Adzka/reward-model-distilbert-indo
Browse files
README.md
ADDED
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: w11wo/indonesian-roberta-base-sentiment-classifier
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
model-index:
|
9 |
+
- name: train-reward-training
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# train-reward-training
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [w11wo/indonesian-roberta-base-sentiment-classifier](https://huggingface.co/w11wo/indonesian-roberta-base-sentiment-classifier) on the None dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.4306
|
21 |
+
- Accuracy: 0.8197
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 1e-05
|
41 |
+
- train_batch_size: 4
|
42 |
+
- eval_batch_size: 8
|
43 |
+
- seed: 42
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: linear
|
46 |
+
- num_epochs: 12
|
47 |
+
- mixed_precision_training: Native AMP
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
52 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
53 |
+
| 0.7102 | 0.57 | 50 | 0.6741 | 0.7623 |
|
54 |
+
| 0.6583 | 1.15 | 100 | 0.6248 | 0.7705 |
|
55 |
+
| 0.5738 | 1.72 | 150 | 0.5009 | 0.8115 |
|
56 |
+
| 0.438 | 2.3 | 200 | 0.3925 | 0.8443 |
|
57 |
+
| 0.3201 | 2.87 | 250 | 0.3594 | 0.8361 |
|
58 |
+
| 0.2535 | 3.45 | 300 | 0.3908 | 0.8361 |
|
59 |
+
| 0.1875 | 4.02 | 350 | 0.3669 | 0.8443 |
|
60 |
+
| 0.1249 | 4.6 | 400 | 0.3908 | 0.8279 |
|
61 |
+
| 0.1205 | 5.17 | 450 | 0.4065 | 0.8525 |
|
62 |
+
| 0.1083 | 5.75 | 500 | 0.4077 | 0.8443 |
|
63 |
+
| 0.0586 | 6.32 | 550 | 0.3901 | 0.8361 |
|
64 |
+
| 0.0998 | 6.9 | 600 | 0.4196 | 0.8525 |
|
65 |
+
| 0.0634 | 7.47 | 650 | 0.4174 | 0.8525 |
|
66 |
+
| 0.0491 | 8.05 | 700 | 0.4311 | 0.8443 |
|
67 |
+
| 0.0354 | 8.62 | 750 | 0.4140 | 0.8279 |
|
68 |
+
| 0.0375 | 9.2 | 800 | 0.4205 | 0.8115 |
|
69 |
+
| 0.0343 | 9.77 | 850 | 0.4212 | 0.8197 |
|
70 |
+
| 0.0372 | 10.34 | 900 | 0.4132 | 0.8197 |
|
71 |
+
| 0.0238 | 10.92 | 950 | 0.4306 | 0.8197 |
|
72 |
+
| 0.0299 | 11.49 | 1000 | 0.4270 | 0.8197 |
|
73 |
+
|
74 |
+
|
75 |
+
### Framework versions
|
76 |
+
|
77 |
+
- Transformers 4.38.2
|
78 |
+
- Pytorch 2.1.0+cu121
|
79 |
+
- Datasets 2.14.5
|
80 |
+
- Tokenizers 0.15.2
|
emissions.csv
ADDED
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
1 |
+
timestamp,project_name,run_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
|
2 |
+
2024-07-22T21:17:46,codecarbon,fc91f620-87d3-4895-8af7-556ba34e74b9,422.34797716140747,0.01323909658306692,3.13464188275427e-05,42.5,135.115,11.946327209472656,0.004976516694658332,0.014874180417821405,0.0013902786000270229,0.02124097571250675,Indonesia,IDN,west java,,,Windows-10-10.0.19045-SP0,3.11.5,2.2.3,8,12th Gen Intel(R) Core(TM) i3-12100F,1,1 x NVIDIA GeForce RTX 3060,107.6071,-6.9217,31.85687255859375,machine,N,1.0
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 498615900
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b236de6992999ea809bade72b2b7d2fc6045877ca6e65c68c696e0bd671e9547
|
3 |
size 498615900
|
runs/Jul22_21-10-36_DESKTOP-HH0RPGN/events.out.tfevents.1721657443.DESKTOP-HH0RPGN.11108.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f977d779e2ee6fd6ae23f883b4f2574d5b8af09c79b29bf6f696a95dac352f1b
|
3 |
+
size 15939
|
runs/Jul22_21-10-36_DESKTOP-HH0RPGN/events.out.tfevents.1721657951.DESKTOP-HH0RPGN.11108.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4aece026e5515e9929bc968d1d8c364a2f3827e9d25238cf08d7c3268dffd703
|
3 |
+
size 411
|