Model save
Browse files- README.md +66 -0
- generation_config.json +6 -0
- trainer_log.jsonl +1 -0
README.md
ADDED
|
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
base_model: MathSymbol/BasicSFT_1.8_Pretrain_Lightning
|
| 4 |
+
tags:
|
| 5 |
+
- llama-factory
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: WordProblem
|
| 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 |
+
# WordProblem
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [MathSymbol/BasicSFT_1.8_Pretrain_Lightning](https://huggingface.co/MathSymbol/BasicSFT_1.8_Pretrain_Lightning) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.1677
|
| 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: 5e-05
|
| 39 |
+
- train_batch_size: 4
|
| 40 |
+
- eval_batch_size: 4
|
| 41 |
+
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 4
|
| 43 |
+
- total_train_batch_size: 16
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: cosine
|
| 46 |
+
- lr_scheduler_warmup_steps: 500
|
| 47 |
+
- num_epochs: 1.0
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 53 |
+
| 0.1923 | 0.1645 | 1500 | 0.1849 |
|
| 54 |
+
| 0.176 | 0.3289 | 3000 | 0.1761 |
|
| 55 |
+
| 0.1736 | 0.4934 | 4500 | 0.1709 |
|
| 56 |
+
| 0.1688 | 0.6579 | 6000 | 0.1682 |
|
| 57 |
+
| 0.1689 | 0.8223 | 7500 | 0.1677 |
|
| 58 |
+
| 0.168 | 0.9868 | 9000 | 0.1677 |
|
| 59 |
+
|
| 60 |
+
|
| 61 |
+
### Framework versions
|
| 62 |
+
|
| 63 |
+
- Transformers 4.40.0
|
| 64 |
+
- Pytorch 2.2.1+cu121
|
| 65 |
+
- Datasets 2.17.1
|
| 66 |
+
- Tokenizers 0.19.1
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"eos_token_id": 151643,
|
| 4 |
+
"max_new_tokens": 2048,
|
| 5 |
+
"transformers_version": "4.40.0"
|
| 6 |
+
}
|
trainer_log.jsonl
CHANGED
|
@@ -34,3 +34,4 @@
|
|
| 34 |
{"current_steps": 8700, "total_steps": 9120, "loss": 0.1741, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.923113370737779e-07, "epoch": 0.9539212192648228, "percentage": 95.39, "elapsed_time": "5:26:22", "remaining_time": "0:15:45"}
|
| 35 |
{"current_steps": 9000, "total_steps": 9120, "loss": 0.168, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.3904986054812396e-08, "epoch": 0.9868150544118857, "percentage": 98.68, "elapsed_time": "5:36:30", "remaining_time": "0:04:29"}
|
| 36 |
{"current_steps": 9000, "total_steps": 9120, "loss": null, "eval_loss": 0.1676628440618515, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 0.9868150544118857, "percentage": 98.68, "elapsed_time": "5:36:30", "remaining_time": "0:04:29"}
|
|
|
|
|
|
| 34 |
{"current_steps": 8700, "total_steps": 9120, "loss": 0.1741, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.923113370737779e-07, "epoch": 0.9539212192648228, "percentage": 95.39, "elapsed_time": "5:26:22", "remaining_time": "0:15:45"}
|
| 35 |
{"current_steps": 9000, "total_steps": 9120, "loss": 0.168, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.3904986054812396e-08, "epoch": 0.9868150544118857, "percentage": 98.68, "elapsed_time": "5:36:30", "remaining_time": "0:04:29"}
|
| 36 |
{"current_steps": 9000, "total_steps": 9120, "loss": null, "eval_loss": 0.1676628440618515, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 0.9868150544118857, "percentage": 98.68, "elapsed_time": "5:36:30", "remaining_time": "0:04:29"}
|
| 37 |
+
{"current_steps": 9120, "total_steps": 9120, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 0.9999725884707108, "percentage": 100.0, "elapsed_time": "5:43:04", "remaining_time": "0:00:00"}
|