Hugging Face's logo

phucndh
/
vietnamese-qa-finetuned

TensorBoard
Safetensors
gpt2
Generated from Trainer
Model card Files Metrics Community
phucndh commited on
Commit
8285d7a
·
verified ·
1 Parent(s): 4cf49d6

End of training

Browse files
Files changed (20) hide show
  1. .gitattributes +35 -35
  2. README.md +53 -0
  3. config.json +40 -0
  4. emissions.csv +2 -0
  5. generation_config.json +6 -0
  6. model.safetensors +3 -0
  7. runs/Feb18_18-52-14_LAPTOP-4CEU6S6B/events.out.tfevents.1739879541.LAPTOP-4CEU6S6B.22912.0 +3 -0
  8. runs/Feb18_20-18-43_LAPTOP-4CEU6S6B/events.out.tfevents.1739884726.LAPTOP-4CEU6S6B.30596.0 +3 -0
  9. runs/Feb18_20-20-48_LAPTOP-4CEU6S6B/events.out.tfevents.1739884852.LAPTOP-4CEU6S6B.15604.0 +3 -0
  10. runs/Feb18_20-23-10_LAPTOP-4CEU6S6B/events.out.tfevents.1739884994.LAPTOP-4CEU6S6B.13340.0 +3 -0
  11. runs/Feb18_20-25-49_LAPTOP-4CEU6S6B/events.out.tfevents.1739885154.LAPTOP-4CEU6S6B.28268.0 +3 -0
  12. runs/Feb18_20-29-10_LAPTOP-4CEU6S6B/events.out.tfevents.1739885354.LAPTOP-4CEU6S6B.5844.0 +3 -0
  13. runs/Feb18_20-32-42_LAPTOP-4CEU6S6B/events.out.tfevents.1739885566.LAPTOP-4CEU6S6B.14684.0 +3 -0
  14. runs/Feb18_20-37-16_LAPTOP-4CEU6S6B/events.out.tfevents.1739885840.LAPTOP-4CEU6S6B.22252.0 +3 -0
  15. runs/Feb18_20-43-05_LAPTOP-4CEU6S6B/events.out.tfevents.1739886189.LAPTOP-4CEU6S6B.24652.0 +3 -0
  16. runs/Feb18_20-48-16_LAPTOP-4CEU6S6B/events.out.tfevents.1739886500.LAPTOP-4CEU6S6B.29412.0 +3 -0
  17. runs/Feb18_20-54-01_LAPTOP-4CEU6S6B/events.out.tfevents.1739886845.LAPTOP-4CEU6S6B.18472.0 +3 -0
  18. runs/Feb18_20-54-48_LAPTOP-4CEU6S6B/events.out.tfevents.1739886891.LAPTOP-4CEU6S6B.18472.1 +3 -0
  19. runs/Feb18_20-57-51_LAPTOP-4CEU6S6B/events.out.tfevents.1739887075.LAPTOP-4CEU6S6B.24428.0 +3 -0
  20. training_args.bin +3 -0
.gitattributes CHANGED
@@ -1,35 +1,35 @@
1
- *.7z filter=lfs diff=lfs merge=lfs -text
2
- *.arrow filter=lfs diff=lfs merge=lfs -text
3
- *.bin filter=lfs diff=lfs merge=lfs -text
4
- *.bz2 filter=lfs diff=lfs merge=lfs -text
5
- *.ckpt filter=lfs diff=lfs merge=lfs -text
6
- *.ftz filter=lfs diff=lfs merge=lfs -text
7
- *.gz filter=lfs diff=lfs merge=lfs -text
8
- *.h5 filter=lfs diff=lfs merge=lfs -text
9
- *.joblib filter=lfs diff=lfs merge=lfs -text
10
- *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
- *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
- *.model filter=lfs diff=lfs merge=lfs -text
13
- *.msgpack filter=lfs diff=lfs merge=lfs -text
14
- *.npy filter=lfs diff=lfs merge=lfs -text
15
- *.npz filter=lfs diff=lfs merge=lfs -text
16
- *.onnx filter=lfs diff=lfs merge=lfs -text
17
- *.ot filter=lfs diff=lfs merge=lfs -text
18
- *.parquet filter=lfs diff=lfs merge=lfs -text
19
- *.pb filter=lfs diff=lfs merge=lfs -text
20
- *.pickle filter=lfs diff=lfs merge=lfs -text
21
- *.pkl filter=lfs diff=lfs merge=lfs -text
22
- *.pt filter=lfs diff=lfs merge=lfs -text
23
- *.pth filter=lfs diff=lfs merge=lfs -text
24
- *.rar filter=lfs diff=lfs merge=lfs -text
25
- *.safetensors filter=lfs diff=lfs merge=lfs -text
26
- saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
- *.tar.* filter=lfs diff=lfs merge=lfs -text
28
- *.tar filter=lfs diff=lfs merge=lfs -text
29
- *.tflite filter=lfs diff=lfs merge=lfs -text
30
- *.tgz filter=lfs diff=lfs merge=lfs -text
31
- *.wasm filter=lfs diff=lfs merge=lfs -text
32
- *.xz filter=lfs diff=lfs merge=lfs -text
33
- *.zip filter=lfs diff=lfs merge=lfs -text
34
- *.zst filter=lfs diff=lfs merge=lfs -text
35
- *tfevents* filter=lfs diff=lfs merge=lfs -text
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: NlpHUST/gpt2-vietnamese
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: vietnamese-qa-finetuned
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # vietnamese-qa-finetuned
14
+
15
+ This model is a fine-tuned version of [NlpHUST/gpt2-vietnamese](https://huggingface.co/NlpHUST/gpt2-vietnamese) on an unknown dataset.
16
+
17
+ ## Model description
18
+
19
+ More information needed
20
+
21
+ ## Intended uses & limitations
22
+
23
+ More information needed
24
+
25
+ ## Training and evaluation data
26
+
27
+ More information needed
28
+
29
+ ## Training procedure
30
+
31
+ ### Training hyperparameters
32
+
33
+ The following hyperparameters were used during training:
34
+ - learning_rate: 2e-05
35
+ - train_batch_size: 1
36
+ - eval_batch_size: 8
37
+ - seed: 42
38
+ - gradient_accumulation_steps: 4
39
+ - total_train_batch_size: 4
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: linear
42
+ - num_epochs: 3
43
+
44
+ ### Training results
45
+
46
+
47
+
48
+ ### Framework versions
49
+
50
+ - Transformers 4.38.1
51
+ - Pytorch 2.6.0+cpu
52
+ - Datasets 2.14.7
53
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "NlpHUST/gpt2-vietnamese",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.0,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.0,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "pad_token_id": 50257,
21
+ "reorder_and_upcast_attn": false,
22
+ "resid_pdrop": 0.0,
23
+ "scale_attn_by_inverse_layer_idx": false,
24
+ "scale_attn_weights": true,
25
+ "summary_activation": null,
26
+ "summary_first_dropout": 0.1,
27
+ "summary_proj_to_labels": true,
28
+ "summary_type": "cls_index",
29
+ "summary_use_proj": true,
30
+ "task_specific_params": {
31
+ "text-generation": {
32
+ "do_sample": true,
33
+ "max_length": 50
34
+ }
35
+ },
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.38.1",
38
+ "use_cache": true,
39
+ "vocab_size": 50257
40
+ }
emissions.csv ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ timestamp,project_name,run_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
2
+ 2025-02-18T21:01:26,codecarbon,7c6de38c-84a1-44b2-88a2-ced849ee11c3,211.5249261856079,0.0005821964402922135,2.7523774658186167e-06,14.0,0.0,5.9206438064575195,0.0008225891551706527,0,0.00034746679621849814,0.0011700559513891505,Vietnam,VNM,ho chi minh,,,Windows-10-10.0.22631-SP0,3.11.9,2.2.3,8,11th Gen Intel(R) Core(TM) i5-1135G7 @ 2.40GHz,,,106.6257,10.822,15.788383483886719,machine,N,1.0
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.38.1"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:705152a713d9467c2cb0ecbff237157025dcfe55c4b580aaf5e08ab6f43d52d0
3
+ size 497774208
runs/Feb18_18-52-14_LAPTOP-4CEU6S6B/events.out.tfevents.1739879541.LAPTOP-4CEU6S6B.22912.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa8fe7996a68f98be5a87594884161d52f3ee241d7166e927bced63bc55607ea
3
+ size 4880
runs/Feb18_20-18-43_LAPTOP-4CEU6S6B/events.out.tfevents.1739884726.LAPTOP-4CEU6S6B.30596.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb0bdd7878e62b266236f619b48549383ceaa9c5c123245cb72f3004831ac29b
3
+ size 4879
runs/Feb18_20-20-48_LAPTOP-4CEU6S6B/events.out.tfevents.1739884852.LAPTOP-4CEU6S6B.15604.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1378f00b6899055bbdfcf2fd908998a65f953c277aa08fd5b388d1e2588b4ae0
3
+ size 4878
runs/Feb18_20-23-10_LAPTOP-4CEU6S6B/events.out.tfevents.1739884994.LAPTOP-4CEU6S6B.13340.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f183e7f47281442e2b4ddacc793e424cacb9dd797bc795be52bc37356d1fea3
3
+ size 4878
runs/Feb18_20-25-49_LAPTOP-4CEU6S6B/events.out.tfevents.1739885154.LAPTOP-4CEU6S6B.28268.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:882d6a60f2ff01570786c2a5f05f115ca60acf908a1497a5c089ba86351b61cc
3
+ size 4878
runs/Feb18_20-29-10_LAPTOP-4CEU6S6B/events.out.tfevents.1739885354.LAPTOP-4CEU6S6B.5844.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:749396bf42dbf53fec4ca5cdc459c2ea6f648142f059924400f794a4ee1a478b
3
+ size 4878
runs/Feb18_20-32-42_LAPTOP-4CEU6S6B/events.out.tfevents.1739885566.LAPTOP-4CEU6S6B.14684.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6851e91b6fc7c300437355452991a9f033cf978ac6b256c8b7d5b2bbbc2e02ad
3
+ size 4878
runs/Feb18_20-37-16_LAPTOP-4CEU6S6B/events.out.tfevents.1739885840.LAPTOP-4CEU6S6B.22252.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4959c92f1159261b41dd90f95aeb9171a53f6a785aba9335a83fd1eea54966d7
3
+ size 4878
runs/Feb18_20-43-05_LAPTOP-4CEU6S6B/events.out.tfevents.1739886189.LAPTOP-4CEU6S6B.24652.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dc1e222c7d3f7614dca9b765f8998dd43283701ce1d0de34fb419dd7bbce088
3
+ size 4878
runs/Feb18_20-48-16_LAPTOP-4CEU6S6B/events.out.tfevents.1739886500.LAPTOP-4CEU6S6B.29412.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d94297d8b147c05b413d7db16c54d099b3c9937b3b899b2c11eb4deba7ab4e11
3
+ size 4878
runs/Feb18_20-54-01_LAPTOP-4CEU6S6B/events.out.tfevents.1739886845.LAPTOP-4CEU6S6B.18472.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b39bc84062d3fc53111ddca0996f0175926b86411f9054107ab2cc8e34965f5b
3
+ size 4878
runs/Feb18_20-54-48_LAPTOP-4CEU6S6B/events.out.tfevents.1739886891.LAPTOP-4CEU6S6B.18472.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a9724e889a0f099f10cba2b8b03d1628a36670060bd4df64ed8cdb9d6d715e3
3
+ size 4878
runs/Feb18_20-57-51_LAPTOP-4CEU6S6B/events.out.tfevents.1739887075.LAPTOP-4CEU6S6B.24428.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:921dc5c8c8e5764dc8d87f8a692631df25334f097c3e5c7999cf8f7f8289e4c6
3
+ size 6054
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb362d7e52a0e334eaeda2b030e96fa0ab8fc5e41175844b0bbebf924bf01e42
3
+ size 4984