QuantaSparkLabs commited on
Commit
1c16493
·
verified ·
1 Parent(s): 6460ebb

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. checkpoint-100/config.json +34 -0
  2. checkpoint-100/generation_config.json +10 -0
  3. checkpoint-100/model.safetensors +3 -0
  4. checkpoint-100/optimizer.pt +3 -0
  5. checkpoint-100/rng_state.pth +3 -0
  6. checkpoint-100/scheduler.pt +3 -0
  7. checkpoint-100/tokenizer.json +87 -0
  8. checkpoint-100/tokenizer_config.json +8 -0
  9. checkpoint-100/trainer_state.json +104 -0
  10. checkpoint-100/training_args.bin +3 -0
  11. checkpoint-150/config.json +34 -0
  12. checkpoint-150/generation_config.json +10 -0
  13. checkpoint-150/model.safetensors +3 -0
  14. checkpoint-150/optimizer.pt +3 -0
  15. checkpoint-150/rng_state.pth +3 -0
  16. checkpoint-150/scheduler.pt +3 -0
  17. checkpoint-150/tokenizer.json +87 -0
  18. checkpoint-150/tokenizer_config.json +8 -0
  19. checkpoint-150/trainer_state.json +139 -0
  20. checkpoint-150/training_args.bin +3 -0
  21. checkpoint-200/config.json +34 -0
  22. checkpoint-200/generation_config.json +10 -0
  23. checkpoint-200/model.safetensors +3 -0
  24. checkpoint-200/optimizer.pt +3 -0
  25. checkpoint-200/rng_state.pth +3 -0
  26. checkpoint-200/scheduler.pt +3 -0
  27. checkpoint-200/tokenizer.json +87 -0
  28. checkpoint-200/tokenizer_config.json +8 -0
  29. checkpoint-200/trainer_state.json +174 -0
  30. checkpoint-200/training_args.bin +3 -0
  31. checkpoint-250/config.json +34 -0
  32. checkpoint-250/generation_config.json +10 -0
  33. checkpoint-250/model.safetensors +3 -0
  34. checkpoint-250/optimizer.pt +3 -0
  35. checkpoint-250/rng_state.pth +3 -0
  36. checkpoint-250/scheduler.pt +3 -0
  37. checkpoint-250/tokenizer.json +87 -0
  38. checkpoint-250/tokenizer_config.json +8 -0
  39. checkpoint-250/trainer_state.json +209 -0
  40. checkpoint-250/training_args.bin +3 -0
  41. checkpoint-300/config.json +34 -0
  42. checkpoint-300/generation_config.json +10 -0
  43. checkpoint-300/model.safetensors +3 -0
  44. checkpoint-300/optimizer.pt +3 -0
  45. checkpoint-300/rng_state.pth +3 -0
  46. checkpoint-300/scheduler.pt +3 -0
  47. checkpoint-300/tokenizer.json +87 -0
  48. checkpoint-300/tokenizer_config.json +8 -0
  49. checkpoint-300/trainer_state.json +244 -0
  50. checkpoint-300/training_args.bin +3 -0
checkpoint-100/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu",
3
+ "add_cross_attention": false,
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.0,
8
+ "bos_token_id": 0,
9
+ "dtype": "float32",
10
+ "embd_pdrop": 0.0,
11
+ "eos_token_id": 0,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_embd": 1,
16
+ "n_head": 1,
17
+ "n_inner": 1,
18
+ "n_layer": 1,
19
+ "n_positions": 4,
20
+ "pad_token_id": 1,
21
+ "reorder_and_upcast_attn": false,
22
+ "resid_pdrop": 0.0,
23
+ "scale_attn_by_inverse_layer_idx": false,
24
+ "scale_attn_weights": true,
25
+ "summary_activation": null,
26
+ "summary_first_dropout": 0.1,
27
+ "summary_proj_to_labels": true,
28
+ "summary_type": "cls_index",
29
+ "summary_use_proj": true,
30
+ "tie_word_embeddings": true,
31
+ "transformers_version": "5.12.0",
32
+ "use_cache": false,
33
+ "vocab_size": 5
34
+ }
checkpoint-100/generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "pad_token_id": 1,
8
+ "transformers_version": "5.12.0",
9
+ "use_cache": true
10
+ }
checkpoint-100/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f927f8d4885457b7e4a078b38df051b0a0d42821a1eb2536418a7f10cbb3523e
3
+ size 1476
checkpoint-100/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53a1e772436ea3d9ca60697fd61cb7a423cb96b621a51eb795cfa5a73b56f206
3
+ size 13823
checkpoint-100/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:656c952bc98f1ba6483f4b602ab79d3a7eb64d231d7b2b6ae517f06e7e137155
3
+ size 14455
checkpoint-100/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:020d4bf8d4465c2a1ed676a5debf1d4d7d4c2928299260126c8103e7b8f781f1
3
+ size 1465
checkpoint-100/tokenizer.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 4,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
+ "padding": null,
10
+ "added_tokens": [
11
+ {
12
+ "id": 0,
13
+ "content": "<|endoftext|>",
14
+ "single_word": false,
15
+ "lstrip": false,
16
+ "rstrip": false,
17
+ "normalized": false,
18
+ "special": true
19
+ },
20
+ {
21
+ "id": 1,
22
+ "content": "<|pad|>",
23
+ "single_word": false,
24
+ "lstrip": false,
25
+ "rstrip": false,
26
+ "normalized": false,
27
+ "special": true
28
+ }
29
+ ],
30
+ "normalizer": null,
31
+ "pre_tokenizer": {
32
+ "type": "ByteLevel",
33
+ "add_prefix_space": true,
34
+ "trim_offsets": true,
35
+ "use_regex": true
36
+ },
37
+ "post_processor": {
38
+ "type": "TemplateProcessing",
39
+ "single": [
40
+ {
41
+ "Sequence": {
42
+ "id": "A",
43
+ "type_id": 0
44
+ }
45
+ }
46
+ ],
47
+ "pair": [
48
+ {
49
+ "Sequence": {
50
+ "id": "A",
51
+ "type_id": 0
52
+ }
53
+ },
54
+ {
55
+ "Sequence": {
56
+ "id": "B",
57
+ "type_id": 1
58
+ }
59
+ }
60
+ ],
61
+ "special_tokens": {}
62
+ },
63
+ "decoder": {
64
+ "type": "ByteLevel",
65
+ "add_prefix_space": true,
66
+ "trim_offsets": true,
67
+ "use_regex": true
68
+ },
69
+ "model": {
70
+ "type": "BPE",
71
+ "dropout": null,
72
+ "unk_token": null,
73
+ "continuing_subword_prefix": null,
74
+ "end_of_word_suffix": null,
75
+ "fuse_unk": false,
76
+ "byte_fallback": false,
77
+ "ignore_merges": false,
78
+ "vocab": {
79
+ "<|endoftext|>": 0,
80
+ "<|pad|>": 1,
81
+ "a": 2,
82
+ "b": 3,
83
+ "Ġ": 4
84
+ },
85
+ "merges": []
86
+ }
87
+ }
checkpoint-100/tokenizer_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<|endoftext|>",
4
+ "eos_token": "<|endoftext|>",
5
+ "model_max_length": 1000000000000000019884624838656,
6
+ "pad_token": "<|pad|>",
7
+ "tokenizer_class": "TokenizersBackend"
8
+ }
checkpoint-100/trainer_state.json ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 12.5,
6
+ "eval_steps": 500,
7
+ "global_step": 100,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.25,
14
+ "grad_norm": 0.05793992057442665,
15
+ "learning_rate": 0.009949685534591196,
16
+ "loss": 1.206215763092041,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 2.5,
21
+ "grad_norm": 0.15641599893569946,
22
+ "learning_rate": 0.009823899371069183,
23
+ "loss": 1.1944643020629884,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 3.75,
28
+ "grad_norm": 0.25837442278862,
29
+ "learning_rate": 0.00969811320754717,
30
+ "loss": 1.1607371330261231,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 5.0,
35
+ "grad_norm": 0.34708642959594727,
36
+ "learning_rate": 0.009572327044025157,
37
+ "loss": 1.101412010192871,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 6.25,
42
+ "grad_norm": 0.4044564962387085,
43
+ "learning_rate": 0.009446540880503144,
44
+ "loss": 1.0188076972961426,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 7.5,
49
+ "grad_norm": 0.4182046055793762,
50
+ "learning_rate": 0.009320754716981133,
51
+ "loss": 0.9222237586975097,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 8.75,
56
+ "grad_norm": 0.38868534564971924,
57
+ "learning_rate": 0.00919496855345912,
58
+ "loss": 0.8254497528076172,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 10.0,
63
+ "grad_norm": 0.3328922390937805,
64
+ "learning_rate": 0.009069182389937107,
65
+ "loss": 0.7411866188049316,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 11.25,
70
+ "grad_norm": 0.27316856384277344,
71
+ "learning_rate": 0.008943396226415094,
72
+ "loss": 0.6766499042510986,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 12.5,
77
+ "grad_norm": 0.21604125201702118,
78
+ "learning_rate": 0.008817610062893081,
79
+ "loss": 0.6312645435333252,
80
+ "step": 100
81
+ }
82
+ ],
83
+ "logging_steps": 10,
84
+ "max_steps": 800,
85
+ "num_input_tokens_seen": 0,
86
+ "num_train_epochs": 100,
87
+ "save_steps": 50,
88
+ "stateful_callbacks": {
89
+ "TrainerControl": {
90
+ "args": {
91
+ "should_epoch_stop": false,
92
+ "should_evaluate": false,
93
+ "should_log": false,
94
+ "should_save": true,
95
+ "should_training_stop": false
96
+ },
97
+ "attributes": {}
98
+ }
99
+ },
100
+ "total_flos": 5405184.0,
101
+ "train_batch_size": 128,
102
+ "trial_name": null,
103
+ "trial_params": null
104
+ }
checkpoint-100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ec7c4970e40c66e374eb444e43c769446c8d48e5a1f681b2a7f4187462d269e
3
+ size 5137
checkpoint-150/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu",
3
+ "add_cross_attention": false,
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.0,
8
+ "bos_token_id": 0,
9
+ "dtype": "float32",
10
+ "embd_pdrop": 0.0,
11
+ "eos_token_id": 0,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_embd": 1,
16
+ "n_head": 1,
17
+ "n_inner": 1,
18
+ "n_layer": 1,
19
+ "n_positions": 4,
20
+ "pad_token_id": 1,
21
+ "reorder_and_upcast_attn": false,
22
+ "resid_pdrop": 0.0,
23
+ "scale_attn_by_inverse_layer_idx": false,
24
+ "scale_attn_weights": true,
25
+ "summary_activation": null,
26
+ "summary_first_dropout": 0.1,
27
+ "summary_proj_to_labels": true,
28
+ "summary_type": "cls_index",
29
+ "summary_use_proj": true,
30
+ "tie_word_embeddings": true,
31
+ "transformers_version": "5.12.0",
32
+ "use_cache": false,
33
+ "vocab_size": 5
34
+ }
checkpoint-150/generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "pad_token_id": 1,
8
+ "transformers_version": "5.12.0",
9
+ "use_cache": true
10
+ }
checkpoint-150/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32eff4e377c9154406c6531317ef9fe6fc7c87cbd462ae8c22ce79bf4d0a2364
3
+ size 1476
checkpoint-150/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e369a422da25bd5901a3ae44e654f670635dd373d294a4901a53c0e8817ad956
3
+ size 13823
checkpoint-150/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9b5fdf389d8144a43074a17a83045fcaacf31701f4eb93ca74497b6fb1054c0
3
+ size 14455
checkpoint-150/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d473e01573c435c93b9926bad634d71a4f933f621580066f41ec91a5f0b8451e
3
+ size 1465
checkpoint-150/tokenizer.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 4,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
+ "padding": null,
10
+ "added_tokens": [
11
+ {
12
+ "id": 0,
13
+ "content": "<|endoftext|>",
14
+ "single_word": false,
15
+ "lstrip": false,
16
+ "rstrip": false,
17
+ "normalized": false,
18
+ "special": true
19
+ },
20
+ {
21
+ "id": 1,
22
+ "content": "<|pad|>",
23
+ "single_word": false,
24
+ "lstrip": false,
25
+ "rstrip": false,
26
+ "normalized": false,
27
+ "special": true
28
+ }
29
+ ],
30
+ "normalizer": null,
31
+ "pre_tokenizer": {
32
+ "type": "ByteLevel",
33
+ "add_prefix_space": true,
34
+ "trim_offsets": true,
35
+ "use_regex": true
36
+ },
37
+ "post_processor": {
38
+ "type": "TemplateProcessing",
39
+ "single": [
40
+ {
41
+ "Sequence": {
42
+ "id": "A",
43
+ "type_id": 0
44
+ }
45
+ }
46
+ ],
47
+ "pair": [
48
+ {
49
+ "Sequence": {
50
+ "id": "A",
51
+ "type_id": 0
52
+ }
53
+ },
54
+ {
55
+ "Sequence": {
56
+ "id": "B",
57
+ "type_id": 1
58
+ }
59
+ }
60
+ ],
61
+ "special_tokens": {}
62
+ },
63
+ "decoder": {
64
+ "type": "ByteLevel",
65
+ "add_prefix_space": true,
66
+ "trim_offsets": true,
67
+ "use_regex": true
68
+ },
69
+ "model": {
70
+ "type": "BPE",
71
+ "dropout": null,
72
+ "unk_token": null,
73
+ "continuing_subword_prefix": null,
74
+ "end_of_word_suffix": null,
75
+ "fuse_unk": false,
76
+ "byte_fallback": false,
77
+ "ignore_merges": false,
78
+ "vocab": {
79
+ "<|endoftext|>": 0,
80
+ "<|pad|>": 1,
81
+ "a": 2,
82
+ "b": 3,
83
+ "Ġ": 4
84
+ },
85
+ "merges": []
86
+ }
87
+ }
checkpoint-150/tokenizer_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<|endoftext|>",
4
+ "eos_token": "<|endoftext|>",
5
+ "model_max_length": 1000000000000000019884624838656,
6
+ "pad_token": "<|pad|>",
7
+ "tokenizer_class": "TokenizersBackend"
8
+ }
checkpoint-150/trainer_state.json ADDED
@@ -0,0 +1,139 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 18.75,
6
+ "eval_steps": 500,
7
+ "global_step": 150,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.25,
14
+ "grad_norm": 0.05793992057442665,
15
+ "learning_rate": 0.009949685534591196,
16
+ "loss": 1.206215763092041,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 2.5,
21
+ "grad_norm": 0.15641599893569946,
22
+ "learning_rate": 0.009823899371069183,
23
+ "loss": 1.1944643020629884,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 3.75,
28
+ "grad_norm": 0.25837442278862,
29
+ "learning_rate": 0.00969811320754717,
30
+ "loss": 1.1607371330261231,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 5.0,
35
+ "grad_norm": 0.34708642959594727,
36
+ "learning_rate": 0.009572327044025157,
37
+ "loss": 1.101412010192871,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 6.25,
42
+ "grad_norm": 0.4044564962387085,
43
+ "learning_rate": 0.009446540880503144,
44
+ "loss": 1.0188076972961426,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 7.5,
49
+ "grad_norm": 0.4182046055793762,
50
+ "learning_rate": 0.009320754716981133,
51
+ "loss": 0.9222237586975097,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 8.75,
56
+ "grad_norm": 0.38868534564971924,
57
+ "learning_rate": 0.00919496855345912,
58
+ "loss": 0.8254497528076172,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 10.0,
63
+ "grad_norm": 0.3328922390937805,
64
+ "learning_rate": 0.009069182389937107,
65
+ "loss": 0.7411866188049316,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 11.25,
70
+ "grad_norm": 0.27316856384277344,
71
+ "learning_rate": 0.008943396226415094,
72
+ "loss": 0.6766499042510986,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 12.5,
77
+ "grad_norm": 0.21604125201702118,
78
+ "learning_rate": 0.008817610062893081,
79
+ "loss": 0.6312645435333252,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 13.75,
84
+ "grad_norm": 0.17572654783725739,
85
+ "learning_rate": 0.00869182389937107,
86
+ "loss": 0.6011325359344483,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 15.0,
91
+ "grad_norm": 0.15216749906539917,
92
+ "learning_rate": 0.008566037735849057,
93
+ "loss": 0.5812094688415528,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 16.25,
98
+ "grad_norm": 0.12060005962848663,
99
+ "learning_rate": 0.008440251572327044,
100
+ "loss": 0.5678437232971192,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 17.5,
105
+ "grad_norm": 0.11622311919927597,
106
+ "learning_rate": 0.008314465408805032,
107
+ "loss": 0.5585259437561035,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 18.75,
112
+ "grad_norm": 0.08831977844238281,
113
+ "learning_rate": 0.008188679245283019,
114
+ "loss": 0.5519348621368408,
115
+ "step": 150
116
+ }
117
+ ],
118
+ "logging_steps": 10,
119
+ "max_steps": 800,
120
+ "num_input_tokens_seen": 0,
121
+ "num_train_epochs": 100,
122
+ "save_steps": 50,
123
+ "stateful_callbacks": {
124
+ "TrainerControl": {
125
+ "args": {
126
+ "should_epoch_stop": false,
127
+ "should_evaluate": false,
128
+ "should_log": false,
129
+ "should_save": true,
130
+ "should_training_stop": false
131
+ },
132
+ "attributes": {}
133
+ }
134
+ },
135
+ "total_flos": 8107776.0,
136
+ "train_batch_size": 128,
137
+ "trial_name": null,
138
+ "trial_params": null
139
+ }
checkpoint-150/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ec7c4970e40c66e374eb444e43c769446c8d48e5a1f681b2a7f4187462d269e
3
+ size 5137
checkpoint-200/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu",
3
+ "add_cross_attention": false,
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.0,
8
+ "bos_token_id": 0,
9
+ "dtype": "float32",
10
+ "embd_pdrop": 0.0,
11
+ "eos_token_id": 0,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_embd": 1,
16
+ "n_head": 1,
17
+ "n_inner": 1,
18
+ "n_layer": 1,
19
+ "n_positions": 4,
20
+ "pad_token_id": 1,
21
+ "reorder_and_upcast_attn": false,
22
+ "resid_pdrop": 0.0,
23
+ "scale_attn_by_inverse_layer_idx": false,
24
+ "scale_attn_weights": true,
25
+ "summary_activation": null,
26
+ "summary_first_dropout": 0.1,
27
+ "summary_proj_to_labels": true,
28
+ "summary_type": "cls_index",
29
+ "summary_use_proj": true,
30
+ "tie_word_embeddings": true,
31
+ "transformers_version": "5.12.0",
32
+ "use_cache": false,
33
+ "vocab_size": 5
34
+ }
checkpoint-200/generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "pad_token_id": 1,
8
+ "transformers_version": "5.12.0",
9
+ "use_cache": true
10
+ }
checkpoint-200/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f025fd5de3bb085eb395da425fca96a02fe2f4506b53e3ae913dead14cc3349
3
+ size 1476
checkpoint-200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:904a89c566860fdd80b54b080f3c5db858451714b993b090b1e954f0536574c7
3
+ size 13823
checkpoint-200/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:578e8799d025fe13990ba869b383010b37f57725e649414cca523ec437e2196e
3
+ size 14455
checkpoint-200/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0461a487c93a1d5d456c21f2f0d6053e6cc43aa65ed6f9187fa4e810cd6b0a8a
3
+ size 1465
checkpoint-200/tokenizer.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 4,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
+ "padding": null,
10
+ "added_tokens": [
11
+ {
12
+ "id": 0,
13
+ "content": "<|endoftext|>",
14
+ "single_word": false,
15
+ "lstrip": false,
16
+ "rstrip": false,
17
+ "normalized": false,
18
+ "special": true
19
+ },
20
+ {
21
+ "id": 1,
22
+ "content": "<|pad|>",
23
+ "single_word": false,
24
+ "lstrip": false,
25
+ "rstrip": false,
26
+ "normalized": false,
27
+ "special": true
28
+ }
29
+ ],
30
+ "normalizer": null,
31
+ "pre_tokenizer": {
32
+ "type": "ByteLevel",
33
+ "add_prefix_space": true,
34
+ "trim_offsets": true,
35
+ "use_regex": true
36
+ },
37
+ "post_processor": {
38
+ "type": "TemplateProcessing",
39
+ "single": [
40
+ {
41
+ "Sequence": {
42
+ "id": "A",
43
+ "type_id": 0
44
+ }
45
+ }
46
+ ],
47
+ "pair": [
48
+ {
49
+ "Sequence": {
50
+ "id": "A",
51
+ "type_id": 0
52
+ }
53
+ },
54
+ {
55
+ "Sequence": {
56
+ "id": "B",
57
+ "type_id": 1
58
+ }
59
+ }
60
+ ],
61
+ "special_tokens": {}
62
+ },
63
+ "decoder": {
64
+ "type": "ByteLevel",
65
+ "add_prefix_space": true,
66
+ "trim_offsets": true,
67
+ "use_regex": true
68
+ },
69
+ "model": {
70
+ "type": "BPE",
71
+ "dropout": null,
72
+ "unk_token": null,
73
+ "continuing_subword_prefix": null,
74
+ "end_of_word_suffix": null,
75
+ "fuse_unk": false,
76
+ "byte_fallback": false,
77
+ "ignore_merges": false,
78
+ "vocab": {
79
+ "<|endoftext|>": 0,
80
+ "<|pad|>": 1,
81
+ "a": 2,
82
+ "b": 3,
83
+ "Ġ": 4
84
+ },
85
+ "merges": []
86
+ }
87
+ }
checkpoint-200/tokenizer_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<|endoftext|>",
4
+ "eos_token": "<|endoftext|>",
5
+ "model_max_length": 1000000000000000019884624838656,
6
+ "pad_token": "<|pad|>",
7
+ "tokenizer_class": "TokenizersBackend"
8
+ }
checkpoint-200/trainer_state.json ADDED
@@ -0,0 +1,174 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 25.0,
6
+ "eval_steps": 500,
7
+ "global_step": 200,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.25,
14
+ "grad_norm": 0.05793992057442665,
15
+ "learning_rate": 0.009949685534591196,
16
+ "loss": 1.206215763092041,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 2.5,
21
+ "grad_norm": 0.15641599893569946,
22
+ "learning_rate": 0.009823899371069183,
23
+ "loss": 1.1944643020629884,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 3.75,
28
+ "grad_norm": 0.25837442278862,
29
+ "learning_rate": 0.00969811320754717,
30
+ "loss": 1.1607371330261231,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 5.0,
35
+ "grad_norm": 0.34708642959594727,
36
+ "learning_rate": 0.009572327044025157,
37
+ "loss": 1.101412010192871,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 6.25,
42
+ "grad_norm": 0.4044564962387085,
43
+ "learning_rate": 0.009446540880503144,
44
+ "loss": 1.0188076972961426,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 7.5,
49
+ "grad_norm": 0.4182046055793762,
50
+ "learning_rate": 0.009320754716981133,
51
+ "loss": 0.9222237586975097,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 8.75,
56
+ "grad_norm": 0.38868534564971924,
57
+ "learning_rate": 0.00919496855345912,
58
+ "loss": 0.8254497528076172,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 10.0,
63
+ "grad_norm": 0.3328922390937805,
64
+ "learning_rate": 0.009069182389937107,
65
+ "loss": 0.7411866188049316,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 11.25,
70
+ "grad_norm": 0.27316856384277344,
71
+ "learning_rate": 0.008943396226415094,
72
+ "loss": 0.6766499042510986,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 12.5,
77
+ "grad_norm": 0.21604125201702118,
78
+ "learning_rate": 0.008817610062893081,
79
+ "loss": 0.6312645435333252,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 13.75,
84
+ "grad_norm": 0.17572654783725739,
85
+ "learning_rate": 0.00869182389937107,
86
+ "loss": 0.6011325359344483,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 15.0,
91
+ "grad_norm": 0.15216749906539917,
92
+ "learning_rate": 0.008566037735849057,
93
+ "loss": 0.5812094688415528,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 16.25,
98
+ "grad_norm": 0.12060005962848663,
99
+ "learning_rate": 0.008440251572327044,
100
+ "loss": 0.5678437232971192,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 17.5,
105
+ "grad_norm": 0.11622311919927597,
106
+ "learning_rate": 0.008314465408805032,
107
+ "loss": 0.5585259437561035,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 18.75,
112
+ "grad_norm": 0.08831977844238281,
113
+ "learning_rate": 0.008188679245283019,
114
+ "loss": 0.5519348621368408,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 20.0,
119
+ "grad_norm": 0.09614107757806778,
120
+ "learning_rate": 0.008062893081761007,
121
+ "loss": 0.5471037864685059,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 21.25,
126
+ "grad_norm": 0.07089235633611679,
127
+ "learning_rate": 0.007937106918238995,
128
+ "loss": 0.5432851314544678,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 22.5,
133
+ "grad_norm": 0.061037734150886536,
134
+ "learning_rate": 0.007811320754716982,
135
+ "loss": 0.5403900146484375,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 23.75,
140
+ "grad_norm": 0.09448318183422089,
141
+ "learning_rate": 0.00768553459119497,
142
+ "loss": 0.53807373046875,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 25.0,
147
+ "grad_norm": 0.050825681537389755,
148
+ "learning_rate": 0.007559748427672957,
149
+ "loss": 0.5360239028930665,
150
+ "step": 200
151
+ }
152
+ ],
153
+ "logging_steps": 10,
154
+ "max_steps": 800,
155
+ "num_input_tokens_seen": 0,
156
+ "num_train_epochs": 100,
157
+ "save_steps": 50,
158
+ "stateful_callbacks": {
159
+ "TrainerControl": {
160
+ "args": {
161
+ "should_epoch_stop": false,
162
+ "should_evaluate": false,
163
+ "should_log": false,
164
+ "should_save": true,
165
+ "should_training_stop": false
166
+ },
167
+ "attributes": {}
168
+ }
169
+ },
170
+ "total_flos": 10800000.0,
171
+ "train_batch_size": 128,
172
+ "trial_name": null,
173
+ "trial_params": null
174
+ }
checkpoint-200/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ec7c4970e40c66e374eb444e43c769446c8d48e5a1f681b2a7f4187462d269e
3
+ size 5137
checkpoint-250/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu",
3
+ "add_cross_attention": false,
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.0,
8
+ "bos_token_id": 0,
9
+ "dtype": "float32",
10
+ "embd_pdrop": 0.0,
11
+ "eos_token_id": 0,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_embd": 1,
16
+ "n_head": 1,
17
+ "n_inner": 1,
18
+ "n_layer": 1,
19
+ "n_positions": 4,
20
+ "pad_token_id": 1,
21
+ "reorder_and_upcast_attn": false,
22
+ "resid_pdrop": 0.0,
23
+ "scale_attn_by_inverse_layer_idx": false,
24
+ "scale_attn_weights": true,
25
+ "summary_activation": null,
26
+ "summary_first_dropout": 0.1,
27
+ "summary_proj_to_labels": true,
28
+ "summary_type": "cls_index",
29
+ "summary_use_proj": true,
30
+ "tie_word_embeddings": true,
31
+ "transformers_version": "5.12.0",
32
+ "use_cache": false,
33
+ "vocab_size": 5
34
+ }
checkpoint-250/generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "pad_token_id": 1,
8
+ "transformers_version": "5.12.0",
9
+ "use_cache": true
10
+ }
checkpoint-250/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a50b4f9c0e64d6662e265d416f7098696bb647c785cb9d96ce1ed0bc52c106f
3
+ size 1476
checkpoint-250/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0509ebbf56f1ff5def338103f070cd55005f3b196cc7f15f64ce938a3f3c8a9
3
+ size 13823
checkpoint-250/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d93cf2a6f5b82bd08f8b51ea11b7d93fb36e5dee432e6b631b5bd5365d1aa213
3
+ size 14455
checkpoint-250/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bea7ab5973051bc08e6b64d8b657fe2c7761fc2e91b84dbe5ebf70251f1d9c7
3
+ size 1465
checkpoint-250/tokenizer.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 4,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
+ "padding": null,
10
+ "added_tokens": [
11
+ {
12
+ "id": 0,
13
+ "content": "<|endoftext|>",
14
+ "single_word": false,
15
+ "lstrip": false,
16
+ "rstrip": false,
17
+ "normalized": false,
18
+ "special": true
19
+ },
20
+ {
21
+ "id": 1,
22
+ "content": "<|pad|>",
23
+ "single_word": false,
24
+ "lstrip": false,
25
+ "rstrip": false,
26
+ "normalized": false,
27
+ "special": true
28
+ }
29
+ ],
30
+ "normalizer": null,
31
+ "pre_tokenizer": {
32
+ "type": "ByteLevel",
33
+ "add_prefix_space": true,
34
+ "trim_offsets": true,
35
+ "use_regex": true
36
+ },
37
+ "post_processor": {
38
+ "type": "TemplateProcessing",
39
+ "single": [
40
+ {
41
+ "Sequence": {
42
+ "id": "A",
43
+ "type_id": 0
44
+ }
45
+ }
46
+ ],
47
+ "pair": [
48
+ {
49
+ "Sequence": {
50
+ "id": "A",
51
+ "type_id": 0
52
+ }
53
+ },
54
+ {
55
+ "Sequence": {
56
+ "id": "B",
57
+ "type_id": 1
58
+ }
59
+ }
60
+ ],
61
+ "special_tokens": {}
62
+ },
63
+ "decoder": {
64
+ "type": "ByteLevel",
65
+ "add_prefix_space": true,
66
+ "trim_offsets": true,
67
+ "use_regex": true
68
+ },
69
+ "model": {
70
+ "type": "BPE",
71
+ "dropout": null,
72
+ "unk_token": null,
73
+ "continuing_subword_prefix": null,
74
+ "end_of_word_suffix": null,
75
+ "fuse_unk": false,
76
+ "byte_fallback": false,
77
+ "ignore_merges": false,
78
+ "vocab": {
79
+ "<|endoftext|>": 0,
80
+ "<|pad|>": 1,
81
+ "a": 2,
82
+ "b": 3,
83
+ "Ġ": 4
84
+ },
85
+ "merges": []
86
+ }
87
+ }
checkpoint-250/tokenizer_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<|endoftext|>",
4
+ "eos_token": "<|endoftext|>",
5
+ "model_max_length": 1000000000000000019884624838656,
6
+ "pad_token": "<|pad|>",
7
+ "tokenizer_class": "TokenizersBackend"
8
+ }
checkpoint-250/trainer_state.json ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 31.25,
6
+ "eval_steps": 500,
7
+ "global_step": 250,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.25,
14
+ "grad_norm": 0.05793992057442665,
15
+ "learning_rate": 0.009949685534591196,
16
+ "loss": 1.206215763092041,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 2.5,
21
+ "grad_norm": 0.15641599893569946,
22
+ "learning_rate": 0.009823899371069183,
23
+ "loss": 1.1944643020629884,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 3.75,
28
+ "grad_norm": 0.25837442278862,
29
+ "learning_rate": 0.00969811320754717,
30
+ "loss": 1.1607371330261231,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 5.0,
35
+ "grad_norm": 0.34708642959594727,
36
+ "learning_rate": 0.009572327044025157,
37
+ "loss": 1.101412010192871,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 6.25,
42
+ "grad_norm": 0.4044564962387085,
43
+ "learning_rate": 0.009446540880503144,
44
+ "loss": 1.0188076972961426,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 7.5,
49
+ "grad_norm": 0.4182046055793762,
50
+ "learning_rate": 0.009320754716981133,
51
+ "loss": 0.9222237586975097,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 8.75,
56
+ "grad_norm": 0.38868534564971924,
57
+ "learning_rate": 0.00919496855345912,
58
+ "loss": 0.8254497528076172,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 10.0,
63
+ "grad_norm": 0.3328922390937805,
64
+ "learning_rate": 0.009069182389937107,
65
+ "loss": 0.7411866188049316,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 11.25,
70
+ "grad_norm": 0.27316856384277344,
71
+ "learning_rate": 0.008943396226415094,
72
+ "loss": 0.6766499042510986,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 12.5,
77
+ "grad_norm": 0.21604125201702118,
78
+ "learning_rate": 0.008817610062893081,
79
+ "loss": 0.6312645435333252,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 13.75,
84
+ "grad_norm": 0.17572654783725739,
85
+ "learning_rate": 0.00869182389937107,
86
+ "loss": 0.6011325359344483,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 15.0,
91
+ "grad_norm": 0.15216749906539917,
92
+ "learning_rate": 0.008566037735849057,
93
+ "loss": 0.5812094688415528,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 16.25,
98
+ "grad_norm": 0.12060005962848663,
99
+ "learning_rate": 0.008440251572327044,
100
+ "loss": 0.5678437232971192,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 17.5,
105
+ "grad_norm": 0.11622311919927597,
106
+ "learning_rate": 0.008314465408805032,
107
+ "loss": 0.5585259437561035,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 18.75,
112
+ "grad_norm": 0.08831977844238281,
113
+ "learning_rate": 0.008188679245283019,
114
+ "loss": 0.5519348621368408,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 20.0,
119
+ "grad_norm": 0.09614107757806778,
120
+ "learning_rate": 0.008062893081761007,
121
+ "loss": 0.5471037864685059,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 21.25,
126
+ "grad_norm": 0.07089235633611679,
127
+ "learning_rate": 0.007937106918238995,
128
+ "loss": 0.5432851314544678,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 22.5,
133
+ "grad_norm": 0.061037734150886536,
134
+ "learning_rate": 0.007811320754716982,
135
+ "loss": 0.5403900146484375,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 23.75,
140
+ "grad_norm": 0.09448318183422089,
141
+ "learning_rate": 0.00768553459119497,
142
+ "loss": 0.53807373046875,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 25.0,
147
+ "grad_norm": 0.050825681537389755,
148
+ "learning_rate": 0.007559748427672957,
149
+ "loss": 0.5360239028930665,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 26.25,
154
+ "grad_norm": 0.11754798144102097,
155
+ "learning_rate": 0.007433962264150943,
156
+ "loss": 0.5343667507171631,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 27.5,
161
+ "grad_norm": 0.04136759415268898,
162
+ "learning_rate": 0.00730817610062893,
163
+ "loss": 0.5332566738128662,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 28.75,
168
+ "grad_norm": 0.061312805861234665,
169
+ "learning_rate": 0.007182389937106918,
170
+ "loss": 0.5320106983184815,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 30.0,
175
+ "grad_norm": 0.045437928289175034,
176
+ "learning_rate": 0.007056603773584905,
177
+ "loss": 0.5310849666595459,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 31.25,
182
+ "grad_norm": 0.041931431740522385,
183
+ "learning_rate": 0.006930817610062893,
184
+ "loss": 0.5302073001861572,
185
+ "step": 250
186
+ }
187
+ ],
188
+ "logging_steps": 10,
189
+ "max_steps": 800,
190
+ "num_input_tokens_seen": 0,
191
+ "num_train_epochs": 100,
192
+ "save_steps": 50,
193
+ "stateful_callbacks": {
194
+ "TrainerControl": {
195
+ "args": {
196
+ "should_epoch_stop": false,
197
+ "should_evaluate": false,
198
+ "should_log": false,
199
+ "should_save": true,
200
+ "should_training_stop": false
201
+ },
202
+ "attributes": {}
203
+ }
204
+ },
205
+ "total_flos": 13502592.0,
206
+ "train_batch_size": 128,
207
+ "trial_name": null,
208
+ "trial_params": null
209
+ }
checkpoint-250/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ec7c4970e40c66e374eb444e43c769446c8d48e5a1f681b2a7f4187462d269e
3
+ size 5137
checkpoint-300/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu",
3
+ "add_cross_attention": false,
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.0,
8
+ "bos_token_id": 0,
9
+ "dtype": "float32",
10
+ "embd_pdrop": 0.0,
11
+ "eos_token_id": 0,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_embd": 1,
16
+ "n_head": 1,
17
+ "n_inner": 1,
18
+ "n_layer": 1,
19
+ "n_positions": 4,
20
+ "pad_token_id": 1,
21
+ "reorder_and_upcast_attn": false,
22
+ "resid_pdrop": 0.0,
23
+ "scale_attn_by_inverse_layer_idx": false,
24
+ "scale_attn_weights": true,
25
+ "summary_activation": null,
26
+ "summary_first_dropout": 0.1,
27
+ "summary_proj_to_labels": true,
28
+ "summary_type": "cls_index",
29
+ "summary_use_proj": true,
30
+ "tie_word_embeddings": true,
31
+ "transformers_version": "5.12.0",
32
+ "use_cache": false,
33
+ "vocab_size": 5
34
+ }
checkpoint-300/generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "pad_token_id": 1,
8
+ "transformers_version": "5.12.0",
9
+ "use_cache": true
10
+ }
checkpoint-300/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97fffa1ffb0d8cfea3175841cdaadc065dbc524a156ab6794cc4defcdb443466
3
+ size 1476
checkpoint-300/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22f1cbf4f54dc99d5f9cf6f96190e76a53018986e798912dfadb864ea9b83abc
3
+ size 13823
checkpoint-300/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e3dc2ffd417ca43335dc7e4f9ae2b0c82cd1201b3451b1285b0c2b5c355f483
3
+ size 14455
checkpoint-300/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f95bed23f8bb86a3a3ad2aac60be9c505895c2819ebd5aedc95d6f297f479db
3
+ size 1465
checkpoint-300/tokenizer.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 4,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
+ "padding": null,
10
+ "added_tokens": [
11
+ {
12
+ "id": 0,
13
+ "content": "<|endoftext|>",
14
+ "single_word": false,
15
+ "lstrip": false,
16
+ "rstrip": false,
17
+ "normalized": false,
18
+ "special": true
19
+ },
20
+ {
21
+ "id": 1,
22
+ "content": "<|pad|>",
23
+ "single_word": false,
24
+ "lstrip": false,
25
+ "rstrip": false,
26
+ "normalized": false,
27
+ "special": true
28
+ }
29
+ ],
30
+ "normalizer": null,
31
+ "pre_tokenizer": {
32
+ "type": "ByteLevel",
33
+ "add_prefix_space": true,
34
+ "trim_offsets": true,
35
+ "use_regex": true
36
+ },
37
+ "post_processor": {
38
+ "type": "TemplateProcessing",
39
+ "single": [
40
+ {
41
+ "Sequence": {
42
+ "id": "A",
43
+ "type_id": 0
44
+ }
45
+ }
46
+ ],
47
+ "pair": [
48
+ {
49
+ "Sequence": {
50
+ "id": "A",
51
+ "type_id": 0
52
+ }
53
+ },
54
+ {
55
+ "Sequence": {
56
+ "id": "B",
57
+ "type_id": 1
58
+ }
59
+ }
60
+ ],
61
+ "special_tokens": {}
62
+ },
63
+ "decoder": {
64
+ "type": "ByteLevel",
65
+ "add_prefix_space": true,
66
+ "trim_offsets": true,
67
+ "use_regex": true
68
+ },
69
+ "model": {
70
+ "type": "BPE",
71
+ "dropout": null,
72
+ "unk_token": null,
73
+ "continuing_subword_prefix": null,
74
+ "end_of_word_suffix": null,
75
+ "fuse_unk": false,
76
+ "byte_fallback": false,
77
+ "ignore_merges": false,
78
+ "vocab": {
79
+ "<|endoftext|>": 0,
80
+ "<|pad|>": 1,
81
+ "a": 2,
82
+ "b": 3,
83
+ "Ġ": 4
84
+ },
85
+ "merges": []
86
+ }
87
+ }
checkpoint-300/tokenizer_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<|endoftext|>",
4
+ "eos_token": "<|endoftext|>",
5
+ "model_max_length": 1000000000000000019884624838656,
6
+ "pad_token": "<|pad|>",
7
+ "tokenizer_class": "TokenizersBackend"
8
+ }
checkpoint-300/trainer_state.json ADDED
@@ -0,0 +1,244 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 37.5,
6
+ "eval_steps": 500,
7
+ "global_step": 300,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.25,
14
+ "grad_norm": 0.05793992057442665,
15
+ "learning_rate": 0.009949685534591196,
16
+ "loss": 1.206215763092041,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 2.5,
21
+ "grad_norm": 0.15641599893569946,
22
+ "learning_rate": 0.009823899371069183,
23
+ "loss": 1.1944643020629884,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 3.75,
28
+ "grad_norm": 0.25837442278862,
29
+ "learning_rate": 0.00969811320754717,
30
+ "loss": 1.1607371330261231,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 5.0,
35
+ "grad_norm": 0.34708642959594727,
36
+ "learning_rate": 0.009572327044025157,
37
+ "loss": 1.101412010192871,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 6.25,
42
+ "grad_norm": 0.4044564962387085,
43
+ "learning_rate": 0.009446540880503144,
44
+ "loss": 1.0188076972961426,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 7.5,
49
+ "grad_norm": 0.4182046055793762,
50
+ "learning_rate": 0.009320754716981133,
51
+ "loss": 0.9222237586975097,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 8.75,
56
+ "grad_norm": 0.38868534564971924,
57
+ "learning_rate": 0.00919496855345912,
58
+ "loss": 0.8254497528076172,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 10.0,
63
+ "grad_norm": 0.3328922390937805,
64
+ "learning_rate": 0.009069182389937107,
65
+ "loss": 0.7411866188049316,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 11.25,
70
+ "grad_norm": 0.27316856384277344,
71
+ "learning_rate": 0.008943396226415094,
72
+ "loss": 0.6766499042510986,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 12.5,
77
+ "grad_norm": 0.21604125201702118,
78
+ "learning_rate": 0.008817610062893081,
79
+ "loss": 0.6312645435333252,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 13.75,
84
+ "grad_norm": 0.17572654783725739,
85
+ "learning_rate": 0.00869182389937107,
86
+ "loss": 0.6011325359344483,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 15.0,
91
+ "grad_norm": 0.15216749906539917,
92
+ "learning_rate": 0.008566037735849057,
93
+ "loss": 0.5812094688415528,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 16.25,
98
+ "grad_norm": 0.12060005962848663,
99
+ "learning_rate": 0.008440251572327044,
100
+ "loss": 0.5678437232971192,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 17.5,
105
+ "grad_norm": 0.11622311919927597,
106
+ "learning_rate": 0.008314465408805032,
107
+ "loss": 0.5585259437561035,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 18.75,
112
+ "grad_norm": 0.08831977844238281,
113
+ "learning_rate": 0.008188679245283019,
114
+ "loss": 0.5519348621368408,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 20.0,
119
+ "grad_norm": 0.09614107757806778,
120
+ "learning_rate": 0.008062893081761007,
121
+ "loss": 0.5471037864685059,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 21.25,
126
+ "grad_norm": 0.07089235633611679,
127
+ "learning_rate": 0.007937106918238995,
128
+ "loss": 0.5432851314544678,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 22.5,
133
+ "grad_norm": 0.061037734150886536,
134
+ "learning_rate": 0.007811320754716982,
135
+ "loss": 0.5403900146484375,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 23.75,
140
+ "grad_norm": 0.09448318183422089,
141
+ "learning_rate": 0.00768553459119497,
142
+ "loss": 0.53807373046875,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 25.0,
147
+ "grad_norm": 0.050825681537389755,
148
+ "learning_rate": 0.007559748427672957,
149
+ "loss": 0.5360239028930665,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 26.25,
154
+ "grad_norm": 0.11754798144102097,
155
+ "learning_rate": 0.007433962264150943,
156
+ "loss": 0.5343667507171631,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 27.5,
161
+ "grad_norm": 0.04136759415268898,
162
+ "learning_rate": 0.00730817610062893,
163
+ "loss": 0.5332566738128662,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 28.75,
168
+ "grad_norm": 0.061312805861234665,
169
+ "learning_rate": 0.007182389937106918,
170
+ "loss": 0.5320106983184815,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 30.0,
175
+ "grad_norm": 0.045437928289175034,
176
+ "learning_rate": 0.007056603773584905,
177
+ "loss": 0.5310849666595459,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 31.25,
182
+ "grad_norm": 0.041931431740522385,
183
+ "learning_rate": 0.006930817610062893,
184
+ "loss": 0.5302073001861572,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 32.5,
189
+ "grad_norm": 0.07813303917646408,
190
+ "learning_rate": 0.00680503144654088,
191
+ "loss": 0.5294707775115967,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 33.75,
196
+ "grad_norm": 0.03454748913645744,
197
+ "learning_rate": 0.006679245283018867,
198
+ "loss": 0.5287383079528809,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 35.0,
203
+ "grad_norm": 0.03431857377290726,
204
+ "learning_rate": 0.006553459119496855,
205
+ "loss": 0.5282272815704345,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 36.25,
210
+ "grad_norm": 0.08966688811779022,
211
+ "learning_rate": 0.006427672955974842,
212
+ "loss": 0.5277254581451416,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 37.5,
217
+ "grad_norm": 0.052265942096710205,
218
+ "learning_rate": 0.00630188679245283,
219
+ "loss": 0.5272915840148926,
220
+ "step": 300
221
+ }
222
+ ],
223
+ "logging_steps": 10,
224
+ "max_steps": 800,
225
+ "num_input_tokens_seen": 0,
226
+ "num_train_epochs": 100,
227
+ "save_steps": 50,
228
+ "stateful_callbacks": {
229
+ "TrainerControl": {
230
+ "args": {
231
+ "should_epoch_stop": false,
232
+ "should_evaluate": false,
233
+ "should_log": false,
234
+ "should_save": true,
235
+ "should_training_stop": false
236
+ },
237
+ "attributes": {}
238
+ }
239
+ },
240
+ "total_flos": 16205184.0,
241
+ "train_batch_size": 128,
242
+ "trial_name": null,
243
+ "trial_params": null
244
+ }
checkpoint-300/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ec7c4970e40c66e374eb444e43c769446c8d48e5a1f681b2a7f4187462d269e
3
+ size 5137