Hugging Face's logo

harshagnihotri14
/
SOP_Generator

Text Generation
Adapters
TensorBoard
Safetensors
gpt_neo
Model card Files
xet
Metrics Community
harshagnihotri14 commited on
Commit
b10451a
·
verified ·
1 Parent(s): 87b0851

Upload folder using huggingface_hub

Browse files
Files changed (27) hide show
  1. checkpoint-250/config.json +55 -0
  2. checkpoint-250/generation_config.json +6 -0
  3. checkpoint-250/model.safetensors +3 -0
  4. checkpoint-250/optimizer.pt +3 -0
  5. checkpoint-250/rng_state.pth +3 -0
  6. checkpoint-250/scheduler.pt +3 -0
  7. checkpoint-250/trainer_state.json +32 -0
  8. checkpoint-250/training_args.bin +3 -0
  9. checkpoint-63/config.json +55 -0
  10. checkpoint-63/generation_config.json +6 -0
  11. checkpoint-63/model.safetensors +3 -0
  12. checkpoint-63/optimizer.pt +3 -0
  13. checkpoint-63/rng_state.pth +3 -0
  14. checkpoint-63/scheduler.pt +3 -0
  15. checkpoint-63/trainer_state.json +32 -0
  16. checkpoint-63/training_args.bin +3 -0
  17. config.json +41 -6
  18. generation_config.json +6 -0
  19. model.safetensors +3 -0
  20. runs/Oct14_07-39-24_ca83b710e823/events.out.tfevents.1728891565.ca83b710e823.3134.0 +3 -0
  21. runs/Oct14_07-46-40_ca83b710e823/events.out.tfevents.1728892000.ca83b710e823.3134.1 +3 -0
  22. runs/Oct14_08-10-22_ca83b710e823/events.out.tfevents.1728893425.ca83b710e823.11448.0 +3 -0
  23. runs/Oct14_09-37-31_ca83b710e823/events.out.tfevents.1728898653.ca83b710e823.11448.1 +3 -0
  24. runs/Oct14_09-46-11_ca83b710e823/events.out.tfevents.1728899173.ca83b710e823.11448.2 +3 -0
  25. special_tokens_map.json +23 -5
  26. tokenizer_config.json +21 -9
  27. vocab.json +0 -0
checkpoint-250/config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/gpt-neo-125M",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPTNeoForCausalLM"
6
+ ],
7
+ "attention_dropout": 0,
8
+ "attention_layers": [
9
+ "global",
10
+ "local",
11
+ "global",
12
+ "local",
13
+ "global",
14
+ "local",
15
+ "global",
16
+ "local",
17
+ "global",
18
+ "local",
19
+ "global",
20
+ "local"
21
+ ],
22
+ "attention_types": [
23
+ [
24
+ [
25
+ "global",
26
+ "local"
27
+ ],
28
+ 6
29
+ ]
30
+ ],
31
+ "bos_token_id": 50256,
32
+ "classifier_dropout": 0.1,
33
+ "embed_dropout": 0,
34
+ "eos_token_id": 50256,
35
+ "gradient_checkpointing": false,
36
+ "hidden_size": 768,
37
+ "initializer_range": 0.02,
38
+ "intermediate_size": null,
39
+ "layer_norm_epsilon": 1e-05,
40
+ "max_position_embeddings": 2048,
41
+ "model_type": "gpt_neo",
42
+ "num_heads": 12,
43
+ "num_layers": 12,
44
+ "resid_dropout": 0,
45
+ "summary_activation": null,
46
+ "summary_first_dropout": 0.1,
47
+ "summary_proj_to_labels": true,
48
+ "summary_type": "cls_index",
49
+ "summary_use_proj": true,
50
+ "torch_dtype": "float32",
51
+ "transformers_version": "4.44.2",
52
+ "use_cache": true,
53
+ "vocab_size": 50257,
54
+ "window_size": 256
55
+ }
checkpoint-250/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-250/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cbe7bab39f3ae9407d3b35c900b82f7412b74a39afda4feca9230b2c185dd03
3
+ size 500811336
checkpoint-250/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d420d0fa0f2333ba4287d908cc74856b4071e9cd0e55503a8e52173b02b6853
3
+ size 1001718458
checkpoint-250/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bb8daa2218f661aab713b5c8d6a88cb76f435e9067862f52676baa950ad6801
3
+ size 13990
checkpoint-250/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:043e829d8b37b27991c97100faafefff4d4da481d5b3d95feba3b539e8f039f8
3
+ size 1064
checkpoint-250/trainer_state.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 250,
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": 250,
13
+ "num_input_tokens_seen": 0,
14
+ "num_train_epochs": 1,
15
+ "save_steps": 10000,
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": 130603548672000.0,
29
+ "train_batch_size": 2,
30
+ "trial_name": null,
31
+ "trial_params": null
32
+ }
checkpoint-250/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66bbf89196624a75507a6827541e8bb7e850d635b6cc7d8beae2d6cef5fb5817
3
+ size 5176
checkpoint-63/config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/gpt-neo-125M",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPTNeoForCausalLM"
6
+ ],
7
+ "attention_dropout": 0,
8
+ "attention_layers": [
9
+ "global",
10
+ "local",
11
+ "global",
12
+ "local",
13
+ "global",
14
+ "local",
15
+ "global",
16
+ "local",
17
+ "global",
18
+ "local",
19
+ "global",
20
+ "local"
21
+ ],
22
+ "attention_types": [
23
+ [
24
+ [
25
+ "global",
26
+ "local"
27
+ ],
28
+ 6
29
+ ]
30
+ ],
31
+ "bos_token_id": 50256,
32
+ "classifier_dropout": 0.1,
33
+ "embed_dropout": 0,
34
+ "eos_token_id": 50256,
35
+ "gradient_checkpointing": false,
36
+ "hidden_size": 768,
37
+ "initializer_range": 0.02,
38
+ "intermediate_size": null,
39
+ "layer_norm_epsilon": 1e-05,
40
+ "max_position_embeddings": 2048,
41
+ "model_type": "gpt_neo",
42
+ "num_heads": 12,
43
+ "num_layers": 12,
44
+ "resid_dropout": 0,
45
+ "summary_activation": null,
46
+ "summary_first_dropout": 0.1,
47
+ "summary_proj_to_labels": true,
48
+ "summary_type": "cls_index",
49
+ "summary_use_proj": true,
50
+ "torch_dtype": "float32",
51
+ "transformers_version": "4.44.2",
52
+ "use_cache": true,
53
+ "vocab_size": 50257,
54
+ "window_size": 256
55
+ }
checkpoint-63/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-63/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:856ecd17970445ed3ce6ea151230a42011395df010eb73d9fd801d51cae8fc2e
3
+ size 500811336
checkpoint-63/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2e3afcfc8bf0840209fbd15bb1345ed533d6d06a336ce9b64b71c4675c3c806
3
+ size 1001718458
checkpoint-63/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bb8daa2218f661aab713b5c8d6a88cb76f435e9067862f52676baa950ad6801
3
+ size 13990
checkpoint-63/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84046e9cb326f6f79e2616dde110214d87dd5c250e2578e6e05a3287a946545e
3
+ size 1064
checkpoint-63/trainer_state.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.504,
5
+ "eval_steps": 500,
6
+ "global_step": 63,
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": 63,
13
+ "num_input_tokens_seen": 0,
14
+ "num_train_epochs": 1,
15
+ "save_steps": 10000,
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": 65824188530688.0,
29
+ "train_batch_size": 4,
30
+ "trial_name": null,
31
+ "trial_params": null
32
+ }
checkpoint-63/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d06aba1d8b915b2d9ab6c09fdd1b7b6efa32a9015cac51d1b27c9a0a52ad994
3
+ size 5176
config.json CHANGED
@@ -1,20 +1,55 @@
1
  {
 
2
  "activation_function": "gelu_new",
3
- "architectures": ["GPTNeoForCausalLM"],
 
 
4
  "attention_dropout": 0,
5
- "attention_layers": ["global", "local", "global", "local", "global", "local", "global", "local", "global", "local", "global", "local"],
6
- "attention_types": [[["global", "local"], 6]],
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  "bos_token_id": 50256,
 
8
  "embed_dropout": 0,
9
  "eos_token_id": 50256,
 
10
  "hidden_size": 768,
11
  "initializer_range": 0.02,
12
- "layer_norm_epsilon": 1e-5,
 
13
  "max_position_embeddings": 2048,
14
  "model_type": "gpt_neo",
15
  "num_heads": 12,
16
  "num_layers": 12,
17
  "resid_dropout": 0,
 
 
 
 
 
 
 
18
  "use_cache": true,
19
- "vocab_size": 50257
20
- }
 
 
1
  {
2
+ "_name_or_path": "EleutherAI/gpt-neo-125M",
3
  "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPTNeoForCausalLM"
6
+ ],
7
  "attention_dropout": 0,
8
+ "attention_layers": [
9
+ "global",
10
+ "local",
11
+ "global",
12
+ "local",
13
+ "global",
14
+ "local",
15
+ "global",
16
+ "local",
17
+ "global",
18
+ "local",
19
+ "global",
20
+ "local"
21
+ ],
22
+ "attention_types": [
23
+ [
24
+ [
25
+ "global",
26
+ "local"
27
+ ],
28
+ 6
29
+ ]
30
+ ],
31
  "bos_token_id": 50256,
32
+ "classifier_dropout": 0.1,
33
  "embed_dropout": 0,
34
  "eos_token_id": 50256,
35
+ "gradient_checkpointing": false,
36
  "hidden_size": 768,
37
  "initializer_range": 0.02,
38
+ "intermediate_size": null,
39
+ "layer_norm_epsilon": 1e-05,
40
  "max_position_embeddings": 2048,
41
  "model_type": "gpt_neo",
42
  "num_heads": 12,
43
  "num_layers": 12,
44
  "resid_dropout": 0,
45
+ "summary_activation": null,
46
+ "summary_first_dropout": 0.1,
47
+ "summary_proj_to_labels": true,
48
+ "summary_type": "cls_index",
49
+ "summary_use_proj": true,
50
+ "torch_dtype": "float32",
51
+ "transformers_version": "4.44.2",
52
  "use_cache": true,
53
+ "vocab_size": 50257,
54
+ "window_size": 256
55
+ }
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
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:856ecd17970445ed3ce6ea151230a42011395df010eb73d9fd801d51cae8fc2e
3
+ size 500811336
runs/Oct14_07-39-24_ca83b710e823/events.out.tfevents.1728891565.ca83b710e823.3134.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f656faf44bd4f930a6862344947c5e5c8dc49badc26ae92316b1f27c17fc7e2
3
+ size 5308
runs/Oct14_07-46-40_ca83b710e823/events.out.tfevents.1728892000.ca83b710e823.3134.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1ffae657012fe8ae4479a6030594140ea522d580a7f043ad89c8734c036609c
3
+ size 5309
runs/Oct14_08-10-22_ca83b710e823/events.out.tfevents.1728893425.ca83b710e823.11448.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26445e056aef3b9bf4cf21c8761d835d638dbbba228845655280e251d799b89f
3
+ size 5662
runs/Oct14_09-37-31_ca83b710e823/events.out.tfevents.1728898653.ca83b710e823.11448.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c90b7cb596d0bb60dd9c0421a4728fa7e76acb3abbdc9461fa27af6b971f52b
3
+ size 5308
runs/Oct14_09-46-11_ca83b710e823/events.out.tfevents.1728899173.ca83b710e823.11448.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:024fcc5898485b3c03f3b98035b1a09fff878102dba8c0149d8d92702384c064
3
+ size 5658
special_tokens_map.json CHANGED
@@ -1,6 +1,24 @@
1
  {
2
- "bos_token": "<s>",
3
- "eos_token": "</s>",
4
- "unk_token": "<unk>",
5
- "pad_token": "<pad>"
6
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 CHANGED
@@ -1,10 +1,22 @@
1
  {
2
- "model_max_length": 1024,
3
- "padding_side": "right",
4
- "truncation_side": "right",
5
- "bos_token": "<s>",
6
- "eos_token": "</s>",
7
- "unk_token": "<unk>",
8
- "pad_token": "<pad>",
9
- "model_type": "gpt_neo"
10
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
16
+ "eos_token": "<|endoftext|>",
17
+ "errors": "replace",
18
+ "model_max_length": 2048,
19
+ "pad_token": "<|endoftext|>",
20
+ "tokenizer_class": "GPT2Tokenizer",
21
+ "unk_token": "<|endoftext|>"
22
+ }
vocab.json CHANGED
The diff for this file is too large to render. See raw diff