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/mistral-7b-v0.3-bnb-4bit
|
| 3 |
+
library_name: peft
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
tags:
|
| 6 |
+
- unsloth
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
model-index:
|
| 9 |
+
- name: Mistral-7B-v0.3_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 |
+
# Mistral-7B-v0.3_pct_ortho
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [unsloth/mistral-7b-v0.3-bnb-4bit](https://huggingface.co/unsloth/mistral-7b-v0.3-bnb-4bit) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 7.1305
|
| 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 |
+
| 2.145 | 0.0206 | 8 | 2.3112 |
|
| 55 |
+
| 10.5488 | 0.0413 | 16 | 9.3681 |
|
| 56 |
+
| 7.9067 | 0.0619 | 24 | 7.7434 |
|
| 57 |
+
| 7.8557 | 0.0825 | 32 | 7.7804 |
|
| 58 |
+
| 7.7959 | 0.1032 | 40 | 7.6185 |
|
| 59 |
+
| 7.6599 | 0.1238 | 48 | 7.6087 |
|
| 60 |
+
| 7.6244 | 0.1444 | 56 | 7.6251 |
|
| 61 |
+
| 7.5899 | 0.1651 | 64 | 7.7005 |
|
| 62 |
+
| 7.7052 | 0.1857 | 72 | 7.6484 |
|
| 63 |
+
| 7.713 | 0.2063 | 80 | 7.6468 |
|
| 64 |
+
| 7.7653 | 0.2270 | 88 | 7.7124 |
|
| 65 |
+
| 7.7345 | 0.2476 | 96 | 7.6673 |
|
| 66 |
+
| 7.7397 | 0.2682 | 104 | 7.6182 |
|
| 67 |
+
| 7.6695 | 0.2888 | 112 | 7.6591 |
|
| 68 |
+
| 7.6495 | 0.3095 | 120 | 7.6658 |
|
| 69 |
+
| 7.7849 | 0.3301 | 128 | 7.7384 |
|
| 70 |
+
| 7.6106 | 0.3507 | 136 | 7.5564 |
|
| 71 |
+
| 7.6111 | 0.3714 | 144 | 7.6163 |
|
| 72 |
+
| 7.7065 | 0.3920 | 152 | 7.6644 |
|
| 73 |
+
| 7.6184 | 0.4126 | 160 | 7.5686 |
|
| 74 |
+
| 7.616 | 0.4333 | 168 | 7.5656 |
|
| 75 |
+
| 7.5454 | 0.4539 | 176 | 7.5597 |
|
| 76 |
+
| 7.6258 | 0.4745 | 184 | 7.5779 |
|
| 77 |
+
| 7.5473 | 0.4952 | 192 | 7.4016 |
|
| 78 |
+
| 7.2947 | 0.5158 | 200 | 7.2932 |
|
| 79 |
+
| 7.2767 | 0.5364 | 208 | 7.2147 |
|
| 80 |
+
| 7.3113 | 0.5571 | 216 | 7.2121 |
|
| 81 |
+
| 7.259 | 0.5777 | 224 | 7.1758 |
|
| 82 |
+
| 7.0926 | 0.5983 | 232 | 7.1164 |
|
| 83 |
+
| 7.1931 | 0.6190 | 240 | 7.1261 |
|
| 84 |
+
| 7.2239 | 0.6396 | 248 | 7.3268 |
|
| 85 |
+
| 7.3554 | 0.6602 | 256 | 7.1475 |
|
| 86 |
+
| 7.1835 | 0.6809 | 264 | 7.3103 |
|
| 87 |
+
| 7.2527 | 0.7015 | 272 | 7.3083 |
|
| 88 |
+
| 7.2578 | 0.7221 | 280 | 7.0611 |
|
| 89 |
+
| 7.3073 | 0.7427 | 288 | 7.2281 |
|
| 90 |
+
| 7.0778 | 0.7634 | 296 | 7.0481 |
|
| 91 |
+
| 7.196 | 0.7840 | 304 | 7.0595 |
|
| 92 |
+
| 7.194 | 0.8046 | 312 | 7.1102 |
|
| 93 |
+
| 7.1961 | 0.8253 | 320 | 7.1123 |
|
| 94 |
+
| 7.1855 | 0.8459 | 328 | 7.1000 |
|
| 95 |
+
| 7.263 | 0.8665 | 336 | 7.1072 |
|
| 96 |
+
| 7.1925 | 0.8872 | 344 | 7.1302 |
|
| 97 |
+
| 7.1506 | 0.9078 | 352 | 7.1543 |
|
| 98 |
+
| 7.2592 | 0.9284 | 360 | 7.1034 |
|
| 99 |
+
| 7.1493 | 0.9491 | 368 | 7.1163 |
|
| 100 |
+
| 7.2687 | 0.9697 | 376 | 7.1285 |
|
| 101 |
+
| 7.2225 | 0.9903 | 384 | 7.1305 |
|
| 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:e3ec3f3c044ed60e1285bc77132fd2a6a23121f9bd63603f575bf40d90ec5131
|
| 3 |
size 83945296
|