thanhdath commited on
Commit
fe8891c
1 Parent(s): 6e98f57

Training in progress, epoch 1

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 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: microsoft/Multilingual-MiniLM-L12-H384
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: intent_trading
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
+ # intent_trading
17
+
18
+ This model is a fine-tuned version of [microsoft/Multilingual-MiniLM-L12-H384](https://huggingface.co/microsoft/Multilingual-MiniLM-L12-H384) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.1741
21
+ - Accuracy: 0.9548
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: 2e-05
41
+ - train_batch_size: 64
42
+ - eval_batch_size: 64
43
+ - seed: 42
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 40
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
+ | No log | 1.0 | 227 | 1.5904 | 0.7689 |
53
+ | No log | 2.0 | 454 | 1.0086 | 0.8670 |
54
+ | 1.6528 | 3.0 | 681 | 0.6706 | 0.9055 |
55
+ | 1.6528 | 4.0 | 908 | 0.4376 | 0.9518 |
56
+ | 0.6124 | 5.0 | 1135 | 0.2966 | 0.9551 |
57
+ | 0.6124 | 6.0 | 1362 | 0.2373 | 0.9504 |
58
+ | 0.2536 | 7.0 | 1589 | 0.1967 | 0.9537 |
59
+ | 0.2536 | 8.0 | 1816 | 0.1666 | 0.9565 |
60
+ | 0.1476 | 9.0 | 2043 | 0.1642 | 0.9543 |
61
+ | 0.1476 | 10.0 | 2270 | 0.1570 | 0.9551 |
62
+ | 0.1476 | 11.0 | 2497 | 0.1500 | 0.9543 |
63
+ | 0.1067 | 12.0 | 2724 | 0.1469 | 0.9548 |
64
+ | 0.1067 | 13.0 | 2951 | 0.1458 | 0.9557 |
65
+ | 0.0817 | 14.0 | 3178 | 0.1409 | 0.9540 |
66
+ | 0.0817 | 15.0 | 3405 | 0.1426 | 0.9595 |
67
+ | 0.0709 | 16.0 | 3632 | 0.1418 | 0.9540 |
68
+ | 0.0709 | 17.0 | 3859 | 0.1416 | 0.9557 |
69
+ | 0.0631 | 18.0 | 4086 | 0.1373 | 0.9581 |
70
+ | 0.0631 | 19.0 | 4313 | 0.1458 | 0.9559 |
71
+ | 0.0557 | 20.0 | 4540 | 0.1391 | 0.9559 |
72
+ | 0.0557 | 21.0 | 4767 | 0.1526 | 0.9518 |
73
+ | 0.0557 | 22.0 | 4994 | 0.1511 | 0.9529 |
74
+ | 0.0495 | 23.0 | 5221 | 0.1578 | 0.9526 |
75
+ | 0.0495 | 24.0 | 5448 | 0.1360 | 0.9568 |
76
+ | 0.0443 | 25.0 | 5675 | 0.1451 | 0.9565 |
77
+ | 0.0443 | 26.0 | 5902 | 0.1477 | 0.9562 |
78
+ | 0.0419 | 27.0 | 6129 | 0.1624 | 0.9540 |
79
+ | 0.0419 | 28.0 | 6356 | 0.1659 | 0.9537 |
80
+ | 0.0371 | 29.0 | 6583 | 0.1607 | 0.9548 |
81
+ | 0.0371 | 30.0 | 6810 | 0.1638 | 0.9543 |
82
+ | 0.035 | 31.0 | 7037 | 0.1655 | 0.9529 |
83
+ | 0.035 | 32.0 | 7264 | 0.1662 | 0.9562 |
84
+ | 0.035 | 33.0 | 7491 | 0.1702 | 0.9532 |
85
+ | 0.033 | 34.0 | 7718 | 0.1662 | 0.9562 |
86
+ | 0.033 | 35.0 | 7945 | 0.1667 | 0.9532 |
87
+ | 0.0309 | 36.0 | 8172 | 0.1794 | 0.9554 |
88
+ | 0.0309 | 37.0 | 8399 | 0.1756 | 0.9546 |
89
+ | 0.0292 | 38.0 | 8626 | 0.1722 | 0.9559 |
90
+ | 0.0292 | 39.0 | 8853 | 0.1706 | 0.9559 |
91
+ | 0.0281 | 40.0 | 9080 | 0.1741 | 0.9548 |
92
+
93
+
94
+ ### Framework versions
95
+
96
+ - Transformers 4.40.2
97
+ - Pytorch 2.1.0+cu121
98
+ - Datasets 2.14.5
99
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-base",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "buy_coin",
15
+ "1": "sell_coin",
16
+ "2": "current_coin_price",
17
+ "3": "predict_signal",
18
+ "4": "check_human",
19
+ "5": "affirm",
20
+ "6": "deny",
21
+ "7": "goodbye",
22
+ "8": "greet",
23
+ "9": "inform",
24
+ "10": "thankyou",
25
+ "11": "help",
26
+ "12": "human_handoff",
27
+ "13": "out_of_scope",
28
+ "14": "check_image"
29
+ },
30
+ "initializer_range": 0.02,
31
+ "intermediate_size": 3072,
32
+ "label2id": {
33
+ "affirm": 5,
34
+ "buy_coin": 0,
35
+ "check_human": 4,
36
+ "check_image": 14,
37
+ "current_coin_price": 2,
38
+ "deny": 6,
39
+ "goodbye": 7,
40
+ "greet": 8,
41
+ "help": 11,
42
+ "human_handoff": 12,
43
+ "inform": 9,
44
+ "out_of_scope": 13,
45
+ "predict_signal": 3,
46
+ "sell_coin": 1,
47
+ "thankyou": 10
48
+ },
49
+ "layer_norm_eps": 1e-05,
50
+ "max_position_embeddings": 514,
51
+ "model_type": "xlm-roberta",
52
+ "num_attention_heads": 12,
53
+ "num_hidden_layers": 12,
54
+ "output_past": true,
55
+ "pad_token_id": 1,
56
+ "position_embedding_type": "absolute",
57
+ "problem_type": "single_label_classification",
58
+ "torch_dtype": "float32",
59
+ "transformers_version": "4.40.2",
60
+ "type_vocab_size": 1,
61
+ "use_cache": true,
62
+ "vocab_size": 250002
63
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fd2d6942a4b1cdcac44ad66af3d9d94508d1885cbd884edf32681f9fc39440a
3
+ size 1112244996
runs/May25_22-14-38_Precision-3660/events.out.tfevents.1716639279.Precision-3660.1574450.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a4e417b0b4d8fee60986c2b8e5db45737ce6f3185350530f54f5cb47c7b8fc0
3
+ size 22403
runs/May25_22-54-42_Precision-3660/events.out.tfevents.1716641682.Precision-3660.1584143.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18482c3f91944a56183be7af650348c60dde951922f67cb1c4a73d482d4ece41
3
+ size 22403
runs/May25_23-26-39_Precision-3660/events.out.tfevents.1716643600.Precision-3660.1589267.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72b4a363556db3274a034cf692bb23bab9c17c0727506671e182cbceb3996e4f
3
+ size 5724
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
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
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8373f9cd3d27591e1924426bcc1c8799bc5a9affc4fc857982c5d66668dd1f41
3
+ size 17082832
tokenizer_config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "model_max_length": 512,
50
+ "pad_token": "<pad>",
51
+ "sep_token": "</s>",
52
+ "tokenizer_class": "XLMRobertaTokenizer",
53
+ "unk_token": "<unk>"
54
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b24f802a67caca333c5240012d56c1a6f8561b153e5e9a7942a03f60d590f9de
3
+ size 5048