Hugging Face's logo

Electricarchmage
/
cookbookgpt

PyTorch
gpt2
Model card Files Community
Electricarchmage commited on
Commit
3bb0283
·
verified ·
1 Parent(s): e603d9e

Upload folder using huggingface_hub

Browse files
Files changed (37) hide show
  1. checkpoint-1000/config.json +36 -0
  2. checkpoint-1000/optimizer.pt +3 -0
  3. checkpoint-1000/pytorch_model.bin +3 -0
  4. checkpoint-1000/scheduler.pt +3 -0
  5. checkpoint-1000/trainer_state.json +28 -0
  6. checkpoint-1000/training_args.bin +3 -0
  7. checkpoint-1500/config.json +36 -0
  8. checkpoint-1500/optimizer.pt +3 -0
  9. checkpoint-1500/pytorch_model.bin +3 -0
  10. checkpoint-1500/scheduler.pt +3 -0
  11. checkpoint-1500/trainer_state.json +34 -0
  12. checkpoint-1500/training_args.bin +3 -0
  13. checkpoint-2000/config.json +36 -0
  14. checkpoint-2000/optimizer.pt +3 -0
  15. checkpoint-2000/pytorch_model.bin +3 -0
  16. checkpoint-2000/scheduler.pt +3 -0
  17. checkpoint-2000/trainer_state.json +40 -0
  18. checkpoint-2000/training_args.bin +3 -0
  19. checkpoint-2500/config.json +36 -0
  20. checkpoint-2500/optimizer.pt +3 -0
  21. checkpoint-2500/pytorch_model.bin +3 -0
  22. checkpoint-2500/scheduler.pt +3 -0
  23. checkpoint-2500/trainer_state.json +46 -0
  24. checkpoint-2500/training_args.bin +3 -0
  25. checkpoint-500/config.json +36 -0
  26. checkpoint-500/optimizer.pt +3 -0
  27. checkpoint-500/pytorch_model.bin +3 -0
  28. checkpoint-500/scheduler.pt +3 -0
  29. checkpoint-500/trainer_state.json +22 -0
  30. checkpoint-500/training_args.bin +3 -0
  31. config.json +36 -0
  32. merges.txt +0 -0
  33. pytorch_model.bin +3 -0
  34. special_tokens_map.json +1 -0
  35. tokenizer_config.json +1 -0
  36. training_args.bin +3 -0
  37. vocab.json +0 -0
checkpoint-1000/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "gradient_checkpointing": false,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_ctx": 1024,
16
+ "n_embd": 768,
17
+ "n_head": 12,
18
+ "n_inner": null,
19
+ "n_layer": 12,
20
+ "n_positions": 1024,
21
+ "resid_pdrop": 0.1,
22
+ "summary_activation": null,
23
+ "summary_first_dropout": 0.1,
24
+ "summary_proj_to_labels": true,
25
+ "summary_type": "cls_index",
26
+ "summary_use_proj": true,
27
+ "task_specific_params": {
28
+ "text-generation": {
29
+ "do_sample": true,
30
+ "max_length": 50
31
+ }
32
+ },
33
+ "transformers_version": "4.5.1",
34
+ "use_cache": true,
35
+ "vocab_size": 50257
36
+ }
checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f63e66a1a26ffcfebf1314aeb9abbd3abf6c6629386cfd2bd3138bd7fd87698a
3
+ size 995611287
checkpoint-1000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e133321d38bcf7e8c19bc6a8e99e06fb28b31ee6f3a6835288ee7eabf8e7e4a
3
+ size 510408315
checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ff041ee588bb7c24b268940aa60323de14015cae4a35073615ec0ebea8861cb
3
+ size 623
checkpoint-1000/trainer_state.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.721170395869191,
5
+ "global_step": 1000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.86,
12
+ "learning_rate": 4.1394148020654047e-05,
13
+ "loss": 2.054,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 1.72,
18
+ "learning_rate": 3.278829604130809e-05,
19
+ "loss": 1.8443,
20
+ "step": 1000
21
+ }
22
+ ],
23
+ "max_steps": 2905,
24
+ "num_train_epochs": 5,
25
+ "total_flos": 1528925221158912.0,
26
+ "trial_name": null,
27
+ "trial_params": null
28
+ }
checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b512c2246ea8ce40f0e79ca9339f773b42d9398b27fc07181baaad57bd109ea4
3
+ size 2351
checkpoint-1500/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "gradient_checkpointing": false,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_ctx": 1024,
16
+ "n_embd": 768,
17
+ "n_head": 12,
18
+ "n_inner": null,
19
+ "n_layer": 12,
20
+ "n_positions": 1024,
21
+ "resid_pdrop": 0.1,
22
+ "summary_activation": null,
23
+ "summary_first_dropout": 0.1,
24
+ "summary_proj_to_labels": true,
25
+ "summary_type": "cls_index",
26
+ "summary_use_proj": true,
27
+ "task_specific_params": {
28
+ "text-generation": {
29
+ "do_sample": true,
30
+ "max_length": 50
31
+ }
32
+ },
33
+ "transformers_version": "4.5.1",
34
+ "use_cache": true,
35
+ "vocab_size": 50257
36
+ }
checkpoint-1500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b2daac124e824e49bd31b399ca087659d346c1a1ac7aa9193295bf9ec45f156
3
+ size 995611287
checkpoint-1500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74b1ab44b3ce1d07a755f7cce767d178844e6e30b6a2fbb6fca3b8ba6f4382a5
3
+ size 510408315
checkpoint-1500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eab5b6b8d802a03af35dcd062a20071bed7b0ec5c9e12fd7537d44ffd562b2c2
3
+ size 623
checkpoint-1500/trainer_state.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.581755593803787,
5
+ "global_step": 1500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.86,
12
+ "learning_rate": 4.1394148020654047e-05,
13
+ "loss": 2.054,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 1.72,
18
+ "learning_rate": 3.278829604130809e-05,
19
+ "loss": 1.8443,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 2.58,
24
+ "learning_rate": 2.418244406196214e-05,
25
+ "loss": 1.7694,
26
+ "step": 1500
27
+ }
28
+ ],
29
+ "max_steps": 2905,
30
+ "num_train_epochs": 5,
31
+ "total_flos": 2293292261965824.0,
32
+ "trial_name": null,
33
+ "trial_params": null
34
+ }
checkpoint-1500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b512c2246ea8ce40f0e79ca9339f773b42d9398b27fc07181baaad57bd109ea4
3
+ size 2351
checkpoint-2000/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "gradient_checkpointing": false,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_ctx": 1024,
16
+ "n_embd": 768,
17
+ "n_head": 12,
18
+ "n_inner": null,
19
+ "n_layer": 12,
20
+ "n_positions": 1024,
21
+ "resid_pdrop": 0.1,
22
+ "summary_activation": null,
23
+ "summary_first_dropout": 0.1,
24
+ "summary_proj_to_labels": true,
25
+ "summary_type": "cls_index",
26
+ "summary_use_proj": true,
27
+ "task_specific_params": {
28
+ "text-generation": {
29
+ "do_sample": true,
30
+ "max_length": 50
31
+ }
32
+ },
33
+ "transformers_version": "4.5.1",
34
+ "use_cache": true,
35
+ "vocab_size": 50257
36
+ }
checkpoint-2000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f909c1e62849153ee15e900f8c0433705cf7c7ac783525575114c8af6e581e4
3
+ size 995611287
checkpoint-2000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21e693fab4d7c534dcb42baf90cdc6cfc35c8cdd3d9b205d243ae649b32987bf
3
+ size 510408315
checkpoint-2000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e350a5dc2daebb8a63b7dfbb20a7c162dfff62f2ce389205d7579ecb8c28e1fc
3
+ size 623
checkpoint-2000/trainer_state.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.442340791738382,
5
+ "global_step": 2000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.86,
12
+ "learning_rate": 4.1394148020654047e-05,
13
+ "loss": 2.054,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 1.72,
18
+ "learning_rate": 3.278829604130809e-05,
19
+ "loss": 1.8443,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 2.58,
24
+ "learning_rate": 2.418244406196214e-05,
25
+ "loss": 1.7694,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 3.44,
30
+ "learning_rate": 1.557659208261618e-05,
31
+ "loss": 1.7264,
32
+ "step": 2000
33
+ }
34
+ ],
35
+ "max_steps": 2905,
36
+ "num_train_epochs": 5,
37
+ "total_flos": 3057659302772736.0,
38
+ "trial_name": null,
39
+ "trial_params": null
40
+ }
checkpoint-2000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b512c2246ea8ce40f0e79ca9339f773b42d9398b27fc07181baaad57bd109ea4
3
+ size 2351
checkpoint-2500/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "gradient_checkpointing": false,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_ctx": 1024,
16
+ "n_embd": 768,
17
+ "n_head": 12,
18
+ "n_inner": null,
19
+ "n_layer": 12,
20
+ "n_positions": 1024,
21
+ "resid_pdrop": 0.1,
22
+ "summary_activation": null,
23
+ "summary_first_dropout": 0.1,
24
+ "summary_proj_to_labels": true,
25
+ "summary_type": "cls_index",
26
+ "summary_use_proj": true,
27
+ "task_specific_params": {
28
+ "text-generation": {
29
+ "do_sample": true,
30
+ "max_length": 50
31
+ }
32
+ },
33
+ "transformers_version": "4.5.1",
34
+ "use_cache": true,
35
+ "vocab_size": 50257
36
+ }
checkpoint-2500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae01e5fdedb27d8e1360ef6ca388e1ecc14ece34b7abaecdc945723834975b10
3
+ size 995611287
checkpoint-2500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5574596717a6a554450d509244cb62d156371157ed091dc252107832b8377e0
3
+ size 510408315
checkpoint-2500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f3ad3f2c4a67c5b749fc34f16f20e3ea27e487d311ad4aab625cc68487af8e3
3
+ size 623
checkpoint-2500/trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.3029259896729775,
5
+ "global_step": 2500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.86,
12
+ "learning_rate": 4.1394148020654047e-05,
13
+ "loss": 2.054,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 1.72,
18
+ "learning_rate": 3.278829604130809e-05,
19
+ "loss": 1.8443,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 2.58,
24
+ "learning_rate": 2.418244406196214e-05,
25
+ "loss": 1.7694,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 3.44,
30
+ "learning_rate": 1.557659208261618e-05,
31
+ "loss": 1.7264,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 4.3,
36
+ "learning_rate": 6.970740103270223e-06,
37
+ "loss": 1.6912,
38
+ "step": 2500
39
+ }
40
+ ],
41
+ "max_steps": 2905,
42
+ "num_train_epochs": 5,
43
+ "total_flos": 3822026343579648.0,
44
+ "trial_name": null,
45
+ "trial_params": null
46
+ }
checkpoint-2500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b512c2246ea8ce40f0e79ca9339f773b42d9398b27fc07181baaad57bd109ea4
3
+ size 2351
checkpoint-500/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "gradient_checkpointing": false,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_ctx": 1024,
16
+ "n_embd": 768,
17
+ "n_head": 12,
18
+ "n_inner": null,
19
+ "n_layer": 12,
20
+ "n_positions": 1024,
21
+ "resid_pdrop": 0.1,
22
+ "summary_activation": null,
23
+ "summary_first_dropout": 0.1,
24
+ "summary_proj_to_labels": true,
25
+ "summary_type": "cls_index",
26
+ "summary_use_proj": true,
27
+ "task_specific_params": {
28
+ "text-generation": {
29
+ "do_sample": true,
30
+ "max_length": 50
31
+ }
32
+ },
33
+ "transformers_version": "4.5.1",
34
+ "use_cache": true,
35
+ "vocab_size": 50257
36
+ }
checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34da1a820dc6c05c132c9ed9f1fe0507f0f06a6e525bccfe0086ed2e8ebaa872
3
+ size 995611287
checkpoint-500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6583f64305d2c1c7030b8912d53d166aa4187ab2ed0815f36e6923edf41d6028
3
+ size 510408315
checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:856361f9b6a54898158931d388acfb0680a58a59bcd141d39c8cc219ff523d60
3
+ size 623
checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.8605851979345955,
5
+ "global_step": 500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.86,
12
+ "learning_rate": 4.1394148020654047e-05,
13
+ "loss": 2.054,
14
+ "step": 500
15
+ }
16
+ ],
17
+ "max_steps": 2905,
18
+ "num_train_epochs": 5,
19
+ "total_flos": 764558180352000.0,
20
+ "trial_name": null,
21
+ "trial_params": null
22
+ }
checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b512c2246ea8ce40f0e79ca9339f773b42d9398b27fc07181baaad57bd109ea4
3
+ size 2351
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/kaggle/working/result",
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
+ "gradient_checkpointing": false,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_ctx": 1024,
16
+ "n_embd": 768,
17
+ "n_head": 12,
18
+ "n_inner": null,
19
+ "n_layer": 12,
20
+ "n_positions": 1024,
21
+ "resid_pdrop": 0.1,
22
+ "summary_activation": null,
23
+ "summary_first_dropout": 0.1,
24
+ "summary_proj_to_labels": true,
25
+ "summary_type": "cls_index",
26
+ "summary_use_proj": true,
27
+ "task_specific_params": {
28
+ "text-generation": {
29
+ "do_sample": true,
30
+ "max_length": 50
31
+ }
32
+ },
33
+ "transformers_version": "4.5.1",
34
+ "use_cache": true,
35
+ "vocab_size": 50257
36
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb2feeb9158acb7d5822361bb81b4b9132324399f6fe4213710c304ae4457f48
3
+ size 510405883
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "/kaggle/working/result"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b512c2246ea8ce40f0e79ca9339f773b42d9398b27fc07181baaad57bd109ea4
3
+ size 2351
vocab.json ADDED
The diff for this file is too large to render. See raw diff