october-sd commited on
Commit
e7cd2ba
1 Parent(s): 8467365

Training complete

Browse files
README.md ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: ai4bharat/IndicBART
3
+ tags:
4
+ - summarization
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: IndicBART_new_2
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
+ # IndicBART_new_2
15
+
16
+ This model is a fine-tuned version of [ai4bharat/IndicBART](https://huggingface.co/ai4bharat/IndicBART) on the None dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 3.3218
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: 0.001
38
+ - train_batch_size: 32
39
+ - eval_batch_size: 32
40
+ - seed: 42
41
+ - gradient_accumulation_steps: 32
42
+ - total_train_batch_size: 1024
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - lr_scheduler_warmup_steps: 500
46
+ - num_epochs: 8
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:-----:|:----:|:---------------:|
52
+ | No log | 0.96 | 11 | 5.4424 |
53
+ | No log | 2.0 | 23 | 4.3784 |
54
+ | No log | 2.96 | 34 | 4.0395 |
55
+ | No log | 4.0 | 46 | 3.7066 |
56
+ | No log | 4.96 | 57 | 3.5332 |
57
+ | No log | 6.0 | 69 | 3.4435 |
58
+ | No log | 6.96 | 80 | 3.3687 |
59
+ | No log | 7.65 | 88 | 3.3218 |
60
+
61
+
62
+ ### Framework versions
63
+
64
+ - Transformers 4.38.2
65
+ - Pytorch 2.1.2
66
+ - Datasets 2.15.0
67
+ - Tokenizers 0.15.2
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 64000,
4
+ "eos_token_id": 64001,
5
+ "forced_eos_token_id": 2,
6
+ "pad_token_id": 0,
7
+ "transformers_version": "4.38.2"
8
+ }
runs/Apr07_05-11-26_cee67a20753b/events.out.tfevents.1712466698.cee67a20753b.34.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a44778b4656796cb74e19f5ed9b294014bb9fa4d5a12ca1a4eea7de828216331
3
- size 7118
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2291202a7929e21a5e9763144275cbf06a266e1f82c78a81ba42b462768c412f
3
+ size 7466