Commit
•
78ea665
1
Parent(s):
9043b4a
End of training
Browse files
README.md
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
library_name: peft
|
| 4 |
tags:
|
| 5 |
-
- unsloth
|
| 6 |
- trl
|
| 7 |
- sft
|
|
|
|
| 8 |
- generated_from_trainer
|
| 9 |
base_model: unsloth/llama-3-8b-Instruct-bnb-4bit
|
| 10 |
model-index:
|
|
@@ -17,7 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
|
| 18 |
# llama3-chat_10000_500
|
| 19 |
|
| 20 |
-
This model is a fine-tuned version of [unsloth/llama-3-8b-Instruct-bnb-4bit](https://huggingface.co/unsloth/llama-3-8b-Instruct-bnb-4bit) on
|
|
|
|
|
|
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
@@ -48,6 +50,27 @@ The following hyperparameters were used during training:
|
|
| 48 |
- num_epochs: 5
|
| 49 |
- mixed_precision_training: Native AMP
|
| 50 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
### Framework versions
|
| 52 |
|
| 53 |
- PEFT 0.10.0
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
library_name: peft
|
| 4 |
tags:
|
|
|
|
| 5 |
- trl
|
| 6 |
- sft
|
| 7 |
+
- unsloth
|
| 8 |
- generated_from_trainer
|
| 9 |
base_model: unsloth/llama-3-8b-Instruct-bnb-4bit
|
| 10 |
model-index:
|
|
|
|
| 17 |
|
| 18 |
# llama3-chat_10000_500
|
| 19 |
|
| 20 |
+
This model is a fine-tuned version of [unsloth/llama-3-8b-Instruct-bnb-4bit](https://huggingface.co/unsloth/llama-3-8b-Instruct-bnb-4bit) on the None dataset.
|
| 21 |
+
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 1.8491
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
|
|
| 50 |
- num_epochs: 5
|
| 51 |
- mixed_precision_training: Native AMP
|
| 52 |
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 56 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 57 |
+
| 1.765 | 0.33 | 104 | 1.4841 |
|
| 58 |
+
| 1.5146 | 0.67 | 208 | 1.4604 |
|
| 59 |
+
| 1.4912 | 1.0 | 312 | 1.4545 |
|
| 60 |
+
| 1.3584 | 1.33 | 416 | 1.4698 |
|
| 61 |
+
| 1.358 | 1.66 | 520 | 1.4671 |
|
| 62 |
+
| 1.3483 | 2.0 | 624 | 1.4637 |
|
| 63 |
+
| 1.1105 | 2.33 | 728 | 1.5471 |
|
| 64 |
+
| 1.101 | 2.66 | 832 | 1.5512 |
|
| 65 |
+
| 1.1007 | 3.0 | 936 | 1.5522 |
|
| 66 |
+
| 0.8526 | 3.33 | 1040 | 1.7081 |
|
| 67 |
+
| 0.8445 | 3.66 | 1144 | 1.7156 |
|
| 68 |
+
| 0.8463 | 3.99 | 1248 | 1.7115 |
|
| 69 |
+
| 0.6865 | 4.33 | 1352 | 1.8423 |
|
| 70 |
+
| 0.6811 | 4.66 | 1456 | 1.8458 |
|
| 71 |
+
| 0.6859 | 4.99 | 1560 | 1.8491 |
|
| 72 |
+
|
| 73 |
+
|
| 74 |
### Framework versions
|
| 75 |
|
| 76 |
- PEFT 0.10.0
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 167832240
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3177235d526eac3300c78e452793dbe0cbf05bc370814af4caaa0f887785603a
|
| 3 |
size 167832240
|
runs/Apr20_12-51-26_9927202466e0/events.out.tfevents.1713617491.9927202466e0.402.0
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:eeb589031c5064686e73c76fe031a2f25d718e93c767ec3308e1c1da00de9c87
|
| 3 |
+
size 12701
|