yzhuang/phi-1_5_fictional
Browse files
README.md
CHANGED
@@ -6,7 +6,7 @@ tags:
|
|
6 |
- sft
|
7 |
- generated_from_trainer
|
8 |
datasets:
|
9 |
-
-
|
10 |
model-index:
|
11 |
- name: phi-1_5_fictional
|
12 |
results: []
|
@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
# phi-1_5_fictional
|
19 |
|
20 |
-
This model is a fine-tuned version of [microsoft/phi-1_5](https://huggingface.co/microsoft/phi-1_5) on the
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -36,13 +36,13 @@ More information needed
|
|
36 |
### Training hyperparameters
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
-
- learning_rate:
|
40 |
- train_batch_size: 2
|
41 |
- eval_batch_size: 2
|
42 |
- seed: 42
|
43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
- lr_scheduler_type: linear
|
45 |
-
- num_epochs:
|
46 |
|
47 |
### Training results
|
48 |
|
|
|
6 |
- sft
|
7 |
- generated_from_trainer
|
8 |
datasets:
|
9 |
+
- mmlu_no_train
|
10 |
model-index:
|
11 |
- name: phi-1_5_fictional
|
12 |
results: []
|
|
|
17 |
|
18 |
# phi-1_5_fictional
|
19 |
|
20 |
+
This model is a fine-tuned version of [microsoft/phi-1_5](https://huggingface.co/microsoft/phi-1_5) on the mmlu_no_train dataset.
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
36 |
### Training hyperparameters
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
+
- learning_rate: 1e-05
|
40 |
- train_batch_size: 2
|
41 |
- eval_batch_size: 2
|
42 |
- seed: 42
|
43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
- lr_scheduler_type: linear
|
45 |
+
- num_epochs: 5
|
46 |
|
47 |
### Training results
|
48 |
|