End of training
Browse files- README.md +100 -0
- adapter_model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,100 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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_magiccoder_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_magiccoder_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: 7.8233
|
| 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: 0.0001
|
| 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 |
+
| 4.7819 | 0.0262 | 4 | 5.1512 |
|
| 55 |
+
| 9.2164 | 0.0523 | 8 | 8.3377 |
|
| 56 |
+
| 8.1082 | 0.0785 | 12 | 8.9375 |
|
| 57 |
+
| 9.0762 | 0.1047 | 16 | 8.3063 |
|
| 58 |
+
| 8.2007 | 0.1308 | 20 | 8.0203 |
|
| 59 |
+
| 8.168 | 0.1570 | 24 | 8.2340 |
|
| 60 |
+
| 7.8692 | 0.1832 | 28 | 7.8876 |
|
| 61 |
+
| 7.8831 | 0.2093 | 32 | 7.8978 |
|
| 62 |
+
| 7.7946 | 0.2355 | 36 | 7.8117 |
|
| 63 |
+
| 7.8717 | 0.2617 | 40 | 7.8140 |
|
| 64 |
+
| 7.9497 | 0.2878 | 44 | 7.9363 |
|
| 65 |
+
| 8.0978 | 0.3140 | 48 | 7.9038 |
|
| 66 |
+
| 7.8654 | 0.3401 | 52 | 7.8165 |
|
| 67 |
+
| 7.8036 | 0.3663 | 56 | 7.8578 |
|
| 68 |
+
| 7.8264 | 0.3925 | 60 | 7.8504 |
|
| 69 |
+
| 7.8333 | 0.4186 | 64 | 7.8426 |
|
| 70 |
+
| 7.8526 | 0.4448 | 68 | 7.8285 |
|
| 71 |
+
| 7.802 | 0.4710 | 72 | 7.7864 |
|
| 72 |
+
| 7.8376 | 0.4971 | 76 | 7.8583 |
|
| 73 |
+
| 7.8992 | 0.5233 | 80 | 7.8449 |
|
| 74 |
+
| 7.8557 | 0.5495 | 84 | 7.8771 |
|
| 75 |
+
| 7.8194 | 0.5756 | 88 | 7.8423 |
|
| 76 |
+
| 7.9157 | 0.6018 | 92 | 7.8123 |
|
| 77 |
+
| 7.8291 | 0.6280 | 96 | 7.7872 |
|
| 78 |
+
| 7.8662 | 0.6541 | 100 | 7.8912 |
|
| 79 |
+
| 7.8973 | 0.6803 | 104 | 7.9091 |
|
| 80 |
+
| 7.9194 | 0.7065 | 108 | 7.9010 |
|
| 81 |
+
| 7.8688 | 0.7326 | 112 | 7.8714 |
|
| 82 |
+
| 7.8032 | 0.7588 | 116 | 7.7568 |
|
| 83 |
+
| 7.7982 | 0.7850 | 120 | 7.7807 |
|
| 84 |
+
| 7.9577 | 0.8111 | 124 | 7.8259 |
|
| 85 |
+
| 7.886 | 0.8373 | 128 | 7.8117 |
|
| 86 |
+
| 7.8537 | 0.8635 | 132 | 7.7975 |
|
| 87 |
+
| 7.832 | 0.8896 | 136 | 7.8116 |
|
| 88 |
+
| 7.7412 | 0.9158 | 140 | 7.8055 |
|
| 89 |
+
| 7.822 | 0.9419 | 144 | 7.8141 |
|
| 90 |
+
| 7.7889 | 0.9681 | 148 | 7.8214 |
|
| 91 |
+
| 7.8316 | 0.9943 | 152 | 7.8233 |
|
| 92 |
+
|
| 93 |
+
|
| 94 |
+
### Framework versions
|
| 95 |
+
|
| 96 |
+
- PEFT 0.12.0
|
| 97 |
+
- Transformers 4.44.0
|
| 98 |
+
- Pytorch 2.4.0+cu121
|
| 99 |
+
- Datasets 2.20.0
|
| 100 |
+
- 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:bcbfa1c46d5e1aca67581d5fb373ff70e4e342e6f22347618a4c6076f100f978
|
| 3 |
size 83945296
|