Hugging Face's logo

tomekkorbak
/
test9485844

Transformers
PyTorch
English
gpt2
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
tomekkorbak commited on
Commit
4a07707
•
1 Parent(s): 76723ae

update model card README.md

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. README.md +94 -0
  2. checkpoint-10/config.json +39 -0
  3. checkpoint-10/merges.txt +0 -0
  4. checkpoint-10/optimizer.pt +3 -0
  5. checkpoint-10/pytorch_model.bin +3 -0
  6. checkpoint-10/rng_state.pth +3 -0
  7. checkpoint-10/scaler.pt +3 -0
  8. checkpoint-10/scheduler.pt +3 -0
  9. checkpoint-10/special_tokens_map.json +6 -0
  10. checkpoint-10/tokenizer.json +0 -0
  11. checkpoint-10/tokenizer_config.json +10 -0
  12. checkpoint-10/trainer_state.json +86 -0
  13. checkpoint-10/training_args.bin +3 -0
  14. checkpoint-10/vocab.json +0 -0
  15. checkpoint-12/config.json +39 -0
  16. checkpoint-12/merges.txt +0 -0
  17. checkpoint-12/optimizer.pt +3 -0
  18. checkpoint-12/pytorch_model.bin +3 -0
  19. checkpoint-12/rng_state.pth +3 -0
  20. checkpoint-12/scaler.pt +3 -0
  21. checkpoint-12/scheduler.pt +3 -0
  22. checkpoint-12/special_tokens_map.json +6 -0
  23. checkpoint-12/tokenizer.json +0 -0
  24. checkpoint-12/tokenizer_config.json +10 -0
  25. checkpoint-12/trainer_state.json +100 -0
  26. checkpoint-12/training_args.bin +3 -0
  27. checkpoint-12/vocab.json +0 -0
  28. checkpoint-14/config.json +39 -0
  29. checkpoint-14/merges.txt +0 -0
  30. checkpoint-14/optimizer.pt +3 -0
  31. checkpoint-14/pytorch_model.bin +3 -0
  32. checkpoint-14/rng_state.pth +3 -0
  33. checkpoint-14/scaler.pt +3 -0
  34. checkpoint-14/scheduler.pt +3 -0
  35. checkpoint-14/special_tokens_map.json +6 -0
  36. checkpoint-14/tokenizer.json +0 -0
  37. checkpoint-14/tokenizer_config.json +10 -0
  38. checkpoint-14/trainer_state.json +114 -0
  39. checkpoint-14/training_args.bin +3 -0
  40. checkpoint-14/vocab.json +0 -0
  41. checkpoint-16/config.json +39 -0
  42. checkpoint-16/merges.txt +0 -0
  43. checkpoint-16/optimizer.pt +3 -0
  44. checkpoint-16/pytorch_model.bin +3 -0
  45. checkpoint-16/rng_state.pth +3 -0
  46. checkpoint-16/scaler.pt +3 -0
  47. checkpoint-16/scheduler.pt +3 -0
  48. checkpoint-16/special_tokens_map.json +6 -0
  49. checkpoint-16/tokenizer.json +0 -0
  50. checkpoint-16/tokenizer_config.json +10 -0
README.md ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - tomekkorbak/detoxify-pile-chunk3-0-50000
8
+ - tomekkorbak/detoxify-pile-chunk3-50000-100000
9
+ - tomekkorbak/detoxify-pile-chunk3-100000-150000
10
+ - tomekkorbak/detoxify-pile-chunk3-150000-200000
11
+ - tomekkorbak/detoxify-pile-chunk3-200000-250000
12
+ - tomekkorbak/detoxify-pile-chunk3-250000-300000
13
+ - tomekkorbak/detoxify-pile-chunk3-300000-350000
14
+ - tomekkorbak/detoxify-pile-chunk3-350000-400000
15
+ - tomekkorbak/detoxify-pile-chunk3-400000-450000
16
+ - tomekkorbak/detoxify-pile-chunk3-450000-500000
17
+ - tomekkorbak/detoxify-pile-chunk3-500000-550000
18
+ - tomekkorbak/detoxify-pile-chunk3-550000-600000
19
+ - tomekkorbak/detoxify-pile-chunk3-600000-650000
20
+ - tomekkorbak/detoxify-pile-chunk3-650000-700000
21
+ - tomekkorbak/detoxify-pile-chunk3-700000-750000
22
+ - tomekkorbak/detoxify-pile-chunk3-750000-800000
23
+ - tomekkorbak/detoxify-pile-chunk3-800000-850000
24
+ - tomekkorbak/detoxify-pile-chunk3-850000-900000
25
+ - tomekkorbak/detoxify-pile-chunk3-900000-950000
26
+ - tomekkorbak/detoxify-pile-chunk3-950000-1000000
27
+ - tomekkorbak/detoxify-pile-chunk3-1000000-1050000
28
+ - tomekkorbak/detoxify-pile-chunk3-1050000-1100000
29
+ - tomekkorbak/detoxify-pile-chunk3-1100000-1150000
30
+ - tomekkorbak/detoxify-pile-chunk3-1150000-1200000
31
+ - tomekkorbak/detoxify-pile-chunk3-1200000-1250000
32
+ - tomekkorbak/detoxify-pile-chunk3-1250000-1300000
33
+ - tomekkorbak/detoxify-pile-chunk3-1300000-1350000
34
+ - tomekkorbak/detoxify-pile-chunk3-1350000-1400000
35
+ - tomekkorbak/detoxify-pile-chunk3-1400000-1450000
36
+ - tomekkorbak/detoxify-pile-chunk3-1450000-1500000
37
+ - tomekkorbak/detoxify-pile-chunk3-1500000-1550000
38
+ - tomekkorbak/detoxify-pile-chunk3-1550000-1600000
39
+ - tomekkorbak/detoxify-pile-chunk3-1600000-1650000
40
+ - tomekkorbak/detoxify-pile-chunk3-1650000-1700000
41
+ - tomekkorbak/detoxify-pile-chunk3-1700000-1750000
42
+ - tomekkorbak/detoxify-pile-chunk3-1750000-1800000
43
+ - tomekkorbak/detoxify-pile-chunk3-1800000-1850000
44
+ - tomekkorbak/detoxify-pile-chunk3-1850000-1900000
45
+ - tomekkorbak/detoxify-pile-chunk3-1900000-1950000
46
+ model-index:
47
+ - name: tomekkorbak/test9485844
48
+ results: []
49
+ ---
50
+
51
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
52
+ should probably proofread and complete it, then remove this comment. -->
53
+
54
+ # tomekkorbak/test9485844
55
+
56
+ This model is a fine-tuned version of [n/a](https://huggingface.co/n/a) on the tomekkorbak/detoxify-pile-chunk3-0-50000, the tomekkorbak/detoxify-pile-chunk3-50000-100000, the tomekkorbak/detoxify-pile-chunk3-100000-150000, the tomekkorbak/detoxify-pile-chunk3-150000-200000, the tomekkorbak/detoxify-pile-chunk3-200000-250000, the tomekkorbak/detoxify-pile-chunk3-250000-300000, the tomekkorbak/detoxify-pile-chunk3-300000-350000, the tomekkorbak/detoxify-pile-chunk3-350000-400000, the tomekkorbak/detoxify-pile-chunk3-400000-450000, the tomekkorbak/detoxify-pile-chunk3-450000-500000, the tomekkorbak/detoxify-pile-chunk3-500000-550000, the tomekkorbak/detoxify-pile-chunk3-550000-600000, the tomekkorbak/detoxify-pile-chunk3-600000-650000, the tomekkorbak/detoxify-pile-chunk3-650000-700000, the tomekkorbak/detoxify-pile-chunk3-700000-750000, the tomekkorbak/detoxify-pile-chunk3-750000-800000, the tomekkorbak/detoxify-pile-chunk3-800000-850000, the tomekkorbak/detoxify-pile-chunk3-850000-900000, the tomekkorbak/detoxify-pile-chunk3-900000-950000, the tomekkorbak/detoxify-pile-chunk3-950000-1000000, the tomekkorbak/detoxify-pile-chunk3-1000000-1050000, the tomekkorbak/detoxify-pile-chunk3-1050000-1100000, the tomekkorbak/detoxify-pile-chunk3-1100000-1150000, the tomekkorbak/detoxify-pile-chunk3-1150000-1200000, the tomekkorbak/detoxify-pile-chunk3-1200000-1250000, the tomekkorbak/detoxify-pile-chunk3-1250000-1300000, the tomekkorbak/detoxify-pile-chunk3-1300000-1350000, the tomekkorbak/detoxify-pile-chunk3-1350000-1400000, the tomekkorbak/detoxify-pile-chunk3-1400000-1450000, the tomekkorbak/detoxify-pile-chunk3-1450000-1500000, the tomekkorbak/detoxify-pile-chunk3-1500000-1550000, the tomekkorbak/detoxify-pile-chunk3-1550000-1600000, the tomekkorbak/detoxify-pile-chunk3-1600000-1650000, the tomekkorbak/detoxify-pile-chunk3-1650000-1700000, the tomekkorbak/detoxify-pile-chunk3-1700000-1750000, the tomekkorbak/detoxify-pile-chunk3-1750000-1800000, the tomekkorbak/detoxify-pile-chunk3-1800000-1850000, the tomekkorbak/detoxify-pile-chunk3-1850000-1900000 and the tomekkorbak/detoxify-pile-chunk3-1900000-1950000 datasets.
57
+
58
+ ## Model description
59
+
60
+ More information needed
61
+
62
+ ## Intended uses & limitations
63
+
64
+ More information needed
65
+
66
+ ## Training and evaluation data
67
+
68
+ More information needed
69
+
70
+ ## Training procedure
71
+
72
+ ### Training hyperparameters
73
+
74
+ The following hyperparameters were used during training:
75
+ - learning_rate: 0.1
76
+ - train_batch_size: 8
77
+ - eval_batch_size: 8
78
+ - seed: 42
79
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
80
+ - lr_scheduler_type: linear
81
+ - lr_scheduler_warmup_ratio: 0.01
82
+ - training_steps: 16
83
+ - mixed_precision_training: Native AMP
84
+
85
+ ### Training results
86
+
87
+
88
+
89
+ ### Framework versions
90
+
91
+ - Transformers 4.20.1
92
+ - Pytorch 1.11.0+cu113
93
+ - Datasets 2.5.1
94
+ - Tokenizers 0.11.6
checkpoint-10/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMAndValueHeadModel"
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": true,
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": "4.20.1",
37
+ "use_cache": true,
38
+ "vocab_size": 50257
39
+ }
checkpoint-10/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-10/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38403eaa8ead14683ae6475fb74fc7950be309ce18490ff638591fd5ca8f8339
3
+ size 995603825
checkpoint-10/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58b2f04992e21b98618cd5b0222cdfb2ef811ec85ba9737067a5d2e4517a951b
3
+ size 510396521
checkpoint-10/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:958dc5243729e05b193ba0c0133224d9d4435dbf7997ddf9f5cd71c67d7800d7
3
+ size 14503
checkpoint-10/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77fc39983f76e5dacd4493c8d73a807cdf1d734f385370b41be32fe5a54a7055
3
+ size 559
checkpoint-10/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b93669654e5d8582bd3bb76fa861ab262af82216e3913228317dcebd51c5a28
3
+ size 623
checkpoint-10/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-10/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-10/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-10/trainer_state.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.625,
5
+ "global_step": 10,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.06,
12
+ "learning_rate": 0.1,
13
+ "loss": 10.9672,
14
+ "theoretical_loss": 35.35283692336181,
15
+ "tokens_seen": 8192
16
+ },
17
+ {
18
+ "epoch": 0.12,
19
+ "learning_rate": 0.09333333333333334,
20
+ "loss": 10.9619,
21
+ "theoretical_loss": 29.541230243953947,
22
+ "tokens_seen": 16384
23
+ },
24
+ {
25
+ "epoch": 0.19,
26
+ "learning_rate": 0.09333333333333334,
27
+ "loss": 15.0187,
28
+ "theoretical_loss": 26.629312696422083,
29
+ "tokens_seen": 24576
30
+ },
31
+ {
32
+ "epoch": 0.25,
33
+ "learning_rate": 0.08666666666666667,
34
+ "loss": 16.1625,
35
+ "theoretical_loss": 24.7548431869014,
36
+ "tokens_seen": 32768
37
+ },
38
+ {
39
+ "epoch": 0.31,
40
+ "learning_rate": 0.08000000000000002,
41
+ "loss": 21.1529,
42
+ "theoretical_loss": 23.401386600029422,
43
+ "tokens_seen": 40960
44
+ },
45
+ {
46
+ "epoch": 0.38,
47
+ "learning_rate": 0.07333333333333333,
48
+ "loss": 38.7194,
49
+ "theoretical_loss": 22.356614051730336,
50
+ "tokens_seen": 49152
51
+ },
52
+ {
53
+ "epoch": 0.44,
54
+ "learning_rate": 0.07333333333333333,
55
+ "loss": 32.4432,
56
+ "theoretical_loss": 21.513943523970973,
57
+ "tokens_seen": 57344
58
+ },
59
+ {
60
+ "epoch": 0.5,
61
+ "learning_rate": 0.06666666666666667,
62
+ "loss": 36.2714,
63
+ "theoretical_loss": 20.81281780154715,
64
+ "tokens_seen": 65536
65
+ },
66
+ {
67
+ "epoch": 0.56,
68
+ "learning_rate": 0.06,
69
+ "loss": 44.0589,
70
+ "theoretical_loss": 20.21576955809348,
71
+ "tokens_seen": 73728
72
+ },
73
+ {
74
+ "epoch": 0.62,
75
+ "learning_rate": 0.06,
76
+ "loss": 0.0,
77
+ "theoretical_loss": 19.69812311433776,
78
+ "tokens_seen": 81920
79
+ }
80
+ ],
81
+ "max_steps": 16,
82
+ "num_train_epochs": 9223372036854775807,
83
+ "total_flos": 41806725120000.0,
84
+ "trial_name": null,
85
+ "trial_params": null
86
+ }
checkpoint-10/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:932385677e44aa0ea6c146e0d4bf72c604e434157254e23c06eb2a22d7d11e48
3
+ size 3311
checkpoint-10/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-12/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMAndValueHeadModel"
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": true,
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": "4.20.1",
37
+ "use_cache": true,
38
+ "vocab_size": 50257
39
+ }
checkpoint-12/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-12/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38403eaa8ead14683ae6475fb74fc7950be309ce18490ff638591fd5ca8f8339
3
+ size 995603825
checkpoint-12/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58b2f04992e21b98618cd5b0222cdfb2ef811ec85ba9737067a5d2e4517a951b
3
+ size 510396521
checkpoint-12/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5966fcbb2539dde30a0997c61097c07bb9a2533b8d7a65b3e716ef41c4c1c28b
3
+ size 14503
checkpoint-12/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5b21f6aa3404ae2f5a5a0dd1e7905906aca69a65a6baaee8487149b646a27fe
3
+ size 559
checkpoint-12/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b93669654e5d8582bd3bb76fa861ab262af82216e3913228317dcebd51c5a28
3
+ size 623
checkpoint-12/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-12/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-12/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-12/trainer_state.json ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.75,
5
+ "global_step": 12,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.06,
12
+ "learning_rate": 0.1,
13
+ "loss": 10.9672,
14
+ "theoretical_loss": 35.35283692336181,
15
+ "tokens_seen": 8192
16
+ },
17
+ {
18
+ "epoch": 0.12,
19
+ "learning_rate": 0.09333333333333334,
20
+ "loss": 10.9619,
21
+ "theoretical_loss": 29.541230243953947,
22
+ "tokens_seen": 16384
23
+ },
24
+ {
25
+ "epoch": 0.19,
26
+ "learning_rate": 0.09333333333333334,
27
+ "loss": 15.0187,
28
+ "theoretical_loss": 26.629312696422083,
29
+ "tokens_seen": 24576
30
+ },
31
+ {
32
+ "epoch": 0.25,
33
+ "learning_rate": 0.08666666666666667,
34
+ "loss": 16.1625,
35
+ "theoretical_loss": 24.7548431869014,
36
+ "tokens_seen": 32768
37
+ },
38
+ {
39
+ "epoch": 0.31,
40
+ "learning_rate": 0.08000000000000002,
41
+ "loss": 21.1529,
42
+ "theoretical_loss": 23.401386600029422,
43
+ "tokens_seen": 40960
44
+ },
45
+ {
46
+ "epoch": 0.38,
47
+ "learning_rate": 0.07333333333333333,
48
+ "loss": 38.7194,
49
+ "theoretical_loss": 22.356614051730336,
50
+ "tokens_seen": 49152
51
+ },
52
+ {
53
+ "epoch": 0.44,
54
+ "learning_rate": 0.07333333333333333,
55
+ "loss": 32.4432,
56
+ "theoretical_loss": 21.513943523970973,
57
+ "tokens_seen": 57344
58
+ },
59
+ {
60
+ "epoch": 0.5,
61
+ "learning_rate": 0.06666666666666667,
62
+ "loss": 36.2714,
63
+ "theoretical_loss": 20.81281780154715,
64
+ "tokens_seen": 65536
65
+ },
66
+ {
67
+ "epoch": 0.56,
68
+ "learning_rate": 0.06,
69
+ "loss": 44.0589,
70
+ "theoretical_loss": 20.21576955809348,
71
+ "tokens_seen": 73728
72
+ },
73
+ {
74
+ "epoch": 0.62,
75
+ "learning_rate": 0.06,
76
+ "loss": 0.0,
77
+ "theoretical_loss": 19.69812311433776,
78
+ "tokens_seen": 81920
79
+ },
80
+ {
81
+ "epoch": 0.69,
82
+ "learning_rate": 0.06,
83
+ "loss": 0.0,
84
+ "theoretical_loss": 19.242830348017627,
85
+ "tokens_seen": 90112
86
+ },
87
+ {
88
+ "epoch": 0.75,
89
+ "learning_rate": 0.06,
90
+ "loss": 0.0,
91
+ "theoretical_loss": 18.83765782847088,
92
+ "tokens_seen": 98304
93
+ }
94
+ ],
95
+ "max_steps": 16,
96
+ "num_train_epochs": 9223372036854775807,
97
+ "total_flos": 50168070144000.0,
98
+ "trial_name": null,
99
+ "trial_params": null
100
+ }
checkpoint-12/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:932385677e44aa0ea6c146e0d4bf72c604e434157254e23c06eb2a22d7d11e48
3
+ size 3311
checkpoint-12/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-14/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMAndValueHeadModel"
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": true,
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": "4.20.1",
37
+ "use_cache": true,
38
+ "vocab_size": 50257
39
+ }
checkpoint-14/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-14/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38403eaa8ead14683ae6475fb74fc7950be309ce18490ff638591fd5ca8f8339
3
+ size 995603825
checkpoint-14/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58b2f04992e21b98618cd5b0222cdfb2ef811ec85ba9737067a5d2e4517a951b
3
+ size 510396521
checkpoint-14/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53c9d9f3b6b28d3960ce3bf3bfb1a4da0bc6b3aa70dafd309679909e18191dad
3
+ size 14503
checkpoint-14/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81203995f0822de6ed51d600e94d6f7d40cd4741b0f277d950b37bbc13d4b61e
3
+ size 559
checkpoint-14/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b93669654e5d8582bd3bb76fa861ab262af82216e3913228317dcebd51c5a28
3
+ size 623
checkpoint-14/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-14/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-14/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-14/trainer_state.json ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.875,
5
+ "global_step": 14,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.06,
12
+ "learning_rate": 0.1,
13
+ "loss": 10.9672,
14
+ "theoretical_loss": 35.35283692336181,
15
+ "tokens_seen": 8192
16
+ },
17
+ {
18
+ "epoch": 0.12,
19
+ "learning_rate": 0.09333333333333334,
20
+ "loss": 10.9619,
21
+ "theoretical_loss": 29.541230243953947,
22
+ "tokens_seen": 16384
23
+ },
24
+ {
25
+ "epoch": 0.19,
26
+ "learning_rate": 0.09333333333333334,
27
+ "loss": 15.0187,
28
+ "theoretical_loss": 26.629312696422083,
29
+ "tokens_seen": 24576
30
+ },
31
+ {
32
+ "epoch": 0.25,
33
+ "learning_rate": 0.08666666666666667,
34
+ "loss": 16.1625,
35
+ "theoretical_loss": 24.7548431869014,
36
+ "tokens_seen": 32768
37
+ },
38
+ {
39
+ "epoch": 0.31,
40
+ "learning_rate": 0.08000000000000002,
41
+ "loss": 21.1529,
42
+ "theoretical_loss": 23.401386600029422,
43
+ "tokens_seen": 40960
44
+ },
45
+ {
46
+ "epoch": 0.38,
47
+ "learning_rate": 0.07333333333333333,
48
+ "loss": 38.7194,
49
+ "theoretical_loss": 22.356614051730336,
50
+ "tokens_seen": 49152
51
+ },
52
+ {
53
+ "epoch": 0.44,
54
+ "learning_rate": 0.07333333333333333,
55
+ "loss": 32.4432,
56
+ "theoretical_loss": 21.513943523970973,
57
+ "tokens_seen": 57344
58
+ },
59
+ {
60
+ "epoch": 0.5,
61
+ "learning_rate": 0.06666666666666667,
62
+ "loss": 36.2714,
63
+ "theoretical_loss": 20.81281780154715,
64
+ "tokens_seen": 65536
65
+ },
66
+ {
67
+ "epoch": 0.56,
68
+ "learning_rate": 0.06,
69
+ "loss": 44.0589,
70
+ "theoretical_loss": 20.21576955809348,
71
+ "tokens_seen": 73728
72
+ },
73
+ {
74
+ "epoch": 0.62,
75
+ "learning_rate": 0.06,
76
+ "loss": 0.0,
77
+ "theoretical_loss": 19.69812311433776,
78
+ "tokens_seen": 81920
79
+ },
80
+ {
81
+ "epoch": 0.69,
82
+ "learning_rate": 0.06,
83
+ "loss": 0.0,
84
+ "theoretical_loss": 19.242830348017627,
85
+ "tokens_seen": 90112
86
+ },
87
+ {
88
+ "epoch": 0.75,
89
+ "learning_rate": 0.06,
90
+ "loss": 0.0,
91
+ "theoretical_loss": 18.83765782847088,
92
+ "tokens_seen": 98304
93
+ },
94
+ {
95
+ "epoch": 0.81,
96
+ "learning_rate": 0.06,
97
+ "loss": 0.0,
98
+ "theoretical_loss": 18.47355255671254,
99
+ "tokens_seen": 106496
100
+ },
101
+ {
102
+ "epoch": 0.88,
103
+ "learning_rate": 0.06,
104
+ "loss": 0.0,
105
+ "theoretical_loss": 18.143641951292143,
106
+ "tokens_seen": 114688
107
+ }
108
+ ],
109
+ "max_steps": 16,
110
+ "num_train_epochs": 9223372036854775807,
111
+ "total_flos": 58529415168000.0,
112
+ "trial_name": null,
113
+ "trial_params": null
114
+ }
checkpoint-14/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:932385677e44aa0ea6c146e0d4bf72c604e434157254e23c06eb2a22d7d11e48
3
+ size 3311
checkpoint-14/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-16/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMAndValueHeadModel"
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": true,
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": "4.20.1",
37
+ "use_cache": true,
38
+ "vocab_size": 50257
39
+ }
checkpoint-16/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-16/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38403eaa8ead14683ae6475fb74fc7950be309ce18490ff638591fd5ca8f8339
3
+ size 995603825
checkpoint-16/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58b2f04992e21b98618cd5b0222cdfb2ef811ec85ba9737067a5d2e4517a951b
3
+ size 510396521
checkpoint-16/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7653f13de7306118868c30c51ade095ae3c49a91dfca659c6881388ef33626ed
3
+ size 14503
checkpoint-16/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa13e2bd87a0ced3033a2eca0d8adb438aedf0aaa809e4e8ea0cb0e64687e1d6
3
+ size 559
checkpoint-16/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b93669654e5d8582bd3bb76fa861ab262af82216e3913228317dcebd51c5a28
3
+ size 623
checkpoint-16/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-16/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-16/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
+ }