End of training
Browse files- README.md +102 -0
- generation_config.json +6 -0
README.md
ADDED
|
@@ -0,0 +1,102 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: train-bioR-concat
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# train-bioR-concat
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 1.6559
|
| 18 |
+
|
| 19 |
+
## Model description
|
| 20 |
+
|
| 21 |
+
More information needed
|
| 22 |
+
|
| 23 |
+
## Intended uses & limitations
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Training and evaluation data
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training procedure
|
| 32 |
+
|
| 33 |
+
### Training hyperparameters
|
| 34 |
+
|
| 35 |
+
The following hyperparameters were used during training:
|
| 36 |
+
- learning_rate: 0.001
|
| 37 |
+
- train_batch_size: 24
|
| 38 |
+
- eval_batch_size: 24
|
| 39 |
+
- seed: 42
|
| 40 |
+
- distributed_type: multi-GPU
|
| 41 |
+
- num_devices: 4
|
| 42 |
+
- total_train_batch_size: 96
|
| 43 |
+
- total_eval_batch_size: 96
|
| 44 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-06 and optimizer_args=No additional optimizer arguments
|
| 45 |
+
- lr_scheduler_type: cosine
|
| 46 |
+
- lr_scheduler_warmup_steps: 1000
|
| 47 |
+
- training_steps: 41803
|
| 48 |
+
- mixed_precision_training: Native AMP
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
+
|:-------------:|:------:|:-----:|:---------------:|
|
| 54 |
+
| 1.2076 | 0.0239 | 1000 | 1.8223 |
|
| 55 |
+
| 1.2901 | 0.0478 | 2000 | 1.8245 |
|
| 56 |
+
| 1.1528 | 0.0718 | 3000 | 1.8674 |
|
| 57 |
+
| 1.0056 | 0.0957 | 4000 | 1.9692 |
|
| 58 |
+
| 0.8399 | 0.1196 | 5000 | 2.0165 |
|
| 59 |
+
| 0.7892 | 0.1435 | 6000 | 1.9441 |
|
| 60 |
+
| 0.7658 | 0.1674 | 7000 | 1.8904 |
|
| 61 |
+
| 0.7284 | 0.1914 | 8000 | 1.8260 |
|
| 62 |
+
| 0.7217 | 0.2153 | 9000 | 1.8162 |
|
| 63 |
+
| 0.7122 | 0.2392 | 10000 | 1.7559 |
|
| 64 |
+
| 0.7055 | 0.2631 | 11000 | 1.7974 |
|
| 65 |
+
| 0.6943 | 0.2871 | 12000 | 1.7621 |
|
| 66 |
+
| 0.6942 | 0.3110 | 13000 | 1.7651 |
|
| 67 |
+
| 0.6868 | 0.3349 | 14000 | 1.7228 |
|
| 68 |
+
| 0.6817 | 0.3588 | 15000 | 1.7558 |
|
| 69 |
+
| 0.6911 | 0.3827 | 16000 | 1.7466 |
|
| 70 |
+
| 0.6889 | 0.4067 | 17000 | 1.7291 |
|
| 71 |
+
| 0.6798 | 0.4306 | 18000 | 1.6921 |
|
| 72 |
+
| 0.675 | 0.4545 | 19000 | 1.7139 |
|
| 73 |
+
| 0.6779 | 0.4784 | 20000 | 1.6933 |
|
| 74 |
+
| 0.6851 | 0.5023 | 21000 | 1.7136 |
|
| 75 |
+
| 0.675 | 0.5263 | 22000 | 1.6874 |
|
| 76 |
+
| 0.6747 | 0.5502 | 23000 | 1.6950 |
|
| 77 |
+
| 0.6724 | 0.5741 | 24000 | 1.6884 |
|
| 78 |
+
| 0.6631 | 0.5980 | 25000 | 1.6873 |
|
| 79 |
+
| 0.6671 | 0.6220 | 26000 | 1.6983 |
|
| 80 |
+
| 0.6645 | 0.6459 | 27000 | 1.6729 |
|
| 81 |
+
| 0.658 | 0.6698 | 28000 | 1.6809 |
|
| 82 |
+
| 0.6605 | 0.6937 | 29000 | 1.6656 |
|
| 83 |
+
| 0.6599 | 0.7176 | 30000 | 1.6704 |
|
| 84 |
+
| 0.6591 | 0.7416 | 31000 | 1.6679 |
|
| 85 |
+
| 0.6664 | 0.7655 | 32000 | 1.6555 |
|
| 86 |
+
| 0.6608 | 0.7894 | 33000 | 1.6487 |
|
| 87 |
+
| 0.6609 | 0.8133 | 34000 | 1.6522 |
|
| 88 |
+
| 0.6553 | 0.8372 | 35000 | 1.6502 |
|
| 89 |
+
| 0.6527 | 0.8612 | 36000 | 1.6568 |
|
| 90 |
+
| 0.6648 | 0.8851 | 37000 | 1.6587 |
|
| 91 |
+
| 0.6515 | 0.9090 | 38000 | 1.6471 |
|
| 92 |
+
| 0.65 | 0.9329 | 39000 | 1.6461 |
|
| 93 |
+
| 0.65 | 0.9568 | 40000 | 1.6499 |
|
| 94 |
+
| 0.6533 | 0.9808 | 41000 | 1.6559 |
|
| 95 |
+
|
| 96 |
+
|
| 97 |
+
### Framework versions
|
| 98 |
+
|
| 99 |
+
- Transformers 4.47.0
|
| 100 |
+
- Pytorch 2.5.1+cu124
|
| 101 |
+
- Datasets 3.2.0
|
| 102 |
+
- Tokenizers 0.21.0
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.47.0"
|
| 6 |
+
}
|