bala3040/finally_done
Browse files
README.md
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
---
|
2 |
-
|
3 |
library_name: peft
|
|
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
-
base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
|
7 |
model-index:
|
8 |
- name: balagpt-ft2
|
9 |
results: []
|
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
This model is a fine-tuned version of [TheBloke/Mistral-7B-Instruct-v0.2-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GPTQ) on the None dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 0.
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -44,29 +44,22 @@ The following hyperparameters were used during training:
|
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
- lr_scheduler_warmup_steps: 2
|
47 |
-
- num_epochs:
|
48 |
- mixed_precision_training: Native AMP
|
49 |
|
50 |
### Training results
|
51 |
|
52 |
-
| Training Loss | Epoch
|
53 |
-
|
54 |
-
| 2.
|
55 |
-
| 1.
|
56 |
-
|
|
57 |
-
| 1.0399 | 4.0 | 20 | 0.9500 |
|
58 |
-
| 0.7569 | 5.0 | 25 | 0.7594 |
|
59 |
-
| 0.59 | 6.0 | 30 | 0.6689 |
|
60 |
-
| 0.5004 | 7.0 | 35 | 0.6295 |
|
61 |
-
| 0.4488 | 8.0 | 40 | 0.6123 |
|
62 |
-
| 0.4119 | 9.0 | 45 | 0.5994 |
|
63 |
-
| 0.386 | 10.0 | 50 | 0.5969 |
|
64 |
|
65 |
|
66 |
### Framework versions
|
67 |
|
68 |
-
- PEFT 0.
|
69 |
-
- Transformers 4.
|
70 |
- Pytorch 2.1.0+cu121
|
71 |
-
- Datasets 2.
|
72 |
-
- Tokenizers 0.
|
|
|
1 |
---
|
2 |
+
base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
|
3 |
library_name: peft
|
4 |
+
license: apache-2.0
|
5 |
tags:
|
6 |
- generated_from_trainer
|
|
|
7 |
model-index:
|
8 |
- name: balagpt-ft2
|
9 |
results: []
|
|
|
16 |
|
17 |
This model is a fine-tuned version of [TheBloke/Mistral-7B-Instruct-v0.2-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GPTQ) on the None dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.8438
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
- lr_scheduler_warmup_steps: 2
|
47 |
+
- num_epochs: 3
|
48 |
- mixed_precision_training: Native AMP
|
49 |
|
50 |
### Training results
|
51 |
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
+
|:-------------:|:------:|:----:|:---------------:|
|
54 |
+
| 2.1065 | 0.9231 | 9 | 1.4824 |
|
55 |
+
| 1.1553 | 1.9487 | 19 | 0.9793 |
|
56 |
+
| 0.7704 | 2.7692 | 27 | 0.8438 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
57 |
|
58 |
|
59 |
### Framework versions
|
60 |
|
61 |
+
- PEFT 0.11.1
|
62 |
+
- Transformers 4.41.2
|
63 |
- Pytorch 2.1.0+cu121
|
64 |
+
- Datasets 2.20.0
|
65 |
+
- 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 8397056
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f21bfdf96de82956129050d87fc5b7f6e8852f47eab987307fba0efb9a44295
|
3 |
size 8397056
|
runs/Jul17_14-32-58_cc8519d491ae/events.out.tfevents.1721226783.cc8519d491ae.284.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1aac2a61168dd97edb916cf31a39778988c54eeb808fce9a7735ed800ddfb499
|
3 |
+
size 10535
|
runs/Jul17_15-31-39_cc8519d491ae/events.out.tfevents.1721230305.cc8519d491ae.284.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c05c567f9ce866587412638e36823b7821f4bfee6fb6aaa013f15565c6767d08
|
3 |
+
size 7223
|
training_args.bin
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:b7c5ddd89521a4abe1dbfc0eab0fce560afe5656bc5823edcef32529e5547385
|
3 |
+
size 5112
|