Hugging Face's logo

ishanjmukherjee
/
tiny-shakespeare-gpt1l

Safetensors
gpt2
Model card Files
xet
 Community
ishanjmukherjee commited on
Commit
7c30147
·
verified ·
1 Parent(s): 0e06800

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +10 -33
  2. checkpoint-17/config.json +32 -0
  3. checkpoint-17/generation_config.json +6 -0
  4. checkpoint-17/merges.txt +0 -0
  5. checkpoint-17/model.safetensors +3 -0
  6. checkpoint-17/optimizer.pt +3 -0
  7. checkpoint-17/rng_state.pth +3 -0
  8. checkpoint-17/scaler.pt +3 -0
  9. checkpoint-17/scheduler.pt +3 -0
  10. checkpoint-17/special_tokens_map.json +6 -0
  11. checkpoint-17/tokenizer.json +0 -0
  12. checkpoint-17/tokenizer_config.json +21 -0
  13. checkpoint-17/trainer_state.json +33 -0
  14. checkpoint-17/training_args.bin +3 -0
  15. checkpoint-17/vocab.json +0 -0
  16. checkpoint-34/config.json +32 -0
  17. checkpoint-34/generation_config.json +6 -0
  18. checkpoint-34/merges.txt +0 -0
  19. checkpoint-34/model.safetensors +3 -0
  20. checkpoint-34/optimizer.pt +3 -0
  21. checkpoint-34/rng_state.pth +3 -0
  22. checkpoint-34/scaler.pt +3 -0
  23. checkpoint-34/scheduler.pt +3 -0
  24. checkpoint-34/special_tokens_map.json +6 -0
  25. checkpoint-34/tokenizer.json +0 -0
  26. checkpoint-34/tokenizer_config.json +21 -0
  27. checkpoint-34/trainer_state.json +33 -0
  28. checkpoint-34/training_args.bin +3 -0
  29. checkpoint-34/vocab.json +0 -0
  30. checkpoint-51/config.json +32 -0
  31. checkpoint-51/generation_config.json +6 -0
  32. checkpoint-51/merges.txt +0 -0
  33. checkpoint-51/model.safetensors +3 -0
  34. checkpoint-51/optimizer.pt +3 -0
  35. checkpoint-51/rng_state.pth +3 -0
  36. checkpoint-51/scaler.pt +3 -0
  37. checkpoint-51/scheduler.pt +3 -0
  38. checkpoint-51/special_tokens_map.json +6 -0
  39. checkpoint-51/tokenizer.json +0 -0
  40. checkpoint-51/tokenizer_config.json +21 -0
  41. checkpoint-51/trainer_state.json +41 -0
  42. checkpoint-51/training_args.bin +3 -0
  43. checkpoint-51/vocab.json +0 -0
  44. checkpoint-68/config.json +32 -0
  45. checkpoint-68/generation_config.json +6 -0
  46. checkpoint-68/merges.txt +0 -0
  47. checkpoint-68/model.safetensors +3 -0
  48. checkpoint-68/optimizer.pt +3 -0
  49. checkpoint-68/rng_state.pth +3 -0
  50. checkpoint-68/scaler.pt +3 -0
.gitattributes CHANGED
@@ -1,35 +1,12 @@
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
  *.pt filter=lfs diff=lfs merge=lfs -text
 
 
2
  *.safetensors filter=lfs diff=lfs merge=lfs -text
3
+ checkpoint-17/rng_state.pth filter=lfs diff=lfs merge=lfs -text
4
+ checkpoint-17/training_args.bin filter=lfs diff=lfs merge=lfs -text
5
+ checkpoint-34/rng_state.pth filter=lfs diff=lfs merge=lfs -text
6
+ checkpoint-34/training_args.bin filter=lfs diff=lfs merge=lfs -text
7
+ checkpoint-51/rng_state.pth filter=lfs diff=lfs merge=lfs -text
8
+ checkpoint-51/training_args.bin filter=lfs diff=lfs merge=lfs -text
9
+ checkpoint-68/rng_state.pth filter=lfs diff=lfs merge=lfs -text
10
+ checkpoint-68/training_args.bin filter=lfs diff=lfs merge=lfs -text
11
+ checkpoint-85/rng_state.pth filter=lfs diff=lfs merge=lfs -text
12
+ checkpoint-85/training_args.bin filter=lfs diff=lfs merge=lfs -text
checkpoint-17/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 256,
14
+ "n_embd": 256,
15
+ "n_head": 8,
16
+ "n_inner": null,
17
+ "n_layer": 1,
18
+ "n_positions": 256,
19
+ "reorder_and_upcast_attn": false,
20
+ "resid_pdrop": 0.1,
21
+ "scale_attn_by_inverse_layer_idx": false,
22
+ "scale_attn_weights": true,
23
+ "summary_activation": null,
24
+ "summary_first_dropout": 0.1,
25
+ "summary_proj_to_labels": true,
26
+ "summary_type": "cls_index",
27
+ "summary_use_proj": true,
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.51.1",
30
+ "use_cache": true,
31
+ "vocab_size": 50257
32
+ }
checkpoint-17/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": "4.51.1"
6
+ }
checkpoint-17/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-17/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56551acc6a68a0cc4d5b342580c2ffd691fc05eefa86c450c1a7df7a94ee1983
3
+ size 54887960
checkpoint-17/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09e7aa0ee803141441bfdc5a5a284c68be0fdca231fb2b80af96c84c710df1be
3
+ size 109786734
checkpoint-17/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6d0d91b5bc6e9691ed7364be92f59bb2deb563b5f52a9bba38807dff8ffde4c
3
+ size 14244
checkpoint-17/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b36f9f9da7f9a43392e1546f0951580df7cf2b05852568ad71dd1cbbc8949bd
3
+ size 988
checkpoint-17/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a3e1c9304f2f675eab78166b78a275c3cf7a1d4c324eee3b71b58998d94c749
3
+ size 1064
checkpoint-17/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
checkpoint-17/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-17/tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": false,
15
+ "eos_token": "<|endoftext|>",
16
+ "extra_special_tokens": {},
17
+ "model_max_length": 256,
18
+ "pad_token": "<|endoftext|>",
19
+ "tokenizer_class": "GPT2Tokenizer",
20
+ "unk_token": "<|endoftext|>"
21
+ }
checkpoint-17/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": 17,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [],
12
+ "logging_steps": 50,
13
+ "max_steps": 85,
14
+ "num_input_tokens_seen": 0,
15
+ "num_train_epochs": 5,
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": 1304897126400.0,
30
+ "train_batch_size": 64,
31
+ "trial_name": null,
32
+ "trial_params": null
33
+ }
checkpoint-17/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbd54d744f6e2b06779e3eca053c7fab92f0e450b6eb337ca111d8bc1ddba6eb
3
+ size 5304
checkpoint-17/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-34/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 256,
14
+ "n_embd": 256,
15
+ "n_head": 8,
16
+ "n_inner": null,
17
+ "n_layer": 1,
18
+ "n_positions": 256,
19
+ "reorder_and_upcast_attn": false,
20
+ "resid_pdrop": 0.1,
21
+ "scale_attn_by_inverse_layer_idx": false,
22
+ "scale_attn_weights": true,
23
+ "summary_activation": null,
24
+ "summary_first_dropout": 0.1,
25
+ "summary_proj_to_labels": true,
26
+ "summary_type": "cls_index",
27
+ "summary_use_proj": true,
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.51.1",
30
+ "use_cache": true,
31
+ "vocab_size": 50257
32
+ }
checkpoint-34/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": "4.51.1"
6
+ }
checkpoint-34/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-34/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bef5c041167366b208002ced81cb768bbfae6c0a3a58ad1e7f233e7f0370c7f
3
+ size 54887960
checkpoint-34/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:405cfe4de8efb5f6103fc40e4263dff6f47161e5b4333d313075a7c7a5c4a5e1
3
+ size 109786734
checkpoint-34/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cfbeca834254eac7ca1d9822b17c439547472392417d5ef08f88cb2b2cfd8b3
3
+ size 14244
checkpoint-34/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c405c130e2e235f32fd51b34f74f0c3f11185df7e44685c0bbfa96125c7afd2
3
+ size 988
checkpoint-34/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c480a447ef425d8df1c69e6d189740752b65e6a069485ce6d4ff2d597075137
3
+ size 1064
checkpoint-34/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
checkpoint-34/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-34/tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": false,
15
+ "eos_token": "<|endoftext|>",
16
+ "extra_special_tokens": {},
17
+ "model_max_length": 256,
18
+ "pad_token": "<|endoftext|>",
19
+ "tokenizer_class": "GPT2Tokenizer",
20
+ "unk_token": "<|endoftext|>"
21
+ }
checkpoint-34/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": 34,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [],
12
+ "logging_steps": 50,
13
+ "max_steps": 85,
14
+ "num_input_tokens_seen": 0,
15
+ "num_train_epochs": 5,
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": 2609794252800.0,
30
+ "train_batch_size": 64,
31
+ "trial_name": null,
32
+ "trial_params": null
33
+ }
checkpoint-34/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbd54d744f6e2b06779e3eca053c7fab92f0e450b6eb337ca111d8bc1ddba6eb
3
+ size 5304
checkpoint-34/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-51/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 256,
14
+ "n_embd": 256,
15
+ "n_head": 8,
16
+ "n_inner": null,
17
+ "n_layer": 1,
18
+ "n_positions": 256,
19
+ "reorder_and_upcast_attn": false,
20
+ "resid_pdrop": 0.1,
21
+ "scale_attn_by_inverse_layer_idx": false,
22
+ "scale_attn_weights": true,
23
+ "summary_activation": null,
24
+ "summary_first_dropout": 0.1,
25
+ "summary_proj_to_labels": true,
26
+ "summary_type": "cls_index",
27
+ "summary_use_proj": true,
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.51.1",
30
+ "use_cache": true,
31
+ "vocab_size": 50257
32
+ }
checkpoint-51/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": "4.51.1"
6
+ }
checkpoint-51/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-51/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:229a84c8d6cda6a6bba5f98468b9c182fa134934778ab79344cfa559f5152989
3
+ size 54887960
checkpoint-51/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22fe652e7cdc124f1e6a3d5705df048c129eca365ee8d1c89048b3d35ee17a4d
3
+ size 109786734
checkpoint-51/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:060c41b49dd746440be3eb6b9d92456cd32461950bdd7f9cc7ab879f72ed08c2
3
+ size 14244
checkpoint-51/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c70f5fda3e3f10ae43092c60fc7a5bcf5b180b13161c91ed3c35da40559c615
3
+ size 988
checkpoint-51/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d595c012f5bcc59cff3ab85fb46cf677fbf178dd9e08cb472b68b211dd1fffde
3
+ size 1064
checkpoint-51/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
checkpoint-51/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-51/tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": false,
15
+ "eos_token": "<|endoftext|>",
16
+ "extra_special_tokens": {},
17
+ "model_max_length": 256,
18
+ "pad_token": "<|endoftext|>",
19
+ "tokenizer_class": "GPT2Tokenizer",
20
+ "unk_token": "<|endoftext|>"
21
+ }
checkpoint-51/trainer_state.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 51,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 2.9411764705882355,
14
+ "grad_norm": 1.4065072536468506,
15
+ "learning_rate": 0.000147,
16
+ "loss": 10.2326,
17
+ "step": 50
18
+ }
19
+ ],
20
+ "logging_steps": 50,
21
+ "max_steps": 85,
22
+ "num_input_tokens_seen": 0,
23
+ "num_train_epochs": 5,
24
+ "save_steps": 500,
25
+ "stateful_callbacks": {
26
+ "TrainerControl": {
27
+ "args": {
28
+ "should_epoch_stop": false,
29
+ "should_evaluate": false,
30
+ "should_log": false,
31
+ "should_save": true,
32
+ "should_training_stop": false
33
+ },
34
+ "attributes": {}
35
+ }
36
+ },
37
+ "total_flos": 3914691379200.0,
38
+ "train_batch_size": 64,
39
+ "trial_name": null,
40
+ "trial_params": null
41
+ }
checkpoint-51/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbd54d744f6e2b06779e3eca053c7fab92f0e450b6eb337ca111d8bc1ddba6eb
3
+ size 5304
checkpoint-51/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-68/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 256,
14
+ "n_embd": 256,
15
+ "n_head": 8,
16
+ "n_inner": null,
17
+ "n_layer": 1,
18
+ "n_positions": 256,
19
+ "reorder_and_upcast_attn": false,
20
+ "resid_pdrop": 0.1,
21
+ "scale_attn_by_inverse_layer_idx": false,
22
+ "scale_attn_weights": true,
23
+ "summary_activation": null,
24
+ "summary_first_dropout": 0.1,
25
+ "summary_proj_to_labels": true,
26
+ "summary_type": "cls_index",
27
+ "summary_use_proj": true,
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.51.1",
30
+ "use_cache": true,
31
+ "vocab_size": 50257
32
+ }
checkpoint-68/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": "4.51.1"
6
+ }
checkpoint-68/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-68/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bd3babd7325de0105df71989f028531a0cd74100f8bda1407615a026ddf6ff4
3
+ size 54887960
checkpoint-68/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad9dd5f0b340fd74fcad077a6aa043c209151706bd8d1f7727227109dd30733e
3
+ size 109786734
checkpoint-68/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c7c86a7444ec8926df32c2bb83a60665b7e2b25cc84e26802de8475e8b26515
3
+ size 14244
checkpoint-68/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e2793a3fd250c9ea48df20fc87e8ee9da5cf793d771ea053864f59b05c347cd
3
+ size 988