Hugging Face's logo

cosail-knu
/
pythia-12b-draft-70m-code

Safetensors
gpt_neox
Model card Files
xet
 Community
knu-mhan commited on
Commit
99f3ceb
·
1 Parent(s): 2237f9d

update

Browse files
Files changed (8) hide show
  1. config.json +32 -0
  2. generation_config.json +7 -0
  3. model.safetensors +3 -0
  4. special_tokens_map.json +24 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +216 -0
  7. trainer_state.json +196 -0
  8. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cosail-knu/pythia-70m",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "attention_bias": true,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": 0.1,
10
+ "eos_token_id": 0,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout": 0.0,
13
+ "hidden_size": 512,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 2048,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 2048,
18
+ "model_type": "gpt_neox",
19
+ "num_attention_heads": 8,
20
+ "num_hidden_layers": 6,
21
+ "partial_rotary_factor": 0.25,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000,
24
+ "rotary_emb_base": 10000,
25
+ "rotary_pct": 0.25,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.49.0",
29
+ "use_cache": false,
30
+ "use_parallel_residual": true,
31
+ "vocab_size": 50277
32
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "transformers_version": "4.49.0",
6
+ "use_cache": false
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae96ed0a8831a3ba438ae2864c0036e7ddb52b452e5bb55bf9842df0552ec19f
3
+ size 281604584
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,216 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
207
+ "bos_token": "<|endoftext|>",
208
+ "clean_up_tokenization_spaces": false,
209
+ "eos_token": "<|endoftext|>",
210
+ "extra_special_tokens": {},
211
+ "model_max_length": 1024,
212
+ "pad_token": "<|endoftext|>",
213
+ "padding_side": "right",
214
+ "tokenizer_class": "GPTNeoXTokenizer",
215
+ "unk_token": "<|endoftext|>"
216
+ }
trainer_state.json ADDED
@@ -0,0 +1,196 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 222,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.13513513513513514,
13
+ "grad_norm": Infinity,
14
+ "learning_rate": 3e-05,
15
+ "loss": 1.435,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.2702702702702703,
20
+ "grad_norm": 47.6257438659668,
21
+ "learning_rate": 2.9840150521126656e-05,
22
+ "loss": 1.4664,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.40540540540540543,
27
+ "grad_norm": 28.86147689819336,
28
+ "learning_rate": 2.936400899862609e-05,
29
+ "loss": 1.3927,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.5405405405405406,
34
+ "grad_norm": 31.34147071838379,
35
+ "learning_rate": 2.8581723562397203e-05,
36
+ "loss": 1.3359,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.6756756756756757,
41
+ "grad_norm": 40.83176803588867,
42
+ "learning_rate": 2.7509967268348168e-05,
43
+ "loss": 1.2689,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.8108108108108109,
48
+ "grad_norm": 28.7069034576416,
49
+ "learning_rate": 2.617158274115673e-05,
50
+ "loss": 1.3124,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.9459459459459459,
55
+ "grad_norm": 31.556358337402344,
56
+ "learning_rate": 2.459509532338337e-05,
57
+ "loss": 1.1676,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 1.0810810810810811,
62
+ "grad_norm": 30.21744155883789,
63
+ "learning_rate": 2.2814105107318955e-05,
64
+ "loss": 1.178,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 1.2162162162162162,
69
+ "grad_norm": 24.259174346923828,
70
+ "learning_rate": 2.086657080735234e-05,
71
+ "loss": 1.1852,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 1.3513513513513513,
76
+ "grad_norm": 19.32608413696289,
77
+ "learning_rate": 1.879400073587521e-05,
78
+ "loss": 1.0562,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 1.4864864864864864,
83
+ "grad_norm": 28.069013595581055,
84
+ "learning_rate": 1.664056812566812e-05,
85
+ "loss": 1.0509,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 1.6216216216216215,
90
+ "grad_norm": 25.697093963623047,
91
+ "learning_rate": 1.4452169654135116e-05,
92
+ "loss": 1.1403,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 1.7567567567567568,
97
+ "grad_norm": 21.39369773864746,
98
+ "learning_rate": 1.2275447235308454e-05,
99
+ "loss": 1.1449,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 1.8918918918918919,
104
+ "grad_norm": 22.039438247680664,
105
+ "learning_rate": 1.015679392842831e-05,
106
+ "loss": 1.0383,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 2.027027027027027,
111
+ "grad_norm": 25.26503562927246,
112
+ "learning_rate": 8.141365150430423e-06,
113
+ "loss": 1.0871,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 2.1621621621621623,
118
+ "grad_norm": 19.504608154296875,
119
+ "learning_rate": 6.27211626663071e-06,
120
+ "loss": 0.966,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 2.2972972972972974,
125
+ "grad_norm": 22.5753173828125,
126
+ "learning_rate": 4.588887071690491e-06,
127
+ "loss": 0.9257,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 2.4324324324324325,
132
+ "grad_norm": 30.79815101623535,
133
+ "learning_rate": 3.12755267356119e-06,
134
+ "loss": 0.9889,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 2.5675675675675675,
139
+ "grad_norm": 22.710554122924805,
140
+ "learning_rate": 1.9192588778428844e-06,
141
+ "loss": 0.9634,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 2.7027027027027026,
146
+ "grad_norm": 27.529897689819336,
147
+ "learning_rate": 9.897583690117813e-07,
148
+ "loss": 0.9673,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 2.8378378378378377,
153
+ "grad_norm": 23.513914108276367,
154
+ "learning_rate": 3.588618366610941e-07,
155
+ "loss": 1.0004,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 2.972972972972973,
160
+ "grad_norm": 20.257404327392578,
161
+ "learning_rate": 4.0015745046725336e-08,
162
+ "loss": 0.962,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 3.0,
167
+ "step": 222,
168
+ "total_flos": 967989855780864.0,
169
+ "train_loss": 1.1366610301507485,
170
+ "train_runtime": 118.4216,
171
+ "train_samples_per_second": 29.792,
172
+ "train_steps_per_second": 1.875
173
+ }
174
+ ],
175
+ "logging_steps": 10,
176
+ "max_steps": 222,
177
+ "num_input_tokens_seen": 0,
178
+ "num_train_epochs": 3,
179
+ "save_steps": 500,
180
+ "stateful_callbacks": {
181
+ "TrainerControl": {
182
+ "args": {
183
+ "should_epoch_stop": false,
184
+ "should_evaluate": false,
185
+ "should_log": false,
186
+ "should_save": false,
187
+ "should_training_stop": false
188
+ },
189
+ "attributes": {}
190
+ }
191
+ },
192
+ "total_flos": 967989855780864.0,
193
+ "train_batch_size": 16,
194
+ "trial_name": null,
195
+ "trial_params": null
196
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ea39cc42da8a6285b4bd6f38f00c91c37aa1f505d3b5b8328a87ece4f2db900
3
+ size 5905