 | 800 | 0.7449 |
|
| 62 |
+
| 0.7394 | 0.57 | 900 | 0.7416 |
|
| 63 |
+
| 0.7368 | 0.63 | 1000 | 0.7387 |
|
| 64 |
+
| 0.7412 | 0.69 | 1100 | 0.7361 |
|
| 65 |
+
| 0.7344 | 0.76 | 1200 | 0.7288 |
|
| 66 |
+
| 0.7383 | 0.82 | 1300 | 0.7281 |
|
| 67 |
+
| 0.7378 | 0.88 | 1400 | 0.7274 |
|
| 68 |
+
| 0.7204 | 0.95 | 1500 | 0.7271 |
|
| 69 |
+
|
| 70 |
+
|
| 71 |
+
### Framework versions
|
| 72 |
+
|
| 73 |
+
- Transformers 4.28.0.dev0
|
| 74 |
+
- Pytorch 2.0.0+cu117
|
| 75 |
+
- Datasets 2.10.1
|
| 76 |
+
- Tokenizers 0.13.2
|