End of training
Browse files- README.md +110 -0
- adapter_model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: unsloth/llama-3-8b-bnb-4bit
|
| 3 |
+
library_name: peft
|
| 4 |
+
license: llama3
|
| 5 |
+
tags:
|
| 6 |
+
- unsloth
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
model-index:
|
| 9 |
+
- name: Meta-Llama-3-8B_pct_ortho
|
| 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 |
+
# Meta-Llama-3-8B_pct_ortho
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [unsloth/llama-3-8b-bnb-4bit](https://huggingface.co/unsloth/llama-3-8b-bnb-4bit) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 2.2409
|
| 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: 0.0003
|
| 40 |
+
- train_batch_size: 8
|
| 41 |
+
- eval_batch_size: 8
|
| 42 |
+
- seed: 42
|
| 43 |
+
- gradient_accumulation_steps: 8
|
| 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: 0.02
|
| 48 |
+
- num_epochs: 1
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 54 |
+
| 2.3045 | 0.0206 | 8 | 2.2825 |
|
| 55 |
+
| 2.2746 | 0.0412 | 16 | 2.2479 |
|
| 56 |
+
| 2.2264 | 0.0618 | 24 | 2.2587 |
|
| 57 |
+
| 2.3001 | 0.0824 | 32 | 2.2813 |
|
| 58 |
+
| 2.3006 | 0.1030 | 40 | 2.2798 |
|
| 59 |
+
| 2.2719 | 0.1236 | 48 | 2.2780 |
|
| 60 |
+
| 2.2942 | 0.1442 | 56 | 2.2881 |
|
| 61 |
+
| 2.314 | 0.1648 | 64 | 2.2993 |
|
| 62 |
+
| 2.2747 | 0.1854 | 72 | 2.3101 |
|
| 63 |
+
| 2.3086 | 0.2060 | 80 | 2.3069 |
|
| 64 |
+
| 2.3318 | 0.2266 | 88 | 2.2899 |
|
| 65 |
+
| 2.3957 | 0.2472 | 96 | 2.3000 |
|
| 66 |
+
| 2.3704 | 0.2678 | 104 | 2.2998 |
|
| 67 |
+
| 2.3319 | 0.2884 | 112 | 2.3124 |
|
| 68 |
+
| 2.3908 | 0.3090 | 120 | 2.3099 |
|
| 69 |
+
| 2.3865 | 0.3296 | 128 | 2.3063 |
|
| 70 |
+
| 2.3306 | 0.3502 | 136 | 2.2947 |
|
| 71 |
+
| 2.326 | 0.3708 | 144 | 2.2973 |
|
| 72 |
+
| 2.3421 | 0.3914 | 152 | 2.2987 |
|
| 73 |
+
| 2.3277 | 0.4120 | 160 | 2.2820 |
|
| 74 |
+
| 2.3739 | 0.4326 | 168 | 2.2931 |
|
| 75 |
+
| 2.3157 | 0.4532 | 176 | 2.2898 |
|
| 76 |
+
| 2.3296 | 0.4738 | 184 | 2.2915 |
|
| 77 |
+
| 2.3274 | 0.4944 | 192 | 2.2818 |
|
| 78 |
+
| 2.3225 | 0.5150 | 200 | 2.2861 |
|
| 79 |
+
| 2.3181 | 0.5356 | 208 | 2.2817 |
|
| 80 |
+
| 2.3393 | 0.5562 | 216 | 2.2708 |
|
| 81 |
+
| 2.3276 | 0.5768 | 224 | 2.2763 |
|
| 82 |
+
| 2.3053 | 0.5974 | 232 | 2.2791 |
|
| 83 |
+
| 2.2739 | 0.6180 | 240 | 2.2721 |
|
| 84 |
+
| 2.311 | 0.6386 | 248 | 2.2749 |
|
| 85 |
+
| 2.3049 | 0.6592 | 256 | 2.2706 |
|
| 86 |
+
| 2.2615 | 0.6798 | 264 | 2.2703 |
|
| 87 |
+
| 2.312 | 0.7004 | 272 | 2.2633 |
|
| 88 |
+
| 2.3017 | 0.7210 | 280 | 2.2594 |
|
| 89 |
+
| 2.3066 | 0.7416 | 288 | 2.2572 |
|
| 90 |
+
| 2.2966 | 0.7621 | 296 | 2.2579 |
|
| 91 |
+
| 2.3375 | 0.7827 | 304 | 2.2461 |
|
| 92 |
+
| 2.2704 | 0.8033 | 312 | 2.2474 |
|
| 93 |
+
| 2.2512 | 0.8239 | 320 | 2.2496 |
|
| 94 |
+
| 2.2834 | 0.8445 | 328 | 2.2431 |
|
| 95 |
+
| 2.2962 | 0.8651 | 336 | 2.2452 |
|
| 96 |
+
| 2.3071 | 0.8857 | 344 | 2.2405 |
|
| 97 |
+
| 2.2739 | 0.9063 | 352 | 2.2401 |
|
| 98 |
+
| 2.2437 | 0.9269 | 360 | 2.2435 |
|
| 99 |
+
| 2.2634 | 0.9475 | 368 | 2.2417 |
|
| 100 |
+
| 2.3116 | 0.9681 | 376 | 2.2406 |
|
| 101 |
+
| 2.2995 | 0.9887 | 384 | 2.2409 |
|
| 102 |
+
|
| 103 |
+
|
| 104 |
+
### Framework versions
|
| 105 |
+
|
| 106 |
+
- PEFT 0.12.0
|
| 107 |
+
- Transformers 4.44.0
|
| 108 |
+
- Pytorch 2.4.0+cu121
|
| 109 |
+
- Datasets 2.20.0
|
| 110 |
+
- Tokenizers 0.19.1
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 83945296
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ae76ae65c942a15113e73d966e353cab9c89c35fa94309d704cb304445557623
|
| 3 |
size 83945296
|