bala3040/team_dpb
Browse files
README.md
CHANGED
|
@@ -16,7 +16,12 @@ 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 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -47,22 +52,6 @@ The following hyperparameters were used during training:
|
|
| 47 |
- num_epochs: 10
|
| 48 |
- mixed_precision_training: Native AMP
|
| 49 |
|
| 50 |
-
### Training results
|
| 51 |
-
|
| 52 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
-
|:-------------:|:-----:|:----:|:---------------:|
|
| 54 |
-
| 2.092 | 0.92 | 9 | 1.4516 |
|
| 55 |
-
| 1.0312 | 1.95 | 19 | 0.7849 |
|
| 56 |
-
| 0.5407 | 2.97 | 29 | 0.5922 |
|
| 57 |
-
| 0.4035 | 4.0 | 39 | 0.5433 |
|
| 58 |
-
| 0.3684 | 4.92 | 48 | 0.5227 |
|
| 59 |
-
| 0.2708 | 5.95 | 58 | 0.5200 |
|
| 60 |
-
| 0.2348 | 6.97 | 68 | 0.5358 |
|
| 61 |
-
| 0.2091 | 8.0 | 78 | 0.5485 |
|
| 62 |
-
| 0.2125 | 8.92 | 87 | 0.5655 |
|
| 63 |
-
| 0.1607 | 9.23 | 90 | 0.5664 |
|
| 64 |
-
|
| 65 |
-
|
| 66 |
### Framework versions
|
| 67 |
|
| 68 |
- 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 |
+
- eval_loss: 0.4806
|
| 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 |
- num_epochs: 10
|
| 53 |
- mixed_precision_training: Native AMP
|
| 54 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
### Framework versions
|
| 56 |
|
| 57 |
- 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": null,
|
| 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 sha256:8ab40b610fa9e12d59b2762e2595968e1aab8c86b73c7ade7e72ef2c35844b77
|
| 3 |
+
size 8398144
|
runs/Mar25_02-48-51_7b74c093dd10/events.out.tfevents.1711334931.7b74c093dd10.547.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b277fc268469d3710fc4c068755a9ff38c8b3f4b0c3b00eabc1a45ce6fef5e16
|
| 3 |
+
size 5684
|
runs/Mar25_03-03-00_7b74c093dd10/events.out.tfevents.1711335780.7b74c093dd10.547.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:57712115b914d466e7ffed7b22716792e4dfb4fe15a94b6213a01c16b9dc5665
|
| 3 |
+
size 9013
|
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 sha256:1c5ee3f4a19e085531a13eb386222dc266a1637c9c536efe153641fb217c03c1
|
| 3 |
size 4856
|