abdulrahman-nuzha commited on
Commit
1437a0a
·
verified ·
1 Parent(s): d44880d

End of training

Browse files
README.md ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: mit
4
+ base_model: intfloat/e5-small
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - accuracy
9
+ - precision
10
+ - recall
11
+ - f1
12
+ model-index:
13
+ - name: intfloat-e5-small-arabic-fp16
14
+ results: []
15
+ ---
16
+
17
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
18
+ should probably proofread and complete it, then remove this comment. -->
19
+
20
+ # intfloat-e5-small-arabic-fp16
21
+
22
+ This model is a fine-tuned version of [intfloat/e5-small](https://huggingface.co/intfloat/e5-small) on an unknown dataset.
23
+ It achieves the following results on the evaluation set:
24
+ - Loss: 0.7833
25
+ - Accuracy: 0.6782
26
+ - Precision: 0.6650
27
+ - Recall: 0.6782
28
+ - F1: 0.6560
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: 64
49
+ - eval_batch_size: 64
50
+ - seed: 42
51
+ - gradient_accumulation_steps: 2
52
+ - total_train_batch_size: 128
53
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
54
+ - lr_scheduler_type: linear
55
+ - lr_scheduler_warmup_ratio: 0.3
56
+ - num_epochs: 10
57
+ - mixed_precision_training: Native AMP
58
+
59
+ ### Training results
60
+
61
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
62
+ |:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
63
+ | 1.0984 | 0.3636 | 50 | 1.0847 | 0.4373 | 0.5309 | 0.4373 | 0.2662 |
64
+ | 1.069 | 0.7273 | 100 | 1.0270 | 0.5677 | 0.6816 | 0.5677 | 0.4864 |
65
+ | 1.0003 | 1.0873 | 150 | 0.9488 | 0.6041 | 0.6923 | 0.6041 | 0.5281 |
66
+ | 0.9438 | 1.4509 | 200 | 0.9085 | 0.6095 | 0.7017 | 0.6095 | 0.5340 |
67
+ | 0.9178 | 1.8145 | 250 | 0.9204 | 0.5895 | 0.6283 | 0.5895 | 0.5182 |
68
+ | 0.8936 | 2.1745 | 300 | 0.8394 | 0.6441 | 0.5970 | 0.6441 | 0.5653 |
69
+ | 0.8824 | 2.5382 | 350 | 0.8447 | 0.6464 | 0.7275 | 0.6464 | 0.5674 |
70
+ | 0.8774 | 2.9018 | 400 | 0.8706 | 0.625 | 0.6165 | 0.625 | 0.5859 |
71
+ | 0.8655 | 3.2618 | 450 | 0.8125 | 0.6541 | 0.6337 | 0.6541 | 0.6378 |
72
+ | 0.8517 | 3.6255 | 500 | 0.8528 | 0.6477 | 0.6565 | 0.6477 | 0.6013 |
73
+ | 0.8451 | 3.9891 | 550 | 0.7914 | 0.6686 | 0.6502 | 0.6686 | 0.6340 |
74
+ | 0.8084 | 4.3491 | 600 | 0.7833 | 0.6782 | 0.6650 | 0.6782 | 0.6560 |
75
+ | 0.8028 | 4.7127 | 650 | 0.7635 | 0.6923 | 0.6832 | 0.6923 | 0.6803 |
76
+ | 0.7874 | 5.0727 | 700 | 0.7815 | 0.6709 | 0.6828 | 0.6709 | 0.6754 |
77
+ | 0.7861 | 5.4364 | 750 | 0.7629 | 0.6873 | 0.6811 | 0.6873 | 0.6820 |
78
+ | 0.7593 | 5.8 | 800 | 0.7794 | 0.6823 | 0.6744 | 0.6823 | 0.6684 |
79
+ | 0.753 | 6.16 | 850 | 0.7680 | 0.6845 | 0.6859 | 0.6845 | 0.6838 |
80
+ | 0.753 | 6.5236 | 900 | 0.8404 | 0.6395 | 0.6783 | 0.6395 | 0.6459 |
81
+
82
+
83
+ ### Framework versions
84
+
85
+ - Transformers 4.51.1
86
+ - Pytorch 2.6.0+cu124
87
+ - Datasets 3.5.0
88
+ - Tokenizers 0.21.1
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 384,
10
+ "id2label": {
11
+ "0": "negative",
12
+ "1": "positive",
13
+ "2": "neutral"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 1536,
17
+ "label2id": {
18
+ "negative": 0,
19
+ "neutral": 2,
20
+ "positive": 1
21
+ },
22
+ "layer_norm_eps": 1e-12,
23
+ "max_position_embeddings": 512,
24
+ "model_type": "bert",
25
+ "num_attention_heads": 12,
26
+ "num_hidden_layers": 12,
27
+ "pad_token_id": 0,
28
+ "position_embedding_type": "absolute",
29
+ "problem_type": "single_label_classification",
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.51.1",
32
+ "type_vocab_size": 2,
33
+ "use_cache": true,
34
+ "vocab_size": 30522
35
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b1ca30001670523f8aaaaddabbd13e3d33d46a553f9401e7043c71281de6919
3
+ size 133467916
runs/Apr16_16-30-46_c1766b0a1233/events.out.tfevents.1744821057.c1766b0a1233.2393.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26ac6d629105633807b97f9dd54ba8fb5b7cafbd9fcc62a7856a632bdaf7f01b
3
+ size 17779
runs/Apr16_16-30-46_c1766b0a1233/events.out.tfevents.1744821508.c1766b0a1233.2393.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46fc29ab3b2f84ab267c00bb9db1eb7bd0c8cc5407d6810c9a813ecbf859e26c
3
+ size 560
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:881be0f80a21e0340ad9a2feafd0c77e49a967179cc8492628db4a7063253848
3
+ size 5368