MohammadKarami commited on
Commit
5341d88
1 Parent(s): e9815c2

IberTextClassificationBloom560mTask2

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: bigscience-bloom-rail-1.0
3
+ base_model: bigscience/bloom-560m
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - f1
8
+ model-index:
9
+ - name: Model
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # Model
17
+
18
+ This model is a fine-tuned version of [bigscience/bloom-560m](https://huggingface.co/bigscience/bloom-560m) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 1.3562
21
+ - F1: 0.7886
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 5e-05
41
+ - train_batch_size: 4
42
+ - eval_batch_size: 4
43
+ - seed: 42
44
+ - gradient_accumulation_steps: 4
45
+ - total_train_batch_size: 16
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: linear
48
+ - num_epochs: 3
49
+ - mixed_precision_training: Native AMP
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | F1 |
54
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
55
+ | 0.9849 | 1.0 | 2500 | 0.8808 | 0.6951 |
56
+ | 0.4775 | 2.0 | 5000 | 0.8355 | 0.739 |
57
+ | 0.1347 | 3.0 | 7500 | 1.3562 | 0.7886 |
58
+
59
+
60
+ ### Framework versions
61
+
62
+ - Transformers 4.41.2
63
+ - Pytorch 2.3.0+cu121
64
+ - Datasets 2.19.2
65
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bigscience/bloom-560m",
3
+ "apply_residual_connection_post_layernorm": false,
4
+ "architectures": [
5
+ "BloomForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "attention_softmax_in_fp32": true,
9
+ "bias_dropout_fusion": true,
10
+ "bos_token_id": 1,
11
+ "eos_token_id": 2,
12
+ "hidden_dropout": 0.0,
13
+ "hidden_size": 1024,
14
+ "id2label": {
15
+ "0": "A",
16
+ "1": "B",
17
+ "2": "C",
18
+ "3": "D",
19
+ "4": "E",
20
+ "5": "F"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "label2id": {
24
+ "A": 0,
25
+ "B": 1,
26
+ "C": 2,
27
+ "D": 3,
28
+ "E": 4,
29
+ "F": 5
30
+ },
31
+ "layer_norm_epsilon": 1e-05,
32
+ "masked_softmax_fusion": true,
33
+ "model_type": "bloom",
34
+ "n_head": 16,
35
+ "n_inner": null,
36
+ "n_layer": 24,
37
+ "offset_alibi": 100,
38
+ "pad_token_id": 3,
39
+ "pretraining_tp": 1,
40
+ "problem_type": "single_label_classification",
41
+ "skip_bias_add": true,
42
+ "skip_bias_add_qkv": false,
43
+ "slow_but_exact": false,
44
+ "torch_dtype": "float32",
45
+ "transformers_version": "4.41.2",
46
+ "unk_token_id": 0,
47
+ "use_cache": true,
48
+ "vocab_size": 250880
49
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7483ae5e760d6794c504414fb2479df6f2e44e680d9186c9cd1f899334d3b3a
3
+ size 2236916960
runs/Jun09_13-50-58_884b999f5375/events.out.tfevents.1717941059.884b999f5375.3379.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22ac2c8f7512fc13db7161fc6088cdd2a4a3f92e0ff4dcac733423c4569dc74d
3
+ size 9664
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c15972849c91c78dfab27e2ef0eb53b17f95c4fe81be6664f7e85c6a7fffde0e
3
+ size 14500499
tokenizer_config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<unk>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<pad>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ }
36
+ },
37
+ "bos_token": "<s>",
38
+ "clean_up_tokenization_spaces": false,
39
+ "eos_token": "</s>",
40
+ "model_max_length": 1000000000000000019884624838656,
41
+ "pad_token": "<pad>",
42
+ "padding_side": "left",
43
+ "tokenizer_class": "BloomTokenizer",
44
+ "unk_token": "<unk>"
45
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0be9525647ea7064d90169b41e5e7717c070e36472343d756e1e0748c712aff
3
+ size 5176