Hugging Face's logo

DNA-LLM
/
virus-pythia-302M-2048-cross_entropy

Safetensors
gpt_neox
Generated from Trainer
Model card Files Community
Muedi commited on
Commit
9fb351e
·
verified ·
1 Parent(s): cf43cec

Training in progress, step 3000, checkpoint

Browse files
Files changed (11) hide show
  1. checkpoint-3000/config.json +30 -0
  2. checkpoint-3000/generation_config.json +6 -0
  3. checkpoint-3000/model.safetensors +3 -0
  4. checkpoint-3000/optimizer.pt +3 -0
  5. checkpoint-3000/rng_state.pth +3 -0
  6. checkpoint-3000/scheduler.pt +3 -0
  7. checkpoint-3000/special_tokens_map.json +24 -0
  8. checkpoint-3000/tokenizer.json +96 -0
  9. checkpoint-3000/tokenizer_config.json +38 -0
  10. checkpoint-3000/trainer_state.json +243 -0
  11. checkpoint-3000/training_args.bin +3 -0
checkpoint-3000/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/pythia-410m",
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": 1024,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 4096,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 2048,
18
+ "model_type": "gpt_neox",
19
+ "num_attention_heads": 16,
20
+ "num_hidden_layers": 24,
21
+ "rope_scaling": null,
22
+ "rotary_emb_base": 10000,
23
+ "rotary_pct": 0.25,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.42.3",
27
+ "use_cache": true,
28
+ "use_parallel_residual": true,
29
+ "vocab_size": 8
30
+ }
checkpoint-3000/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "transformers_version": "4.42.3"
6
+ }
checkpoint-3000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:804709b02e3dcfbe7151a34796a55269ee1f8611f65aa5f64a061be6054388bc
3
+ size 1209345104
checkpoint-3000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c6508e241b3adc10d93c4502bb74caef90a4e235e891488e6d72240af72156f
3
+ size 2418866362
checkpoint-3000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:835f869ea325fd6edf27b48b589309fb66641cb92b45f2fc13d1bb6e8814106c
3
+ size 14244
checkpoint-3000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f33b84733c97ae6d9fe3eac9049b7598cc32141b7e9ef7a8a67eb4bd45a1c49
3
+ size 1064
checkpoint-3000/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|beginoftext|>",
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": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|unknown|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-3000/tokenizer.json ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "<|beginoftext|>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": true,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "<|endoftext|>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "<|unknown|>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ }
33
+ ],
34
+ "normalizer": {
35
+ "type": "NFC"
36
+ },
37
+ "pre_tokenizer": {
38
+ "type": "ByteLevel",
39
+ "add_prefix_space": false,
40
+ "trim_offsets": true,
41
+ "use_regex": true
42
+ },
43
+ "post_processor": {
44
+ "type": "TemplateProcessing",
45
+ "single": [
46
+ {
47
+ "Sequence": {
48
+ "id": "A",
49
+ "type_id": 0
50
+ }
51
+ }
52
+ ],
53
+ "pair": [
54
+ {
55
+ "Sequence": {
56
+ "id": "A",
57
+ "type_id": 0
58
+ }
59
+ },
60
+ {
61
+ "Sequence": {
62
+ "id": "B",
63
+ "type_id": 1
64
+ }
65
+ }
66
+ ],
67
+ "special_tokens": {}
68
+ },
69
+ "decoder": {
70
+ "type": "ByteLevel",
71
+ "add_prefix_space": false,
72
+ "trim_offsets": true,
73
+ "use_regex": true
74
+ },
75
+ "model": {
76
+ "type": "BPE",
77
+ "dropout": null,
78
+ "unk_token": "<|unknown|>",
79
+ "continuing_subword_prefix": null,
80
+ "end_of_word_suffix": null,
81
+ "fuse_unk": false,
82
+ "byte_fallback": false,
83
+ "ignore_merges": false,
84
+ "vocab": {
85
+ "<|beginoftext|>": 0,
86
+ "<|padding|>": 1,
87
+ "<|unknown|>": 2,
88
+ "a": 3,
89
+ "c": 4,
90
+ "g": 5,
91
+ "t": 6,
92
+ "n": 7
93
+ },
94
+ "merges": []
95
+ }
96
+ }
checkpoint-3000/tokenizer_config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<|beginoftext|>",
8
+ "lstrip": false,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<|endoftext|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "<|unknown|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<|beginoftext|>",
32
+ "clean_up_tokenization_spaces": true,
33
+ "eos_token": "<|endoftext|>",
34
+ "model_max_length": 1000000000000000019884624838656,
35
+ "pad_token": "<|endoftext|>",
36
+ "tokenizer_class": "GPTNeoXTokenizer",
37
+ "unk_token": "<|unknown|>"
38
+ }
checkpoint-3000/trainer_state.json ADDED
@@ -0,0 +1,243 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.009771891479887818,
5
+ "eval_steps": 500,
6
+ "global_step": 3000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0003257297159962606,
13
+ "grad_norm": 2.2308592796325684,
14
+ "learning_rate": 4.99853416853153e-05,
15
+ "loss": 1.4483,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 0.0006514594319925212,
20
+ "grad_norm": 2.3997225761413574,
21
+ "learning_rate": 4.996905466899897e-05,
22
+ "loss": 1.3276,
23
+ "step": 200
24
+ },
25
+ {
26
+ "epoch": 0.0009771891479887819,
27
+ "grad_norm": 1.4687339067459106,
28
+ "learning_rate": 4.995276765268264e-05,
29
+ "loss": 1.3394,
30
+ "step": 300
31
+ },
32
+ {
33
+ "epoch": 0.0013029188639850425,
34
+ "grad_norm": 0.6583470702171326,
35
+ "learning_rate": 4.993648063636631e-05,
36
+ "loss": 1.3245,
37
+ "step": 400
38
+ },
39
+ {
40
+ "epoch": 0.0016286485799813031,
41
+ "grad_norm": 1.6252340078353882,
42
+ "learning_rate": 4.992019362004997e-05,
43
+ "loss": 1.3249,
44
+ "step": 500
45
+ },
46
+ {
47
+ "epoch": 0.0019543782959775637,
48
+ "grad_norm": 2.0806777477264404,
49
+ "learning_rate": 4.9903906603733634e-05,
50
+ "loss": 1.32,
51
+ "step": 600
52
+ },
53
+ {
54
+ "epoch": 0.002280108011973824,
55
+ "grad_norm": 1.376539707183838,
56
+ "learning_rate": 4.988761958741731e-05,
57
+ "loss": 1.3133,
58
+ "step": 700
59
+ },
60
+ {
61
+ "epoch": 0.002605837727970085,
62
+ "grad_norm": 2.234644889831543,
63
+ "learning_rate": 4.987133257110097e-05,
64
+ "loss": 1.3179,
65
+ "step": 800
66
+ },
67
+ {
68
+ "epoch": 0.0029315674439663454,
69
+ "grad_norm": 1.4599684476852417,
70
+ "learning_rate": 4.985504555478464e-05,
71
+ "loss": 1.3097,
72
+ "step": 900
73
+ },
74
+ {
75
+ "epoch": 0.0032572971599626062,
76
+ "grad_norm": 1.7078094482421875,
77
+ "learning_rate": 4.9838758538468304e-05,
78
+ "loss": 1.3083,
79
+ "step": 1000
80
+ },
81
+ {
82
+ "epoch": 0.0035830268759588666,
83
+ "grad_norm": 0.6953567266464233,
84
+ "learning_rate": 4.9822471522151976e-05,
85
+ "loss": 1.3075,
86
+ "step": 1100
87
+ },
88
+ {
89
+ "epoch": 0.0039087565919551275,
90
+ "grad_norm": 1.225602626800537,
91
+ "learning_rate": 4.980618450583564e-05,
92
+ "loss": 1.3054,
93
+ "step": 1200
94
+ },
95
+ {
96
+ "epoch": 0.004234486307951388,
97
+ "grad_norm": 1.3010519742965698,
98
+ "learning_rate": 4.978989748951931e-05,
99
+ "loss": 1.3066,
100
+ "step": 1300
101
+ },
102
+ {
103
+ "epoch": 0.004560216023947648,
104
+ "grad_norm": 0.6475724577903748,
105
+ "learning_rate": 4.9773610473202974e-05,
106
+ "loss": 1.3109,
107
+ "step": 1400
108
+ },
109
+ {
110
+ "epoch": 0.004885945739943909,
111
+ "grad_norm": 1.046614646911621,
112
+ "learning_rate": 4.975732345688664e-05,
113
+ "loss": 1.3074,
114
+ "step": 1500
115
+ },
116
+ {
117
+ "epoch": 0.00521167545594017,
118
+ "grad_norm": 1.113573670387268,
119
+ "learning_rate": 4.974103644057031e-05,
120
+ "loss": 1.3083,
121
+ "step": 1600
122
+ },
123
+ {
124
+ "epoch": 0.005537405171936431,
125
+ "grad_norm": 1.4273550510406494,
126
+ "learning_rate": 4.972474942425398e-05,
127
+ "loss": 1.3018,
128
+ "step": 1700
129
+ },
130
+ {
131
+ "epoch": 0.005863134887932691,
132
+ "grad_norm": 0.5519908666610718,
133
+ "learning_rate": 4.970846240793764e-05,
134
+ "loss": 1.2945,
135
+ "step": 1800
136
+ },
137
+ {
138
+ "epoch": 0.006188864603928952,
139
+ "grad_norm": 0.6653416156768799,
140
+ "learning_rate": 4.969217539162131e-05,
141
+ "loss": 1.3004,
142
+ "step": 1900
143
+ },
144
+ {
145
+ "epoch": 0.0065145943199252125,
146
+ "grad_norm": 0.732170581817627,
147
+ "learning_rate": 4.9675888375304975e-05,
148
+ "loss": 1.3014,
149
+ "step": 2000
150
+ },
151
+ {
152
+ "epoch": 0.006840324035921473,
153
+ "grad_norm": 0.405608594417572,
154
+ "learning_rate": 4.965960135898865e-05,
155
+ "loss": 1.2939,
156
+ "step": 2100
157
+ },
158
+ {
159
+ "epoch": 0.007166053751917733,
160
+ "grad_norm": 0.9849847555160522,
161
+ "learning_rate": 4.9643314342672306e-05,
162
+ "loss": 1.2922,
163
+ "step": 2200
164
+ },
165
+ {
166
+ "epoch": 0.007491783467913994,
167
+ "grad_norm": 0.7152832746505737,
168
+ "learning_rate": 4.962702732635598e-05,
169
+ "loss": 1.2905,
170
+ "step": 2300
171
+ },
172
+ {
173
+ "epoch": 0.007817513183910255,
174
+ "grad_norm": 1.1164734363555908,
175
+ "learning_rate": 4.9610740310039644e-05,
176
+ "loss": 1.3024,
177
+ "step": 2400
178
+ },
179
+ {
180
+ "epoch": 0.008143242899906516,
181
+ "grad_norm": 0.574243426322937,
182
+ "learning_rate": 4.959445329372332e-05,
183
+ "loss": 1.2944,
184
+ "step": 2500
185
+ },
186
+ {
187
+ "epoch": 0.008468972615902777,
188
+ "grad_norm": 0.6976324319839478,
189
+ "learning_rate": 4.9578166277406976e-05,
190
+ "loss": 1.2939,
191
+ "step": 2600
192
+ },
193
+ {
194
+ "epoch": 0.008794702331899037,
195
+ "grad_norm": 0.4648737609386444,
196
+ "learning_rate": 4.956187926109064e-05,
197
+ "loss": 1.2841,
198
+ "step": 2700
199
+ },
200
+ {
201
+ "epoch": 0.009120432047895297,
202
+ "grad_norm": 1.189271092414856,
203
+ "learning_rate": 4.9545592244774314e-05,
204
+ "loss": 1.294,
205
+ "step": 2800
206
+ },
207
+ {
208
+ "epoch": 0.009446161763891557,
209
+ "grad_norm": 0.6437670588493347,
210
+ "learning_rate": 4.952930522845798e-05,
211
+ "loss": 1.2882,
212
+ "step": 2900
213
+ },
214
+ {
215
+ "epoch": 0.009771891479887818,
216
+ "grad_norm": 1.591304898262024,
217
+ "learning_rate": 4.9513018212141646e-05,
218
+ "loss": 1.2805,
219
+ "step": 3000
220
+ }
221
+ ],
222
+ "logging_steps": 100,
223
+ "max_steps": 307003,
224
+ "num_input_tokens_seen": 0,
225
+ "num_train_epochs": 1,
226
+ "save_steps": 500,
227
+ "stateful_callbacks": {
228
+ "TrainerControl": {
229
+ "args": {
230
+ "should_epoch_stop": false,
231
+ "should_evaluate": false,
232
+ "should_log": false,
233
+ "should_save": true,
234
+ "should_training_stop": false
235
+ },
236
+ "attributes": {}
237
+ }
238
+ },
239
+ "total_flos": 4.4578841296896e+16,
240
+ "train_batch_size": 4,
241
+ "trial_name": null,
242
+ "trial_params": null
243
+ }
checkpoint-3000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1be2d5594a22f4bff72c544c78dc0a47a5bb1e2a1e204a42972561dc45351391
3
+ size 5176