Hugging Face's logo

anezatra
/
gpt2-HxH

Text Generation
Transformers
TensorBoard
Safetensors
gpt2
Inference Endpoints
text-generation-inference
Model card Files Metrics Community
anezatra commited on
Commit
2ffab0c
•
1 Parent(s): c16ba40

Upload folder using huggingface_hub

Browse files
Files changed (39) hide show
  1. all_results.json +8 -0
  2. checkpoint-1000/config.json +39 -0
  3. checkpoint-1000/generation_config.json +6 -0
  4. checkpoint-1000/merges.txt +0 -0
  5. checkpoint-1000/model.safetensors +3 -0
  6. checkpoint-1000/optimizer.pt +3 -0
  7. checkpoint-1000/rng_state.pth +3 -0
  8. checkpoint-1000/scheduler.pt +3 -0
  9. checkpoint-1000/special_tokens_map.json +5 -0
  10. checkpoint-1000/tokenizer.json +0 -0
  11. checkpoint-1000/tokenizer_config.json +19 -0
  12. checkpoint-1000/trainer_state.json +35 -0
  13. checkpoint-1000/training_args.bin +3 -0
  14. checkpoint-1000/vocab.json +0 -0
  15. checkpoint-1500/config.json +39 -0
  16. checkpoint-1500/generation_config.json +6 -0
  17. checkpoint-1500/merges.txt +0 -0
  18. checkpoint-1500/model.safetensors +3 -0
  19. checkpoint-1500/optimizer.pt +3 -0
  20. checkpoint-1500/rng_state.pth +3 -0
  21. checkpoint-1500/scheduler.pt +3 -0
  22. checkpoint-1500/special_tokens_map.json +5 -0
  23. checkpoint-1500/tokenizer.json +0 -0
  24. checkpoint-1500/tokenizer_config.json +19 -0
  25. checkpoint-1500/trainer_state.json +42 -0
  26. checkpoint-1500/training_args.bin +3 -0
  27. checkpoint-1500/vocab.json +0 -0
  28. config.json +39 -0
  29. generation_config.json +6 -0
  30. merges.txt +0 -0
  31. model.safetensors +3 -0
  32. runs/Apr03_15-56-49_6d3767883e5d/events.out.tfevents.1712159815.6d3767883e5d.8202.0 +3 -0
  33. special_tokens_map.json +5 -0
  34. tokenizer.json +0 -0
  35. tokenizer_config.json +19 -0
  36. train_results.json +8 -0
  37. trainer_state.json +51 -0
  38. training_args.bin +3 -0
  39. vocab.json +0 -0
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "train_loss": 3.507169401431512,
4
+ "train_runtime": 525.6016,
5
+ "train_samples": 16662,
6
+ "train_samples_per_second": 158.504,
7
+ "train_steps_per_second": 3.177
8
+ }
checkpoint-1000/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": "4.40.0.dev0",
37
+ "use_cache": true,
38
+ "vocab_size": 50257
39
+ }
checkpoint-1000/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": "4.40.0.dev0"
6
+ }
checkpoint-1000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2004a62b3ebbb00b32996f672e0b9235cf4ac077fa3eb176f2bda2e8f5a08c7
3
+ size 497774208
checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9adf942a10d4382b17763ab49c1cbb9674f8949212230b627dfea0fb97f85d8f
3
+ size 995642298
checkpoint-1000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:261a0caf36cd2f56e9ea21ae4fa941ca624d200c655f107dc1f41ac38337f0ae
3
+ size 14244
checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6336ad8d4bb99491b0de9b257dbea7f4a2dd35e5e71733d808d1bc6d96da73ef
3
+ size 1064
checkpoint-1000/special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>"
5
+ }
checkpoint-1000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1000/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
+ }
checkpoint-1000/trainer_state.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.9940119760479043,
5
+ "eval_steps": 500,
6
+ "global_step": 1000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.5,
13
+ "grad_norm": 6.208858013153076,
14
+ "learning_rate": 3.973265321538069e-05,
15
+ "loss": 3.8276,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 2.99,
20
+ "grad_norm": 5.765829086303711,
21
+ "learning_rate": 1.7364085661173347e-05,
22
+ "loss": 3.4714,
23
+ "step": 1000
24
+ }
25
+ ],
26
+ "logging_steps": 500,
27
+ "max_steps": 1670,
28
+ "num_input_tokens_seen": 0,
29
+ "num_train_epochs": 5,
30
+ "save_steps": 500,
31
+ "total_flos": 509560289280000.0,
32
+ "train_batch_size": 50,
33
+ "trial_name": null,
34
+ "trial_params": null
35
+ }
checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d3a923ef3f1f0a4e5770d1080aba18321f2cd4bb3e4cad90d5b5be0329c5be6
3
+ size 4920
checkpoint-1000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1500/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": "4.40.0.dev0",
37
+ "use_cache": true,
38
+ "vocab_size": 50257
39
+ }
checkpoint-1500/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": "4.40.0.dev0"
6
+ }
checkpoint-1500/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0fd590d444e06bf9304a523eb9c15d8c8fa7eb66820c1c7df1f83e2341f7668
3
+ size 497774208
checkpoint-1500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0191f9db4f78241c3281ef70eb216769f1c0e007c5e92a62657da1c7f851f7bd
3
+ size 995642298
checkpoint-1500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0ceab7bb2d990b489a1813a1ff917bbd8b6f9befe9f916c072645481cbae315
3
+ size 14244
checkpoint-1500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbfa7259a8cfae8fc989f33c9c9eba26864f15f05029279ab9aef7d57ea88b01
3
+ size 1064
checkpoint-1500/special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>"
5
+ }
checkpoint-1500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1500/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
+ }
checkpoint-1500/trainer_state.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.491017964071856,
5
+ "eval_steps": 500,
6
+ "global_step": 1500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.5,
13
+ "grad_norm": 6.208858013153076,
14
+ "learning_rate": 3.973265321538069e-05,
15
+ "loss": 3.8276,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 2.99,
20
+ "grad_norm": 5.765829086303711,
21
+ "learning_rate": 1.7364085661173347e-05,
22
+ "loss": 3.4714,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 4.49,
27
+ "grad_norm": 6.052618026733398,
28
+ "learning_rate": 1.267564549716435e-06,
29
+ "loss": 3.3029,
30
+ "step": 1500
31
+ }
32
+ ],
33
+ "logging_steps": 500,
34
+ "max_steps": 1670,
35
+ "num_input_tokens_seen": 0,
36
+ "num_train_epochs": 5,
37
+ "save_steps": 500,
38
+ "total_flos": 763952578560000.0,
39
+ "train_batch_size": 50,
40
+ "trial_name": null,
41
+ "trial_params": null
42
+ }
checkpoint-1500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d3a923ef3f1f0a4e5770d1080aba18321f2cd4bb3e4cad90d5b5be0329c5be6
3
+ size 4920
checkpoint-1500/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": "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": "4.40.0.dev0",
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": "4.40.0.dev0"
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:db55fe1c4fed4f435219f54aaefc7f50653d286ec1b11a7c0bc60ee9db92b4e2
3
+ size 497774208
runs/Apr03_15-56-49_6d3767883e5d/events.out.tfevents.1712159815.6d3767883e5d.8202.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00e197f9278978632a5005a8d32b9bdf26372a6bcab68df37bf93c43f8e49501
3
+ size 5834
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
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "train_loss": 3.507169401431512,
4
+ "train_runtime": 525.6016,
5
+ "train_samples": 16662,
6
+ "train_samples_per_second": 158.504,
7
+ "train_steps_per_second": 3.177
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1670,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.5,
13
+ "grad_norm": 6.208858013153076,
14
+ "learning_rate": 3.973265321538069e-05,
15
+ "loss": 3.8276,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 2.99,
20
+ "grad_norm": 5.765829086303711,
21
+ "learning_rate": 1.7364085661173347e-05,
22
+ "loss": 3.4714,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 4.49,
27
+ "grad_norm": 6.052618026733398,
28
+ "learning_rate": 1.267564549716435e-06,
29
+ "loss": 3.3029,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 5.0,
34
+ "step": 1670,
35
+ "total_flos": 850321843200000.0,
36
+ "train_loss": 3.507169401431512,
37
+ "train_runtime": 525.6016,
38
+ "train_samples_per_second": 158.504,
39
+ "train_steps_per_second": 3.177
40
+ }
41
+ ],
42
+ "logging_steps": 500,
43
+ "max_steps": 1670,
44
+ "num_input_tokens_seen": 0,
45
+ "num_train_epochs": 5,
46
+ "save_steps": 500,
47
+ "total_flos": 850321843200000.0,
48
+ "train_batch_size": 50,
49
+ "trial_name": null,
50
+ "trial_params": null
51
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d3a923ef3f1f0a4e5770d1080aba18321f2cd4bb3e4cad90d5b5be0329c5be6
3
+ size 4920
vocab.json ADDED
The diff for this file is too large to render. See raw diff