Hugging Face's logo

DNA-LLM
/
virus-pythia-19M-2048-cross_entropy

Safetensors
gpt_neox
Generated from Trainer
Model card Files Community
Muedi commited on
Commit
b8fe9de
·
verified ·
1 Parent(s): b320434

Training in progress, step 2500, checkpoint

Browse files
Files changed (11) hide show
  1. checkpoint-2500/config.json +30 -0
  2. checkpoint-2500/generation_config.json +6 -0
  3. checkpoint-2500/model.safetensors +3 -0
  4. checkpoint-2500/optimizer.pt +3 -0
  5. checkpoint-2500/rng_state.pth +3 -0
  6. checkpoint-2500/scheduler.pt +3 -0
  7. checkpoint-2500/special_tokens_map.json +24 -0
  8. checkpoint-2500/tokenizer.json +96 -0
  9. checkpoint-2500/tokenizer_config.json +38 -0
  10. checkpoint-2500/trainer_state.json +208 -0
  11. checkpoint-2500/training_args.bin +3 -0
checkpoint-2500/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/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
+ "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-2500/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-2500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:427e49cd81f56f5072fc804b6c3a15c154f1a83bba08c52c3dcbebdd7fd7f9e2
3
+ size 75702552
checkpoint-2500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36346c49011e91bce63ceaae87985722def26a3a06cb1ed9f25c88f0623e1f23
3
+ size 151452026
checkpoint-2500/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-2500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de6f3e3ffa9403fd507866358d0fce9f039edd00692eeed2557a13d152eddf90
3
+ size 1064
checkpoint-2500/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-2500/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-2500/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-2500/trainer_state.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.07328799249530957,
5
+ "eval_steps": 500,
6
+ "global_step": 2500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0029315196998123826,
13
+ "grad_norm": 0.7248865962028503,
14
+ "learning_rate": 4.9868042930033434e-05,
15
+ "loss": 1.3593,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 0.005863039399624765,
20
+ "grad_norm": 0.3698488771915436,
21
+ "learning_rate": 4.972142396340391e-05,
22
+ "loss": 1.3285,
23
+ "step": 200
24
+ },
25
+ {
26
+ "epoch": 0.008794559099437148,
27
+ "grad_norm": 0.24848727881908417,
28
+ "learning_rate": 4.957480499677439e-05,
29
+ "loss": 1.324,
30
+ "step": 300
31
+ },
32
+ {
33
+ "epoch": 0.01172607879924953,
34
+ "grad_norm": 0.2648352086544037,
35
+ "learning_rate": 4.942818603014486e-05,
36
+ "loss": 1.3145,
37
+ "step": 400
38
+ },
39
+ {
40
+ "epoch": 0.014657598499061914,
41
+ "grad_norm": 0.3995356559753418,
42
+ "learning_rate": 4.928156706351534e-05,
43
+ "loss": 1.3141,
44
+ "step": 500
45
+ },
46
+ {
47
+ "epoch": 0.017589118198874296,
48
+ "grad_norm": 0.32299748063087463,
49
+ "learning_rate": 4.913494809688581e-05,
50
+ "loss": 1.3087,
51
+ "step": 600
52
+ },
53
+ {
54
+ "epoch": 0.02052063789868668,
55
+ "grad_norm": 0.33237338066101074,
56
+ "learning_rate": 4.898832913025629e-05,
57
+ "loss": 1.3071,
58
+ "step": 700
59
+ },
60
+ {
61
+ "epoch": 0.02345215759849906,
62
+ "grad_norm": 0.2716487646102905,
63
+ "learning_rate": 4.8841710163626766e-05,
64
+ "loss": 1.3048,
65
+ "step": 800
66
+ },
67
+ {
68
+ "epoch": 0.026383677298311446,
69
+ "grad_norm": 0.8654017448425293,
70
+ "learning_rate": 4.869509119699725e-05,
71
+ "loss": 1.3087,
72
+ "step": 900
73
+ },
74
+ {
75
+ "epoch": 0.02931519699812383,
76
+ "grad_norm": 0.27945375442504883,
77
+ "learning_rate": 4.854847223036773e-05,
78
+ "loss": 1.3015,
79
+ "step": 1000
80
+ },
81
+ {
82
+ "epoch": 0.03224671669793621,
83
+ "grad_norm": 0.27838173508644104,
84
+ "learning_rate": 4.84018532637382e-05,
85
+ "loss": 1.2998,
86
+ "step": 1100
87
+ },
88
+ {
89
+ "epoch": 0.03517823639774859,
90
+ "grad_norm": 0.24157749116420746,
91
+ "learning_rate": 4.8255234297108676e-05,
92
+ "loss": 1.3016,
93
+ "step": 1200
94
+ },
95
+ {
96
+ "epoch": 0.038109756097560975,
97
+ "grad_norm": 0.45793822407722473,
98
+ "learning_rate": 4.810861533047915e-05,
99
+ "loss": 1.2983,
100
+ "step": 1300
101
+ },
102
+ {
103
+ "epoch": 0.04104127579737336,
104
+ "grad_norm": 0.1312064826488495,
105
+ "learning_rate": 4.796199636384963e-05,
106
+ "loss": 1.2978,
107
+ "step": 1400
108
+ },
109
+ {
110
+ "epoch": 0.04397279549718574,
111
+ "grad_norm": 0.33062976598739624,
112
+ "learning_rate": 4.7815377397220105e-05,
113
+ "loss": 1.2972,
114
+ "step": 1500
115
+ },
116
+ {
117
+ "epoch": 0.04690431519699812,
118
+ "grad_norm": 0.29819390177726746,
119
+ "learning_rate": 4.766875843059058e-05,
120
+ "loss": 1.2945,
121
+ "step": 1600
122
+ },
123
+ {
124
+ "epoch": 0.0498358348968105,
125
+ "grad_norm": 0.3396131694316864,
126
+ "learning_rate": 4.752213946396106e-05,
127
+ "loss": 1.2921,
128
+ "step": 1700
129
+ },
130
+ {
131
+ "epoch": 0.05276735459662289,
132
+ "grad_norm": 0.3231181502342224,
133
+ "learning_rate": 4.737552049733154e-05,
134
+ "loss": 1.2932,
135
+ "step": 1800
136
+ },
137
+ {
138
+ "epoch": 0.055698874296435275,
139
+ "grad_norm": 0.4015660285949707,
140
+ "learning_rate": 4.7228901530702015e-05,
141
+ "loss": 1.2899,
142
+ "step": 1900
143
+ },
144
+ {
145
+ "epoch": 0.05863039399624766,
146
+ "grad_norm": 0.436213880777359,
147
+ "learning_rate": 4.708228256407249e-05,
148
+ "loss": 1.2906,
149
+ "step": 2000
150
+ },
151
+ {
152
+ "epoch": 0.06156191369606004,
153
+ "grad_norm": 0.3451833426952362,
154
+ "learning_rate": 4.693566359744297e-05,
155
+ "loss": 1.2884,
156
+ "step": 2100
157
+ },
158
+ {
159
+ "epoch": 0.06449343339587242,
160
+ "grad_norm": 0.41890543699264526,
161
+ "learning_rate": 4.6789044630813445e-05,
162
+ "loss": 1.2892,
163
+ "step": 2200
164
+ },
165
+ {
166
+ "epoch": 0.0674249530956848,
167
+ "grad_norm": 0.3117181062698364,
168
+ "learning_rate": 4.664242566418392e-05,
169
+ "loss": 1.2866,
170
+ "step": 2300
171
+ },
172
+ {
173
+ "epoch": 0.07035647279549719,
174
+ "grad_norm": 0.2703840136528015,
175
+ "learning_rate": 4.64958066975544e-05,
176
+ "loss": 1.2869,
177
+ "step": 2400
178
+ },
179
+ {
180
+ "epoch": 0.07328799249530957,
181
+ "grad_norm": 0.31400740146636963,
182
+ "learning_rate": 4.6349187730924874e-05,
183
+ "loss": 1.2844,
184
+ "step": 2500
185
+ }
186
+ ],
187
+ "logging_steps": 100,
188
+ "max_steps": 34112,
189
+ "num_input_tokens_seen": 0,
190
+ "num_train_epochs": 1,
191
+ "save_steps": 500,
192
+ "stateful_callbacks": {
193
+ "TrainerControl": {
194
+ "args": {
195
+ "should_epoch_stop": false,
196
+ "should_evaluate": false,
197
+ "should_log": false,
198
+ "should_save": true,
199
+ "should_training_stop": false
200
+ },
201
+ "attributes": {}
202
+ }
203
+ },
204
+ "total_flos": 2.092336939008e+16,
205
+ "train_batch_size": 36,
206
+ "trial_name": null,
207
+ "trial_params": null
208
+ }
checkpoint-2500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9591953a84ca47c12016b5607aa6af8b03d94b1b1c3e735d4e7c3645542c9a3c
3
+ size 5176