Model save
Browse files- README.md +5 -1
- tokenizer.json +2 -14
README.md
CHANGED
|
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
# llama_train_seq_cls_run1
|
| 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
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
@@ -44,6 +44,10 @@ The following hyperparameters were used during training:
|
|
| 44 |
- lr_scheduler_warmup_ratio: 0.03
|
| 45 |
- num_epochs: 1
|
| 46 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 47 |
### Framework versions
|
| 48 |
|
| 49 |
- PEFT 0.7.2.dev0
|
|
|
|
| 14 |
|
| 15 |
# llama_train_seq_cls_run1
|
| 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 None dataset.
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
|
|
| 44 |
- lr_scheduler_warmup_ratio: 0.03
|
| 45 |
- num_epochs: 1
|
| 46 |
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
|
| 50 |
+
|
| 51 |
### Framework versions
|
| 52 |
|
| 53 |
- PEFT 0.7.2.dev0
|
tokenizer.json
CHANGED
|
@@ -1,19 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
|
| 5 |
-
"max_length": 4096,
|
| 6 |
-
"strategy": "LongestFirst",
|
| 7 |
-
"stride": 0
|
| 8 |
-
},
|
| 9 |
-
"padding": {
|
| 10 |
-
"strategy": "BatchLongest",
|
| 11 |
-
"direction": "Left",
|
| 12 |
-
"pad_to_multiple_of": null,
|
| 13 |
-
"pad_id": 32000,
|
| 14 |
-
"pad_type_id": 0,
|
| 15 |
-
"pad_token": "<|im_end|>"
|
| 16 |
-
},
|
| 17 |
"added_tokens": [
|
| 18 |
{
|
| 19 |
"id": 0,
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 0,
|