mhr2004/roberta-basemhr2004-atomic.anion.train.no1e-06-128
Browse files- README.md +87 -0
- config.json +27 -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-basemhr2004-atomic.anion.train.no1e-06-128
|
| 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-basemhr2004-atomic.anion.train.no1e-06-128
|
| 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: 0.4132
|
| 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: 512
|
| 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 |
+
| 0.6094 | 1.0 | 576 | 0.5127 |
|
| 51 |
+
| 0.5113 | 2.0 | 1152 | 0.4806 |
|
| 52 |
+
| 0.488 | 3.0 | 1728 | 0.4670 |
|
| 53 |
+
| 0.4759 | 4.0 | 2304 | 0.4560 |
|
| 54 |
+
| 0.4641 | 5.0 | 2880 | 0.4496 |
|
| 55 |
+
| 0.4572 | 6.0 | 3456 | 0.4432 |
|
| 56 |
+
| 0.4512 | 7.0 | 4032 | 0.4390 |
|
| 57 |
+
| 0.4452 | 8.0 | 4608 | 0.4343 |
|
| 58 |
+
| 0.4407 | 9.0 | 5184 | 0.4338 |
|
| 59 |
+
| 0.4387 | 10.0 | 5760 | 0.4299 |
|
| 60 |
+
| 0.4333 | 11.0 | 6336 | 0.4272 |
|
| 61 |
+
| 0.4332 | 12.0 | 6912 | 0.4242 |
|
| 62 |
+
| 0.4257 | 13.0 | 7488 | 0.4244 |
|
| 63 |
+
| 0.4245 | 14.0 | 8064 | 0.4229 |
|
| 64 |
+
| 0.4207 | 15.0 | 8640 | 0.4212 |
|
| 65 |
+
| 0.4209 | 16.0 | 9216 | 0.4184 |
|
| 66 |
+
| 0.4167 | 17.0 | 9792 | 0.4185 |
|
| 67 |
+
| 0.417 | 18.0 | 10368 | 0.4179 |
|
| 68 |
+
| 0.4163 | 19.0 | 10944 | 0.4178 |
|
| 69 |
+
| 0.4119 | 20.0 | 11520 | 0.4167 |
|
| 70 |
+
| 0.4089 | 21.0 | 12096 | 0.4159 |
|
| 71 |
+
| 0.4125 | 22.0 | 12672 | 0.4153 |
|
| 72 |
+
| 0.4097 | 23.0 | 13248 | 0.4143 |
|
| 73 |
+
| 0.4092 | 24.0 | 13824 | 0.4141 |
|
| 74 |
+
| 0.4073 | 25.0 | 14400 | 0.4133 |
|
| 75 |
+
| 0.408 | 26.0 | 14976 | 0.4135 |
|
| 76 |
+
| 0.4054 | 27.0 | 15552 | 0.4135 |
|
| 77 |
+
| 0.4068 | 28.0 | 16128 | 0.4131 |
|
| 78 |
+
| 0.4043 | 29.0 | 16704 | 0.4133 |
|
| 79 |
+
| 0.4069 | 30.0 | 17280 | 0.4132 |
|
| 80 |
+
|
| 81 |
+
|
| 82 |
+
### Framework versions
|
| 83 |
+
|
| 84 |
+
- Transformers 4.51.2
|
| 85 |
+
- Pytorch 2.6.0+cu124
|
| 86 |
+
- Datasets 3.5.0
|
| 87 |
+
- Tokenizers 0.21.1
|
config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"RobertaForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-05,
|
| 15 |
+
"max_position_embeddings": 514,
|
| 16 |
+
"model_type": "roberta",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 12,
|
| 19 |
+
"pad_token_id": 1,
|
| 20 |
+
"position_embedding_type": "absolute",
|
| 21 |
+
"problem_type": "single_label_classification",
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.51.2",
|
| 24 |
+
"type_vocab_size": 1,
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"vocab_size": 50265
|
| 27 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c6e3fb2e2a5b7398869da13097a05192651d6ca101429251807339c9af12f4b
|
| 3 |
+
size 498612824
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eceb6e491bdc9e593b8049aca3f5ab88e86d222b915b000e5a9cf06e6a3aadf6
|
| 3 |
+
size 5368
|