Commit
•
aafcf21
1
Parent(s):
2f900da
End of training
Browse files- README.md +10 -6
- adapter_model.safetensors +1 -1
README.md
CHANGED
|
@@ -7,7 +7,6 @@ datasets:
|
|
| 7 |
model-index:
|
| 8 |
- name: tweet-summarization-llama-2-finetuned
|
| 9 |
results: []
|
| 10 |
-
pipeline_tag: text-generation
|
| 11 |
---
|
| 12 |
|
| 13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -17,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the Salesforce/dialogstudio dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss: 1.
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
@@ -45,14 +44,19 @@ The following hyperparameters were used during training:
|
|
| 45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
- lr_scheduler_type: cosine
|
| 47 |
- lr_scheduler_warmup_ratio: 0.05
|
| 48 |
-
- num_epochs:
|
| 49 |
|
| 50 |
### Training results
|
| 51 |
|
| 52 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 54 |
-
| 1.
|
| 55 |
-
| 1.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 56 |
|
| 57 |
|
| 58 |
### Framework versions
|
|
@@ -60,4 +64,4 @@ The following hyperparameters were used during training:
|
|
| 60 |
- Transformers 4.32.1
|
| 61 |
- Pytorch 2.0.1+cu117
|
| 62 |
- Datasets 2.14.4
|
| 63 |
-
- Tokenizers 0.13.3
|
|
|
|
| 7 |
model-index:
|
| 8 |
- name: tweet-summarization-llama-2-finetuned
|
| 9 |
results: []
|
|
|
|
| 10 |
---
|
| 11 |
|
| 12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the Salesforce/dialogstudio dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.8672
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
- lr_scheduler_type: cosine
|
| 46 |
- lr_scheduler_warmup_ratio: 0.05
|
| 47 |
+
- num_epochs: 7
|
| 48 |
|
| 49 |
### Training results
|
| 50 |
|
| 51 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 53 |
+
| 1.8996 | 1.0 | 55 | 1.9491 |
|
| 54 |
+
| 1.8415 | 2.0 | 110 | 1.8857 |
|
| 55 |
+
| 1.7693 | 3.0 | 165 | 1.8749 |
|
| 56 |
+
| 1.7136 | 4.0 | 220 | 1.8678 |
|
| 57 |
+
| 1.7533 | 5.0 | 275 | 1.8663 |
|
| 58 |
+
| 1.6182 | 6.0 | 330 | 1.8665 |
|
| 59 |
+
| 1.69 | 7.0 | 385 | 1.8672 |
|
| 60 |
|
| 61 |
|
| 62 |
### Framework versions
|
|
|
|
| 64 |
- Transformers 4.32.1
|
| 65 |
- Pytorch 2.0.1+cu117
|
| 66 |
- Datasets 2.14.4
|
| 67 |
+
- Tokenizers 0.13.3
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 33571624
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:652bc9e3624b3beceebcc5f60311ac77d76fc76eae0643651475538b8324f3ee
|
| 3 |
size 33571624
|