Model save
Browse files- README.md +3 -5
- generation_config.json +7 -0
README.md
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
license: other
|
| 4 |
-
base_model: facebook/opt-
|
| 5 |
tags:
|
| 6 |
- trl
|
| 7 |
- sft
|
|
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
# sft_openassistant-guanaco
|
| 18 |
|
| 19 |
-
This model is a fine-tuned version of [facebook/opt-
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -40,10 +40,8 @@ The following hyperparameters were used during training:
|
|
| 40 |
- eval_batch_size: 8
|
| 41 |
- seed: 42
|
| 42 |
- distributed_type: multi-GPU
|
| 43 |
-
- num_devices: 4
|
| 44 |
- gradient_accumulation_steps: 16
|
| 45 |
-
- total_train_batch_size:
|
| 46 |
-
- total_eval_batch_size: 32
|
| 47 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
- lr_scheduler_type: linear
|
| 49 |
- num_epochs: 3.0
|
|
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
license: other
|
| 4 |
+
base_model: facebook/opt-350m
|
| 5 |
tags:
|
| 6 |
- trl
|
| 7 |
- sft
|
|
|
|
| 16 |
|
| 17 |
# sft_openassistant-guanaco
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [facebook/opt-350m](https://huggingface.co/facebook/opt-350m) on an unknown dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 40 |
- eval_batch_size: 8
|
| 41 |
- seed: 42
|
| 42 |
- distributed_type: multi-GPU
|
|
|
|
| 43 |
- gradient_accumulation_steps: 16
|
| 44 |
+
- total_train_batch_size: 1024
|
|
|
|
| 45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
- lr_scheduler_type: linear
|
| 47 |
- num_epochs: 3.0
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 2,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 1,
|
| 6 |
+
"transformers_version": "4.44.2"
|
| 7 |
+
}
|