Instructions to use v700a/output with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use v700a/output with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
End of training
Browse files
README.md
CHANGED
|
@@ -40,11 +40,16 @@ The following hyperparameters were used during training:
|
|
| 40 |
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 41 |
- lr_scheduler_type: linear
|
| 42 |
- num_epochs: 3
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 43 |
|
| 44 |
### Framework versions
|
| 45 |
|
| 46 |
-
- PEFT 0.
|
| 47 |
-
- Transformers 4.
|
| 48 |
-
- Pytorch 2.
|
| 49 |
-
- Datasets
|
| 50 |
-
- Tokenizers 0.21.
|
|
|
|
| 40 |
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 41 |
- lr_scheduler_type: linear
|
| 42 |
- num_epochs: 3
|
| 43 |
+
- mixed_precision_training: Native AMP
|
| 44 |
+
|
| 45 |
+
### Training results
|
| 46 |
+
|
| 47 |
+
|
| 48 |
|
| 49 |
### Framework versions
|
| 50 |
|
| 51 |
+
- PEFT 0.14.0
|
| 52 |
+
- Transformers 4.48.3
|
| 53 |
+
- Pytorch 2.5.1+cu124
|
| 54 |
+
- Datasets 3.6.0
|
| 55 |
+
- Tokenizers 0.21.0
|
adapter_config.json
CHANGED
|
@@ -6,7 +6,6 @@
|
|
| 6 |
},
|
| 7 |
"base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
|
| 8 |
"bias": "none",
|
| 9 |
-
"corda_config": null,
|
| 10 |
"eva_config": null,
|
| 11 |
"exclude_modules": null,
|
| 12 |
"fan_in_fan_out": false,
|
|
@@ -31,7 +30,6 @@
|
|
| 31 |
"v_proj"
|
| 32 |
],
|
| 33 |
"task_type": null,
|
| 34 |
-
"trainable_token_indices": null,
|
| 35 |
"use_dora": false,
|
| 36 |
"use_rslora": false
|
| 37 |
}
|
|
|
|
| 6 |
},
|
| 7 |
"base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
|
| 8 |
"bias": "none",
|
|
|
|
| 9 |
"eva_config": null,
|
| 10 |
"exclude_modules": null,
|
| 11 |
"fan_in_fan_out": false,
|
|
|
|
| 30 |
"v_proj"
|
| 31 |
],
|
| 32 |
"task_type": null,
|
|
|
|
| 33 |
"use_dora": false,
|
| 34 |
"use_rslora": false
|
| 35 |
}
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4517152
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:09b9b0b2e3a06e69850de8defa77d31a7d76d20534ef0ae8f7f4e9a6e91a95fc
|
| 3 |
size 4517152
|
runs/May14_20-18-32_ef20abf07d99/events.out.tfevents.1747253922.ef20abf07d99.497.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a15f1b67c023e3336b6a138b0514464dfa7020ab550a421958df2da2634b9e5
|
| 3 |
+
size 5675
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5304
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3c148a499870b8ff98f98eebd4e42304f0deae003148fe0be894d930c72cf013
|
| 3 |
size 5304
|