mhr2004/roberta-base-negcommonsensebalanced-1e-06-64
Browse files- README.md +87 -0
- config.json +28 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: mit
|
| 4 |
+
base_model: roberta-base
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: roberta-base-negcommonsensebalanced-1e-06-64
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# roberta-base-negcommonsensebalanced-1e-06-64
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.3964
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 1e-06
|
| 39 |
+
- train_batch_size: 256
|
| 40 |
+
- eval_batch_size: 1024
|
| 41 |
+
- seed: 42
|
| 42 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 43 |
+
- lr_scheduler_type: linear
|
| 44 |
+
- num_epochs: 30
|
| 45 |
+
|
| 46 |
+
### Training results
|
| 47 |
+
|
| 48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 49 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 50 |
+
| 0.6084 | 1.0 | 795 | 0.5485 |
|
| 51 |
+
| 0.5297 | 2.0 | 1590 | 0.5047 |
|
| 52 |
+
| 0.5021 | 3.0 | 2385 | 0.4816 |
|
| 53 |
+
| 0.4891 | 4.0 | 3180 | 0.4691 |
|
| 54 |
+
| 0.4716 | 5.0 | 3975 | 0.4565 |
|
| 55 |
+
| 0.4622 | 6.0 | 4770 | 0.4519 |
|
| 56 |
+
| 0.4537 | 7.0 | 5565 | 0.4408 |
|
| 57 |
+
| 0.4437 | 8.0 | 6360 | 0.4387 |
|
| 58 |
+
| 0.4345 | 9.0 | 7155 | 0.4311 |
|
| 59 |
+
| 0.4295 | 10.0 | 7950 | 0.4286 |
|
| 60 |
+
| 0.4219 | 11.0 | 8745 | 0.4229 |
|
| 61 |
+
| 0.4169 | 12.0 | 9540 | 0.4175 |
|
| 62 |
+
| 0.413 | 13.0 | 10335 | 0.4176 |
|
| 63 |
+
| 0.4098 | 14.0 | 11130 | 0.4139 |
|
| 64 |
+
| 0.4046 | 15.0 | 11925 | 0.4096 |
|
| 65 |
+
| 0.4012 | 16.0 | 12720 | 0.4079 |
|
| 66 |
+
| 0.3958 | 17.0 | 13515 | 0.4069 |
|
| 67 |
+
| 0.3915 | 18.0 | 14310 | 0.4066 |
|
| 68 |
+
| 0.3928 | 19.0 | 15105 | 0.4046 |
|
| 69 |
+
| 0.3896 | 20.0 | 15900 | 0.4017 |
|
| 70 |
+
| 0.3856 | 21.0 | 16695 | 0.4004 |
|
| 71 |
+
| 0.3795 | 22.0 | 17490 | 0.3984 |
|
| 72 |
+
| 0.3809 | 23.0 | 18285 | 0.3989 |
|
| 73 |
+
| 0.3796 | 24.0 | 19080 | 0.3983 |
|
| 74 |
+
| 0.3782 | 25.0 | 19875 | 0.3983 |
|
| 75 |
+
| 0.3793 | 26.0 | 20670 | 0.3977 |
|
| 76 |
+
| 0.3747 | 27.0 | 21465 | 0.3959 |
|
| 77 |
+
| 0.3743 | 28.0 | 22260 | 0.3970 |
|
| 78 |
+
| 0.3795 | 29.0 | 23055 | 0.3962 |
|
| 79 |
+
| 0.373 | 30.0 | 23850 | 0.3964 |
|
| 80 |
+
|
| 81 |
+
|
| 82 |
+
### Framework versions
|
| 83 |
+
|
| 84 |
+
- Transformers 4.48.3
|
| 85 |
+
- Pytorch 2.6.0+cu124
|
| 86 |
+
- Datasets 3.2.0
|
| 87 |
+
- Tokenizers 0.21.0
|
config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "roberta-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 514,
|
| 17 |
+
"model_type": "roberta",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"position_embedding_type": "absolute",
|
| 22 |
+
"problem_type": "single_label_classification",
|
| 23 |
+
"torch_dtype": "float32",
|
| 24 |
+
"transformers_version": "4.48.3",
|
| 25 |
+
"type_vocab_size": 1,
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"vocab_size": 50265
|
| 28 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b94f7b1a7a9679a8eb11448016fd74a7b5f4cbce069cbd7ebc70527486d8316
|
| 3 |
+
size 498612824
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:80ba3c189f4e9f319b98fe3f1d10eb6e5f611eb7d886098c21d19a4db657f261
|
| 3 |
+
size 5368
|