Pushing fine-tuned model to Hugging Face Hub
Browse files- README.md +49 -0
- adapter_config.json +39 -0
- adapter_model.safetensors +3 -0
- run_experiment.log +0 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
language:
|
| 4 |
+
- pt
|
| 5 |
+
- en
|
| 6 |
+
tags:
|
| 7 |
+
- aes
|
| 8 |
+
datasets:
|
| 9 |
+
- kamel-usp/aes_enem_dataset
|
| 10 |
+
base_model: microsoft/Phi-3.5-mini-instruct
|
| 11 |
+
metrics:
|
| 12 |
+
- accuracy
|
| 13 |
+
- qwk
|
| 14 |
+
library_name: peft
|
| 15 |
+
model-index:
|
| 16 |
+
- name: phi35-balanced-C3
|
| 17 |
+
results:
|
| 18 |
+
- task:
|
| 19 |
+
type: text-classification
|
| 20 |
+
name: Automated Essay Score
|
| 21 |
+
dataset:
|
| 22 |
+
name: Automated Essay Score ENEM Dataset
|
| 23 |
+
type: kamel-usp/aes_enem_dataset
|
| 24 |
+
config: JBCS2025
|
| 25 |
+
split: test
|
| 26 |
+
metrics:
|
| 27 |
+
- name: Macro F1 (ignoring nan)
|
| 28 |
+
type: f1
|
| 29 |
+
value: 0.3150704718786213
|
| 30 |
+
- name: QWK
|
| 31 |
+
type: qwk
|
| 32 |
+
value: 0.2353562005277044
|
| 33 |
+
- name: Weighted Macro F1
|
| 34 |
+
type: f1
|
| 35 |
+
value: 0.3336611749101599
|
| 36 |
+
---
|
| 37 |
+
# Model ID: phi35-balanced-C3
|
| 38 |
+
## Results
|
| 39 |
+
| | test_data |
|
| 40 |
+
|:-----------------------------|------------:|
|
| 41 |
+
| eval_accuracy | 0.333333 |
|
| 42 |
+
| eval_RMSE | 60.4332 |
|
| 43 |
+
| eval_QWK | 0.235356 |
|
| 44 |
+
| eval_Macro_F1 | 0.262559 |
|
| 45 |
+
| eval_Macro_F1_(ignoring_nan) | 0.31507 |
|
| 46 |
+
| eval_Weighted_F1 | 0.333661 |
|
| 47 |
+
| eval_Micro_F1 | 0.333333 |
|
| 48 |
+
| eval_HDIV | 0.115942 |
|
| 49 |
+
|
adapter_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "microsoft/Phi-3.5-mini-instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 16,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.05,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": [
|
| 22 |
+
"classifier",
|
| 23 |
+
"score"
|
| 24 |
+
],
|
| 25 |
+
"peft_type": "LORA",
|
| 26 |
+
"r": 8,
|
| 27 |
+
"rank_pattern": {},
|
| 28 |
+
"revision": null,
|
| 29 |
+
"target_modules": [
|
| 30 |
+
"down_proj",
|
| 31 |
+
"gate_up_proj",
|
| 32 |
+
"o_proj",
|
| 33 |
+
"qkv_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "SEQ_CLS",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f571a3c04cff9bba0d4af71d065980c030fef33096fd942bb104cab81d3f5100
|
| 3 |
+
size 50402728
|
run_experiment.log
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dd20c8a0192f7c18c9290e38147b3edbbf8e6b01abbb2d822b6fa649dd698ff1
|
| 3 |
+
size 5432
|