tapt_helpfulness_base_pretraining_model_full_train
Browse files
README.md
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: roberta-base
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: tapt_helpfulness_base_pretraining_model_full_train
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# tapt_helpfulness_base_pretraining_model_full_train
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 1.2718
|
| 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: 0.0001
|
| 38 |
+
- train_batch_size: 21
|
| 39 |
+
- eval_batch_size: 21
|
| 40 |
+
- seed: 42
|
| 41 |
+
- gradient_accumulation_steps: 2
|
| 42 |
+
- total_train_batch_size: 42
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-06
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- num_epochs: 20
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 51 |
+
| 1.6862 | 1.0 | 1068 | 1.5262 |
|
| 52 |
+
| 1.5864 | 2.0 | 2137 | 1.4706 |
|
| 53 |
+
| 1.5423 | 3.0 | 3205 | 1.4346 |
|
| 54 |
+
| 1.5058 | 4.0 | 4274 | 1.4223 |
|
| 55 |
+
| 1.4792 | 5.0 | 5342 | 1.4100 |
|
| 56 |
+
| 1.4549 | 6.0 | 6411 | 1.3948 |
|
| 57 |
+
| 1.435 | 7.0 | 7479 | 1.3851 |
|
| 58 |
+
| 1.4148 | 8.0 | 8548 | 1.3749 |
|
| 59 |
+
| 1.3968 | 9.0 | 9616 | 1.3567 |
|
| 60 |
+
| 1.3806 | 10.0 | 10685 | 1.3548 |
|
| 61 |
+
| 1.3662 | 11.0 | 11753 | 1.3347 |
|
| 62 |
+
| 1.3495 | 12.0 | 12822 | 1.3369 |
|
| 63 |
+
| 1.3382 | 13.0 | 13890 | 1.3232 |
|
| 64 |
+
| 1.3238 | 14.0 | 14959 | 1.3231 |
|
| 65 |
+
| 1.3138 | 15.0 | 16027 | 1.3157 |
|
| 66 |
+
| 1.2983 | 16.0 | 17096 | 1.3012 |
|
| 67 |
+
| 1.2916 | 17.0 | 18164 | 1.2871 |
|
| 68 |
+
| 1.282 | 18.0 | 19233 | 1.2919 |
|
| 69 |
+
| 1.2738 | 19.0 | 20301 | 1.2825 |
|
| 70 |
+
| 1.267 | 19.99 | 21360 | 1.2842 |
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
### Framework versions
|
| 74 |
+
|
| 75 |
+
- Transformers 4.36.2
|
| 76 |
+
- Pytorch 2.2.1+cu121
|
| 77 |
+
- Datasets 2.19.0
|
| 78 |
+
- Tokenizers 0.15.2
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 498813948
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d8bdfb7a7e626006f25979307bb7a3740e4c1950ff71f382d566531445b4e70
|
| 3 |
size 498813948
|
runs/Apr20_20-12-11_cda4fd27c114/events.out.tfevents.1713655022.cda4fd27c114.752.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fbef52732210c4950f7643c7ad5297f540db581ec615c256e13c562bb17b1ac3
|
| 3 |
+
size 364
|