Hugging Face's logo

benjamin
/
gpt2-wechsel-scottish-gaelic

Text Generation
Transformers
PyTorch
Scottish Gaelic
gpt2
text-generation-inference
Model card Files
xet
 Community
1
benjamin commited on
Commit
d921e55
·
1 Parent(s): 21bc847

initial commit

Browse files
Files changed (19) hide show
  1. README.md +0 -3
  2. config.json +39 -0
  3. merges.txt +0 -0
  4. pytorch_model.bin +3 -0
  5. rng_state_0.pth +3 -0
  6. rng_state_1.pth +3 -0
  7. rng_state_2.pth +3 -0
  8. rng_state_3.pth +3 -0
  9. rng_state_4.pth +3 -0
  10. rng_state_5.pth +3 -0
  11. rng_state_6.pth +3 -0
  12. rng_state_7.pth +3 -0
  13. scheduler.pt +3 -0
  14. special_tokens_map.json +1 -0
  15. tokenizer.json +0 -0
  16. tokenizer_config.json +1 -0
  17. trainer_state.json +231 -0
  18. training_args.bin +3 -0
  19. vocab.json +0 -0
README.md DELETED
@@ -1,3 +0,0 @@
1
- ---
2
- license: mit
3
- ---
 
 
 
 
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50
33
+ }
34
+ },
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.12.0.dev0",
37
+ "use_cache": true,
38
+ "vocab_size": 50257
39
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66d310057768d0ac50214b73b737fc0f144184d1d0adb08825f20d3a1c895695
3
+ size 664786896
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6db289377e87260b30e7a038b7ae3e602a7f5fd45fd3e6c2b7c0bfe35f3220de
3
+ size 13620
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff15b5397276a138766be3217fb6efaccb671efbe88942445b2fcca321abd128
3
+ size 13620
rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07f4fbeac75ec88e13b7cdbc52282877fa93ac47d5f26eb6504cf9b516769f84
3
+ size 13619
rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22e1c70f695da1d3cd347898de856fce19707342223894f7bae09f5c929617f4
3
+ size 13620
rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3abd01ff7ff151c14f20cb9180a78540885a25fb03593be24a90ddcb4061120a
3
+ size 13619
rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4e6131cb63e757005207995e5bfb564455c11f58f716c3b6c6ca288e04c81d0
3
+ size 13619
rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9fe52bf4bbe529fa001f23c42895d2c598fd6d790df0946600885f3b69c7148
3
+ size 13619
rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4807565cd559725b4f860bc4212d572062fc5682e33e943326c65334a2d9c484
3
+ size 13619
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:509c1140754d05ee312a2f9333409890a5796243ad77e602e60b8a29f868e86d
3
+ size 623
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "models/gpt2_scottish_gaelic", "tokenizer_class": "GPT2Tokenizer"}
trainer_state.json ADDED
@@ -0,0 +1,231 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 130.20671834625324,
5
+ "global_step": 12500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 5.21,
12
+ "learning_rate": 1e-05,
13
+ "learning_rate_embeddings": 1e-05,
14
+ "loss": 8.4554,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 10.41,
19
+ "learning_rate": 2e-05,
20
+ "learning_rate_embeddings": 2e-05,
21
+ "loss": 5.9825,
22
+ "step": 1000
23
+ },
24
+ {
25
+ "epoch": 15.62,
26
+ "learning_rate": 3e-05,
27
+ "learning_rate_embeddings": 3e-05,
28
+ "loss": 5.1246,
29
+ "step": 1500
30
+ },
31
+ {
32
+ "epoch": 20.83,
33
+ "learning_rate": 4e-05,
34
+ "learning_rate_embeddings": 4e-05,
35
+ "loss": 4.648,
36
+ "step": 2000
37
+ },
38
+ {
39
+ "epoch": 26.04,
40
+ "learning_rate": 5e-05,
41
+ "learning_rate_embeddings": 5e-05,
42
+ "loss": 4.333,
43
+ "step": 2500
44
+ },
45
+ {
46
+ "epoch": 26.04,
47
+ "eval_loss": 4.06018590927124,
48
+ "eval_runtime": 21.6357,
49
+ "eval_samples_per_second": 251.945,
50
+ "eval_steps_per_second": 1.987,
51
+ "step": 2500
52
+ },
53
+ {
54
+ "epoch": 31.25,
55
+ "learning_rate": 6e-05,
56
+ "learning_rate_embeddings": 6e-05,
57
+ "loss": 4.0801,
58
+ "step": 3000
59
+ },
60
+ {
61
+ "epoch": 36.45,
62
+ "learning_rate": 7.000000000000001e-05,
63
+ "learning_rate_embeddings": 7.000000000000001e-05,
64
+ "loss": 3.8748,
65
+ "step": 3500
66
+ },
67
+ {
68
+ "epoch": 41.66,
69
+ "learning_rate": 8e-05,
70
+ "learning_rate_embeddings": 8e-05,
71
+ "loss": 3.7065,
72
+ "step": 4000
73
+ },
74
+ {
75
+ "epoch": 46.87,
76
+ "learning_rate": 8.999999999999999e-05,
77
+ "learning_rate_embeddings": 8.999999999999999e-05,
78
+ "loss": 3.5779,
79
+ "step": 4500
80
+ },
81
+ {
82
+ "epoch": 52.08,
83
+ "learning_rate": 0.0001,
84
+ "learning_rate_embeddings": 0.0001,
85
+ "loss": 3.4682,
86
+ "step": 5000
87
+ },
88
+ {
89
+ "epoch": 52.08,
90
+ "eval_loss": 3.347400665283203,
91
+ "eval_runtime": 7.4364,
92
+ "eval_samples_per_second": 733.017,
93
+ "eval_steps_per_second": 5.782,
94
+ "step": 5000
95
+ },
96
+ {
97
+ "epoch": 57.29,
98
+ "learning_rate": 0.00011,
99
+ "learning_rate_embeddings": 0.00011,
100
+ "loss": 3.3567,
101
+ "step": 5500
102
+ },
103
+ {
104
+ "epoch": 62.5,
105
+ "learning_rate": 0.00012,
106
+ "learning_rate_embeddings": 0.00012,
107
+ "loss": 3.2615,
108
+ "step": 6000
109
+ },
110
+ {
111
+ "epoch": 67.7,
112
+ "learning_rate": 0.00013000000000000002,
113
+ "learning_rate_embeddings": 0.00013000000000000002,
114
+ "loss": 3.1695,
115
+ "step": 6500
116
+ },
117
+ {
118
+ "epoch": 72.91,
119
+ "learning_rate": 0.00014000000000000001,
120
+ "learning_rate_embeddings": 0.00014000000000000001,
121
+ "loss": 3.0914,
122
+ "step": 7000
123
+ },
124
+ {
125
+ "epoch": 78.12,
126
+ "learning_rate": 0.00015,
127
+ "learning_rate_embeddings": 0.00015,
128
+ "loss": 3.0173,
129
+ "step": 7500
130
+ },
131
+ {
132
+ "epoch": 78.12,
133
+ "eval_loss": 3.027360200881958,
134
+ "eval_runtime": 7.56,
135
+ "eval_samples_per_second": 721.027,
136
+ "eval_steps_per_second": 5.688,
137
+ "step": 7500
138
+ },
139
+ {
140
+ "epoch": 83.33,
141
+ "learning_rate": 0.00016,
142
+ "learning_rate_embeddings": 0.00016,
143
+ "loss": 2.9281,
144
+ "step": 8000
145
+ },
146
+ {
147
+ "epoch": 88.54,
148
+ "learning_rate": 0.00017,
149
+ "learning_rate_embeddings": 0.00017,
150
+ "loss": 2.8527,
151
+ "step": 8500
152
+ },
153
+ {
154
+ "epoch": 93.74,
155
+ "learning_rate": 0.00017999999999999998,
156
+ "learning_rate_embeddings": 0.00017999999999999998,
157
+ "loss": 2.7853,
158
+ "step": 9000
159
+ },
160
+ {
161
+ "epoch": 98.95,
162
+ "learning_rate": 0.00019,
163
+ "learning_rate_embeddings": 0.00019,
164
+ "loss": 2.7177,
165
+ "step": 9500
166
+ },
167
+ {
168
+ "epoch": 104.17,
169
+ "learning_rate": 0.0002,
170
+ "learning_rate_embeddings": 0.0002,
171
+ "loss": 2.6528,
172
+ "step": 10000
173
+ },
174
+ {
175
+ "epoch": 104.17,
176
+ "eval_loss": 2.862852096557617,
177
+ "eval_runtime": 7.3882,
178
+ "eval_samples_per_second": 737.797,
179
+ "eval_steps_per_second": 5.82,
180
+ "step": 10000
181
+ },
182
+ {
183
+ "epoch": 109.37,
184
+ "learning_rate": 0.00021,
185
+ "learning_rate_embeddings": 0.00021,
186
+ "loss": 2.5833,
187
+ "step": 10500
188
+ },
189
+ {
190
+ "epoch": 114.58,
191
+ "learning_rate": 0.00022,
192
+ "learning_rate_embeddings": 0.00022,
193
+ "loss": 2.5229,
194
+ "step": 11000
195
+ },
196
+ {
197
+ "epoch": 119.79,
198
+ "learning_rate": 0.00023,
199
+ "learning_rate_embeddings": 0.00023,
200
+ "loss": 2.4533,
201
+ "step": 11500
202
+ },
203
+ {
204
+ "epoch": 124.99,
205
+ "learning_rate": 0.00024,
206
+ "learning_rate_embeddings": 0.00024,
207
+ "loss": 2.3875,
208
+ "step": 12000
209
+ },
210
+ {
211
+ "epoch": 130.21,
212
+ "learning_rate": 0.00025,
213
+ "learning_rate_embeddings": 0.00025,
214
+ "loss": 2.3269,
215
+ "step": 12500
216
+ },
217
+ {
218
+ "epoch": 130.21,
219
+ "eval_loss": 2.7988603115081787,
220
+ "eval_runtime": 7.5079,
221
+ "eval_samples_per_second": 726.039,
222
+ "eval_steps_per_second": 5.727,
223
+ "step": 12500
224
+ }
225
+ ],
226
+ "max_steps": 250000,
227
+ "num_train_epochs": 2605,
228
+ "total_flos": 2.1066408787968e+17,
229
+ "trial_name": null,
230
+ "trial_params": null
231
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f4014c57a0e9e87a98a276968e9cba824b64a47ff4d94173c012d22af916e26
3
+ size 2991
vocab.json ADDED
The diff for this file is too large to render. See raw diff