Hugging Face's logo

Goldenwert
/
standard_finetuned

Safetensors
gpt2
Model card Files
xet
 Community
Goldenwert commited on
Commit
8a9c24f
·
verified ·
1 Parent(s): 154d992

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-11109/config.json +38 -0
  2. checkpoint-11109/generation_config.json +6 -0
  3. checkpoint-11109/merges.txt +0 -0
  4. checkpoint-11109/model.safetensors +3 -0
  5. checkpoint-11109/optimizer.pt +3 -0
  6. checkpoint-11109/rng_state.pth +3 -0
  7. checkpoint-11109/scaler.pt +3 -0
  8. checkpoint-11109/scheduler.pt +3 -0
  9. checkpoint-11109/special_tokens_map.json +6 -0
  10. checkpoint-11109/tokenizer.json +0 -0
  11. checkpoint-11109/tokenizer_config.json +21 -0
  12. checkpoint-11109/trainer_state.json +188 -0
  13. checkpoint-11109/training_args.bin +3 -0
  14. checkpoint-11109/vocab.json +0 -0
  15. checkpoint-14/config.json +38 -0
  16. checkpoint-14/generation_config.json +6 -0
  17. checkpoint-14/merges.txt +0 -0
  18. checkpoint-14/model.safetensors +3 -0
  19. checkpoint-14/optimizer.pt +3 -0
  20. checkpoint-14/rng_state.pth +3 -0
  21. checkpoint-14/scaler.pt +3 -0
  22. checkpoint-14/scheduler.pt +3 -0
  23. checkpoint-14/special_tokens_map.json +6 -0
  24. checkpoint-14/tokenizer.json +0 -0
  25. checkpoint-14/tokenizer_config.json +21 -0
  26. checkpoint-14/trainer_state.json +33 -0
  27. checkpoint-14/training_args.bin +3 -0
  28. checkpoint-14/vocab.json +0 -0
  29. checkpoint-28/config.json +38 -0
  30. checkpoint-28/generation_config.json +6 -0
  31. checkpoint-28/merges.txt +0 -0
  32. checkpoint-28/model.safetensors +3 -0
  33. checkpoint-28/optimizer.pt +3 -0
  34. checkpoint-28/rng_state.pth +3 -0
  35. checkpoint-28/scaler.pt +3 -0
  36. checkpoint-28/scheduler.pt +3 -0
  37. checkpoint-28/special_tokens_map.json +6 -0
  38. checkpoint-28/tokenizer.json +0 -0
  39. checkpoint-28/tokenizer_config.json +21 -0
  40. checkpoint-28/trainer_state.json +33 -0
  41. checkpoint-28/training_args.bin +3 -0
  42. checkpoint-28/vocab.json +0 -0
  43. config.json +38 -0
  44. generation_config.json +6 -0
  45. merges.txt +0 -0
  46. model.safetensors +3 -0
  47. special_tokens_map.json +6 -0
  48. tokenizer.json +0 -0
  49. tokenizer_config.json +21 -0
  50. training_args.bin +3 -0
checkpoint-11109/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 50256,
8
+ "embd_pdrop": 0.1,
9
+ "eos_token_id": 50256,
10
+ "initializer_range": 0.02,
11
+ "layer_norm_epsilon": 1e-05,
12
+ "model_type": "gpt2",
13
+ "n_ctx": 1024,
14
+ "n_embd": 768,
15
+ "n_head": 12,
16
+ "n_inner": null,
17
+ "n_layer": 12,
18
+ "n_positions": 1024,
19
+ "reorder_and_upcast_attn": false,
20
+ "resid_pdrop": 0.1,
21
+ "scale_attn_by_inverse_layer_idx": false,
22
+ "scale_attn_weights": true,
23
+ "summary_activation": null,
24
+ "summary_first_dropout": 0.1,
25
+ "summary_proj_to_labels": true,
26
+ "summary_type": "cls_index",
27
+ "summary_use_proj": true,
28
+ "task_specific_params": {
29
+ "text-generation": {
30
+ "do_sample": true,
31
+ "max_length": 50
32
+ }
33
+ },
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.51.3",
36
+ "use_cache": false,
37
+ "vocab_size": 50257
38
+ }
checkpoint-11109/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": "4.51.3"
6
+ }
checkpoint-11109/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-11109/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dddf12ad1b428d138f76c49ba251b8358ba840fd02623c64660faac91b48210
3
+ size 497774208
checkpoint-11109/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efc6b200e896a22e12867c38d8beea6cf512ee214f74a5e3cc4cc2bce237877f
3
+ size 995642298
checkpoint-11109/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13535aa9cfd450c18d235ed73731e52ad11ebc4a7ac8e6d26c8ee34d5f8c3365
3
+ size 14244
checkpoint-11109/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fac5bc2a45d16b05671ba7c361af7f254a67d8b2a0996dacb10fc7b8aa2a4d85
3
+ size 988
checkpoint-11109/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a72f8a059a98a2458ab7808a5e5c20dd052e142fee055cde9e846b287f9903f7
3
+ size 1064
checkpoint-11109/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-11109/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-11109/tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": false,
15
+ "eos_token": "<|endoftext|>",
16
+ "extra_special_tokens": {},
17
+ "model_max_length": 1024,
18
+ "pad_token": "<|endoftext|>",
19
+ "tokenizer_class": "GPT2Tokenizer",
20
+ "unk_token": "<|endoftext|>"
21
+ }
checkpoint-11109/trainer_state.json ADDED
@@ -0,0 +1,188 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.9999662447257384,
6
+ "eval_steps": 500,
7
+ "global_step": 11109,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0450070323488045,
14
+ "grad_norm": 1.3325860500335693,
15
+ "learning_rate": 4.7772076694571974e-05,
16
+ "loss": 0.7668,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.090014064697609,
21
+ "grad_norm": 0.9469890594482422,
22
+ "learning_rate": 4.552164911333153e-05,
23
+ "loss": 0.5694,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.1350210970464135,
28
+ "grad_norm": 1.3886737823486328,
29
+ "learning_rate": 4.32712215320911e-05,
30
+ "loss": 0.521,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 0.180028129395218,
35
+ "grad_norm": 1.1051844358444214,
36
+ "learning_rate": 4.102079395085066e-05,
37
+ "loss": 0.4929,
38
+ "step": 2000
39
+ },
40
+ {
41
+ "epoch": 0.2250351617440225,
42
+ "grad_norm": 0.9152352809906006,
43
+ "learning_rate": 3.877036636961023e-05,
44
+ "loss": 0.4786,
45
+ "step": 2500
46
+ },
47
+ {
48
+ "epoch": 0.270042194092827,
49
+ "grad_norm": 0.867607057094574,
50
+ "learning_rate": 3.651993878836979e-05,
51
+ "loss": 0.4592,
52
+ "step": 3000
53
+ },
54
+ {
55
+ "epoch": 0.3150492264416315,
56
+ "grad_norm": 1.071778655052185,
57
+ "learning_rate": 3.4269511207129355e-05,
58
+ "loss": 0.4421,
59
+ "step": 3500
60
+ },
61
+ {
62
+ "epoch": 0.360056258790436,
63
+ "grad_norm": 0.9107626080513,
64
+ "learning_rate": 3.201908362588892e-05,
65
+ "loss": 0.4326,
66
+ "step": 4000
67
+ },
68
+ {
69
+ "epoch": 0.4050632911392405,
70
+ "grad_norm": 0.8906437158584595,
71
+ "learning_rate": 2.9768656044648484e-05,
72
+ "loss": 0.4232,
73
+ "step": 4500
74
+ },
75
+ {
76
+ "epoch": 0.450070323488045,
77
+ "grad_norm": 0.797953188419342,
78
+ "learning_rate": 2.7518228463408046e-05,
79
+ "loss": 0.4186,
80
+ "step": 5000
81
+ },
82
+ {
83
+ "epoch": 0.49507735583684953,
84
+ "grad_norm": 0.7932363152503967,
85
+ "learning_rate": 2.5267800882167615e-05,
86
+ "loss": 0.4079,
87
+ "step": 5500
88
+ },
89
+ {
90
+ "epoch": 0.540084388185654,
91
+ "grad_norm": 0.9231603145599365,
92
+ "learning_rate": 2.3017373300927178e-05,
93
+ "loss": 0.4028,
94
+ "step": 6000
95
+ },
96
+ {
97
+ "epoch": 0.5850914205344585,
98
+ "grad_norm": 0.7973820567131042,
99
+ "learning_rate": 2.0766945719686744e-05,
100
+ "loss": 0.3968,
101
+ "step": 6500
102
+ },
103
+ {
104
+ "epoch": 0.630098452883263,
105
+ "grad_norm": 0.7791222333908081,
106
+ "learning_rate": 1.8516518138446306e-05,
107
+ "loss": 0.3943,
108
+ "step": 7000
109
+ },
110
+ {
111
+ "epoch": 0.6751054852320675,
112
+ "grad_norm": 0.9621289372444153,
113
+ "learning_rate": 1.6266090557205872e-05,
114
+ "loss": 0.3903,
115
+ "step": 7500
116
+ },
117
+ {
118
+ "epoch": 0.720112517580872,
119
+ "grad_norm": 0.8593667149543762,
120
+ "learning_rate": 1.4015662975965436e-05,
121
+ "loss": 0.3868,
122
+ "step": 8000
123
+ },
124
+ {
125
+ "epoch": 0.7651195499296765,
126
+ "grad_norm": 0.8511173129081726,
127
+ "learning_rate": 1.1765235394724998e-05,
128
+ "loss": 0.3839,
129
+ "step": 8500
130
+ },
131
+ {
132
+ "epoch": 0.810126582278481,
133
+ "grad_norm": 0.7761066555976868,
134
+ "learning_rate": 9.514807813484562e-06,
135
+ "loss": 0.3774,
136
+ "step": 9000
137
+ },
138
+ {
139
+ "epoch": 0.8551336146272855,
140
+ "grad_norm": 0.8108276128768921,
141
+ "learning_rate": 7.2643802322441265e-06,
142
+ "loss": 0.3764,
143
+ "step": 9500
144
+ },
145
+ {
146
+ "epoch": 0.90014064697609,
147
+ "grad_norm": 0.6598201394081116,
148
+ "learning_rate": 5.013952651003691e-06,
149
+ "loss": 0.3782,
150
+ "step": 10000
151
+ },
152
+ {
153
+ "epoch": 0.9451476793248945,
154
+ "grad_norm": 0.8302701115608215,
155
+ "learning_rate": 2.763525069763255e-06,
156
+ "loss": 0.3776,
157
+ "step": 10500
158
+ },
159
+ {
160
+ "epoch": 0.9901547116736991,
161
+ "grad_norm": 0.9311410188674927,
162
+ "learning_rate": 5.130974885228194e-07,
163
+ "loss": 0.3735,
164
+ "step": 11000
165
+ }
166
+ ],
167
+ "logging_steps": 500,
168
+ "max_steps": 11109,
169
+ "num_input_tokens_seen": 0,
170
+ "num_train_epochs": 1,
171
+ "save_steps": 99999999,
172
+ "stateful_callbacks": {
173
+ "TrainerControl": {
174
+ "args": {
175
+ "should_epoch_stop": false,
176
+ "should_evaluate": false,
177
+ "should_log": false,
178
+ "should_save": true,
179
+ "should_training_stop": true
180
+ },
181
+ "attributes": {}
182
+ }
183
+ },
184
+ "total_flos": 6.3992727396864e+16,
185
+ "train_batch_size": 4,
186
+ "trial_name": null,
187
+ "trial_params": null
188
+ }
checkpoint-11109/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4265973de208e50f04c50f599a3f9ee41c8055a5695ae420c0872f394713398d
3
+ size 5240
checkpoint-11109/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-14/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 50256,
8
+ "embd_pdrop": 0.1,
9
+ "eos_token_id": 50256,
10
+ "initializer_range": 0.02,
11
+ "layer_norm_epsilon": 1e-05,
12
+ "model_type": "gpt2",
13
+ "n_ctx": 1024,
14
+ "n_embd": 768,
15
+ "n_head": 12,
16
+ "n_inner": null,
17
+ "n_layer": 12,
18
+ "n_positions": 1024,
19
+ "reorder_and_upcast_attn": false,
20
+ "resid_pdrop": 0.1,
21
+ "scale_attn_by_inverse_layer_idx": false,
22
+ "scale_attn_weights": true,
23
+ "summary_activation": null,
24
+ "summary_first_dropout": 0.1,
25
+ "summary_proj_to_labels": true,
26
+ "summary_type": "cls_index",
27
+ "summary_use_proj": true,
28
+ "task_specific_params": {
29
+ "text-generation": {
30
+ "do_sample": true,
31
+ "max_length": 50
32
+ }
33
+ },
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.51.3",
36
+ "use_cache": false,
37
+ "vocab_size": 50257
38
+ }
checkpoint-14/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": "4.51.3"
6
+ }
checkpoint-14/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-14/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:904cac28f1293d87e8580057968ba585f6314cf981007c61f1937b90ca9f24ad
3
+ size 497774208
checkpoint-14/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2beec720ec59924447f64475db5c7886e20b416554b96accc494b745c582bb88
3
+ size 995642298
checkpoint-14/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f6b6284868ed8d876b0202a101138015a99f4e514c5d063ce8b1fca59f571bc
3
+ size 14244
checkpoint-14/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0234a3d35731eb1ae49aac0e971882b31092f782878a3f2ed048eb4d95e00af
3
+ size 988
checkpoint-14/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92ad68b81ded7d32c578dcb45279ba57a0e7eef9c4d93d83331574cf4a3f6624
3
+ size 1064
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 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": false,
15
+ "eos_token": "<|endoftext|>",
16
+ "extra_special_tokens": {},
17
+ "model_max_length": 1024,
18
+ "pad_token": "<|endoftext|>",
19
+ "tokenizer_class": "GPT2Tokenizer",
20
+ "unk_token": "<|endoftext|>"
21
+ }
checkpoint-14/trainer_state.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.9911504424778761,
6
+ "eval_steps": 500,
7
+ "global_step": 14,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [],
12
+ "logging_steps": 500,
13
+ "max_steps": 14,
14
+ "num_input_tokens_seen": 0,
15
+ "num_train_epochs": 1,
16
+ "save_steps": 99999999,
17
+ "stateful_callbacks": {
18
+ "TrainerControl": {
19
+ "args": {
20
+ "should_epoch_stop": false,
21
+ "should_evaluate": false,
22
+ "should_log": false,
23
+ "should_save": true,
24
+ "should_training_stop": true
25
+ },
26
+ "attributes": {}
27
+ }
28
+ },
29
+ "total_flos": 77791537152000.0,
30
+ "train_batch_size": 4,
31
+ "trial_name": null,
32
+ "trial_params": null
33
+ }
checkpoint-14/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4265973de208e50f04c50f599a3f9ee41c8055a5695ae420c0872f394713398d
3
+ size 5240
checkpoint-14/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-28/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 50256,
8
+ "embd_pdrop": 0.1,
9
+ "eos_token_id": 50256,
10
+ "initializer_range": 0.02,
11
+ "layer_norm_epsilon": 1e-05,
12
+ "model_type": "gpt2",
13
+ "n_ctx": 1024,
14
+ "n_embd": 768,
15
+ "n_head": 12,
16
+ "n_inner": null,
17
+ "n_layer": 12,
18
+ "n_positions": 1024,
19
+ "reorder_and_upcast_attn": false,
20
+ "resid_pdrop": 0.1,
21
+ "scale_attn_by_inverse_layer_idx": false,
22
+ "scale_attn_weights": true,
23
+ "summary_activation": null,
24
+ "summary_first_dropout": 0.1,
25
+ "summary_proj_to_labels": true,
26
+ "summary_type": "cls_index",
27
+ "summary_use_proj": true,
28
+ "task_specific_params": {
29
+ "text-generation": {
30
+ "do_sample": true,
31
+ "max_length": 50
32
+ }
33
+ },
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.51.3",
36
+ "use_cache": false,
37
+ "vocab_size": 50257
38
+ }
checkpoint-28/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": "4.51.3"
6
+ }
checkpoint-28/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-28/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b0f565351863833a5b5882780aa001ca6ad0909ec4a4f557028d3e4573534f7
3
+ size 497774208
checkpoint-28/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d27381875ddf5f604d48875378b8a0274054a08922a8a4bb0e52d7911d73c650
3
+ size 995642298
checkpoint-28/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:837b599a64bcf534f5f4b8cd0b5b1c0e4c2c113f590ff448f3f6d5754105444a
3
+ size 14244
checkpoint-28/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e64d4964c75ce482848fa147f2f3354862944b6c5f174bd308fd6e8b1bdf29ca
3
+ size 988
checkpoint-28/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0593b4614b1f655a55017d6b58aaf4218b0f7da42f6687a1906dd41ac0a5127a
3
+ size 1064
checkpoint-28/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-28/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-28/tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": false,
15
+ "eos_token": "<|endoftext|>",
16
+ "extra_special_tokens": {},
17
+ "model_max_length": 1024,
18
+ "pad_token": "<|endoftext|>",
19
+ "tokenizer_class": "GPT2Tokenizer",
20
+ "unk_token": "<|endoftext|>"
21
+ }
checkpoint-28/trainer_state.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.9955555555555555,
6
+ "eval_steps": 500,
7
+ "global_step": 28,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [],
12
+ "logging_steps": 500,
13
+ "max_steps": 28,
14
+ "num_input_tokens_seen": 0,
15
+ "num_train_epochs": 1,
16
+ "save_steps": 99999999,
17
+ "stateful_callbacks": {
18
+ "TrainerControl": {
19
+ "args": {
20
+ "should_epoch_stop": false,
21
+ "should_evaluate": false,
22
+ "should_log": false,
23
+ "should_save": true,
24
+ "should_training_stop": true
25
+ },
26
+ "attributes": {}
27
+ }
28
+ },
29
+ "total_flos": 160204677120000.0,
30
+ "train_batch_size": 4,
31
+ "trial_name": null,
32
+ "trial_params": null
33
+ }
checkpoint-28/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4265973de208e50f04c50f599a3f9ee41c8055a5695ae420c0872f394713398d
3
+ size 5240
checkpoint-28/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 50256,
8
+ "embd_pdrop": 0.1,
9
+ "eos_token_id": 50256,
10
+ "initializer_range": 0.02,
11
+ "layer_norm_epsilon": 1e-05,
12
+ "model_type": "gpt2",
13
+ "n_ctx": 1024,
14
+ "n_embd": 768,
15
+ "n_head": 12,
16
+ "n_inner": null,
17
+ "n_layer": 12,
18
+ "n_positions": 1024,
19
+ "reorder_and_upcast_attn": false,
20
+ "resid_pdrop": 0.1,
21
+ "scale_attn_by_inverse_layer_idx": false,
22
+ "scale_attn_weights": true,
23
+ "summary_activation": null,
24
+ "summary_first_dropout": 0.1,
25
+ "summary_proj_to_labels": true,
26
+ "summary_type": "cls_index",
27
+ "summary_use_proj": true,
28
+ "task_specific_params": {
29
+ "text-generation": {
30
+ "do_sample": true,
31
+ "max_length": 50
32
+ }
33
+ },
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.51.3",
36
+ "use_cache": false,
37
+ "vocab_size": 50257
38
+ }
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": "4.51.3"
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 sha256:4dddf12ad1b428d138f76c49ba251b8358ba840fd02623c64660faac91b48210
3
+ size 497774208
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
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": false,
15
+ "eos_token": "<|endoftext|>",
16
+ "extra_special_tokens": {},
17
+ "model_max_length": 1024,
18
+ "pad_token": "<|endoftext|>",
19
+ "tokenizer_class": "GPT2Tokenizer",
20
+ "unk_token": "<|endoftext|>"
21
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4265973de208e50f04c50f599a3f9ee41c8055a5695ae420c0872f394713398d
3
+ size 5240