Update README.md
Browse files
README.md
CHANGED
|
@@ -6,6 +6,9 @@ tags:
|
|
| 6 |
model-index:
|
| 7 |
- name: flanT5-MoE-7X0.1B-PythonGOD-25k-finetuned-GotAgenticAI
|
| 8 |
results: []
|
|
|
|
|
|
|
|
|
|
| 9 |
---
|
| 10 |
|
| 11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -13,47 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
# flanT5-MoE-7X0.1B-PythonGOD-25k-finetuned-GotAgenticAI
|
| 15 |
|
| 16 |
-
This model is a fine-tuned version of [gss1147/flanT5-MoE-7X0.1B-PythonGOD-25k](https://huggingface.co/gss1147/flanT5-MoE-7X0.1B-PythonGOD-25k) on an
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
- Loss: 0.0155
|
| 19 |
|
| 20 |
-
## Model description
|
| 21 |
-
|
| 22 |
-
More information needed
|
| 23 |
-
|
| 24 |
-
## Intended uses & limitations
|
| 25 |
-
|
| 26 |
-
More information needed
|
| 27 |
-
|
| 28 |
-
## Training and evaluation data
|
| 29 |
-
|
| 30 |
-
More information needed
|
| 31 |
-
|
| 32 |
-
## Training procedure
|
| 33 |
-
|
| 34 |
-
### Training hyperparameters
|
| 35 |
-
|
| 36 |
-
The following hyperparameters were used during training:
|
| 37 |
-
- learning_rate: 2e-05
|
| 38 |
-
- train_batch_size: 8
|
| 39 |
-
- eval_batch_size: 8
|
| 40 |
-
- seed: 42
|
| 41 |
-
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 42 |
-
- lr_scheduler_type: linear
|
| 43 |
-
- num_epochs: 3.0
|
| 44 |
-
|
| 45 |
-
### Training results
|
| 46 |
-
|
| 47 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
-
|:-------------:|:-----:|:----:|:---------------:|
|
| 49 |
-
| 0.1240 | 1.0 | 618 | 0.0179 |
|
| 50 |
-
| 0.0317 | 2.0 | 1236 | 0.0159 |
|
| 51 |
-
| 0.0256 | 3.0 | 1854 | 0.0155 |
|
| 52 |
-
|
| 53 |
-
|
| 54 |
-
### Framework versions
|
| 55 |
-
|
| 56 |
-
- Transformers 5.0.0
|
| 57 |
-
- Pytorch 2.10.0+cu128
|
| 58 |
-
- Datasets 4.0.0
|
| 59 |
-
- Tokenizers 0.22.2
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: flanT5-MoE-7X0.1B-PythonGOD-25k-finetuned-GotAgenticAI
|
| 8 |
results: []
|
| 9 |
+
datasets:
|
| 10 |
+
- gss1147/Python_GOD_Coder_25k
|
| 11 |
+
- WithinUsAI/Got_Agentic_AI_5k
|
| 12 |
---
|
| 13 |
|
| 14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 16 |
|
| 17 |
# flanT5-MoE-7X0.1B-PythonGOD-25k-finetuned-GotAgenticAI
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [gss1147/flanT5-MoE-7X0.1B-PythonGOD-25k](https://huggingface.co/gss1147/flanT5-MoE-7X0.1B-PythonGOD-25k) on an WithinUsAI/Got_Agentic_AI_5k dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.0155
|
| 22 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|