End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: ybelkada/falcon-7b-sharded-bf16
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- sft
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
model-index:
|
| 9 |
+
- name: falcon-7b-sharded-bf16-finetuned-mental-health-dsm5mistral
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# falcon-7b-sharded-bf16-finetuned-mental-health-dsm5mistral
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [ybelkada/falcon-7b-sharded-bf16](https://huggingface.co/ybelkada/falcon-7b-sharded-bf16) on the None dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 1.7448
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 0.0002
|
| 40 |
+
- train_batch_size: 16
|
| 41 |
+
- eval_batch_size: 16
|
| 42 |
+
- seed: 42
|
| 43 |
+
- gradient_accumulation_steps: 4
|
| 44 |
+
- total_train_batch_size: 64
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: cosine
|
| 47 |
+
- lr_scheduler_warmup_ratio: 0.03
|
| 48 |
+
- training_steps: 200
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 54 |
+
| 2.1353 | 0.1028 | 10 | 2.2214 |
|
| 55 |
+
| 2.2465 | 0.2057 | 20 | 2.1292 |
|
| 56 |
+
| 1.8446 | 0.3085 | 30 | 2.0584 |
|
| 57 |
+
| 1.9796 | 0.4113 | 40 | 1.9319 |
|
| 58 |
+
| 1.6682 | 0.5141 | 50 | 2.1183 |
|
| 59 |
+
| 1.9888 | 0.6170 | 60 | 1.8794 |
|
| 60 |
+
| 1.7142 | 0.7198 | 70 | 1.8562 |
|
| 61 |
+
| 1.8108 | 0.8226 | 80 | 1.8650 |
|
| 62 |
+
| 1.7122 | 0.9254 | 90 | 1.8313 |
|
| 63 |
+
| 1.5926 | 1.0283 | 100 | 1.8228 |
|
| 64 |
+
| 1.6881 | 1.1311 | 110 | 1.8095 |
|
| 65 |
+
| 1.4018 | 1.2339 | 120 | 1.8231 |
|
| 66 |
+
| 1.7688 | 1.3368 | 130 | 1.7767 |
|
| 67 |
+
| 1.4843 | 1.4396 | 140 | 1.7667 |
|
| 68 |
+
| 1.5288 | 1.5424 | 150 | 1.7607 |
|
| 69 |
+
| 1.5946 | 1.6452 | 160 | 1.7498 |
|
| 70 |
+
| 1.3308 | 1.7481 | 170 | 1.7463 |
|
| 71 |
+
| 1.6712 | 1.8509 | 180 | 1.7454 |
|
| 72 |
+
| 1.3342 | 1.9537 | 190 | 1.7449 |
|
| 73 |
+
| 1.5714 | 2.0566 | 200 | 1.7448 |
|
| 74 |
+
|
| 75 |
+
|
| 76 |
+
### Framework versions
|
| 77 |
+
|
| 78 |
+
- PEFT 0.13.1.dev0
|
| 79 |
+
- Transformers 4.45.1
|
| 80 |
+
- Pytorch 2.4.1+cu121
|
| 81 |
+
- Datasets 3.0.1
|
| 82 |
+
- Tokenizers 0.20.0
|