Hugging Face's logo

metriccoders
/
fine-tuned-gpt2-mahabharata

TensorBoard
Safetensors
gpt2
Model card Files Metrics Community
metriccoders commited on
Commit
5b2d25c
·
verified ·
1 Parent(s): f2469d6

GPT-2 Mahabharata

Browse files
Files changed (21) hide show
  1. checkpoint-205/config.json +39 -0
  2. checkpoint-205/generation_config.json +6 -0
  3. checkpoint-205/model.safetensors +3 -0
  4. checkpoint-205/optimizer.pt +3 -0
  5. checkpoint-205/rng_state.pth +3 -0
  6. checkpoint-205/scheduler.pt +3 -0
  7. checkpoint-205/trainer_state.json +32 -0
  8. checkpoint-205/training_args.bin +3 -0
  9. config.json +39 -0
  10. generation_config.json +6 -0
  11. merges.txt +0 -0
  12. model.safetensors +3 -0
  13. runs/Aug23_13-44-11_01995dfb5554/events.out.tfevents.1724420654.01995dfb5554.1481.0 +3 -0
  14. runs/Aug23_13-46-53_01995dfb5554/events.out.tfevents.1724420816.01995dfb5554.1481.1 +3 -0
  15. runs/Aug23_13-46-53_01995dfb5554/events.out.tfevents.1724421415.01995dfb5554.1481.2 +3 -0
  16. runs/Aug23_13-46-53_01995dfb5554/events.out.tfevents.1724421419.01995dfb5554.1481.3 +3 -0
  17. special_tokens_map.json +5 -0
  18. tokenizer.json +0 -0
  19. tokenizer_config.json +19 -0
  20. training_args.bin +3 -0
  21. vocab.json +0 -0
checkpoint-205/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": "4.44.2",
37
+ "use_cache": true,
38
+ "vocab_size": 50257
39
+ }
checkpoint-205/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": "4.44.2"
6
+ }
checkpoint-205/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05e541ecbf4c5d792d2b0f407a596404b630ae4c54dd632c8e47a6e1ba726e86
3
+ size 497774208
checkpoint-205/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f8199269df144e5f22da72446313d4f6014748db5f342cc3c2d85d232fc03b4
3
+ size 995642298
checkpoint-205/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:245aa8b8057ead2f264bf0797d9845139b8409f3753a073bc675c3c73620fc3d
3
+ size 14244
checkpoint-205/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8321a4cd120f1904e87bfd6430568629a8fe77618c76464a8838ca0b55fc3e8c
3
+ size 1064
checkpoint-205/trainer_state.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 205,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [],
11
+ "logging_steps": 500,
12
+ "max_steps": 205,
13
+ "num_input_tokens_seen": 0,
14
+ "num_train_epochs": 5,
15
+ "save_steps": 100,
16
+ "stateful_callbacks": {
17
+ "TrainerControl": {
18
+ "args": {
19
+ "should_epoch_stop": false,
20
+ "should_evaluate": false,
21
+ "should_log": false,
22
+ "should_save": true,
23
+ "should_training_stop": true
24
+ },
25
+ "attributes": {}
26
+ }
27
+ },
28
+ "total_flos": 424109629440000.0,
29
+ "train_batch_size": 64,
30
+ "trial_name": null,
31
+ "trial_params": null
32
+ }
checkpoint-205/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:421a38d812086cd9860cf1db857468fe6ab844d540e3d63e7787d0738d503610
3
+ size 5176
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": "4.44.2",
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": "4.44.2"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05e541ecbf4c5d792d2b0f407a596404b630ae4c54dd632c8e47a6e1ba726e86
3
+ size 497774208
runs/Aug23_13-44-11_01995dfb5554/events.out.tfevents.1724420654.01995dfb5554.1481.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e986c78143b2dd74d24da7aa1187cce7cb913e29e0cf1efa6a8a3a91e885ddec
3
+ size 5490
runs/Aug23_13-46-53_01995dfb5554/events.out.tfevents.1724420816.01995dfb5554.1481.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dccc86887bcab009d6d313dd6a91c2bafe61e66c6b6e5035eee7d1379e0af68d
3
+ size 5496
runs/Aug23_13-46-53_01995dfb5554/events.out.tfevents.1724421415.01995dfb5554.1481.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5af94f5a87bd7fc3f3a53618652287fb0c7ea9c43d4da78a1d3f4d3c0d2b9b5
3
+ size 360
runs/Aug23_13-46-53_01995dfb5554/events.out.tfevents.1724421419.01995dfb5554.1481.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a81130bdf5952aebf994871842e0ba2818de650573ed881ee9be2199b1b7d120
3
+ size 360
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>"
5
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
15
+ "eos_token": "<|endoftext|>",
16
+ "model_max_length": 1024,
17
+ "tokenizer_class": "GPT2Tokenizer",
18
+ "unk_token": "<|endoftext|>"
19
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:421a38d812086cd9860cf1db857468fe6ab844d540e3d63e7787d0738d503610
3
+ size 5176
vocab.json ADDED
The diff for this file is too large to render. See raw diff