Model save
Browse files
README.md
CHANGED
|
@@ -1,13 +1,12 @@
|
|
| 1 |
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
library_name: peft
|
|
|
|
|
|
|
| 4 |
tags:
|
| 5 |
-
- trl
|
| 6 |
-
- sft
|
| 7 |
- generated_from_trainer
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
-
|
| 11 |
model-index:
|
| 12 |
- name: Mistral-7B-v0.1_AviationQA
|
| 13 |
results: []
|
|
@@ -18,7 +17,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
|
| 19 |
# Mistral-7B-v0.1_AviationQA
|
| 20 |
|
| 21 |
-
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on the
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
@@ -43,19 +46,22 @@ The following hyperparameters were used during training:
|
|
| 43 |
- seed: 42
|
| 44 |
- gradient_accumulation_steps: 2
|
| 45 |
- total_train_batch_size: 4
|
| 46 |
-
- optimizer:
|
| 47 |
- lr_scheduler_type: constant
|
| 48 |
- lr_scheduler_warmup_ratio: 0.03
|
| 49 |
-
- num_epochs:
|
| 50 |
|
| 51 |
### Training results
|
| 52 |
|
|
|
|
|
|
|
|
|
|
| 53 |
|
| 54 |
|
| 55 |
### Framework versions
|
| 56 |
|
| 57 |
-
- PEFT 0.
|
| 58 |
-
- Transformers 4.
|
| 59 |
-
- Pytorch 2.
|
| 60 |
-
- Datasets
|
| 61 |
-
- Tokenizers 0.
|
|
|
|
| 1 |
---
|
|
|
|
| 2 |
library_name: peft
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: mistralai/Mistral-7B-Instruct-v0.1
|
| 5 |
tags:
|
|
|
|
|
|
|
| 6 |
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- bleu
|
| 9 |
+
- f1
|
| 10 |
model-index:
|
| 11 |
- name: Mistral-7B-v0.1_AviationQA
|
| 12 |
results: []
|
|
|
|
| 17 |
|
| 18 |
# Mistral-7B-v0.1_AviationQA
|
| 19 |
|
| 20 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on the None dataset.
|
| 21 |
+
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 6.3321
|
| 23 |
+
- Bleu: 0.0
|
| 24 |
+
- F1: 0.0033
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
|
|
| 46 |
- seed: 42
|
| 47 |
- gradient_accumulation_steps: 2
|
| 48 |
- total_train_batch_size: 4
|
| 49 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 50 |
- lr_scheduler_type: constant
|
| 51 |
- lr_scheduler_warmup_ratio: 0.03
|
| 52 |
+
- num_epochs: 1
|
| 53 |
|
| 54 |
### Training results
|
| 55 |
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss | Bleu | F1 |
|
| 57 |
+
|:-------------:|:-----:|:----:|:---------------:|:----:|:------:|
|
| 58 |
+
| 9.8041 | 0.8 | 2 | 6.3321 | 0.0 | 0.0033 |
|
| 59 |
|
| 60 |
|
| 61 |
### Framework versions
|
| 62 |
|
| 63 |
+
- PEFT 0.14.0
|
| 64 |
+
- Transformers 4.49.0
|
| 65 |
+
- Pytorch 2.5.1+cu124
|
| 66 |
+
- Datasets 3.3.2
|
| 67 |
+
- Tokenizers 0.21.0
|
runs/Mar03_17-33-10_43e9672942bd/events.out.tfevents.1741023310.43e9672942bd.1405.2
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:55f2e3173884919aa4b63d8dff62867dd44c684b22e211fb3402d017e0b26682
|
| 3 |
+
size 6694
|