IbtiHt/agrobot-llama2-ft
Browse files- README.md +18 -0
- runs/Jun24_22-20-03_de794d1faef8/events.out.tfevents.1719269040.de794d1faef8.316.1 +3 -0
- runs/Jun24_22-58-29_de794d1faef8/events.out.tfevents.1719269911.de794d1faef8.517.0 +3 -0
- runs/Jun24_23-26-41_0e3e72175992/events.out.tfevents.1719271603.0e3e72175992.34.0 +3 -0
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -15,6 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
# agrobot-llama2-ft
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [TheBloke/Llama-2-7B-Chat-GPTQ](https://huggingface.co/TheBloke/Llama-2-7B-Chat-GPTQ) on the None dataset.
|
|
|
|
|
|
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
@@ -45,6 +47,22 @@ The following hyperparameters were used during training:
|
|
| 45 |
- num_epochs: 10
|
| 46 |
- mixed_precision_training: Native AMP
|
| 47 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 48 |
### Framework versions
|
| 49 |
|
| 50 |
- PEFT 0.11.1
|
|
|
|
| 15 |
# agrobot-llama2-ft
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [TheBloke/Llama-2-7B-Chat-GPTQ](https://huggingface.co/TheBloke/Llama-2-7B-Chat-GPTQ) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: nan
|
| 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 |
+
| 6139.9749 | 0.99 | 102 | nan |
|
| 55 |
+
| 906.7905 | 2.0 | 205 | nan |
|
| 56 |
+
| 7469.7591 | 3.0 | 308 | nan |
|
| 57 |
+
| 4521.9417 | 4.0 | 411 | nan |
|
| 58 |
+
| 10357.8309 | 4.99 | 513 | nan |
|
| 59 |
+
| 2193.7805 | 6.0 | 616 | nan |
|
| 60 |
+
| 415.3014 | 7.0 | 719 | nan |
|
| 61 |
+
| 5163.8981 | 8.0 | 822 | nan |
|
| 62 |
+
| 10537.2745 | 8.99 | 924 | nan |
|
| 63 |
+
| 1091.5675 | 9.93 | 1020 | nan |
|
| 64 |
+
|
| 65 |
+
|
| 66 |
### Framework versions
|
| 67 |
|
| 68 |
- PEFT 0.11.1
|
runs/Jun24_22-20-03_de794d1faef8/events.out.tfevents.1719269040.de794d1faef8.316.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20ef7ee27b8f7915669669a4a061d2c3166bee69efc2bd0874d18db4af3debfd
|
| 3 |
+
size 4184
|
runs/Jun24_22-58-29_de794d1faef8/events.out.tfevents.1719269911.de794d1faef8.517.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a9bfe40b7238a545e8c02bf7d3be53eac544a55592344af4252b123434385b35
|
| 3 |
+
size 5307
|
runs/Jun24_23-26-41_0e3e72175992/events.out.tfevents.1719271603.0e3e72175992.34.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b680c9d55d8a6b9534938f99ccb59d871c8d07c9669e65b2ca281af94ce79bcb
|
| 3 |
+
size 10472
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4920
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9582cc8bc81f57ae2a8ccc0ff63b60baa808d08082a13992142a52c46d84001d
|
| 3 |
size 4920
|