varun-v-rao commited on
Commit
0d75d7c
1 Parent(s): 188b0dd

Training in progress, epoch 1

Browse files
README.md ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/bart-base
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - stanfordnlp/snli
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: bart-base-snli-model1
12
+ results:
13
+ - task:
14
+ name: Text Classification
15
+ type: text-classification
16
+ dataset:
17
+ name: snli
18
+ type: stanfordnlp/snli
19
+ metrics:
20
+ - name: Accuracy
21
+ type: accuracy
22
+ value: 0.9129242023978866
23
+ ---
24
+
25
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
26
+ should probably proofread and complete it, then remove this comment. -->
27
+
28
+ # bart-base-snli-model1
29
+
30
+ This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the snli dataset.
31
+ It achieves the following results on the evaluation set:
32
+ - Loss: 0.2576
33
+ - Accuracy: 0.9129
34
+
35
+ ## Model description
36
+
37
+ More information needed
38
+
39
+ ## Intended uses & limitations
40
+
41
+ More information needed
42
+
43
+ ## Training and evaluation data
44
+
45
+ More information needed
46
+
47
+ ## Training procedure
48
+
49
+ ### Training hyperparameters
50
+
51
+ The following hyperparameters were used during training:
52
+ - learning_rate: 2e-05
53
+ - train_batch_size: 64
54
+ - eval_batch_size: 32
55
+ - seed: 58
56
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
57
+ - lr_scheduler_type: linear
58
+ - num_epochs: 3
59
+
60
+ ### Training results
61
+
62
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
63
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
64
+ | 0.3378 | 1.0 | 8584 | 0.2729 | 0.9033 |
65
+ | 0.2912 | 2.0 | 17168 | 0.2589 | 0.9100 |
66
+ | 0.2516 | 3.0 | 25752 | 0.2576 | 0.9129 |
67
+
68
+
69
+ ### Framework versions
70
+
71
+ - Transformers 4.35.2
72
+ - Pytorch 2.0.1+cu118
73
+ - Datasets 2.15.0
74
+ - Tokenizers 0.15.0
config.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/bart-base",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "BartForSequenceClassification"
9
+ ],
10
+ "attention_dropout": 0.1,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.1,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 768,
15
+ "decoder_attention_heads": 12,
16
+ "decoder_ffn_dim": 3072,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 6,
19
+ "decoder_start_token_id": 2,
20
+ "dropout": 0.1,
21
+ "early_stopping": true,
22
+ "encoder_attention_heads": 12,
23
+ "encoder_ffn_dim": 3072,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 6,
26
+ "eos_token_id": 2,
27
+ "forced_bos_token_id": 0,
28
+ "forced_eos_token_id": 2,
29
+ "gradient_checkpointing": false,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1",
33
+ "2": "LABEL_2"
34
+ },
35
+ "init_std": 0.02,
36
+ "is_encoder_decoder": true,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1,
40
+ "LABEL_2": 2
41
+ },
42
+ "max_position_embeddings": 1024,
43
+ "model_type": "bart",
44
+ "no_repeat_ngram_size": 3,
45
+ "normalize_before": false,
46
+ "normalize_embedding": true,
47
+ "num_beams": 4,
48
+ "num_hidden_layers": 6,
49
+ "pad_token_id": 1,
50
+ "problem_type": "single_label_classification",
51
+ "scale_embedding": false,
52
+ "task_specific_params": {
53
+ "summarization": {
54
+ "length_penalty": 1.0,
55
+ "max_length": 128,
56
+ "min_length": 12,
57
+ "num_beams": 4
58
+ },
59
+ "summarization_cnn": {
60
+ "length_penalty": 2.0,
61
+ "max_length": 142,
62
+ "min_length": 56,
63
+ "num_beams": 4
64
+ },
65
+ "summarization_xsum": {
66
+ "length_penalty": 1.0,
67
+ "max_length": 62,
68
+ "min_length": 11,
69
+ "num_beams": 6
70
+ }
71
+ },
72
+ "torch_dtype": "float32",
73
+ "transformers_version": "4.35.2",
74
+ "use_cache": true,
75
+ "vocab_size": 50265
76
+ }
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:f95edf3b3d53b4bf1489f9b9d869ac425d89993aa5462cfc39f6efa8223f4f27
3
+ size 560083468
runs/Jun18_20-54-01_gl1517.arc-ts.umich.edu/events.out.tfevents.1718758446.gl1517.arc-ts.umich.edu.4162892.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:789b4ecb47e83fe1d533f12eaab0788909e5ff89c77c26887486aec335355c2a
3
+ size 15047
runs/Jun19_14-30-36_gl1528.arc-ts.umich.edu/events.out.tfevents.1718821841.gl1528.arc-ts.umich.edu.1068153.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0b610fbc3edadf6e03aba476fb9e6036a732756a5087e520534fa0339b3da04
3
+ size 6606
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": true,
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 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 1024,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "BartTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e82f73829c2c7bd2d883223ebb252f927dbb140fd9bf7f3d9ed1d585b803216b
3
+ size 4856
vocab.json ADDED
The diff for this file is too large to render. See raw diff