Hugging Face's logo

fialfafi
/
gpt2-wikitext2

Text Generation
Transformers
PyTorch
TensorBoard
gpt2
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
fialfafi commited on
Commit
70e9279
•
1 Parent(s): 29ec39b

Model save

Browse files
Files changed (24) hide show
  1. .gitignore +1 -0
  2. config.json +39 -0
  3. generation_config.json +6 -0
  4. pytorch_model.bin +3 -0
  5. runs/May19_03-25-41_DESKTOP-P7J1DBP/1684477618.0016615/events.out.tfevents.1684477618.DESKTOP-P7J1DBP.11768.1 +3 -0
  6. runs/May19_03-25-41_DESKTOP-P7J1DBP/events.out.tfevents.1684477617.DESKTOP-P7J1DBP.11768.0 +3 -0
  7. runs/May19_03-28-00_DESKTOP-P7J1DBP/1684477695.6746051/events.out.tfevents.1684477695.DESKTOP-P7J1DBP.11768.3 +3 -0
  8. runs/May19_03-28-00_DESKTOP-P7J1DBP/1684477725.4759/events.out.tfevents.1684477725.DESKTOP-P7J1DBP.11768.4 +3 -0
  9. runs/May19_03-28-00_DESKTOP-P7J1DBP/1684477742.2466567/events.out.tfevents.1684477742.DESKTOP-P7J1DBP.11768.6 +3 -0
  10. runs/May19_03-28-00_DESKTOP-P7J1DBP/events.out.tfevents.1684477695.DESKTOP-P7J1DBP.11768.2 +3 -0
  11. runs/May19_03-28-00_DESKTOP-P7J1DBP/events.out.tfevents.1684477742.DESKTOP-P7J1DBP.11768.5 +3 -0
  12. runs/May19_03-30-46_DESKTOP-P7J1DBP/1684478025.6666594/events.out.tfevents.1684478025.DESKTOP-P7J1DBP.11768.8 +3 -0
  13. runs/May19_03-30-46_DESKTOP-P7J1DBP/1684478045.9091063/events.out.tfevents.1684478045.DESKTOP-P7J1DBP.11768.10 +3 -0
  14. runs/May19_03-30-46_DESKTOP-P7J1DBP/1684478472.7591643/events.out.tfevents.1684478472.DESKTOP-P7J1DBP.11768.12 +3 -0
  15. runs/May19_03-30-46_DESKTOP-P7J1DBP/1684478475.3116567/events.out.tfevents.1684478475.DESKTOP-P7J1DBP.11768.13 +3 -0
  16. runs/May19_03-30-46_DESKTOP-P7J1DBP/1684479074.5820515/events.out.tfevents.1684479074.DESKTOP-P7J1DBP.11768.14 +3 -0
  17. runs/May19_03-30-46_DESKTOP-P7J1DBP/1684479251.0513365/events.out.tfevents.1684479251.DESKTOP-P7J1DBP.11768.16 +3 -0
  18. runs/May19_03-30-46_DESKTOP-P7J1DBP/events.out.tfevents.1684478025.DESKTOP-P7J1DBP.11768.7 +3 -0
  19. runs/May19_03-30-46_DESKTOP-P7J1DBP/events.out.tfevents.1684478045.DESKTOP-P7J1DBP.11768.9 +3 -0
  20. runs/May19_03-30-46_DESKTOP-P7J1DBP/events.out.tfevents.1684478472.DESKTOP-P7J1DBP.11768.11 +3 -0
  21. runs/May19_03-30-46_DESKTOP-P7J1DBP/events.out.tfevents.1684479251.DESKTOP-P7J1DBP.11768.15 +3 -0
  22. runs/May19_03-30-46_DESKTOP-P7J1DBP/events.out.tfevents.1684480412.DESKTOP-P7J1DBP.11768.17 +3 -0
  23. trainer_state.json +57 -0
  24. training_args.bin +3 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
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
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50
33
+ }
34
+ },
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.27.0.dev0",
37
+ "use_cache": true,
38
+ "vocab_size": 50257
39
+ }
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": "4.27.0.dev0"
6
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b8d7d37e582eca1b1ae9159760ce78bc259c6eb830e576065d88af3480218a5
3
+ size 510395581
runs/May19_03-25-41_DESKTOP-P7J1DBP/1684477618.0016615/events.out.tfevents.1684477618.DESKTOP-P7J1DBP.11768.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06eecbcb252f7bb82b6a4b53041f9e136d7ebace3e2247f0109be02abbb1690e
3
+ size 5763
runs/May19_03-25-41_DESKTOP-P7J1DBP/events.out.tfevents.1684477617.DESKTOP-P7J1DBP.11768.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c8931767766ef6ce1249320512f5b3fa8a630a31487d426001f0d8f23a55286
3
+ size 4153
runs/May19_03-28-00_DESKTOP-P7J1DBP/1684477695.6746051/events.out.tfevents.1684477695.DESKTOP-P7J1DBP.11768.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ea8eeb71fd9f3dd6bc203842275710ce8c123ddce086f0e9455227ff4d125c5
3
+ size 5763
runs/May19_03-28-00_DESKTOP-P7J1DBP/1684477725.4759/events.out.tfevents.1684477725.DESKTOP-P7J1DBP.11768.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e1c1881421fe57a6914842998f8428a3acf64086c5f0ad054cb465641176136
3
+ size 5763
runs/May19_03-28-00_DESKTOP-P7J1DBP/1684477742.2466567/events.out.tfevents.1684477742.DESKTOP-P7J1DBP.11768.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5460b93ead91ac99f7b71c9e106e2535bf65c1bf3f70df5be9080300dc0854d
3
+ size 5763
runs/May19_03-28-00_DESKTOP-P7J1DBP/events.out.tfevents.1684477695.DESKTOP-P7J1DBP.11768.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee68f15d511ab8cf85da68b83bd289cf311548bb7af41783885faab0bbb71e7a
3
+ size 8266
runs/May19_03-28-00_DESKTOP-P7J1DBP/events.out.tfevents.1684477742.DESKTOP-P7J1DBP.11768.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a71e4c72d5bc27e28a21b0c9e64337352fedb2466aec895120dc73ff1a24c78
3
+ size 4153
runs/May19_03-30-46_DESKTOP-P7J1DBP/1684478025.6666594/events.out.tfevents.1684478025.DESKTOP-P7J1DBP.11768.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:690fea9329579252b90f808bb90db8c107d2fd7317340489c0ff22c5dac80abf
3
+ size 5763
runs/May19_03-30-46_DESKTOP-P7J1DBP/1684478045.9091063/events.out.tfevents.1684478045.DESKTOP-P7J1DBP.11768.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a94bbe15aee2e2ba594539237a0ea5001fa785e53764307a0b415808bab899b9
3
+ size 5763
runs/May19_03-30-46_DESKTOP-P7J1DBP/1684478472.7591643/events.out.tfevents.1684478472.DESKTOP-P7J1DBP.11768.12 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4986904a1ce4edc27793125de11802edba10dc964c464879938a2183e3412097
3
+ size 5763
runs/May19_03-30-46_DESKTOP-P7J1DBP/1684478475.3116567/events.out.tfevents.1684478475.DESKTOP-P7J1DBP.11768.13 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25399d529b55efe0b99e25a18c2d6903fc99bc515017fe47f74ee8d3b3947986
3
+ size 5763
runs/May19_03-30-46_DESKTOP-P7J1DBP/1684479074.5820515/events.out.tfevents.1684479074.DESKTOP-P7J1DBP.11768.14 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58f2b81876840d755089ba32ff3a49fda505786410140ff1f2d79f326806a972
3
+ size 5763
runs/May19_03-30-46_DESKTOP-P7J1DBP/1684479251.0513365/events.out.tfevents.1684479251.DESKTOP-P7J1DBP.11768.16 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef8df57250ccae73466374ae57ab3e5e40ed4be6dc9466a9ee65a84b883676f5
3
+ size 5763
runs/May19_03-30-46_DESKTOP-P7J1DBP/events.out.tfevents.1684478025.DESKTOP-P7J1DBP.11768.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bff07f8c909f613afced61283447f4ad22bd18150e4e7cbb07159d34d8c7f53
3
+ size 4153
runs/May19_03-30-46_DESKTOP-P7J1DBP/events.out.tfevents.1684478045.DESKTOP-P7J1DBP.11768.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e87b8df4ecee82841b2628c9862b2a067ad3314dabcbd23e9b97eadeb492f49
3
+ size 4153
runs/May19_03-30-46_DESKTOP-P7J1DBP/events.out.tfevents.1684478472.DESKTOP-P7J1DBP.11768.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e19b1a302adc2fb7921809bdc1b262f7a92e016d7f97a094356c907fe7f5adb
3
+ size 12379
runs/May19_03-30-46_DESKTOP-P7J1DBP/events.out.tfevents.1684479251.DESKTOP-P7J1DBP.11768.15 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a76a83436c131d6d782ab0f27f91566df8a356c11aef2a180f952234a2c4867b
3
+ size 5310
runs/May19_03-30-46_DESKTOP-P7J1DBP/events.out.tfevents.1684480412.DESKTOP-P7J1DBP.11768.17 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a0cb417e2cca85898dcc7e7aad55e356fd9888d1ec021c14955b0cb4b68e7bf
3
+ size 311
trainer_state.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 189,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "eval_loss": 8.61410903930664,
13
+ "eval_runtime": 13.2143,
14
+ "eval_samples_per_second": 3.784,
15
+ "eval_steps_per_second": 0.53,
16
+ "step": 63
17
+ },
18
+ {
19
+ "epoch": 2.0,
20
+ "eval_loss": 8.225358963012695,
21
+ "eval_runtime": 11.7566,
22
+ "eval_samples_per_second": 4.253,
23
+ "eval_steps_per_second": 0.595,
24
+ "step": 126
25
+ },
26
+ {
27
+ "epoch": 3.0,
28
+ "eval_loss": 8.128830909729004,
29
+ "eval_runtime": 11.8544,
30
+ "eval_samples_per_second": 4.218,
31
+ "eval_steps_per_second": 0.59,
32
+ "step": 189
33
+ },
34
+ {
35
+ "epoch": 3.0,
36
+ "step": 189,
37
+ "total_flos": 97984512000000.0,
38
+ "train_loss": 8.390519076554233,
39
+ "train_runtime": 1102.7597,
40
+ "train_samples_per_second": 1.36,
41
+ "train_steps_per_second": 0.171
42
+ },
43
+ {
44
+ "epoch": 3.0,
45
+ "eval_loss": 8.128830909729004,
46
+ "eval_runtime": 11.6588,
47
+ "eval_samples_per_second": 4.289,
48
+ "eval_steps_per_second": 0.6,
49
+ "step": 189
50
+ }
51
+ ],
52
+ "max_steps": 189,
53
+ "num_train_epochs": 3,
54
+ "total_flos": 97984512000000.0,
55
+ "trial_name": null,
56
+ "trial_params": null
57
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df961e670f8cb51b83d91ced6078a74bfe326e7702c3d30fdca6c85f25a33031
3
+ size 3579