aes_sft
Browse files- README.md +90 -0
- generation_config.json +9 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,90 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: llama3.2
|
| 4 |
+
base_model: meta-llama/Llama-3.2-1B
|
| 5 |
+
tags:
|
| 6 |
+
- trl
|
| 7 |
+
- sft
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: rationale_model_e15
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# rationale_model_e15
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 2.1070
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 5e-05
|
| 41 |
+
- train_batch_size: 8
|
| 42 |
+
- eval_batch_size: 8
|
| 43 |
+
- seed: 42
|
| 44 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- num_epochs: 3.0
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 51 |
+
|:-------------:|:------:|:-----:|:---------------:|
|
| 52 |
+
| 2.1363 | 0.0954 | 500 | 2.1185 |
|
| 53 |
+
| 1.7868 | 0.1908 | 1000 | 2.1070 |
|
| 54 |
+
| 1.5132 | 0.2862 | 1500 | 2.1743 |
|
| 55 |
+
| 1.238 | 0.3815 | 2000 | 2.2694 |
|
| 56 |
+
| 0.9723 | 0.4769 | 2500 | 2.3214 |
|
| 57 |
+
| 0.7249 | 0.5723 | 3000 | 2.4423 |
|
| 58 |
+
| 0.5657 | 0.6677 | 3500 | 2.5636 |
|
| 59 |
+
| 0.4404 | 0.7631 | 4000 | 2.6851 |
|
| 60 |
+
| 0.3192 | 0.8585 | 4500 | 2.8630 |
|
| 61 |
+
| 0.2676 | 0.9538 | 5000 | 2.9741 |
|
| 62 |
+
| 0.2057 | 1.0492 | 5500 | 3.0958 |
|
| 63 |
+
| 0.1792 | 1.1446 | 6000 | 3.1219 |
|
| 64 |
+
| 0.1691 | 1.2400 | 6500 | 3.1735 |
|
| 65 |
+
| 0.1597 | 1.3354 | 7000 | 3.2299 |
|
| 66 |
+
| 0.1516 | 1.4308 | 7500 | 3.2997 |
|
| 67 |
+
| 0.1422 | 1.5261 | 8000 | 3.2759 |
|
| 68 |
+
| 0.1372 | 1.6215 | 8500 | 3.3557 |
|
| 69 |
+
| 0.1301 | 1.7169 | 9000 | 3.4023 |
|
| 70 |
+
| 0.1229 | 1.8123 | 9500 | 3.4617 |
|
| 71 |
+
| 0.1183 | 1.9077 | 10000 | 3.4668 |
|
| 72 |
+
| 0.1119 | 2.0031 | 10500 | 3.5609 |
|
| 73 |
+
| 0.0924 | 2.0984 | 11000 | 3.5975 |
|
| 74 |
+
| 0.0926 | 2.1938 | 11500 | 3.6429 |
|
| 75 |
+
| 0.089 | 2.2892 | 12000 | 3.6586 |
|
| 76 |
+
| 0.0881 | 2.3846 | 12500 | 3.6920 |
|
| 77 |
+
| 0.0861 | 2.4800 | 13000 | 3.7656 |
|
| 78 |
+
| 0.0835 | 2.5754 | 13500 | 3.7939 |
|
| 79 |
+
| 0.0803 | 2.6707 | 14000 | 3.8398 |
|
| 80 |
+
| 0.0797 | 2.7661 | 14500 | 3.8909 |
|
| 81 |
+
| 0.0774 | 2.8615 | 15000 | 3.9238 |
|
| 82 |
+
| 0.0759 | 2.9569 | 15500 | 3.9394 |
|
| 83 |
+
|
| 84 |
+
|
| 85 |
+
### Framework versions
|
| 86 |
+
|
| 87 |
+
- Transformers 4.46.3
|
| 88 |
+
- Pytorch 2.3.0
|
| 89 |
+
- Datasets 2.14.4
|
| 90 |
+
- Tokenizers 0.20.3
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 128000,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": 128001,
|
| 6 |
+
"temperature": 0.6,
|
| 7 |
+
"top_p": 0.9,
|
| 8 |
+
"transformers_version": "4.46.3"
|
| 9 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4943274328
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:364b6daf953c4e2d4b47ff91c1e6b06855bd5e212ca9fde3395e4355c5775740
|
| 3 |
size 4943274328
|