Hugging Face's logo

AustinCarthy
/
OnlyPhishGPT2

Text Generation
Transformers
PyTorch
TensorBoard
gpt2
text-generation-inference
Model card Files
xet
Metrics Community
1
AustinCarthy commited on
Commit
b1b112c
·
1 Parent(s): f69e02f

Training in progress, epoch 7

Browse files
Files changed (30) hide show
  1. checkpoint-17112/config.json +39 -0
  2. checkpoint-17112/generation_config.json +6 -0
  3. checkpoint-17112/merges.txt +0 -0
  4. checkpoint-17112/optimizer.pt +3 -0
  5. checkpoint-17112/pytorch_model.bin +3 -0
  6. checkpoint-17112/rng_state.pth +3 -0
  7. checkpoint-17112/scaler.pt +3 -0
  8. checkpoint-17112/scheduler.pt +3 -0
  9. checkpoint-17112/special_tokens_map.json +6 -0
  10. checkpoint-17112/tokenizer.json +0 -0
  11. checkpoint-17112/tokenizer_config.json +10 -0
  12. checkpoint-17112/trainer_state.json +100 -0
  13. checkpoint-17112/training_args.bin +3 -0
  14. checkpoint-17112/vocab.json +0 -0
  15. checkpoint-19964/config.json +39 -0
  16. checkpoint-19964/generation_config.json +6 -0
  17. checkpoint-19964/merges.txt +0 -0
  18. checkpoint-19964/optimizer.pt +3 -0
  19. checkpoint-19964/pytorch_model.bin +3 -0
  20. checkpoint-19964/rng_state.pth +3 -0
  21. checkpoint-19964/scaler.pt +3 -0
  22. checkpoint-19964/scheduler.pt +3 -0
  23. checkpoint-19964/special_tokens_map.json +6 -0
  24. checkpoint-19964/tokenizer.json +0 -0
  25. checkpoint-19964/tokenizer_config.json +10 -0
  26. checkpoint-19964/trainer_state.json +114 -0
  27. checkpoint-19964/training_args.bin +3 -0
  28. checkpoint-19964/vocab.json +0 -0
  29. pytorch_model.bin +1 -1
  30. runs/Mar20_15-06-31_jupyter-austincarthy/events.out.tfevents.1679324800.jupyter-austincarthy.84.0 +2 -2
checkpoint-17112/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": 256,
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": "4.26.0",
37
+ "use_cache": true,
38
+ "vocab_size": 50257
39
+ }
checkpoint-17112/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": "4.26.0"
6
+ }
checkpoint-17112/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-17112/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0caec4fa0e1a961e8f98741e400f506df1af0cf1f5692a84cd0720621469c39a
3
+ size 990885425
checkpoint-17112/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fb3579ed568233065d923086e8d19a11065bf8c72f1b96eda66b4d611ac7361
3
+ size 496240745
checkpoint-17112/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70a2787572e97ef94e2129f4028b207217c9327a387f81c3c273b5c6be60eb3e
3
+ size 14503
checkpoint-17112/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6973c25ac22fc97fc337b4abf4b0f9748bf1eca031decf31dd6b9c007be9bdb0
3
+ size 559
checkpoint-17112/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6465f50eac26e5d8790bd922669189b1d2b2699858c66d03db7f954e8fbe8ca8
3
+ size 623
checkpoint-17112/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-17112/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-17112/tokenizer_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "eos_token": "<|endoftext|>",
5
+ "model_max_length": 1024,
6
+ "name_or_path": "gpt2",
7
+ "special_tokens_map_file": null,
8
+ "tokenizer_class": "GPT2Tokenizer",
9
+ "unk_token": "<|endoftext|>"
10
+ }
checkpoint-17112/trainer_state.json ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 6.0,
5
+ "global_step": 17112,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "learning_rate": 0.0004944335719677752,
13
+ "loss": 1.7574,
14
+ "step": 2852
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_loss": 1.1653077602386475,
19
+ "eval_runtime": 5.8814,
20
+ "eval_samples_per_second": 1723.907,
21
+ "eval_steps_per_second": 53.899,
22
+ "step": 2852
23
+ },
24
+ {
25
+ "epoch": 2.0,
26
+ "learning_rate": 0.0004648126812298226,
27
+ "loss": 1.1185,
28
+ "step": 5704
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "eval_loss": 1.0457065105438232,
33
+ "eval_runtime": 12.2627,
34
+ "eval_samples_per_second": 826.814,
35
+ "eval_steps_per_second": 25.851,
36
+ "step": 5704
37
+ },
38
+ {
39
+ "epoch": 3.0,
40
+ "learning_rate": 0.00041264395087890917,
41
+ "loss": 1.0203,
42
+ "step": 8556
43
+ },
44
+ {
45
+ "epoch": 3.0,
46
+ "eval_loss": 1.0074150562286377,
47
+ "eval_runtime": 12.4439,
48
+ "eval_samples_per_second": 814.775,
49
+ "eval_steps_per_second": 25.474,
50
+ "step": 8556
51
+ },
52
+ {
53
+ "epoch": 4.0,
54
+ "learning_rate": 0.0003433987425131291,
55
+ "loss": 0.9556,
56
+ "step": 11408
57
+ },
58
+ {
59
+ "epoch": 4.0,
60
+ "eval_loss": 0.9763176441192627,
61
+ "eval_runtime": 12.3993,
62
+ "eval_samples_per_second": 817.705,
63
+ "eval_steps_per_second": 25.566,
64
+ "step": 11408
65
+ },
66
+ {
67
+ "epoch": 5.0,
68
+ "learning_rate": 0.00026434731900978713,
69
+ "loss": 0.8938,
70
+ "step": 14260
71
+ },
72
+ {
73
+ "epoch": 5.0,
74
+ "eval_loss": 0.9555851221084595,
75
+ "eval_runtime": 11.4331,
76
+ "eval_samples_per_second": 886.808,
77
+ "eval_steps_per_second": 27.726,
78
+ "step": 14260
79
+ },
80
+ {
81
+ "epoch": 6.0,
82
+ "learning_rate": 0.0001837895272934318,
83
+ "loss": 0.8298,
84
+ "step": 17112
85
+ },
86
+ {
87
+ "epoch": 6.0,
88
+ "eval_loss": 0.9401514530181885,
89
+ "eval_runtime": 11.415,
90
+ "eval_samples_per_second": 888.217,
91
+ "eval_steps_per_second": 27.77,
92
+ "step": 17112
93
+ }
94
+ ],
95
+ "max_steps": 28520,
96
+ "num_train_epochs": 10,
97
+ "total_flos": 1.7633821487616e+16,
98
+ "trial_name": null,
99
+ "trial_params": null
100
+ }
checkpoint-17112/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8c5a084a5cbd7aa033d2c6e8ff526bb65b17feb5570391cc215fdf455a6fd41
3
+ size 3503
checkpoint-17112/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-19964/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": 256,
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": "4.26.0",
37
+ "use_cache": true,
38
+ "vocab_size": 50257
39
+ }
checkpoint-19964/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": "4.26.0"
6
+ }
checkpoint-19964/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-19964/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e6a842d38405dc26283b1b080337b0fe333a12fbabc48b9252a93ad137afe10
3
+ size 990885425
checkpoint-19964/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bd1633547da651133192bdd8db081bb03dee6d0f62581244b9a2acb5a860c0a
3
+ size 496240745
checkpoint-19964/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fb9552244a3079452f0e89d98e66d01731fe487face9c90396090ea670ea924
3
+ size 14503
checkpoint-19964/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8752d0dc2446b6447c672fbb678b41b3ad25666c66986c3cbd9ff66643e2580
3
+ size 559
checkpoint-19964/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca93883c2067ac84ff022b658b2f6124215f6833a6f18cd5c79bb172d6a807b2
3
+ size 623
checkpoint-19964/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-19964/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-19964/tokenizer_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "eos_token": "<|endoftext|>",
5
+ "model_max_length": 1024,
6
+ "name_or_path": "gpt2",
7
+ "special_tokens_map_file": null,
8
+ "tokenizer_class": "GPT2Tokenizer",
9
+ "unk_token": "<|endoftext|>"
10
+ }
checkpoint-19964/trainer_state.json ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 7.0,
5
+ "global_step": 19964,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "learning_rate": 0.0004944335719677752,
13
+ "loss": 1.7574,
14
+ "step": 2852
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_loss": 1.1653077602386475,
19
+ "eval_runtime": 5.8814,
20
+ "eval_samples_per_second": 1723.907,
21
+ "eval_steps_per_second": 53.899,
22
+ "step": 2852
23
+ },
24
+ {
25
+ "epoch": 2.0,
26
+ "learning_rate": 0.0004648126812298226,
27
+ "loss": 1.1185,
28
+ "step": 5704
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "eval_loss": 1.0457065105438232,
33
+ "eval_runtime": 12.2627,
34
+ "eval_samples_per_second": 826.814,
35
+ "eval_steps_per_second": 25.851,
36
+ "step": 5704
37
+ },
38
+ {
39
+ "epoch": 3.0,
40
+ "learning_rate": 0.00041264395087890917,
41
+ "loss": 1.0203,
42
+ "step": 8556
43
+ },
44
+ {
45
+ "epoch": 3.0,
46
+ "eval_loss": 1.0074150562286377,
47
+ "eval_runtime": 12.4439,
48
+ "eval_samples_per_second": 814.775,
49
+ "eval_steps_per_second": 25.474,
50
+ "step": 8556
51
+ },
52
+ {
53
+ "epoch": 4.0,
54
+ "learning_rate": 0.0003433987425131291,
55
+ "loss": 0.9556,
56
+ "step": 11408
57
+ },
58
+ {
59
+ "epoch": 4.0,
60
+ "eval_loss": 0.9763176441192627,
61
+ "eval_runtime": 12.3993,
62
+ "eval_samples_per_second": 817.705,
63
+ "eval_steps_per_second": 25.566,
64
+ "step": 11408
65
+ },
66
+ {
67
+ "epoch": 5.0,
68
+ "learning_rate": 0.00026434731900978713,
69
+ "loss": 0.8938,
70
+ "step": 14260
71
+ },
72
+ {
73
+ "epoch": 5.0,
74
+ "eval_loss": 0.9555851221084595,
75
+ "eval_runtime": 11.4331,
76
+ "eval_samples_per_second": 886.808,
77
+ "eval_steps_per_second": 27.726,
78
+ "step": 14260
79
+ },
80
+ {
81
+ "epoch": 6.0,
82
+ "learning_rate": 0.0001837895272934318,
83
+ "loss": 0.8298,
84
+ "step": 17112
85
+ },
86
+ {
87
+ "epoch": 6.0,
88
+ "eval_loss": 0.9401514530181885,
89
+ "eval_runtime": 11.415,
90
+ "eval_samples_per_second": 888.217,
91
+ "eval_steps_per_second": 27.77,
92
+ "step": 17112
93
+ },
94
+ {
95
+ "epoch": 7.0,
96
+ "learning_rate": 0.00011018337242196222,
97
+ "loss": 0.7611,
98
+ "step": 19964
99
+ },
100
+ {
101
+ "epoch": 7.0,
102
+ "eval_loss": 0.9359964728355408,
103
+ "eval_runtime": 11.3883,
104
+ "eval_samples_per_second": 890.303,
105
+ "eval_steps_per_second": 27.836,
106
+ "step": 19964
107
+ }
108
+ ],
109
+ "max_steps": 28520,
110
+ "num_train_epochs": 10,
111
+ "total_flos": 2.0546404982784e+16,
112
+ "trial_name": null,
113
+ "trial_params": null
114
+ }
checkpoint-19964/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8c5a084a5cbd7aa033d2c6e8ff526bb65b17feb5570391cc215fdf455a6fd41
3
+ size 3503
checkpoint-19964/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06a3ae3286979edb50a767c99451948f5ff70bb64371cb4d8cecd2644aacae46
3
  size 496240745
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bd1633547da651133192bdd8db081bb03dee6d0f62581244b9a2acb5a860c0a
3
  size 496240745
runs/Mar20_15-06-31_jupyter-austincarthy/events.out.tfevents.1679324800.jupyter-austincarthy.84.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e191ecdf3f2512f1b968757b77e5e40a2ddbf779cbf66bb1c86e455aee43f3f5
3
- size 6273
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d248d6ea38907b57923894c772370c02937d48e2ac09e394c98b9ac0fe3c6800
3
+ size 7145