Commit
•
009b841
1
Parent(s):
fa77afe
rejozacharia/lora-course-info
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: 2.4361
|
| 21 |
-
- eval_samples_per_second: 1.642
|
| 22 |
-
- eval_steps_per_second: 0.41
|
| 23 |
-
- epoch: 13.0
|
| 24 |
-
- step: 13
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
@@ -49,9 +44,25 @@ The following hyperparameters were used during training:
|
|
| 49 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 50 |
- lr_scheduler_type: linear
|
| 51 |
- lr_scheduler_warmup_steps: 2
|
| 52 |
-
- num_epochs:
|
| 53 |
- mixed_precision_training: Native AMP
|
| 54 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
### Framework versions
|
| 56 |
|
| 57 |
- PEFT 0.11.1
|
|
|
|
| 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: 1.7839
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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: 10
|
| 48 |
- mixed_precision_training: Native AMP
|
| 49 |
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 54 |
+
| 2.1649 | 1.0 | 1 | 4.3052 |
|
| 55 |
+
| 2.1595 | 2.0 | 2 | 3.9177 |
|
| 56 |
+
| 1.9661 | 3.0 | 3 | 3.1663 |
|
| 57 |
+
| 1.5727 | 4.0 | 4 | 2.6769 |
|
| 58 |
+
| 1.3371 | 5.0 | 5 | 2.4213 |
|
| 59 |
+
| 1.2116 | 6.0 | 6 | 2.2232 |
|
| 60 |
+
| 1.1114 | 7.0 | 7 | 2.0560 |
|
| 61 |
+
| 1.0296 | 8.0 | 8 | 1.9239 |
|
| 62 |
+
| 0.9679 | 9.0 | 9 | 1.8329 |
|
| 63 |
+
| 0.9227 | 10.0 | 10 | 1.7839 |
|
| 64 |
+
|
| 65 |
+
|
| 66 |
### Framework versions
|
| 67 |
|
| 68 |
- PEFT 0.11.1
|
adapter_config.json
CHANGED
|
@@ -20,8 +20,8 @@
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
-
"
|
| 24 |
-
"
|
| 25 |
],
|
| 26 |
"task_type": "CAUSAL_LM",
|
| 27 |
"use_dora": false,
|
|
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
+
"q_proj",
|
| 24 |
+
"v_proj"
|
| 25 |
],
|
| 26 |
"task_type": "CAUSAL_LM",
|
| 27 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 13648432
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2fd058617bc595fa58290f9f028439b992f800e5f3d2684c00d26f04c40ecac6
|
| 3 |
size 13648432
|
runs/Jul08_05-29-34_07b817503238/events.out.tfevents.1720416575.07b817503238.287.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d431a1c362107ac6cadea4a49065c3e322e131c1ab8af5648cee8f51459d41f
|
| 3 |
+
size 10526
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4603
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86aa9f8040b18bc723c239f0b644a7c9de4033db439ba4cc8e1b5d5120cdc3b0
|
| 3 |
size 4603
|