Hugging Face's logo

informatiker
/
agpt-lines-10epochsmed

Safetensors
gpt2
Model card Files Community
informatiker commited on
Commit
a559bed
·
verified ·
1 Parent(s): ea44c6a

Upload folder using huggingface_hub

Browse files
Files changed (32) hide show
  1. checkpoint-1000/config.json +41 -0
  2. checkpoint-1000/generation_config.json +6 -0
  3. checkpoint-1000/model.safetensors +3 -0
  4. checkpoint-1000/optimizer.pt +3 -0
  5. checkpoint-1000/rng_state.pth +3 -0
  6. checkpoint-1000/scheduler.pt +3 -0
  7. checkpoint-1000/trainer_state.json +47 -0
  8. checkpoint-1000/training_args.bin +3 -0
  9. checkpoint-1370/config.json +41 -0
  10. checkpoint-1370/generation_config.json +6 -0
  11. checkpoint-1370/model.safetensors +3 -0
  12. checkpoint-1370/optimizer.pt +3 -0
  13. checkpoint-1370/rng_state.pth +3 -0
  14. checkpoint-1370/scheduler.pt +3 -0
  15. checkpoint-1370/trainer_state.json +47 -0
  16. checkpoint-1370/training_args.bin +3 -0
  17. checkpoint-500/config.json +41 -0
  18. checkpoint-500/generation_config.json +6 -0
  19. checkpoint-500/model.safetensors +3 -0
  20. checkpoint-500/optimizer.pt +3 -0
  21. checkpoint-500/rng_state.pth +3 -0
  22. checkpoint-500/scheduler.pt +3 -0
  23. checkpoint-500/trainer_state.json +40 -0
  24. checkpoint-500/training_args.bin +3 -0
  25. config.json +41 -0
  26. generation_config.json +6 -0
  27. merges.txt +0 -0
  28. model.safetensors +3 -0
  29. special_tokens_map.json +23 -0
  30. tokenizer_config.json +22 -0
  31. training_args.bin +3 -0
  32. vocab.json +0 -0
checkpoint-1000/config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2-medium",
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": 1024,
16
+ "n_head": 16,
17
+ "n_inner": null,
18
+ "n_layer": 24,
19
+ "n_positions": 1024,
20
+ "n_special": 0,
21
+ "predict_special_tokens": true,
22
+ "reorder_and_upcast_attn": false,
23
+ "resid_pdrop": 0.1,
24
+ "scale_attn_by_inverse_layer_idx": false,
25
+ "scale_attn_weights": true,
26
+ "summary_activation": null,
27
+ "summary_first_dropout": 0.1,
28
+ "summary_proj_to_labels": true,
29
+ "summary_type": "cls_index",
30
+ "summary_use_proj": true,
31
+ "task_specific_params": {
32
+ "text-generation": {
33
+ "do_sample": true,
34
+ "max_length": 50
35
+ }
36
+ },
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.45.1",
39
+ "use_cache": true,
40
+ "vocab_size": 50257
41
+ }
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": "4.45.1"
6
+ }
checkpoint-1000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2de84d956a13f63fef40f6b31ed22ce9caea3f1a7001121eae640014e65dfdf
3
+ size 1419322880
checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:178b0ae21778f88b84bbbb43e1d1e372210008d41676cd9c3c77036743bdc621
3
+ size 2838829242
checkpoint-1000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d872d0cfab0d432dedd7da4d7f8d6fce9abf00a9f97d1cdea437b2c905db82b8
3
+ size 14244
checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0a65896ac4e8f43b04ca0e3189d796d36a0360a815322c5542d9751310626ba
3
+ size 1064
checkpoint-1000/trainer_state.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 7.299270072992701,
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": 3.6496350364963503,
13
+ "grad_norm": 8.169337272644043,
14
+ "learning_rate": 3.175182481751825e-05,
15
+ "loss": 3.4139,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 7.299270072992701,
20
+ "grad_norm": 7.2069478034973145,
21
+ "learning_rate": 1.3503649635036497e-05,
22
+ "loss": 2.4615,
23
+ "step": 1000
24
+ }
25
+ ],
26
+ "logging_steps": 500,
27
+ "max_steps": 1370,
28
+ "num_input_tokens_seen": 0,
29
+ "num_train_epochs": 10,
30
+ "save_steps": 500,
31
+ "stateful_callbacks": {
32
+ "TrainerControl": {
33
+ "args": {
34
+ "should_epoch_stop": false,
35
+ "should_evaluate": false,
36
+ "should_log": false,
37
+ "should_save": true,
38
+ "should_training_stop": false
39
+ },
40
+ "attributes": {}
41
+ }
42
+ },
43
+ "total_flos": 1846024805548032.0,
44
+ "train_batch_size": 8,
45
+ "trial_name": null,
46
+ "trial_params": null
47
+ }
checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f87b340bc8350051c87f65a1906c566677b933151cba8c95319068ac9e86f65
3
+ size 5176
checkpoint-1370/config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2-medium",
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": 1024,
16
+ "n_head": 16,
17
+ "n_inner": null,
18
+ "n_layer": 24,
19
+ "n_positions": 1024,
20
+ "n_special": 0,
21
+ "predict_special_tokens": true,
22
+ "reorder_and_upcast_attn": false,
23
+ "resid_pdrop": 0.1,
24
+ "scale_attn_by_inverse_layer_idx": false,
25
+ "scale_attn_weights": true,
26
+ "summary_activation": null,
27
+ "summary_first_dropout": 0.1,
28
+ "summary_proj_to_labels": true,
29
+ "summary_type": "cls_index",
30
+ "summary_use_proj": true,
31
+ "task_specific_params": {
32
+ "text-generation": {
33
+ "do_sample": true,
34
+ "max_length": 50
35
+ }
36
+ },
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.45.1",
39
+ "use_cache": true,
40
+ "vocab_size": 50257
41
+ }
checkpoint-1370/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": "4.45.1"
6
+ }
checkpoint-1370/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dab5c775ac1a239674ebb546d5f4b09bc09048766b874fad7b76fe73bc5ab4d6
3
+ size 1419322880
checkpoint-1370/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e721256403851e7cb98b4da56b188af6fd3b4e09f3153a871bd6964657356e31
3
+ size 2838829242
checkpoint-1370/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63b2909fc611a3d245d99e8c89e95e2fb92cb05575fdfe7bb79b2f1119a5a6af
3
+ size 14244
checkpoint-1370/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19911aa93d2bf84d109d8b1f04bd8086586e935e0ef9e25c6f39009d25826d06
3
+ size 1064
checkpoint-1370/trainer_state.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 10.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1370,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 3.6496350364963503,
13
+ "grad_norm": 8.169337272644043,
14
+ "learning_rate": 3.175182481751825e-05,
15
+ "loss": 3.4139,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 7.299270072992701,
20
+ "grad_norm": 7.2069478034973145,
21
+ "learning_rate": 1.3503649635036497e-05,
22
+ "loss": 2.4615,
23
+ "step": 1000
24
+ }
25
+ ],
26
+ "logging_steps": 500,
27
+ "max_steps": 1370,
28
+ "num_input_tokens_seen": 0,
29
+ "num_train_epochs": 10,
30
+ "save_steps": 500,
31
+ "stateful_callbacks": {
32
+ "TrainerControl": {
33
+ "args": {
34
+ "should_epoch_stop": false,
35
+ "should_evaluate": false,
36
+ "should_log": false,
37
+ "should_save": true,
38
+ "should_training_stop": true
39
+ },
40
+ "attributes": {}
41
+ }
42
+ },
43
+ "total_flos": 2528387640852480.0,
44
+ "train_batch_size": 8,
45
+ "trial_name": null,
46
+ "trial_params": null
47
+ }
checkpoint-1370/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f87b340bc8350051c87f65a1906c566677b933151cba8c95319068ac9e86f65
3
+ size 5176
checkpoint-500/config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2-medium",
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": 1024,
16
+ "n_head": 16,
17
+ "n_inner": null,
18
+ "n_layer": 24,
19
+ "n_positions": 1024,
20
+ "n_special": 0,
21
+ "predict_special_tokens": true,
22
+ "reorder_and_upcast_attn": false,
23
+ "resid_pdrop": 0.1,
24
+ "scale_attn_by_inverse_layer_idx": false,
25
+ "scale_attn_weights": true,
26
+ "summary_activation": null,
27
+ "summary_first_dropout": 0.1,
28
+ "summary_proj_to_labels": true,
29
+ "summary_type": "cls_index",
30
+ "summary_use_proj": true,
31
+ "task_specific_params": {
32
+ "text-generation": {
33
+ "do_sample": true,
34
+ "max_length": 50
35
+ }
36
+ },
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.45.1",
39
+ "use_cache": true,
40
+ "vocab_size": 50257
41
+ }
checkpoint-500/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": "4.45.1"
6
+ }
checkpoint-500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ef04ec21c0dbb0e5b139fc8ca8f40768e3a5007cc6dabb700293b5e0c4ca919
3
+ size 1419322880
checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cf7376cf5a360ec48ebe4de4c18e8100e9fad0f5d5b3606b82a413b51f35645
3
+ size 2838829242
checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:432de95bf48e4190f161536323973056f80bcb953554d6ffac8eaa65563057b3
3
+ size 14244
checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db4a46a26a1b390f9744d1adf3c0063293dadd0390068a13bbeebc3b177fc6b8
3
+ size 1064
checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.6496350364963503,
5
+ "eval_steps": 500,
6
+ "global_step": 500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 3.6496350364963503,
13
+ "grad_norm": 8.169337272644043,
14
+ "learning_rate": 3.175182481751825e-05,
15
+ "loss": 3.4139,
16
+ "step": 500
17
+ }
18
+ ],
19
+ "logging_steps": 500,
20
+ "max_steps": 1370,
21
+ "num_input_tokens_seen": 0,
22
+ "num_train_epochs": 10,
23
+ "save_steps": 500,
24
+ "stateful_callbacks": {
25
+ "TrainerControl": {
26
+ "args": {
27
+ "should_epoch_stop": false,
28
+ "should_evaluate": false,
29
+ "should_log": false,
30
+ "should_save": true,
31
+ "should_training_stop": false
32
+ },
33
+ "attributes": {}
34
+ }
35
+ },
36
+ "total_flos": 923825015881728.0,
37
+ "train_batch_size": 8,
38
+ "trial_name": null,
39
+ "trial_params": null
40
+ }
checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f87b340bc8350051c87f65a1906c566677b933151cba8c95319068ac9e86f65
3
+ size 5176
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2-medium",
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": 1024,
16
+ "n_head": 16,
17
+ "n_inner": null,
18
+ "n_layer": 24,
19
+ "n_positions": 1024,
20
+ "n_special": 0,
21
+ "predict_special_tokens": true,
22
+ "reorder_and_upcast_attn": false,
23
+ "resid_pdrop": 0.1,
24
+ "scale_attn_by_inverse_layer_idx": false,
25
+ "scale_attn_weights": true,
26
+ "summary_activation": null,
27
+ "summary_first_dropout": 0.1,
28
+ "summary_proj_to_labels": true,
29
+ "summary_type": "cls_index",
30
+ "summary_use_proj": true,
31
+ "task_specific_params": {
32
+ "text-generation": {
33
+ "do_sample": true,
34
+ "max_length": 50
35
+ }
36
+ },
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.45.1",
39
+ "use_cache": true,
40
+ "vocab_size": 50257
41
+ }
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": "4.45.1"
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:dab5c775ac1a239674ebb546d5f4b09bc09048766b874fad7b76fe73bc5ab4d6
3
+ size 1419322880
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "unk_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
16
+ "eos_token": "<|endoftext|>",
17
+ "errors": "replace",
18
+ "model_max_length": 1024,
19
+ "pad_token": null,
20
+ "tokenizer_class": "GPT2Tokenizer",
21
+ "unk_token": "<|endoftext|>"
22
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f87b340bc8350051c87f65a1906c566677b933151cba8c95319068ac9e86f65
3
+ size 5176
vocab.json ADDED
The diff for this file is too large to render. See raw diff