Hugging Face's logo

rutvikd0512
/
my-t5-summarization-model

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
rutvikd0512 commited on
Commit
516b3f9
·
verified ·
1 Parent(s): 3391af9

End of training

Browse files
Files changed (7) hide show
  1. README.md +80 -3
  2. adapter_config.json +29 -0
  3. adapter_model.safetensors +3 -0
  4. runs/Aug02_16-01-09_7aed7ede09b6/events.out.tfevents.1722614475.7aed7ede09b6.264.2 +3 -0
  5. runs/Aug02_16-23-50_7aed7ede09b6/events.out.tfevents.1722615834.7aed7ede09b6.264.3 +3 -0
  6. runs/Aug02_16-59-22_7aed7ede09b6/events.out.tfevents.1722617972.7aed7ede09b6.264.4 +3 -0
  7. training_args.bin +3 -0
README.md CHANGED
@@ -1,3 +1,80 @@
1
- ---
2
- license: mit
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: google-t5/t5-base
3
+ datasets:
4
+ - samsum
5
+ library_name: peft
6
+ license: apache-2.0
7
+ tags:
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: my-t5-summarization-model
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
+ # my-t5-summarization-model
18
+
19
+ This model is a fine-tuned version of [google-t5/t5-base](https://huggingface.co/google-t5/t5-base) on the samsum dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.2478
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 1e-05
41
+ - train_batch_size: 8
42
+ - eval_batch_size: 8
43
+ - seed: 42
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 20
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:-----:|:----:|:---------------:|
52
+ | 17.2263 | 1.0 | 74 | 20.5598 |
53
+ | 10.8174 | 2.0 | 148 | 12.3219 |
54
+ | 2.9638 | 3.0 | 222 | 0.6010 |
55
+ | 1.4073 | 4.0 | 296 | 0.2598 |
56
+ | 1.1503 | 5.0 | 370 | 0.2604 |
57
+ | 1.5418 | 6.0 | 444 | 0.2595 |
58
+ | 0.6755 | 7.0 | 518 | 0.2574 |
59
+ | 0.833 | 8.0 | 592 | 0.2550 |
60
+ | 0.5194 | 9.0 | 666 | 0.2549 |
61
+ | 0.7579 | 10.0 | 740 | 0.2553 |
62
+ | 0.6712 | 11.0 | 814 | 0.2545 |
63
+ | 0.6565 | 12.0 | 888 | 0.2540 |
64
+ | 0.262 | 13.0 | 962 | 0.2529 |
65
+ | 0.3144 | 14.0 | 1036 | 0.2518 |
66
+ | 0.6226 | 15.0 | 1110 | 0.2509 |
67
+ | 0.5695 | 16.0 | 1184 | 0.2498 |
68
+ | 0.2856 | 17.0 | 1258 | 0.2490 |
69
+ | 0.2869 | 18.0 | 1332 | 0.2484 |
70
+ | 0.6049 | 19.0 | 1406 | 0.2480 |
71
+ | 0.6421 | 20.0 | 1480 | 0.2478 |
72
+
73
+
74
+ ### Framework versions
75
+
76
+ - PEFT 0.12.0
77
+ - Transformers 4.42.4
78
+ - Pytorch 2.3.1+cu121
79
+ - Datasets 2.20.0
80
+ - Tokenizers 0.19.1
adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "google-t5/t5-base",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 128,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "q",
24
+ "v"
25
+ ],
26
+ "task_type": "SEQ_2_SEQ_LM",
27
+ "use_dora": false,
28
+ "use_rslora": false
29
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbecd45b5ed7a50cbe1c1aae3cb8e98bc1cf015ec047b2f64c61d296af45ecac
3
+ size 56643656
runs/Aug02_16-01-09_7aed7ede09b6/events.out.tfevents.1722614475.7aed7ede09b6.264.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f12797bd224972537bf797d41051be5ac663c4b8b22ea0d23f6079fd9ab0ec4
3
+ size 29947
runs/Aug02_16-23-50_7aed7ede09b6/events.out.tfevents.1722615834.7aed7ede09b6.264.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b45f23adbfbebb0c2dcb680c52785fe24cae0a3d751db51f913ef113e608bef6
3
+ size 20823
runs/Aug02_16-59-22_7aed7ede09b6/events.out.tfevents.1722617972.7aed7ede09b6.264.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51d5ce1e390f39034d576ed29e009b8195bc5e8f1838b6fcf0de625e350a5abe
3
+ size 48311
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90d8fb19de58503d1d413f5309370ad6786d2376e25b3d27f0e5c786783b67b1
3
+ size 5176