bala3040/paper_eval_gpt
Browse files
README.md
CHANGED
|
@@ -16,12 +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 |
-
-
|
| 20 |
-
- eval_runtime: 106.6233
|
| 21 |
-
- eval_samples_per_second: 0.816
|
| 22 |
-
- eval_steps_per_second: 0.816
|
| 23 |
-
- epoch: 8.0
|
| 24 |
-
- step: 160
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
@@ -52,6 +47,22 @@ The following hyperparameters were used during training:
|
|
| 52 |
- num_epochs: 10
|
| 53 |
- mixed_precision_training: Native AMP
|
| 54 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
### Framework versions
|
| 56 |
|
| 57 |
- PEFT 0.10.0
|
|
|
|
| 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: 0.5294
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 47 |
- num_epochs: 10
|
| 48 |
- mixed_precision_training: Native AMP
|
| 49 |
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 54 |
+
| 2.1594 | 1.0 | 5 | 1.8573 |
|
| 55 |
+
| 1.6557 | 2.0 | 10 | 1.3995 |
|
| 56 |
+
| 1.2039 | 3.0 | 15 | 1.0328 |
|
| 57 |
+
| 0.8274 | 4.0 | 20 | 0.7538 |
|
| 58 |
+
| 0.5816 | 5.0 | 25 | 0.6224 |
|
| 59 |
+
| 0.4699 | 6.0 | 30 | 0.5730 |
|
| 60 |
+
| 0.408 | 7.0 | 35 | 0.5498 |
|
| 61 |
+
| 0.3595 | 8.0 | 40 | 0.5377 |
|
| 62 |
+
| 0.3235 | 9.0 | 45 | 0.5319 |
|
| 63 |
+
| 0.3042 | 10.0 | 50 | 0.5294 |
|
| 64 |
+
|
| 65 |
+
|
| 66 |
### Framework versions
|
| 67 |
|
| 68 |
- PEFT 0.10.0
|
adapter_config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"alpha_pattern": {},
|
| 3 |
"auto_mapping": null,
|
| 4 |
-
"base_model_name_or_path":
|
| 5 |
"bias": "none",
|
| 6 |
"fan_in_fan_out": false,
|
| 7 |
"inference_mode": true,
|
|
|
|
| 1 |
{
|
| 2 |
"alpha_pattern": {},
|
| 3 |
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "TheBloke/Mistral-7B-Instruct-v0.2-GPTQ",
|
| 5 |
"bias": "none",
|
| 6 |
"fan_in_fan_out": false,
|
| 7 |
"inference_mode": true,
|
adapter_model.safetensors
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 sha256:10a9947d86f2c6a34bf29d90249f8ff19f420e723f742704413e3231bedf051e
|
| 3 |
+
size 8397056
|
runs/Apr08_09-16-59_91c30f7cc014/events.out.tfevents.1712567819.91c30f7cc014.698.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c60a43f13d5f34857cdf1f451de6585f0cbbd56c036ef466d2292876c599426f
|
| 3 |
+
size 10289
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4856
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4cf8d48594cbcef15c2a218f4b26be8b7e8f28dcacde6925f2c94fbc3d05d247
|
| 3 |
size 4856
|