End of training
Browse files
README.md
CHANGED
|
@@ -1,6 +1,9 @@
|
|
| 1 |
---
|
| 2 |
base_model: ybelkada/falcon-7b-sharded-bf16
|
|
|
|
| 3 |
tags:
|
|
|
|
|
|
|
| 4 |
- generated_from_trainer
|
| 5 |
model-index:
|
| 6 |
- name: falcon-7b-sharded-bf16-finetuned-mental-health-conversational
|
|
@@ -40,7 +43,8 @@ The following hyperparameters were used during training:
|
|
| 40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
- lr_scheduler_type: cosine
|
| 42 |
- lr_scheduler_warmup_ratio: 0.03
|
| 43 |
-
- training_steps:
|
|
|
|
| 44 |
|
| 45 |
### Training results
|
| 46 |
|
|
@@ -48,7 +52,8 @@ The following hyperparameters were used during training:
|
|
| 48 |
|
| 49 |
### Framework versions
|
| 50 |
|
| 51 |
-
-
|
|
|
|
| 52 |
- Pytorch 2.3.1+cu121
|
| 53 |
- Datasets 2.13.1
|
| 54 |
-
- Tokenizers 0.
|
|
|
|
| 1 |
---
|
| 2 |
base_model: ybelkada/falcon-7b-sharded-bf16
|
| 3 |
+
library_name: peft
|
| 4 |
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- sft
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: falcon-7b-sharded-bf16-finetuned-mental-health-conversational
|
|
|
|
| 43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
- lr_scheduler_type: cosine
|
| 45 |
- lr_scheduler_warmup_ratio: 0.03
|
| 46 |
+
- training_steps: 15
|
| 47 |
+
- mixed_precision_training: Native AMP
|
| 48 |
|
| 49 |
### Training results
|
| 50 |
|
|
|
|
| 52 |
|
| 53 |
### Framework versions
|
| 54 |
|
| 55 |
+
- PEFT 0.12.0
|
| 56 |
+
- Transformers 4.44.0
|
| 57 |
- Pytorch 2.3.1+cu121
|
| 58 |
- Datasets 2.13.1
|
| 59 |
+
- Tokenizers 0.19.1
|