Hugging Face's logo

timaeus
/
tetra-induction-w5k-15k

gpt_neox
Model card Files
xet
 Community
bfpill commited on
Commit
b5c595c
·
verified ·
1 Parent(s): a170c7f

Upload tokenizer & config to main

Browse files
Files changed (10) hide show
  1. config.json +32 -0
  2. generation_config.json +7 -0
  3. optimizer.pt +3 -0
  4. rng_state.pth +3 -0
  5. scheduler.pt +3 -0
  6. special_tokens_map.json +30 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +222 -0
  9. trainer_state.json +110 -0
  10. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GPTNeoXForCausalLM"
4
+ ],
5
+ "attention_bias": true,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": 0.1,
9
+ "dtype": "bfloat16",
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout": 0.0,
13
+ "hidden_size": 256,
14
+ "initializer_range": 0.05,
15
+ "intermediate_size": 0,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 1024,
18
+ "model_type": "gpt_neox",
19
+ "num_attention_heads": 8,
20
+ "num_hidden_layers": 2,
21
+ "partial_rotary_factor": 1.0,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000,
24
+ "rotary_emb_base": 10000,
25
+ "rotary_pct": 1.0,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.45.2",
29
+ "use_cache": false,
30
+ "use_parallel_residual": true,
31
+ "vocab_size": 50278
32
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.45.2",
6
+ "use_cache": false
7
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:578b247ac4818119f0985acab926b90131ec3d5fc75555c24a49af63f9efeed5
3
+ size 210197851
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:749fa9eed885e9761c9f2e2d2be95a7bd6918ab0b3a60c83e9d5e0a30c63287a
3
+ size 14645
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5b05955bb197697f5a716e4c344035e12a4a81599fd3ab5b82077b37e185f6c
3
+ size 1465
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,222 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<|padding|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "50254": {
23
+ "content": " ",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "50255": {
31
+ "content": " ",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": false
37
+ },
38
+ "50256": {
39
+ "content": " ",
40
+ "lstrip": false,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ },
46
+ "50257": {
47
+ "content": " ",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": false
53
+ },
54
+ "50258": {
55
+ "content": " ",
56
+ "lstrip": false,
57
+ "normalized": true,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "50259": {
63
+ "content": " ",
64
+ "lstrip": false,
65
+ "normalized": true,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": false
69
+ },
70
+ "50260": {
71
+ "content": " ",
72
+ "lstrip": false,
73
+ "normalized": true,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": false
77
+ },
78
+ "50261": {
79
+ "content": " ",
80
+ "lstrip": false,
81
+ "normalized": true,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": false
85
+ },
86
+ "50262": {
87
+ "content": " ",
88
+ "lstrip": false,
89
+ "normalized": true,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": false
93
+ },
94
+ "50263": {
95
+ "content": " ",
96
+ "lstrip": false,
97
+ "normalized": true,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": false
101
+ },
102
+ "50264": {
103
+ "content": " ",
104
+ "lstrip": false,
105
+ "normalized": true,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": false
109
+ },
110
+ "50265": {
111
+ "content": " ",
112
+ "lstrip": false,
113
+ "normalized": true,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": false
117
+ },
118
+ "50266": {
119
+ "content": " ",
120
+ "lstrip": false,
121
+ "normalized": true,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "50267": {
127
+ "content": " ",
128
+ "lstrip": false,
129
+ "normalized": true,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "50268": {
135
+ "content": " ",
136
+ "lstrip": false,
137
+ "normalized": true,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "50269": {
143
+ "content": " ",
144
+ "lstrip": false,
145
+ "normalized": true,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "50270": {
151
+ "content": " ",
152
+ "lstrip": false,
153
+ "normalized": true,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "50271": {
159
+ "content": " ",
160
+ "lstrip": false,
161
+ "normalized": true,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "50272": {
167
+ "content": " ",
168
+ "lstrip": false,
169
+ "normalized": true,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "50273": {
175
+ "content": " ",
176
+ "lstrip": false,
177
+ "normalized": true,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ },
182
+ "50274": {
183
+ "content": " ",
184
+ "lstrip": false,
185
+ "normalized": true,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": false
189
+ },
190
+ "50275": {
191
+ "content": " ",
192
+ "lstrip": false,
193
+ "normalized": true,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": false
197
+ },
198
+ "50276": {
199
+ "content": " ",
200
+ "lstrip": false,
201
+ "normalized": true,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": false
205
+ },
206
+ "50277": {
207
+ "content": "[PAD]",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": false,
211
+ "single_word": false,
212
+ "special": true
213
+ }
214
+ },
215
+ "bos_token": "<|endoftext|>",
216
+ "clean_up_tokenization_spaces": true,
217
+ "eos_token": "<|endoftext|>",
218
+ "model_max_length": 1000000000000000019884624838656,
219
+ "pad_token": "[PAD]",
220
+ "tokenizer_class": "GPTNeoXTokenizer",
221
+ "unk_token": "<|endoftext|>"
222
+ }
trainer_state.json ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.11835194910866188,
5
+ "eval_steps": 100,
6
+ "global_step": 1000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.00011835194910866188,
13
+ "grad_norm": 3.050482988357544,
14
+ "learning_rate": 0.001,
15
+ "loss": 11.2196,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.011835194910866188,
20
+ "grad_norm": 0.32114312052726746,
21
+ "learning_rate": 0.001,
22
+ "loss": 7.1872,
23
+ "step": 100
24
+ },
25
+ {
26
+ "epoch": 0.023670389821732377,
27
+ "grad_norm": 0.2564636170864105,
28
+ "learning_rate": 0.001,
29
+ "loss": 6.1443,
30
+ "step": 200
31
+ },
32
+ {
33
+ "epoch": 0.035505584732598565,
34
+ "grad_norm": 0.5633418560028076,
35
+ "learning_rate": 0.001,
36
+ "loss": 5.8111,
37
+ "step": 300
38
+ },
39
+ {
40
+ "epoch": 0.04734077964346475,
41
+ "grad_norm": 0.45185068249702454,
42
+ "learning_rate": 0.001,
43
+ "loss": 5.57,
44
+ "step": 400
45
+ },
46
+ {
47
+ "epoch": 0.05917597455433094,
48
+ "grad_norm": 0.41621828079223633,
49
+ "learning_rate": 0.001,
50
+ "loss": 5.4025,
51
+ "step": 500
52
+ },
53
+ {
54
+ "epoch": 0.07101116946519713,
55
+ "grad_norm": 0.5600417852401733,
56
+ "learning_rate": 0.001,
57
+ "loss": 5.2789,
58
+ "step": 600
59
+ },
60
+ {
61
+ "epoch": 0.08284636437606333,
62
+ "grad_norm": 0.3999986946582794,
63
+ "learning_rate": 0.001,
64
+ "loss": 5.1787,
65
+ "step": 700
66
+ },
67
+ {
68
+ "epoch": 0.0946815592869295,
69
+ "grad_norm": 0.9927613735198975,
70
+ "learning_rate": 0.001,
71
+ "loss": 5.1012,
72
+ "step": 800
73
+ },
74
+ {
75
+ "epoch": 0.1065167541977957,
76
+ "grad_norm": 0.76481032371521,
77
+ "learning_rate": 0.001,
78
+ "loss": 5.0373,
79
+ "step": 900
80
+ },
81
+ {
82
+ "epoch": 0.11835194910866188,
83
+ "grad_norm": 0.8310058116912842,
84
+ "learning_rate": 0.001,
85
+ "loss": 4.9801,
86
+ "step": 1000
87
+ }
88
+ ],
89
+ "logging_steps": 100,
90
+ "max_steps": 30000,
91
+ "num_input_tokens_seen": 0,
92
+ "num_train_epochs": 4,
93
+ "save_steps": 1000,
94
+ "stateful_callbacks": {
95
+ "TrainerControl": {
96
+ "args": {
97
+ "should_epoch_stop": false,
98
+ "should_evaluate": false,
99
+ "should_log": false,
100
+ "should_save": true,
101
+ "should_training_stop": false
102
+ },
103
+ "attributes": {}
104
+ }
105
+ },
106
+ "total_flos": 4.2154567139328e+16,
107
+ "train_batch_size": 64,
108
+ "trial_name": null,
109
+ "trial_params": null
110
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:811cf93a8fa3fca051ee62cb502e82db8b61e6b62dbf6941e1e1241ac521a46c
3
+ size 5713