Hugging Face's logo

hidude562
/
Maestro-ctx-L4

Text Generation
Transformers
Safetensors
gpt2
text-generation-inference
Model card Files
xet
 Community
hidude562 commited on
Commit
e90303c
·
verified ·
1 Parent(s): fe26728

Upload 13 files

Browse files
Files changed (13) hide show
  1. added_tokens.json +4 -0
  2. config.json +34 -0
  3. generation_config.json +6 -0
  4. merges.txt +0 -0
  5. model.safetensors +3 -0
  6. optimizer.pt +3 -0
  7. rng_state.pth +3 -0
  8. scheduler.pt +3 -0
  9. special_tokens_map.json +30 -0
  10. tokenizer_config.json +40 -0
  11. trainer_state.json +213 -0
  12. training_args.bin +3 -0
  13. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|pad|>": 50258,
3
+ "<|startoftext|>": 50257
4
+ }
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "hidude562/Maestro-ctx-L3",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "fp16": true,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_ctx": 2048,
16
+ "n_embd": 1024,
17
+ "n_head": 16,
18
+ "n_inner": null,
19
+ "n_layer": 24,
20
+ "n_positions": 2048,
21
+ "reorder_and_upcast_attn": false,
22
+ "resid_pdrop": 0.1,
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
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.37.2",
32
+ "use_cache": true,
33
+ "vocab_size": 50257
34
+ }
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": "4.37.2"
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 sha256:3d4eb03fff0aa38613249bf6c98285bb8a5b77aba4bd8fac86e1166cb771e5ac
3
+ size 1423517184
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae1d58120ca0b8a949b90b771cb281f63c8d7456c8113602bb16d1300d5f0051
3
+ size 2847217850
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bde29e885f292993abacc81155345fe7358fda7e3f49c3254e4d2674ff47de1
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3226fe8407c562563c6e459528f20d7c50837da3b54b31b69b5768113c8b715
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|pad|>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<|startoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": true,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "<|endoftext|>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "errors": "replace",
22
+ "model_max_length": 1024,
23
+ "pad_token": {
24
+ "__type": "AddedToken",
25
+ "content": "<|pad|>",
26
+ "lstrip": false,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ "tokenizer_class": "GPT2Tokenizer",
32
+ "unk_token": {
33
+ "__type": "AddedToken",
34
+ "content": "<|endoftext|>",
35
+ "lstrip": false,
36
+ "normalized": true,
37
+ "rstrip": false,
38
+ "single_word": false
39
+ }
40
+ }
trainer_state.json ADDED
@@ -0,0 +1,213 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.5339028296849974,
5
+ "eval_steps": 500,
6
+ "global_step": 16000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.02,
13
+ "learning_rate": 4.991657768286172e-05,
14
+ "loss": 0.4651,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.03,
19
+ "learning_rate": 4.9833155365723435e-05,
20
+ "loss": 0.4517,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.05,
25
+ "learning_rate": 4.974973304858516e-05,
26
+ "loss": 0.4612,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.07,
31
+ "learning_rate": 4.966631073144688e-05,
32
+ "loss": 0.4565,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 0.08,
37
+ "learning_rate": 4.95828884143086e-05,
38
+ "loss": 0.4501,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 0.1,
43
+ "learning_rate": 4.9499466097170315e-05,
44
+ "loss": 0.4544,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 0.12,
49
+ "learning_rate": 4.941604378003203e-05,
50
+ "loss": 0.4539,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 0.13,
55
+ "learning_rate": 4.9332621462893755e-05,
56
+ "loss": 0.4452,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 0.15,
61
+ "learning_rate": 4.924919914575548e-05,
62
+ "loss": 0.4505,
63
+ "step": 4500
64
+ },
65
+ {
66
+ "epoch": 0.17,
67
+ "learning_rate": 4.9165776828617194e-05,
68
+ "loss": 0.4445,
69
+ "step": 5000
70
+ },
71
+ {
72
+ "epoch": 0.18,
73
+ "learning_rate": 4.908235451147891e-05,
74
+ "loss": 0.4391,
75
+ "step": 5500
76
+ },
77
+ {
78
+ "epoch": 0.2,
79
+ "learning_rate": 4.899893219434063e-05,
80
+ "loss": 0.4455,
81
+ "step": 6000
82
+ },
83
+ {
84
+ "epoch": 0.22,
85
+ "learning_rate": 4.891550987720235e-05,
86
+ "loss": 0.4411,
87
+ "step": 6500
88
+ },
89
+ {
90
+ "epoch": 0.23,
91
+ "learning_rate": 4.8832087560064074e-05,
92
+ "loss": 0.4445,
93
+ "step": 7000
94
+ },
95
+ {
96
+ "epoch": 0.25,
97
+ "learning_rate": 4.874866524292579e-05,
98
+ "loss": 0.443,
99
+ "step": 7500
100
+ },
101
+ {
102
+ "epoch": 0.27,
103
+ "learning_rate": 4.866524292578751e-05,
104
+ "loss": 0.4398,
105
+ "step": 8000
106
+ },
107
+ {
108
+ "epoch": 0.28,
109
+ "learning_rate": 4.85819874532835e-05,
110
+ "loss": 0.4403,
111
+ "step": 8500
112
+ },
113
+ {
114
+ "epoch": 0.3,
115
+ "learning_rate": 4.8498565136145226e-05,
116
+ "loss": 0.4402,
117
+ "step": 9000
118
+ },
119
+ {
120
+ "epoch": 0.32,
121
+ "learning_rate": 4.841514281900694e-05,
122
+ "loss": 0.4417,
123
+ "step": 9500
124
+ },
125
+ {
126
+ "epoch": 0.33,
127
+ "learning_rate": 4.833172050186866e-05,
128
+ "loss": 0.4409,
129
+ "step": 10000
130
+ },
131
+ {
132
+ "epoch": 0.35,
133
+ "learning_rate": 4.824846502936466e-05,
134
+ "loss": 0.4321,
135
+ "step": 10500
136
+ },
137
+ {
138
+ "epoch": 0.37,
139
+ "learning_rate": 4.816504271222638e-05,
140
+ "loss": 0.4276,
141
+ "step": 11000
142
+ },
143
+ {
144
+ "epoch": 0.38,
145
+ "learning_rate": 4.8081620395088095e-05,
146
+ "loss": 0.436,
147
+ "step": 11500
148
+ },
149
+ {
150
+ "epoch": 0.4,
151
+ "learning_rate": 4.799819807794981e-05,
152
+ "loss": 0.4358,
153
+ "step": 12000
154
+ },
155
+ {
156
+ "epoch": 0.42,
157
+ "learning_rate": 4.7914942605445814e-05,
158
+ "loss": 0.4307,
159
+ "step": 12500
160
+ },
161
+ {
162
+ "epoch": 0.43,
163
+ "learning_rate": 4.78316871329418e-05,
164
+ "loss": 0.4363,
165
+ "step": 13000
166
+ },
167
+ {
168
+ "epoch": 0.45,
169
+ "learning_rate": 4.774826481580353e-05,
170
+ "loss": 0.4304,
171
+ "step": 13500
172
+ },
173
+ {
174
+ "epoch": 0.47,
175
+ "learning_rate": 4.766484249866524e-05,
176
+ "loss": 0.4374,
177
+ "step": 14000
178
+ },
179
+ {
180
+ "epoch": 0.48,
181
+ "learning_rate": 4.7581420181526966e-05,
182
+ "loss": 0.4323,
183
+ "step": 14500
184
+ },
185
+ {
186
+ "epoch": 0.5,
187
+ "learning_rate": 4.749799786438868e-05,
188
+ "loss": 0.4312,
189
+ "step": 15000
190
+ },
191
+ {
192
+ "epoch": 0.52,
193
+ "learning_rate": 4.741474239188468e-05,
194
+ "loss": 0.4304,
195
+ "step": 15500
196
+ },
197
+ {
198
+ "epoch": 0.53,
199
+ "learning_rate": 4.73313200747464e-05,
200
+ "loss": 0.4306,
201
+ "step": 16000
202
+ }
203
+ ],
204
+ "logging_steps": 500,
205
+ "max_steps": 299680,
206
+ "num_input_tokens_seen": 0,
207
+ "num_train_epochs": 10,
208
+ "save_steps": 2000,
209
+ "total_flos": 1.188736858931069e+18,
210
+ "train_batch_size": 1,
211
+ "trial_name": null,
212
+ "trial_params": null
213
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00b460369d41677c5ab013495fbce4d51b226af2b799f03d1c5f508726704484
3
+ size 4664
vocab.json ADDED
The diff for this file is too large to render. See raw diff