End of training
Browse files
README.md
ADDED
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- trl
|
6 |
+
- sft
|
7 |
+
- generated_from_trainer
|
8 |
+
base_model: mistralai/Mistral-7B-v0.1
|
9 |
+
model-index:
|
10 |
+
- name: lc_full_balanced
|
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 |
+
# lc_full_balanced
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 1.5766
|
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: 2e-05
|
41 |
+
- train_batch_size: 1
|
42 |
+
- eval_batch_size: 1
|
43 |
+
- seed: 42
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: cosine
|
46 |
+
- num_epochs: 20
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
51 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
52 |
+
| 1.6135 | 1.0 | 282 | 1.5535 |
|
53 |
+
| 1.7292 | 2.0 | 564 | 1.5380 |
|
54 |
+
| 1.502 | 3.0 | 846 | 1.5312 |
|
55 |
+
| 1.5672 | 4.0 | 1128 | 1.5347 |
|
56 |
+
| 1.3714 | 5.0 | 1410 | 1.5365 |
|
57 |
+
| 1.3268 | 6.0 | 1692 | 1.5415 |
|
58 |
+
| 1.6069 | 7.0 | 1974 | 1.5425 |
|
59 |
+
| 1.4057 | 8.0 | 2256 | 1.5483 |
|
60 |
+
| 1.3989 | 9.0 | 2538 | 1.5578 |
|
61 |
+
| 1.6766 | 10.0 | 2820 | 1.5601 |
|
62 |
+
| 1.4027 | 11.0 | 3102 | 1.5673 |
|
63 |
+
| 1.3554 | 12.0 | 3384 | 1.5703 |
|
64 |
+
| 1.3135 | 13.0 | 3666 | 1.5729 |
|
65 |
+
| 1.2954 | 14.0 | 3948 | 1.5745 |
|
66 |
+
| 1.2543 | 15.0 | 4230 | 1.5758 |
|
67 |
+
| 1.4603 | 16.0 | 4512 | 1.5763 |
|
68 |
+
| 1.2734 | 17.0 | 4794 | 1.5765 |
|
69 |
+
| 1.3247 | 18.0 | 5076 | 1.5764 |
|
70 |
+
| 1.2645 | 19.0 | 5358 | 1.5769 |
|
71 |
+
| 1.376 | 20.0 | 5640 | 1.5766 |
|
72 |
+
|
73 |
+
|
74 |
+
### Framework versions
|
75 |
+
|
76 |
+
- PEFT 0.11.1
|
77 |
+
- Transformers 4.41.2
|
78 |
+
- Pytorch 2.1.0+cu118
|
79 |
+
- Datasets 2.19.2
|
80 |
+
- Tokenizers 0.19.1
|