Hugging Face's logo

NataliaH
/
gpt2-finetuned-shakespeare

Text Generation
Transformers
PyTorch
Safetensors
gpt2
text-generation-inference
Model card Files
xet
 Community
NataliaH commited on
Commit
b468aa9
·
verified ·
1 Parent(s): fc5005e

Initial upload of fine-tuned GPT-2 model

Browse files
Files changed (30) hide show
  1. checkpoint-1/config.json +39 -0
  2. checkpoint-1/generation_config.json +6 -0
  3. checkpoint-1/model.safetensors +3 -0
  4. checkpoint-1/optimizer.pt +3 -0
  5. checkpoint-1/rng_state.pth +3 -0
  6. checkpoint-1/scheduler.pt +3 -0
  7. checkpoint-1/trainer_state.json +33 -0
  8. checkpoint-1/training_args.bin +3 -0
  9. checkpoint-2/config.json +39 -0
  10. checkpoint-2/generation_config.json +6 -0
  11. checkpoint-2/model.safetensors +3 -0
  12. checkpoint-2/optimizer.pt +3 -0
  13. checkpoint-2/rng_state.pth +3 -0
  14. checkpoint-2/scheduler.pt +3 -0
  15. checkpoint-2/trainer_state.json +33 -0
  16. checkpoint-2/training_args.bin +3 -0
  17. checkpoint-3/config.json +39 -0
  18. checkpoint-3/generation_config.json +6 -0
  19. checkpoint-3/model.safetensors +3 -0
  20. checkpoint-3/optimizer.pt +3 -0
  21. checkpoint-3/rng_state.pth +3 -0
  22. checkpoint-3/scheduler.pt +3 -0
  23. checkpoint-3/trainer_state.json +33 -0
  24. checkpoint-3/training_args.bin +3 -0
  25. config.json +1 -39
  26. merges.txt +0 -0
  27. pytorch_model.bin +3 -0
  28. special_tokens_map.json +24 -0
  29. tokenizer_config.json +23 -0
  30. vocab.json +0 -0
checkpoint-1/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 50256,
8
+ "embd_pdrop": 0.1,
9
+ "eos_token_id": 50256,
10
+ "initializer_range": 0.02,
11
+ "layer_norm_epsilon": 1e-05,
12
+ "model_type": "gpt2",
13
+ "n_ctx": 1024,
14
+ "n_embd": 768,
15
+ "n_head": 12,
16
+ "n_inner": null,
17
+ "n_layer": 12,
18
+ "n_positions": 1024,
19
+ "pad_token_id": 50256,
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": "4.51.3",
37
+ "use_cache": true,
38
+ "vocab_size": 50257
39
+ }
checkpoint-1/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": "4.51.3"
6
+ }
checkpoint-1/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8439aa7da1da5fbf83a244477ccedf53bcf71e3afe61f73e0d70cb0c63afe16
3
+ size 497774208
checkpoint-1/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3e332db9d1c589001cb7ca0331fdcf9e69dae7fd444ef442a2f6a56af52ed3e
3
+ size 995638202
checkpoint-1/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71aea2240388692c29beac67520fd25643a5bbede6cbbbb0701331c5d7848647
3
+ size 13990
checkpoint-1/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e950ca742066f8b9e62ba80bb5fef60b544f600cfecdd32aa759888c1f280ed0
3
+ size 1064
checkpoint-1/trainer_state.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [],
12
+ "logging_steps": 10,
13
+ "max_steps": 3,
14
+ "num_input_tokens_seen": 0,
15
+ "num_train_epochs": 3,
16
+ "save_steps": 500,
17
+ "stateful_callbacks": {
18
+ "TrainerControl": {
19
+ "args": {
20
+ "should_epoch_stop": false,
21
+ "should_evaluate": false,
22
+ "should_log": false,
23
+ "should_save": true,
24
+ "should_training_stop": false
25
+ },
26
+ "attributes": {}
27
+ }
28
+ },
29
+ "total_flos": 65323008000.0,
30
+ "train_batch_size": 2,
31
+ "trial_name": null,
32
+ "trial_params": null
33
+ }
checkpoint-1/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0d94ecde836a055ea3ad2481161f765fcafbe830e186832b6f525ae366564f7
3
+ size 5368
checkpoint-2/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 50256,
8
+ "embd_pdrop": 0.1,
9
+ "eos_token_id": 50256,
10
+ "initializer_range": 0.02,
11
+ "layer_norm_epsilon": 1e-05,
12
+ "model_type": "gpt2",
13
+ "n_ctx": 1024,
14
+ "n_embd": 768,
15
+ "n_head": 12,
16
+ "n_inner": null,
17
+ "n_layer": 12,
18
+ "n_positions": 1024,
19
+ "pad_token_id": 50256,
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": "4.51.3",
37
+ "use_cache": true,
38
+ "vocab_size": 50257
39
+ }
checkpoint-2/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": "4.51.3"
6
+ }
checkpoint-2/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:414171288e52e8688971005657a62e480248153aa9677790121c24b4561beee1
3
+ size 497774208
checkpoint-2/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dc6a5165a61016d589591e1dd483ceae9bd332901ea59990161c4c93d82185b
3
+ size 995638202
checkpoint-2/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:257767379e6285480edd6e1c884c6152eefff677bf9536caa4e2def5c2e7e640
3
+ size 13990
checkpoint-2/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a27ddd0715a8a938994a234170508c4e373cb0cfabcdcd5c8c55491154f6015a
3
+ size 1064
checkpoint-2/trainer_state.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 2,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [],
12
+ "logging_steps": 10,
13
+ "max_steps": 3,
14
+ "num_input_tokens_seen": 0,
15
+ "num_train_epochs": 3,
16
+ "save_steps": 500,
17
+ "stateful_callbacks": {
18
+ "TrainerControl": {
19
+ "args": {
20
+ "should_epoch_stop": false,
21
+ "should_evaluate": false,
22
+ "should_log": false,
23
+ "should_save": true,
24
+ "should_training_stop": false
25
+ },
26
+ "attributes": {}
27
+ }
28
+ },
29
+ "total_flos": 130646016000.0,
30
+ "train_batch_size": 2,
31
+ "trial_name": null,
32
+ "trial_params": null
33
+ }
checkpoint-2/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0d94ecde836a055ea3ad2481161f765fcafbe830e186832b6f525ae366564f7
3
+ size 5368
checkpoint-3/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 50256,
8
+ "embd_pdrop": 0.1,
9
+ "eos_token_id": 50256,
10
+ "initializer_range": 0.02,
11
+ "layer_norm_epsilon": 1e-05,
12
+ "model_type": "gpt2",
13
+ "n_ctx": 1024,
14
+ "n_embd": 768,
15
+ "n_head": 12,
16
+ "n_inner": null,
17
+ "n_layer": 12,
18
+ "n_positions": 1024,
19
+ "pad_token_id": 50256,
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": "4.51.3",
37
+ "use_cache": true,
38
+ "vocab_size": 50257
39
+ }
checkpoint-3/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": "4.51.3"
6
+ }
checkpoint-3/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88e4f1e479940aa8c9755cce18ac4376fe0c693e393aa2e63157fb19d3fd30d7
3
+ size 497774208
checkpoint-3/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0db42afed3a53d8db2d1f65abf03ee4ecf47dcf2762eb3d4e236552015fe2561
3
+ size 995638202
checkpoint-3/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b58d106cf98b100eba93dc315ed37edb05ebc125976b2f1b6d218dcd40714115
3
+ size 13990
checkpoint-3/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8a41b254d981983d12a5d0bed17f4768863ab9648e2daeb9b71c409365e3b73
3
+ size 1064
checkpoint-3/trainer_state.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 3,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [],
12
+ "logging_steps": 10,
13
+ "max_steps": 3,
14
+ "num_input_tokens_seen": 0,
15
+ "num_train_epochs": 3,
16
+ "save_steps": 500,
17
+ "stateful_callbacks": {
18
+ "TrainerControl": {
19
+ "args": {
20
+ "should_epoch_stop": false,
21
+ "should_evaluate": false,
22
+ "should_log": false,
23
+ "should_save": true,
24
+ "should_training_stop": true
25
+ },
26
+ "attributes": {}
27
+ }
28
+ },
29
+ "total_flos": 195969024000.0,
30
+ "train_batch_size": 2,
31
+ "trial_name": null,
32
+ "trial_params": null
33
+ }
checkpoint-3/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0d94ecde836a055ea3ad2481161f765fcafbe830e186832b6f525ae366564f7
3
+ size 5368
config.json CHANGED
@@ -1,39 +1 @@
1
- {
2
- "activation_function": "gelu_new",
3
- "architectures": [
4
- "GPT2LMHeadModel"
5
- ],
6
- "attn_pdrop": 0.1,
7
- "bos_token_id": 50256,
8
- "embd_pdrop": 0.1,
9
- "eos_token_id": 50256,
10
- "initializer_range": 0.02,
11
- "layer_norm_epsilon": 1e-05,
12
- "model_type": "gpt2",
13
- "n_ctx": 1024,
14
- "n_embd": 768,
15
- "n_head": 12,
16
- "n_inner": null,
17
- "n_layer": 12,
18
- "n_positions": 1024,
19
- "pad_token_id": 50256,
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": "4.51.3",
37
- "use_cache": true,
38
- "vocab_size": 50257
39
- }
 
1
+ {"architectures": ["GPT2LMHeadModel"], "vocab_size": 50257}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 sha256:482189912867a07300373eaa5297a8fa11159490d35e49bca6e62581bc9975e0
3
+ size 497813466
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "50256": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ }
13
+ },
14
+ "bos_token": "<|endoftext|>",
15
+ "clean_up_tokenization_spaces": false,
16
+ "eos_token": "<|endoftext|>",
17
+ "errors": "replace",
18
+ "extra_special_tokens": {},
19
+ "model_max_length": 1024,
20
+ "pad_token": "<|endoftext|>",
21
+ "tokenizer_class": "GPT2Tokenizer",
22
+ "unk_token": "<|endoftext|>"
23
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff