Shijia commited on
Commit
060dc3d
1 Parent(s): 2791cbc

End of training

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 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: FacebookAI/xlm-roberta-base
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: xlm-roberta-base_arq_loss_0.0001
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # xlm-roberta-base_arq_loss_0.0001
15
+
16
+ This model is a fine-tuned version of [FacebookAI/xlm-roberta-base](https://huggingface.co/FacebookAI/xlm-roberta-base) on the None dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.0462
19
+ - Spearman Corr: nan
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 0.0001
39
+ - train_batch_size: 32
40
+ - eval_batch_size: 128
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 2
43
+ - total_train_batch_size: 64
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 30
47
+ - mixed_precision_training: Native AMP
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Spearman Corr |
52
+ |:-------------:|:-----:|:----:|:---------------:|:-------------:|
53
+ | No log | 0.92 | 200 | 0.0484 | nan |
54
+ | No log | 1.84 | 400 | 0.0496 | nan |
55
+ | 0.0501 | 2.76 | 600 | 0.0483 | 0.0501 |
56
+ | 0.0501 | 3.69 | 800 | 0.0488 | -0.0542 |
57
+ | 0.05 | 4.61 | 1000 | 0.0462 | nan |
58
+ | 0.05 | 5.53 | 1200 | 0.0462 | nan |
59
+ | 0.0503 | 6.45 | 1400 | 0.0467 | nan |
60
+ | 0.0503 | 7.37 | 1600 | 0.0487 | -0.0028 |
61
+ | 0.0501 | 8.29 | 1800 | 0.0473 | nan |
62
+ | 0.0501 | 9.22 | 2000 | 0.0490 | 0.0793 |
63
+ | 0.0498 | 10.14 | 2200 | 0.0477 | nan |
64
+ | 0.0498 | 11.06 | 2400 | 0.0474 | 0.0143 |
65
+ | 0.05 | 11.98 | 2600 | 0.0462 | nan |
66
+
67
+
68
+ ### Framework versions
69
+
70
+ - Transformers 4.37.2
71
+ - Pytorch 2.2.0+cu121
72
+ - Datasets 2.17.0
73
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "FacebookAI/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": "LABEL_0"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "LABEL_0": 0
20
+ },
21
+ "layer_norm_eps": 1e-05,
22
+ "max_position_embeddings": 514,
23
+ "model_type": "xlm-roberta",
24
+ "num_attention_heads": 12,
25
+ "num_hidden_layers": 12,
26
+ "output_past": true,
27
+ "pad_token_id": 1,
28
+ "position_embedding_type": "absolute",
29
+ "problem_type": "regression",
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.37.2",
32
+ "type_vocab_size": 1,
33
+ "use_cache": true,
34
+ "vocab_size": 250002
35
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0496a5f3fa6fbf88e5e0306e5f819eb7c7019d5575cd3a36b6c577bf04f5a10f
3
+ size 1112201932
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:b2116c05e7305eea30394284760789681c5b3440dd4cd9a8c77539da68f9e8a6
3
+ size 17082854
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": 1000000000000000019884624838656,
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 sha256:6f338688c7cec0120a1231bded7ca8cf9d51cfc4363c7fab4b278b4599a53d9b
3
+ size 4664