Hugging Face's logo

Lajonbot
/
gpt-neo-125m-EleutherAI-Instruct-10000steps-polish

Text Generation
Transformers
PyTorch
Polish
gpt_neo
Inference Endpoints
Model card Files Community
1
Aspik101 commited on
Commit
3b3201e
•
1 Parent(s): 8bc751a

Hubert commit

Browse files
Files changed (12) hide show
  1. config.json +54 -0
  2. merges.txt +0 -0
  3. optimizer.pt +3 -0
  4. pytorch_model.bin +3 -0
  5. rng_state.pth +3 -0
  6. scheduler.pt +3 -0
  7. special_tokens_map.json +23 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +34 -0
  10. trainer_state.json +256 -0
  11. training_args.bin +3 -0
  12. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "MBZUAI/LaMini-Neo-125M",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPTNeoForCausalLM"
6
+ ],
7
+ "attention_dropout": 0,
8
+ "attention_layers": [
9
+ "global",
10
+ "local",
11
+ "global",
12
+ "local",
13
+ "global",
14
+ "local",
15
+ "global",
16
+ "local",
17
+ "global",
18
+ "local",
19
+ "global",
20
+ "local"
21
+ ],
22
+ "attention_types": [
23
+ [
24
+ [
25
+ "global",
26
+ "local"
27
+ ],
28
+ 6
29
+ ]
30
+ ],
31
+ "bos_token_id": 50256,
32
+ "embed_dropout": 0,
33
+ "eos_token_id": 50256,
34
+ "gradient_checkpointing": false,
35
+ "hidden_size": 768,
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": null,
38
+ "layer_norm_epsilon": 1e-05,
39
+ "max_position_embeddings": 2048,
40
+ "model_type": "gpt_neo",
41
+ "num_heads": 12,
42
+ "num_layers": 12,
43
+ "resid_dropout": 0,
44
+ "summary_activation": null,
45
+ "summary_first_dropout": 0.1,
46
+ "summary_proj_to_labels": true,
47
+ "summary_type": "cls_index",
48
+ "summary_use_proj": true,
49
+ "torch_dtype": "float32",
50
+ "transformers_version": "4.20.1",
51
+ "use_cache": false,
52
+ "vocab_size": 50258,
53
+ "window_size": 256
54
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bae30acb738a4d84ac330fa7ace702e32240ab76fdaa622aa39e444203b1ea83
3
+ size 1001687745
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a97314a5f31f6343d71f556fd650d438cdeb0aa19ef2ea3175c24a77d191b51
3
+ size 551188177
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0217759d118441b4ad07c71fd1be8c09ef99c4c1b9ca5ace0ae209a8872fb667
3
+ size 14503
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b42cb14d666e534ebfdde54b55fdfa95b18ead1daf1103b0c5381954b58b662a
3
+ size 623
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
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
+ "unk_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "eos_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "errors": "replace",
21
+ "model_max_length": 2048,
22
+ "name_or_path": "EleutherAI/gpt-neo-125m",
23
+ "pad_token": null,
24
+ "special_tokens_map_file": null,
25
+ "tokenizer_class": "GPT2Tokenizer",
26
+ "unk_token": {
27
+ "__type": "AddedToken",
28
+ "content": "<|endoftext|>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
trainer_state.json ADDED
@@ -0,0 +1,256 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 14.619883040935672,
5
+ "global_step": 10000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.37,
12
+ "learning_rate": 0.0002966863033873343,
13
+ "loss": 0.6757,
14
+ "step": 250
15
+ },
16
+ {
17
+ "epoch": 0.73,
18
+ "learning_rate": 0.00029116347569955813,
19
+ "loss": 0.516,
20
+ "step": 500
21
+ },
22
+ {
23
+ "epoch": 1.1,
24
+ "learning_rate": 0.00028564064801178197,
25
+ "loss": 0.4685,
26
+ "step": 750
27
+ },
28
+ {
29
+ "epoch": 1.46,
30
+ "learning_rate": 0.00028011782032400586,
31
+ "loss": 0.4306,
32
+ "step": 1000
33
+ },
34
+ {
35
+ "epoch": 1.83,
36
+ "learning_rate": 0.0002745949926362297,
37
+ "loss": 0.4228,
38
+ "step": 1250
39
+ },
40
+ {
41
+ "epoch": 2.19,
42
+ "learning_rate": 0.0002690721649484536,
43
+ "loss": 0.3927,
44
+ "step": 1500
45
+ },
46
+ {
47
+ "epoch": 2.56,
48
+ "learning_rate": 0.0002635493372606774,
49
+ "loss": 0.3716,
50
+ "step": 1750
51
+ },
52
+ {
53
+ "epoch": 2.92,
54
+ "learning_rate": 0.0002580265095729013,
55
+ "loss": 0.3724,
56
+ "step": 2000
57
+ },
58
+ {
59
+ "epoch": 3.29,
60
+ "learning_rate": 0.00025250368188512514,
61
+ "loss": 0.3353,
62
+ "step": 2250
63
+ },
64
+ {
65
+ "epoch": 3.65,
66
+ "learning_rate": 0.000246980854197349,
67
+ "loss": 0.3312,
68
+ "step": 2500
69
+ },
70
+ {
71
+ "epoch": 4.02,
72
+ "learning_rate": 0.0002414580265095729,
73
+ "loss": 0.3317,
74
+ "step": 2750
75
+ },
76
+ {
77
+ "epoch": 4.39,
78
+ "learning_rate": 0.00023593519882179672,
79
+ "loss": 0.2892,
80
+ "step": 3000
81
+ },
82
+ {
83
+ "epoch": 4.75,
84
+ "learning_rate": 0.0002304123711340206,
85
+ "loss": 0.2968,
86
+ "step": 3250
87
+ },
88
+ {
89
+ "epoch": 5.12,
90
+ "learning_rate": 0.00022488954344624445,
91
+ "loss": 0.2817,
92
+ "step": 3500
93
+ },
94
+ {
95
+ "epoch": 5.48,
96
+ "learning_rate": 0.0002193667157584683,
97
+ "loss": 0.2557,
98
+ "step": 3750
99
+ },
100
+ {
101
+ "epoch": 5.85,
102
+ "learning_rate": 0.00021384388807069217,
103
+ "loss": 0.2622,
104
+ "step": 4000
105
+ },
106
+ {
107
+ "epoch": 6.21,
108
+ "learning_rate": 0.00020832106038291603,
109
+ "loss": 0.234,
110
+ "step": 4250
111
+ },
112
+ {
113
+ "epoch": 6.58,
114
+ "learning_rate": 0.0002027982326951399,
115
+ "loss": 0.2228,
116
+ "step": 4500
117
+ },
118
+ {
119
+ "epoch": 6.94,
120
+ "learning_rate": 0.00019727540500736376,
121
+ "loss": 0.2292,
122
+ "step": 4750
123
+ },
124
+ {
125
+ "epoch": 7.31,
126
+ "learning_rate": 0.0001917525773195876,
127
+ "loss": 0.1906,
128
+ "step": 5000
129
+ },
130
+ {
131
+ "epoch": 7.68,
132
+ "learning_rate": 0.00018622974963181148,
133
+ "loss": 0.19,
134
+ "step": 5250
135
+ },
136
+ {
137
+ "epoch": 8.04,
138
+ "learning_rate": 0.00018070692194403532,
139
+ "loss": 0.1914,
140
+ "step": 5500
141
+ },
142
+ {
143
+ "epoch": 8.41,
144
+ "learning_rate": 0.0001751840942562592,
145
+ "loss": 0.1542,
146
+ "step": 5750
147
+ },
148
+ {
149
+ "epoch": 8.77,
150
+ "learning_rate": 0.00016966126656848304,
151
+ "loss": 0.1615,
152
+ "step": 6000
153
+ },
154
+ {
155
+ "epoch": 9.14,
156
+ "learning_rate": 0.00016413843888070693,
157
+ "loss": 0.1495,
158
+ "step": 6250
159
+ },
160
+ {
161
+ "epoch": 9.5,
162
+ "learning_rate": 0.00015861561119293076,
163
+ "loss": 0.1286,
164
+ "step": 6500
165
+ },
166
+ {
167
+ "epoch": 9.87,
168
+ "learning_rate": 0.00015309278350515463,
169
+ "loss": 0.1343,
170
+ "step": 6750
171
+ },
172
+ {
173
+ "epoch": 10.23,
174
+ "learning_rate": 0.0001475699558173785,
175
+ "loss": 0.1151,
176
+ "step": 7000
177
+ },
178
+ {
179
+ "epoch": 10.6,
180
+ "learning_rate": 0.00014204712812960235,
181
+ "loss": 0.1071,
182
+ "step": 7250
183
+ },
184
+ {
185
+ "epoch": 10.96,
186
+ "learning_rate": 0.0001365243004418262,
187
+ "loss": 0.1114,
188
+ "step": 7500
189
+ },
190
+ {
191
+ "epoch": 11.33,
192
+ "learning_rate": 0.00013100147275405007,
193
+ "loss": 0.0887,
194
+ "step": 7750
195
+ },
196
+ {
197
+ "epoch": 11.7,
198
+ "learning_rate": 0.00012547864506627394,
199
+ "loss": 0.0901,
200
+ "step": 8000
201
+ },
202
+ {
203
+ "epoch": 12.06,
204
+ "learning_rate": 0.00011995581737849778,
205
+ "loss": 0.0898,
206
+ "step": 8250
207
+ },
208
+ {
209
+ "epoch": 12.43,
210
+ "learning_rate": 0.00011443298969072163,
211
+ "loss": 0.0745,
212
+ "step": 8500
213
+ },
214
+ {
215
+ "epoch": 12.79,
216
+ "learning_rate": 0.0001089101620029455,
217
+ "loss": 0.0778,
218
+ "step": 8750
219
+ },
220
+ {
221
+ "epoch": 13.16,
222
+ "learning_rate": 0.00010338733431516936,
223
+ "loss": 0.073,
224
+ "step": 9000
225
+ },
226
+ {
227
+ "epoch": 13.52,
228
+ "learning_rate": 9.786450662739322e-05,
229
+ "loss": 0.067,
230
+ "step": 9250
231
+ },
232
+ {
233
+ "epoch": 13.89,
234
+ "learning_rate": 9.234167893961708e-05,
235
+ "loss": 0.069,
236
+ "step": 9500
237
+ },
238
+ {
239
+ "epoch": 14.25,
240
+ "learning_rate": 8.681885125184094e-05,
241
+ "loss": 0.0628,
242
+ "step": 9750
243
+ },
244
+ {
245
+ "epoch": 14.62,
246
+ "learning_rate": 8.129602356406479e-05,
247
+ "loss": 0.0616,
248
+ "step": 10000
249
+ }
250
+ ],
251
+ "max_steps": 13680,
252
+ "num_train_epochs": 20,
253
+ "total_flos": 8.358078580103578e+16,
254
+ "trial_name": null,
255
+ "trial_params": null
256
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23f0228fbd69c4e4cec2641cb901e0db47c1715286281a9d69e881f5e8306bc1
3
+ size 3247
vocab.json ADDED
The diff for this file is too large to render. See raw diff