jgibb commited on
Commit
c57e5d2
1 Parent(s): 845bf6e

training completed[dev]: 512 128

Browse files
README.md ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: t5-base
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - rouge
8
+ - wer
9
+ model-index:
10
+ - name: t-5-base-baseline
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # t-5-base-baseline
18
+
19
+ This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 1.1785
22
+ - Rouge1: 0.6774
23
+ - Rouge2: 0.4106
24
+ - Rougel: 0.6163
25
+ - Rougelsum: 0.6162
26
+ - Wer: 0.4869
27
+ - Bleurt: 0.3779
28
+
29
+ ## Model description
30
+
31
+ More information needed
32
+
33
+ ## Intended uses & limitations
34
+
35
+ More information needed
36
+
37
+ ## Training and evaluation data
38
+
39
+ More information needed
40
+
41
+ ## Training procedure
42
+
43
+ ### Training hyperparameters
44
+
45
+ The following hyperparameters were used during training:
46
+ - learning_rate: 2e-05
47
+ - train_batch_size: 6
48
+ - eval_batch_size: 6
49
+ - seed: 42
50
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
+ - lr_scheduler_type: linear
52
+ - num_epochs: 2
53
+ - mixed_precision_training: Native AMP
54
+
55
+ ### Training results
56
+
57
+ | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Wer | Bleurt |
58
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:------:|:------:|
59
+ | No log | 0.13 | 250 | 1.3316 | 0.651 | 0.3769 | 0.5867 | 0.5868 | 0.5217 | 0.3009 |
60
+ | 1.7919 | 0.27 | 500 | 1.2776 | 0.6595 | 0.3865 | 0.5963 | 0.5963 | 0.5108 | 0.3009 |
61
+ | 1.7919 | 0.4 | 750 | 1.2513 | 0.6635 | 0.393 | 0.6015 | 0.6016 | 0.5039 | 0.3009 |
62
+ | 1.3552 | 0.53 | 1000 | 1.2326 | 0.6668 | 0.3967 | 0.6049 | 0.6049 | 0.5008 | 0.3009 |
63
+ | 1.3552 | 0.66 | 1250 | 1.2236 | 0.6692 | 0.4 | 0.6073 | 0.6073 | 0.4972 | 0.3314 |
64
+ | 1.3074 | 0.8 | 1500 | 1.2118 | 0.6713 | 0.4022 | 0.6094 | 0.6094 | 0.4953 | 0.3314 |
65
+ | 1.3074 | 0.93 | 1750 | 1.2022 | 0.6715 | 0.4035 | 0.6106 | 0.6106 | 0.4932 | 0.2798 |
66
+ | 1.3037 | 1.06 | 2000 | 1.1972 | 0.6731 | 0.4053 | 0.6118 | 0.6118 | 0.4916 | 0.3771 |
67
+ | 1.3037 | 1.2 | 2250 | 1.1909 | 0.675 | 0.4068 | 0.6137 | 0.6136 | 0.4905 | 0.3314 |
68
+ | 1.2676 | 1.33 | 2500 | 1.1889 | 0.6761 | 0.4087 | 0.6144 | 0.6144 | 0.4893 | 0.3314 |
69
+ | 1.2676 | 1.46 | 2750 | 1.1848 | 0.6763 | 0.4091 | 0.6151 | 0.6151 | 0.4884 | 0.3314 |
70
+ | 1.2796 | 1.6 | 3000 | 1.1829 | 0.6771 | 0.4095 | 0.6155 | 0.6155 | 0.488 | 0.3123 |
71
+ | 1.2796 | 1.73 | 3250 | 1.1808 | 0.6769 | 0.4101 | 0.6159 | 0.6159 | 0.4876 | 0.3779 |
72
+ | 1.2489 | 1.86 | 3500 | 1.1787 | 0.6772 | 0.4105 | 0.6162 | 0.6162 | 0.4869 | 0.3771 |
73
+ | 1.2489 | 1.99 | 3750 | 1.1785 | 0.6774 | 0.4106 | 0.6163 | 0.6162 | 0.4869 | 0.3779 |
74
+
75
+
76
+ ### Framework versions
77
+
78
+ - Transformers 4.38.2
79
+ - Pytorch 2.2.1+cu121
80
+ - Datasets 2.18.0
81
+ - Tokenizers 0.15.2
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "test_BLEURT": -0.9706,
3
+ "test_WER": 0.4816,
4
+ "test_loss": 1.195426344871521,
5
+ "test_rouge1": 0.6823,
6
+ "test_rouge2": 0.4189,
7
+ "test_rougeL": 0.6225,
8
+ "test_rougeLsum": 0.6219,
9
+ "test_runtime": 31.876,
10
+ "test_samples_per_second": 11.827,
11
+ "test_steps_per_second": 1.976
12
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.38.2"
7
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:073b1acb793563020eccf00c4d1a4c0cbcc9d3e0f09bec57770f55da1fa060f3
3
  size 891644712
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b9613afbb9d6a6140659f4336ce375e04d821d1506dcda5db5e31ff0cf1c38a
3
  size 891644712
runs/Mar30_02-19-53_9404495fcefe/events.out.tfevents.1711765198.9404495fcefe.1247.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d697dadf4e19a2cd9ba659da8a79655b3f6352b4414d6f9d78ec7f94a8e14138
3
- size 8277
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d680ebf640682e5c704e98c675270309c65587d32949cdab9980c31217703da
3
+ size 15967
test_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "test_BLEURT": -0.9706,
3
+ "test_WER": 0.4816,
4
+ "test_loss": 1.195426344871521,
5
+ "test_rouge1": 0.6823,
6
+ "test_rouge2": 0.4189,
7
+ "test_rougeL": 0.6225,
8
+ "test_rougeLsum": 0.6219,
9
+ "test_runtime": 31.876,
10
+ "test_samples_per_second": 11.827,
11
+ "test_steps_per_second": 1.976
12
+ }