Hugging Face's logo

DNA-LLM
/
virus-pythia-4.7M-2048-cross_entropy

Safetensors
gpt_neox
Generated from Trainer
Model card Files Community
Muedi commited on
Commit
a74e31d
·
verified ·
1 Parent(s): 09776be

Training in progress, step 2000, checkpoint

Browse files
Files changed (11) hide show
  1. checkpoint-2000/config.json +30 -0
  2. checkpoint-2000/generation_config.json +6 -0
  3. checkpoint-2000/model.safetensors +3 -0
  4. checkpoint-2000/optimizer.pt +3 -0
  5. checkpoint-2000/rng_state.pth +3 -0
  6. checkpoint-2000/scheduler.pt +3 -0
  7. checkpoint-2000/special_tokens_map.json +24 -0
  8. checkpoint-2000/tokenizer.json +96 -0
  9. checkpoint-2000/tokenizer_config.json +38 -0
  10. checkpoint-2000/trainer_state.json +173 -0
  11. checkpoint-2000/training_args.bin +3 -0
checkpoint-2000/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/pythia-31m",
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": 256,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 1024,
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-2000/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-2000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5164fd9339e27953d3a0de79b1d230ecaeb124e5384a915bab97df4fad27cfc
3
+ size 18981072
checkpoint-2000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bdebca01ab26fd00f41bfc1118504a018448f5383c2bf6fb5936d76202d32db
3
+ size 38009210
checkpoint-2000/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-2000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4ac74d3cd288354ba418b08ee69f44eb2697c36fc7717f0db9e324f574ab071
3
+ size 1064
checkpoint-2000/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-2000/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-2000/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-2000/trainer_state.json ADDED
@@ -0,0 +1,173 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.07817385866166354,
5
+ "eval_steps": 500,
6
+ "global_step": 2000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.003908692933083177,
13
+ "grad_norm": 0.47716134786605835,
14
+ "learning_rate": 4.98240400406663e-05,
15
+ "loss": 1.3868,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 0.007817385866166354,
20
+ "grad_norm": 0.28900113701820374,
21
+ "learning_rate": 4.9628528974739973e-05,
22
+ "loss": 1.3348,
23
+ "step": 200
24
+ },
25
+ {
26
+ "epoch": 0.01172607879924953,
27
+ "grad_norm": 0.37652796506881714,
28
+ "learning_rate": 4.943301790881364e-05,
29
+ "loss": 1.3298,
30
+ "step": 300
31
+ },
32
+ {
33
+ "epoch": 0.015634771732332707,
34
+ "grad_norm": 0.24992702901363373,
35
+ "learning_rate": 4.923750684288731e-05,
36
+ "loss": 1.3309,
37
+ "step": 400
38
+ },
39
+ {
40
+ "epoch": 0.019543464665415886,
41
+ "grad_norm": 0.3237004280090332,
42
+ "learning_rate": 4.904199577696098e-05,
43
+ "loss": 1.3228,
44
+ "step": 500
45
+ },
46
+ {
47
+ "epoch": 0.02345215759849906,
48
+ "grad_norm": 0.259011447429657,
49
+ "learning_rate": 4.884648471103465e-05,
50
+ "loss": 1.3166,
51
+ "step": 600
52
+ },
53
+ {
54
+ "epoch": 0.02736085053158224,
55
+ "grad_norm": 0.34121841192245483,
56
+ "learning_rate": 4.8650973645108314e-05,
57
+ "loss": 1.3145,
58
+ "step": 700
59
+ },
60
+ {
61
+ "epoch": 0.031269543464665414,
62
+ "grad_norm": 0.41398781538009644,
63
+ "learning_rate": 4.845546257918198e-05,
64
+ "loss": 1.3081,
65
+ "step": 800
66
+ },
67
+ {
68
+ "epoch": 0.03517823639774859,
69
+ "grad_norm": 0.4289904832839966,
70
+ "learning_rate": 4.825995151325565e-05,
71
+ "loss": 1.3073,
72
+ "step": 900
73
+ },
74
+ {
75
+ "epoch": 0.03908692933083177,
76
+ "grad_norm": 0.21226634085178375,
77
+ "learning_rate": 4.8064440447329324e-05,
78
+ "loss": 1.3057,
79
+ "step": 1000
80
+ },
81
+ {
82
+ "epoch": 0.04299562226391495,
83
+ "grad_norm": 0.2929254174232483,
84
+ "learning_rate": 4.786892938140299e-05,
85
+ "loss": 1.3034,
86
+ "step": 1100
87
+ },
88
+ {
89
+ "epoch": 0.04690431519699812,
90
+ "grad_norm": 0.22025109827518463,
91
+ "learning_rate": 4.767341831547666e-05,
92
+ "loss": 1.3048,
93
+ "step": 1200
94
+ },
95
+ {
96
+ "epoch": 0.0508130081300813,
97
+ "grad_norm": 0.36455097794532776,
98
+ "learning_rate": 4.747790724955033e-05,
99
+ "loss": 1.3028,
100
+ "step": 1300
101
+ },
102
+ {
103
+ "epoch": 0.05472170106316448,
104
+ "grad_norm": 0.24527208507061005,
105
+ "learning_rate": 4.728239618362399e-05,
106
+ "loss": 1.2996,
107
+ "step": 1400
108
+ },
109
+ {
110
+ "epoch": 0.05863039399624766,
111
+ "grad_norm": 0.33187615871429443,
112
+ "learning_rate": 4.7086885117697664e-05,
113
+ "loss": 1.3001,
114
+ "step": 1500
115
+ },
116
+ {
117
+ "epoch": 0.06253908692933083,
118
+ "grad_norm": 0.502117931842804,
119
+ "learning_rate": 4.689137405177133e-05,
120
+ "loss": 1.2954,
121
+ "step": 1600
122
+ },
123
+ {
124
+ "epoch": 0.06644777986241401,
125
+ "grad_norm": 0.289112389087677,
126
+ "learning_rate": 4.6695862985845e-05,
127
+ "loss": 1.2969,
128
+ "step": 1700
129
+ },
130
+ {
131
+ "epoch": 0.07035647279549719,
132
+ "grad_norm": 0.24350133538246155,
133
+ "learning_rate": 4.6500351919918674e-05,
134
+ "loss": 1.2929,
135
+ "step": 1800
136
+ },
137
+ {
138
+ "epoch": 0.07426516572858036,
139
+ "grad_norm": 0.2194579690694809,
140
+ "learning_rate": 4.630484085399234e-05,
141
+ "loss": 1.2913,
142
+ "step": 1900
143
+ },
144
+ {
145
+ "epoch": 0.07817385866166354,
146
+ "grad_norm": 0.3578532636165619,
147
+ "learning_rate": 4.6109329788066005e-05,
148
+ "loss": 1.2946,
149
+ "step": 2000
150
+ }
151
+ ],
152
+ "logging_steps": 100,
153
+ "max_steps": 25584,
154
+ "num_input_tokens_seen": 0,
155
+ "num_train_epochs": 1,
156
+ "save_steps": 500,
157
+ "stateful_callbacks": {
158
+ "TrainerControl": {
159
+ "args": {
160
+ "should_epoch_stop": false,
161
+ "should_evaluate": false,
162
+ "should_log": false,
163
+ "should_save": true,
164
+ "should_training_stop": false
165
+ },
166
+ "attributes": {}
167
+ }
168
+ },
169
+ "total_flos": 5592852725760000.0,
170
+ "train_batch_size": 48,
171
+ "trial_name": null,
172
+ "trial_params": null
173
+ }
checkpoint-2000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:805b2d71d9e6f4f633c9bcb1e0cb62d12ec75a69c6a27204388e915e32239763
3
+ size 5176