Hugging Face's logo

harishussain12
/
NeoMed

Text Generation
Transformers
Safetensors
English
gpt2
text-generation-inference
Inference Endpoints
Model card Files Community
harishussain12 commited on
Commit
9b61197
·
verified ·
1 Parent(s): a194b36

Upload folder using huggingface_hub

Browse files
Files changed (35) hide show
  1. checkpoint-1491/config.json +39 -0
  2. checkpoint-1491/generation_config.json +6 -0
  3. checkpoint-1491/merges.txt +0 -0
  4. checkpoint-1491/model.safetensors +3 -0
  5. checkpoint-1491/optimizer.pt +3 -0
  6. checkpoint-1491/rng_state.pth +3 -0
  7. checkpoint-1491/scheduler.pt +3 -0
  8. checkpoint-1491/special_tokens_map.json +6 -0
  9. checkpoint-1491/tokenizer.json +0 -0
  10. checkpoint-1491/tokenizer_config.json +21 -0
  11. checkpoint-1491/trainer_state.json +71 -0
  12. checkpoint-1491/training_args.bin +3 -0
  13. checkpoint-1491/vocab.json +0 -0
  14. checkpoint-994/config.json +39 -0
  15. checkpoint-994/generation_config.json +6 -0
  16. checkpoint-994/merges.txt +0 -0
  17. checkpoint-994/model.safetensors +3 -0
  18. checkpoint-994/optimizer.pt +3 -0
  19. checkpoint-994/rng_state.pth +3 -0
  20. checkpoint-994/scheduler.pt +3 -0
  21. checkpoint-994/special_tokens_map.json +6 -0
  22. checkpoint-994/tokenizer.json +0 -0
  23. checkpoint-994/tokenizer_config.json +21 -0
  24. checkpoint-994/trainer_state.json +56 -0
  25. checkpoint-994/training_args.bin +3 -0
  26. checkpoint-994/vocab.json +0 -0
  27. config.json +39 -0
  28. generation_config.json +6 -0
  29. merges.txt +0 -0
  30. model.safetensors +3 -0
  31. special_tokens_map.json +6 -0
  32. tokenizer.json +0 -0
  33. tokenizer_config.json +21 -0
  34. training_args.bin +3 -0
  35. vocab.json +0 -0
checkpoint-1491/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai-community/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": "4.47.1",
37
+ "use_cache": true,
38
+ "vocab_size": 50257
39
+ }
checkpoint-1491/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": "4.47.1"
6
+ }
checkpoint-1491/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1491/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c01264bd5319d00224d6a108faa16bbc5103ae2a730d122f1e73304cbacb21a8
3
+ size 497774208
checkpoint-1491/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36ef3b9348b5d3a6b19302f4c0fc613798be7c7845f655ba9deb0bcb006722f2
3
+ size 995642298
checkpoint-1491/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eed290a7c36689c93288c8ca6d6052c4da16058be715083737033eccaa412e27
3
+ size 14244
checkpoint-1491/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c4433e750caa811b868ad1dc4ad114651f1f6fa642187407e3e42560564cf66
3
+ size 1064
checkpoint-1491/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-1491/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1491/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": 1024,
18
+ "pad_token": "<|endoftext|>",
19
+ "tokenizer_class": "GPT2Tokenizer",
20
+ "unk_token": "<|endoftext|>"
21
+ }
checkpoint-1491/trainer_state.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1491,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_loss": 2.1311028003692627,
14
+ "eval_runtime": 4.522,
15
+ "eval_samples_per_second": 48.872,
16
+ "eval_steps_per_second": 12.384,
17
+ "step": 497
18
+ },
19
+ {
20
+ "epoch": 1.0060362173038229,
21
+ "grad_norm": 35.682647705078125,
22
+ "learning_rate": 3.3501006036217306e-05,
23
+ "loss": 2.1271,
24
+ "step": 500
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "eval_loss": 1.991774082183838,
29
+ "eval_runtime": 4.5224,
30
+ "eval_samples_per_second": 48.867,
31
+ "eval_steps_per_second": 12.383,
32
+ "step": 994
33
+ },
34
+ {
35
+ "epoch": 2.0120724346076457,
36
+ "grad_norm": 17.350433349609375,
37
+ "learning_rate": 1.6733735747820257e-05,
38
+ "loss": 1.8126,
39
+ "step": 1000
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "eval_loss": 1.9652814865112305,
44
+ "eval_runtime": 4.5504,
45
+ "eval_samples_per_second": 48.567,
46
+ "eval_steps_per_second": 12.307,
47
+ "step": 1491
48
+ }
49
+ ],
50
+ "logging_steps": 500,
51
+ "max_steps": 1491,
52
+ "num_input_tokens_seen": 0,
53
+ "num_train_epochs": 3,
54
+ "save_steps": 500,
55
+ "stateful_callbacks": {
56
+ "TrainerControl": {
57
+ "args": {
58
+ "should_epoch_stop": false,
59
+ "should_evaluate": false,
60
+ "should_log": false,
61
+ "should_save": true,
62
+ "should_training_stop": true
63
+ },
64
+ "attributes": {}
65
+ }
66
+ },
67
+ "total_flos": 1557561802752000.0,
68
+ "train_batch_size": 4,
69
+ "trial_name": null,
70
+ "trial_params": null
71
+ }
checkpoint-1491/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac447340a4a9e4486a9a0299c2ef8b6b6652e2c97246c1c15a43fac9e0bd51d7
3
+ size 5304
checkpoint-1491/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-994/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai-community/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": "4.47.1",
37
+ "use_cache": true,
38
+ "vocab_size": 50257
39
+ }
checkpoint-994/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": "4.47.1"
6
+ }
checkpoint-994/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-994/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef960720d73669076cc59527e8d465eb7b17f069e58806684556b08b4716f6d2
3
+ size 497774208
checkpoint-994/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9abc8ef7806061f32a0fa68ee2b99f4d2362aa586f0baa1b7e56e6efa7caa45
3
+ size 995642298
checkpoint-994/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c78dad584de11788330bbd0d0f3497f1f6a83cb1113ff57f963fb2edbc86d09
3
+ size 14244
checkpoint-994/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1eb3ac594d835f6347befc4b38291d54a55057282754e11c2fecbafdc52679d5
3
+ size 1064
checkpoint-994/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-994/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-994/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": 1024,
18
+ "pad_token": "<|endoftext|>",
19
+ "tokenizer_class": "GPT2Tokenizer",
20
+ "unk_token": "<|endoftext|>"
21
+ }
checkpoint-994/trainer_state.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 994,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_loss": 2.1311028003692627,
14
+ "eval_runtime": 4.522,
15
+ "eval_samples_per_second": 48.872,
16
+ "eval_steps_per_second": 12.384,
17
+ "step": 497
18
+ },
19
+ {
20
+ "epoch": 1.0060362173038229,
21
+ "grad_norm": 35.682647705078125,
22
+ "learning_rate": 3.3501006036217306e-05,
23
+ "loss": 2.1271,
24
+ "step": 500
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "eval_loss": 1.991774082183838,
29
+ "eval_runtime": 4.5224,
30
+ "eval_samples_per_second": 48.867,
31
+ "eval_steps_per_second": 12.383,
32
+ "step": 994
33
+ }
34
+ ],
35
+ "logging_steps": 500,
36
+ "max_steps": 1491,
37
+ "num_input_tokens_seen": 0,
38
+ "num_train_epochs": 3,
39
+ "save_steps": 500,
40
+ "stateful_callbacks": {
41
+ "TrainerControl": {
42
+ "args": {
43
+ "should_epoch_stop": false,
44
+ "should_evaluate": false,
45
+ "should_log": false,
46
+ "should_save": true,
47
+ "should_training_stop": false
48
+ },
49
+ "attributes": {}
50
+ }
51
+ },
52
+ "total_flos": 1038374535168000.0,
53
+ "train_batch_size": 4,
54
+ "trial_name": null,
55
+ "trial_params": null
56
+ }
checkpoint-994/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac447340a4a9e4486a9a0299c2ef8b6b6652e2c97246c1c15a43fac9e0bd51d7
3
+ size 5304
checkpoint-994/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai-community/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": "4.47.1",
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": "4.47.1"
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:c01264bd5319d00224d6a108faa16bbc5103ae2a730d122f1e73304cbacb21a8
3
+ size 497774208
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
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
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": 1024,
18
+ "pad_token": "<|endoftext|>",
19
+ "tokenizer_class": "GPT2Tokenizer",
20
+ "unk_token": "<|endoftext|>"
21
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac447340a4a9e4486a9a0299c2ef8b6b6652e2c97246c1c15a43fac9e0bd51d7
3
+ size 5304
vocab.json ADDED
The diff for this file is too large to render. See raw diff