manimaranpa07 commited on
Commit
722324b
1 Parent(s): ba10b72

End of training

Browse files
README.md ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: facebook/bart-large-mnli
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: mnli_bart_text_classification_1_08th_march_margs
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
+ # mnli_bart_text_classification_1_08th_march_margs
15
+
16
+ This model is a fine-tuned version of [facebook/bart-large-mnli](https://huggingface.co/facebook/bart-large-mnli) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.6755
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 2e-05
38
+ - train_batch_size: 16
39
+ - eval_batch_size: 16
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - num_epochs: 6
44
+ - label_smoothing_factor: 0.1
45
+
46
+ ### Training results
47
+
48
+ | Training Loss | Epoch | Step | Validation Loss |
49
+ |:-------------:|:-----:|:----:|:---------------:|
50
+ | No log | 1.0 | 22 | 0.7349 |
51
+ | No log | 2.0 | 44 | 0.6755 |
52
+ | No log | 3.0 | 66 | 0.7101 |
53
+ | No log | 4.0 | 88 | 0.6882 |
54
+ | No log | 5.0 | 110 | 0.6899 |
55
+ | No log | 6.0 | 132 | 0.6862 |
56
+
57
+
58
+ ### Framework versions
59
+
60
+ - Transformers 4.38.2
61
+ - Pytorch 2.1.0+cu121
62
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/bart-large-mnli",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "gelu",
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "BartForSequenceClassification"
9
+ ],
10
+ "attention_dropout": 0.0,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.0,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 1024,
15
+ "decoder_attention_heads": 16,
16
+ "decoder_ffn_dim": 4096,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 12,
19
+ "decoder_start_token_id": 2,
20
+ "dropout": 0.1,
21
+ "encoder_attention_heads": 16,
22
+ "encoder_ffn_dim": 4096,
23
+ "encoder_layerdrop": 0.0,
24
+ "encoder_layers": 12,
25
+ "eos_token_id": 2,
26
+ "forced_eos_token_id": 2,
27
+ "gradient_checkpointing": false,
28
+ "id2label": {
29
+ "0": "contradiction",
30
+ "1": "neutral",
31
+ "2": "entailment"
32
+ },
33
+ "init_std": 0.02,
34
+ "is_encoder_decoder": true,
35
+ "label2id": {
36
+ "contradiction": 0,
37
+ "entailment": 2,
38
+ "neutral": 1
39
+ },
40
+ "max_position_embeddings": 1024,
41
+ "model_type": "bart",
42
+ "normalize_before": false,
43
+ "num_hidden_layers": 12,
44
+ "output_past": false,
45
+ "pad_token_id": 1,
46
+ "scale_embedding": false,
47
+ "torch_dtype": "float32",
48
+ "transformers_version": "4.38.2",
49
+ "use_cache": true,
50
+ "vocab_size": 50265
51
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3742136a7ef6f3fc95779354a31267a113ae98d9b061f5297ac3db162ec4a25
3
+ size 1629436964
runs/Mar08_17-05-54_a82360cb2031/events.out.tfevents.1709917555.a82360cb2031.657.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0db2e3184d8105411cbf730c533f49585619da0ae6e3fe60e2d2bcd6b1f1664
3
+ size 7170
runs/Mar08_17-05-54_a82360cb2031/events.out.tfevents.1709917999.a82360cb2031.657.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d64e432efbd7a2028743d4f59a10aa63348832e4f9c797f31001fed9e01d799
3
+ size 359
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a243c01760d5ad8e1d0c318aecc365ffe64c4afac796cf6c96fa52c00f8ca361
3
+ size 4984