#1: First attempt
Browse files
README.md
CHANGED
@@ -2,9 +2,10 @@
|
|
2 |
license: apache-2.0
|
3 |
library_name: peft
|
4 |
tags:
|
5 |
-
- unsloth
|
6 |
- trl
|
7 |
- sft
|
|
|
|
|
8 |
- generated_from_trainer
|
9 |
base_model: unsloth/mistral-7b-bnb-4bit
|
10 |
model-index:
|
@@ -17,7 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
# MistralAI_iwslt15_10000
|
19 |
|
20 |
-
This model is a fine-tuned version of [unsloth/mistral-7b-bnb-4bit](https://huggingface.co/unsloth/mistral-7b-bnb-4bit) on
|
|
|
|
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -48,6 +51,27 @@ The following hyperparameters were used during training:
|
|
48 |
- num_epochs: 5
|
49 |
- mixed_precision_training: Native AMP
|
50 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
51 |
### Framework versions
|
52 |
|
53 |
- PEFT 0.10.0
|
|
|
2 |
license: apache-2.0
|
3 |
library_name: peft
|
4 |
tags:
|
|
|
5 |
- trl
|
6 |
- sft
|
7 |
+
- unsloth
|
8 |
+
- translation
|
9 |
- generated_from_trainer
|
10 |
base_model: unsloth/mistral-7b-bnb-4bit
|
11 |
model-index:
|
|
|
18 |
|
19 |
# MistralAI_iwslt15_10000
|
20 |
|
21 |
+
This model is a fine-tuned version of [unsloth/mistral-7b-bnb-4bit](https://huggingface.co/unsloth/mistral-7b-bnb-4bit) on the None dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 1.5245
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
51 |
- num_epochs: 5
|
52 |
- mixed_precision_training: Native AMP
|
53 |
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
58 |
+
| 1.1687 | 0.32 | 100 | 1.0937 |
|
59 |
+
| 1.0905 | 0.64 | 200 | 1.0724 |
|
60 |
+
| 1.0711 | 0.96 | 300 | 1.0552 |
|
61 |
+
| 0.9258 | 1.28 | 400 | 1.0648 |
|
62 |
+
| 0.8979 | 1.6 | 500 | 1.0613 |
|
63 |
+
| 0.8893 | 1.92 | 600 | 1.0512 |
|
64 |
+
| 0.7253 | 2.24 | 700 | 1.1353 |
|
65 |
+
| 0.6713 | 2.56 | 800 | 1.1260 |
|
66 |
+
| 0.6701 | 2.88 | 900 | 1.1252 |
|
67 |
+
| 0.5284 | 3.2 | 1000 | 1.2891 |
|
68 |
+
| 0.446 | 3.52 | 1100 | 1.2803 |
|
69 |
+
| 0.4454 | 3.84 | 1200 | 1.3040 |
|
70 |
+
| 0.3663 | 4.16 | 1300 | 1.5203 |
|
71 |
+
| 0.282 | 4.48 | 1400 | 1.5198 |
|
72 |
+
| 0.2798 | 4.8 | 1500 | 1.5245 |
|
73 |
+
|
74 |
+
|
75 |
### Framework versions
|
76 |
|
77 |
- PEFT 0.10.0
|