IMA-StreamSolve commited on
Commit
652df4d
·
verified ·
1 Parent(s): 506ed9f

Training complete

Browse files
README.md ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: mit
4
+ base_model: FacebookAI/roberta-base
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: sentiment-analysis-roberta-base-V1.4_ima_ds
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # sentiment-analysis-roberta-base-V1.4_ima_ds
18
+
19
+ This model is a fine-tuned version of [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base) on the None dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 1.3065
22
+ - Accuracy: 0.6045
23
+ - Precision Macro: 0.5769
24
+ - Recall Macro: 0.5921
25
+ - F1 Macro: 0.5726
26
+ - Precision Weighted: 0.6266
27
+ - Recall Weighted: 0.6045
28
+ - F1 Weighted: 0.6049
29
+
30
+ ## Model description
31
+
32
+ More information needed
33
+
34
+ ## Intended uses & limitations
35
+
36
+ More information needed
37
+
38
+ ## Training and evaluation data
39
+
40
+ More information needed
41
+
42
+ ## Training procedure
43
+
44
+ ### Training hyperparameters
45
+
46
+ The following hyperparameters were used during training:
47
+ - learning_rate: 2e-05
48
+ - train_batch_size: 32
49
+ - eval_batch_size: 8
50
+ - seed: 3407
51
+ - optimizer: Use OptimizerNames.ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
52
+ - lr_scheduler_type: cosine
53
+ - lr_scheduler_warmup_steps: 50
54
+ - num_epochs: 20
55
+
56
+ ### Training results
57
+
58
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision Macro | Recall Macro | F1 Macro | Precision Weighted | Recall Weighted | F1 Weighted |
59
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------------:|:------------:|:--------:|:------------------:|:---------------:|:-----------:|
60
+ | 1.5869 | 0.4 | 20 | 1.6105 | 0.2821 | 0.0564 | 0.2 | 0.0880 | 0.0796 | 0.2821 | 0.1242 |
61
+ | 1.6423 | 0.8 | 40 | 1.5978 | 0.2922 | 0.2473 | 0.2177 | 0.1478 | 0.3269 | 0.2922 | 0.1993 |
62
+ | 1.4869 | 1.2 | 60 | 1.4559 | 0.4383 | 0.3448 | 0.3580 | 0.3347 | 0.4135 | 0.4383 | 0.4073 |
63
+ | 1.4004 | 1.6 | 80 | 1.3144 | 0.5139 | 0.4732 | 0.4553 | 0.4486 | 0.5264 | 0.5139 | 0.5014 |
64
+ | 1.2658 | 2.0 | 100 | 1.3022 | 0.4710 | 0.4792 | 0.4561 | 0.4008 | 0.5682 | 0.4710 | 0.4429 |
65
+ | 1.3302 | 2.4 | 120 | 1.2608 | 0.4861 | 0.5356 | 0.5254 | 0.4649 | 0.5991 | 0.4861 | 0.4965 |
66
+ | 0.8278 | 2.8 | 140 | 1.2198 | 0.5516 | 0.5583 | 0.5455 | 0.5293 | 0.5972 | 0.5516 | 0.5579 |
67
+ | 0.8199 | 3.2 | 160 | 1.1870 | 0.5743 | 0.5562 | 0.5561 | 0.5367 | 0.6063 | 0.5743 | 0.5728 |
68
+ | 0.9208 | 3.6 | 180 | 1.1146 | 0.5693 | 0.5529 | 0.5727 | 0.5439 | 0.6211 | 0.5693 | 0.5805 |
69
+ | 0.3989 | 4.0 | 200 | 1.1472 | 0.5693 | 0.5512 | 0.5756 | 0.5466 | 0.6132 | 0.5693 | 0.5819 |
70
+ | 0.8179 | 4.4 | 220 | 1.1235 | 0.6045 | 0.5704 | 0.5953 | 0.5772 | 0.6201 | 0.6045 | 0.6086 |
71
+ | 0.8518 | 4.8 | 240 | 1.2760 | 0.5869 | 0.5774 | 0.5818 | 0.5599 | 0.6278 | 0.5869 | 0.5955 |
72
+ | 0.641 | 5.2 | 260 | 1.2151 | 0.5668 | 0.5487 | 0.5737 | 0.5461 | 0.6013 | 0.5668 | 0.5767 |
73
+ | 0.4873 | 5.6 | 280 | 1.3065 | 0.6045 | 0.5769 | 0.5921 | 0.5726 | 0.6266 | 0.6045 | 0.6049 |
74
+
75
+
76
+ ### Framework versions
77
+
78
+ - Transformers 4.51.3
79
+ - Pytorch 2.6.0+cu124
80
+ - Datasets 3.6.0
81
+ - Tokenizers 0.21.1
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "id2label": {
13
+ "0": "basic negative",
14
+ "1": "moderate negative",
15
+ "2": "severe negative",
16
+ "3": "neutral",
17
+ "4": "positive"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "basic negative": 0,
23
+ "moderate negative": 1,
24
+ "neutral": 3,
25
+ "positive": 4,
26
+ "severe negative": 2
27
+ },
28
+ "layer_norm_eps": 1e-05,
29
+ "max_position_embeddings": 514,
30
+ "model_type": "roberta",
31
+ "num_attention_heads": 12,
32
+ "num_hidden_layers": 12,
33
+ "pad_token_id": 1,
34
+ "position_embedding_type": "absolute",
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.51.3",
37
+ "type_vocab_size": 1,
38
+ "use_cache": true,
39
+ "vocab_size": 50265
40
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1696e0effa9672fac810066cbf30aad720dacb161200dbadb2f9ec375cafd4b5
3
+ size 498622052
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": false,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "extra_special_tokens": {},
51
+ "mask_token": "<mask>",
52
+ "model_max_length": 512,
53
+ "pad_token": "<pad>",
54
+ "sep_token": "</s>",
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": "<unk>"
58
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6583a39351afe78a0bf5fd6eb97d54cd88e2bfb47b03f0882a721058f40b4720
3
+ size 5432
vocab.json ADDED
The diff for this file is too large to render. See raw diff