kapliff89 commited on
Commit
4993f35
1 Parent(s): 4ccdef2

End of training

Browse files
README.md ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: kapliff89/roberta-base-finetuned-nmrv
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: roberta-base-finetuned-nmrv-finetuned-gptgenonly-emotioncls
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # roberta-base-finetuned-nmrv-finetuned-gptgenonly-emotioncls
14
+
15
+ This model is a fine-tuned version of [kapliff89/roberta-base-finetuned-nmrv](https://huggingface.co/kapliff89/roberta-base-finetuned-nmrv) on the None dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 0.4446
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 2e-05
37
+ - train_batch_size: 16
38
+ - eval_batch_size: 16
39
+ - seed: 42
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: linear
42
+ - num_epochs: 3.0
43
+ - mixed_precision_training: Native AMP
44
+
45
+ ### Training results
46
+
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:-----:|:----:|:---------------:|
49
+ | 0.9173 | 1.0 | 17 | 0.8468 |
50
+ | 0.5985 | 2.0 | 34 | 0.5935 |
51
+ | 0.3982 | 3.0 | 51 | 0.4446 |
52
+
53
+
54
+ ### Framework versions
55
+
56
+ - Transformers 4.40.2
57
+ - Pytorch 2.3.0+cu118
58
+ - Datasets 2.19.1
59
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "kapliff89/roberta-base-finetuned-nmrv",
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
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "LABEL_0",
16
+ "1": "LABEL_1",
17
+ "2": "LABEL_2"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "LABEL_0": 0,
23
+ "LABEL_1": 1,
24
+ "LABEL_2": 2
25
+ },
26
+ "layer_norm_eps": 1e-05,
27
+ "max_position_embeddings": 514,
28
+ "model_type": "roberta",
29
+ "num_attention_heads": 12,
30
+ "num_hidden_layers": 12,
31
+ "pad_token_id": 1,
32
+ "position_embedding_type": "absolute",
33
+ "problem_type": "single_label_classification",
34
+ "tokenizer_class": "BertTokenizer",
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.40.2",
37
+ "type_vocab_size": 1,
38
+ "use_cache": true,
39
+ "vocab_size": 32000
40
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b48e58c0a5d3425c41063433b66029a22d39290db6a00aa5998c91a637805140
3
+ size 442505820
runs/May13_09-40-51_DESKTOP-HB7J4MA/events.out.tfevents.1715560864.DESKTOP-HB7J4MA.3332.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5aef488f9c3a87a216e2c941101a51d2f66542c58ed1fcfe0a491d518ab920a9
3
+ size 6914
runs/May13_10-06-24_DESKTOP-HB7J4MA/events.out.tfevents.1715562386.DESKTOP-HB7J4MA.3332.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1291943e417b21296568fd74fd4caa27f6ee8d9dbf704008eb9af44f5b2ecb14
3
+ size 6914
runs/May13_12-21-06_DESKTOP-HB7J4MA/events.out.tfevents.1715570469.DESKTOP-HB7J4MA.28336.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9052ee0302dbbd5eace900ff95f95b1c00125afb8593432ecd6072b2b2c713e5
3
+ size 6914
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:563f682369969e7a536995c5f3439ec136e290c0e5d5cf7cd4feb2ccaf11d919
3
+ size 5048