Hugging Face's logo

pszemraj
/
tFINE-850m-24x24-1024ctx

Text2Text Generation
Transformers
Safetensors
English
t5
text-generation-inference
Inference Endpoints
Model card Files Community
pszemraj commited on
Commit
f973cec
•
1 Parent(s): 4296a79

Upload folder using huggingface_hub

Browse files
Files changed (31) hide show
  1. .gitattributes +1 -0
  2. checkpoints/.hydra/config.yaml +50 -0
  3. checkpoints/.hydra/hydra.yaml +154 -0
  4. checkpoints/.hydra/overrides.yaml +1 -0
  5. checkpoints/checkpoint-pt-10000/model.safetensors +3 -0
  6. checkpoints/checkpoint-pt-12500/model.safetensors +3 -0
  7. checkpoints/checkpoint-pt-15000/model.safetensors +3 -0
  8. checkpoints/checkpoint-pt-17500/model.safetensors +3 -0
  9. checkpoints/checkpoint-pt-20000/model.safetensors +3 -0
  10. checkpoints/checkpoint-pt-20001/model.safetensors +3 -0
  11. checkpoints/checkpoint-pt-2500/model.safetensors +3 -0
  12. checkpoints/checkpoint-pt-5000/model.safetensors +3 -0
  13. checkpoints/checkpoint-pt-7500/model.safetensors +3 -0
  14. checkpoints/config.json +31 -0
  15. checkpoints/main.log +0 -0
  16. checkpoints/tokenizer/added_tokens.json +102 -0
  17. checkpoints/tokenizer/special_tokens_map.json +132 -0
  18. checkpoints/tokenizer/tokenizer.json +0 -0
  19. checkpoints/tokenizer/tokenizer.model +3 -0
  20. checkpoints/tokenizer/tokenizer_config.json +952 -0
  21. checkpoints/wandb/debug-internal.log +25 -0
  22. checkpoints/wandb/debug.log +34 -0
  23. checkpoints/wandb/run-20240926_051952-6q92wn34/files/config.yaml +112 -0
  24. checkpoints/wandb/run-20240926_051952-6q92wn34/files/output.log +0 -0
  25. checkpoints/wandb/run-20240926_051952-6q92wn34/files/requirements.txt +201 -0
  26. checkpoints/wandb/run-20240926_051952-6q92wn34/files/wandb-metadata.json +41 -0
  27. checkpoints/wandb/run-20240926_051952-6q92wn34/files/wandb-summary.json +1 -0
  28. checkpoints/wandb/run-20240926_051952-6q92wn34/logs/debug-core.log +14 -0
  29. checkpoints/wandb/run-20240926_051952-6q92wn34/logs/debug-internal.log +25 -0
  30. checkpoints/wandb/run-20240926_051952-6q92wn34/logs/debug.log +34 -0
  31. checkpoints/wandb/run-20240926_051952-6q92wn34/run-6q92wn34.wandb +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ checkpoints/wandb/run-20240926_051952-6q92wn34/run-6q92wn34.wandb filter=lfs diff=lfs merge=lfs -text
checkpoints/.hydra/config.yaml ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ mode: pt
2
+ device: gpu
3
+ precision: bf16
4
+ eval_only: false
5
+ predict_only: false
6
+ seed: 34534
7
+ model:
8
+ klass: hf_t5
9
+ name: pszemraj/tFINE-850m-24x24-512ctx
10
+ overwrite:
11
+ dropout_rate: 0.0
12
+ checkpoint_path: ''
13
+ random_init: false
14
+ compile: true
15
+ tokenizer:
16
+ name: BEE-spoke-data/slimpajama_tok-48128-BPE-forT5
17
+ data:
18
+ input_length: 1024
19
+ mlm_probability: 0.15
20
+ mean_noise_span_length: 3.0
21
+ num_workers: 16
22
+ optim:
23
+ name: adamwscale
24
+ base_lr: 0.01
25
+ batch_size: 128
26
+ total_steps: 20000
27
+ epochs: -1
28
+ warmup_steps: 5000
29
+ lr_scheduler: cosine
30
+ weight_decay: 0.0
31
+ grad_clip: 1.0
32
+ grad_acc: 8
33
+ final_cosine: 2.0e-05
34
+ eval:
35
+ every_steps: 1000000000
36
+ steps: 500
37
+ checkpoint:
38
+ every_steps: 2500
39
+ logging:
40
+ use_wandb: true
41
+ wandb_config:
42
+ project: nanoT5
43
+ entity: pszemraj
44
+ tags:
45
+ - 24x24
46
+ - '1024'
47
+ mode: online
48
+ every_steps: 25
49
+ grad_l2: true
50
+ weights_l2: true
checkpoints/.hydra/hydra.yaml ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ hydra:
2
+ run:
3
+ dir: outputs/${now:%Y-%m-%d}/${now:%H-%M-%S}
4
+ sweep:
5
+ dir: multirun/${now:%Y-%m-%d}/${now:%H-%M-%S}
6
+ subdir: ${hydra.job.num}
7
+ launcher:
8
+ _target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher
9
+ sweeper:
10
+ _target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper
11
+ max_batch_size: null
12
+ params: null
13
+ help:
14
+ app_name: ${hydra.job.name}
15
+ header: '${hydra.help.app_name} is powered by Hydra.
16
+
17
+ '
18
+ footer: 'Powered by Hydra (https://hydra.cc)
19
+
20
+ Use --hydra-help to view Hydra specific help
21
+
22
+ '
23
+ template: '${hydra.help.header}
24
+
25
+ == Configuration groups ==
26
+
27
+ Compose your configuration from those groups (group=option)
28
+
29
+
30
+ $APP_CONFIG_GROUPS
31
+
32
+
33
+ == Config ==
34
+
35
+ Override anything in the config (foo.bar=value)
36
+
37
+
38
+ $CONFIG
39
+
40
+
41
+ ${hydra.help.footer}
42
+
43
+ '
44
+ hydra_help:
45
+ template: 'Hydra (${hydra.runtime.version})
46
+
47
+ See https://hydra.cc for more info.
48
+
49
+
50
+ == Flags ==
51
+
52
+ $FLAGS_HELP
53
+
54
+
55
+ == Configuration groups ==
56
+
57
+ Compose your configuration from those groups (For example, append hydra/job_logging=disabled
58
+ to command line)
59
+
60
+
61
+ $HYDRA_CONFIG_GROUPS
62
+
63
+
64
+ Use ''--cfg hydra'' to Show the Hydra config.
65
+
66
+ '
67
+ hydra_help: ???
68
+ hydra_logging:
69
+ version: 1
70
+ formatters:
71
+ simple:
72
+ format: '[%(asctime)s][HYDRA] %(message)s'
73
+ handlers:
74
+ console:
75
+ class: logging.StreamHandler
76
+ formatter: simple
77
+ stream: ext://sys.stdout
78
+ root:
79
+ level: INFO
80
+ handlers:
81
+ - console
82
+ loggers:
83
+ logging_example:
84
+ level: DEBUG
85
+ disable_existing_loggers: false
86
+ job_logging:
87
+ version: 1
88
+ formatters:
89
+ simple:
90
+ format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s'
91
+ handlers:
92
+ console:
93
+ class: logging.StreamHandler
94
+ formatter: simple
95
+ stream: ext://sys.stdout
96
+ file:
97
+ class: logging.FileHandler
98
+ formatter: simple
99
+ filename: ${hydra.runtime.output_dir}/${hydra.job.name}.log
100
+ root:
101
+ level: INFO
102
+ handlers:
103
+ - console
104
+ - file
105
+ disable_existing_loggers: false
106
+ env: {}
107
+ mode: RUN
108
+ searchpath: []
109
+ callbacks: {}
110
+ output_subdir: .hydra
111
+ overrides:
112
+ hydra:
113
+ - hydra.mode=RUN
114
+ task: []
115
+ job:
116
+ name: main
117
+ chdir: null
118
+ override_dirname: ''
119
+ id: ???
120
+ num: ???
121
+ config_name: default
122
+ env_set: {}
123
+ env_copy: []
124
+ config:
125
+ override_dirname:
126
+ kv_sep: '='
127
+ item_sep: ','
128
+ exclude_keys: []
129
+ runtime:
130
+ version: 1.3.2
131
+ version_base: '1.1'
132
+ cwd: /workspace/nanoT5
133
+ config_sources:
134
+ - path: hydra.conf
135
+ schema: pkg
136
+ provider: hydra
137
+ - path: /workspace/nanoT5/nanoT5/configs
138
+ schema: file
139
+ provider: main
140
+ - path: ''
141
+ schema: structured
142
+ provider: schema
143
+ output_dir: /workspace/nanoT5/outputs/2024-09-26/05-19-51
144
+ choices:
145
+ hydra/env: default
146
+ hydra/callbacks: null
147
+ hydra/job_logging: default
148
+ hydra/hydra_logging: default
149
+ hydra/hydra_help: default
150
+ hydra/help: default
151
+ hydra/sweeper: basic
152
+ hydra/launcher: basic
153
+ hydra/output: default
154
+ verbose: false
checkpoints/.hydra/overrides.yaml ADDED
@@ -0,0 +1 @@
 
 
1
+ []
checkpoints/checkpoint-pt-10000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dc80b7f7dc93e9640f9d25b3a2b406eeefceab66653bca9273e544f085530cc
3
+ size 3415786400
checkpoints/checkpoint-pt-12500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ce051817f73f9ae70447b8ea14a661195658d18e6d9e6402585b178dbb60382
3
+ size 3415786400
checkpoints/checkpoint-pt-15000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7658fc62d76a3b2392c19e234a68164e836868fe9f36d0031b789a570f5ef30
3
+ size 3415786400
checkpoints/checkpoint-pt-17500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3b0a39ed1bd0bf09e259cae11059cdd7701379cefd79b48e4ff0c3325b2c1bd
3
+ size 3415786400
checkpoints/checkpoint-pt-20000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a0f8fff6dbdebc6b3e8d696d4f06932a7acd4d5bf597f025912c783400430bc
3
+ size 3415786400
checkpoints/checkpoint-pt-20001/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a0f8fff6dbdebc6b3e8d696d4f06932a7acd4d5bf597f025912c783400430bc
3
+ size 3415786400
checkpoints/checkpoint-pt-2500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05d2ec8dc4c586bc862b3602a40179ba7ed4301797821f152fdec401aa6a90b9
3
+ size 3415786400
checkpoints/checkpoint-pt-5000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d902fb51c5fb95eb7f0ad4e45e62d3611a2c089266e69f9981a45e12efff793d
3
+ size 3415786400
checkpoints/checkpoint-pt-7500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab9a1c40ef24190daf32bcb71ea76192bec0eaf8257c8ea0a58230ad0cdca7e0
3
+ size 3415786400
checkpoints/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "pszemraj/tFINE-850m-24x24-512ctx",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 3072,
8
+ "d_kv": 64,
9
+ "d_model": 1024,
10
+ "decoder_start_token_id": 3,
11
+ "dense_act_fn": "silu",
12
+ "dropout_rate": 0.0,
13
+ "eos_token_id": 2,
14
+ "feed_forward_proj": "gated-silu",
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": true,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "t5",
20
+ "num_decoder_layers": 24,
21
+ "num_heads": 16,
22
+ "num_layers": 24,
23
+ "output_past": true,
24
+ "pad_token_id": 3,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 48,
27
+ "tie_word_embeddings": false,
28
+ "transformers_version": "4.44.2",
29
+ "use_cache": true,
30
+ "vocab_size": 48256
31
+ }
checkpoints/main.log ADDED
The diff for this file is too large to render. See raw diff
 
checkpoints/tokenizer/added_tokens.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<extra_id_0>": 48128,
3
+ "<extra_id_10>": 48138,
4
+ "<extra_id_11>": 48139,
5
+ "<extra_id_12>": 48140,
6
+ "<extra_id_13>": 48141,
7
+ "<extra_id_14>": 48142,
8
+ "<extra_id_15>": 48143,
9
+ "<extra_id_16>": 48144,
10
+ "<extra_id_17>": 48145,
11
+ "<extra_id_18>": 48146,
12
+ "<extra_id_19>": 48147,
13
+ "<extra_id_1>": 48129,
14
+ "<extra_id_20>": 48148,
15
+ "<extra_id_21>": 48149,
16
+ "<extra_id_22>": 48150,
17
+ "<extra_id_23>": 48151,
18
+ "<extra_id_24>": 48152,
19
+ "<extra_id_25>": 48153,
20
+ "<extra_id_26>": 48154,
21
+ "<extra_id_27>": 48155,
22
+ "<extra_id_28>": 48156,
23
+ "<extra_id_29>": 48157,
24
+ "<extra_id_2>": 48130,
25
+ "<extra_id_30>": 48158,
26
+ "<extra_id_31>": 48159,
27
+ "<extra_id_32>": 48160,
28
+ "<extra_id_33>": 48161,
29
+ "<extra_id_34>": 48162,
30
+ "<extra_id_35>": 48163,
31
+ "<extra_id_36>": 48164,
32
+ "<extra_id_37>": 48165,
33
+ "<extra_id_38>": 48166,
34
+ "<extra_id_39>": 48167,
35
+ "<extra_id_3>": 48131,
36
+ "<extra_id_40>": 48168,
37
+ "<extra_id_41>": 48169,
38
+ "<extra_id_42>": 48170,
39
+ "<extra_id_43>": 48171,
40
+ "<extra_id_44>": 48172,
41
+ "<extra_id_45>": 48173,
42
+ "<extra_id_46>": 48174,
43
+ "<extra_id_47>": 48175,
44
+ "<extra_id_48>": 48176,
45
+ "<extra_id_49>": 48177,
46
+ "<extra_id_4>": 48132,
47
+ "<extra_id_50>": 48178,
48
+ "<extra_id_51>": 48179,
49
+ "<extra_id_52>": 48180,
50
+ "<extra_id_53>": 48181,
51
+ "<extra_id_54>": 48182,
52
+ "<extra_id_55>": 48183,
53
+ "<extra_id_56>": 48184,
54
+ "<extra_id_57>": 48185,
55
+ "<extra_id_58>": 48186,
56
+ "<extra_id_59>": 48187,
57
+ "<extra_id_5>": 48133,
58
+ "<extra_id_60>": 48188,
59
+ "<extra_id_61>": 48189,
60
+ "<extra_id_62>": 48190,
61
+ "<extra_id_63>": 48191,
62
+ "<extra_id_64>": 48192,
63
+ "<extra_id_65>": 48193,
64
+ "<extra_id_66>": 48194,
65
+ "<extra_id_67>": 48195,
66
+ "<extra_id_68>": 48196,
67
+ "<extra_id_69>": 48197,
68
+ "<extra_id_6>": 48134,
69
+ "<extra_id_70>": 48198,
70
+ "<extra_id_71>": 48199,
71
+ "<extra_id_72>": 48200,
72
+ "<extra_id_73>": 48201,
73
+ "<extra_id_74>": 48202,
74
+ "<extra_id_75>": 48203,
75
+ "<extra_id_76>": 48204,
76
+ "<extra_id_77>": 48205,
77
+ "<extra_id_78>": 48206,
78
+ "<extra_id_79>": 48207,
79
+ "<extra_id_7>": 48135,
80
+ "<extra_id_80>": 48208,
81
+ "<extra_id_81>": 48209,
82
+ "<extra_id_82>": 48210,
83
+ "<extra_id_83>": 48211,
84
+ "<extra_id_84>": 48212,
85
+ "<extra_id_85>": 48213,
86
+ "<extra_id_86>": 48214,
87
+ "<extra_id_87>": 48215,
88
+ "<extra_id_88>": 48216,
89
+ "<extra_id_89>": 48217,
90
+ "<extra_id_8>": 48136,
91
+ "<extra_id_90>": 48218,
92
+ "<extra_id_91>": 48219,
93
+ "<extra_id_92>": 48220,
94
+ "<extra_id_93>": 48221,
95
+ "<extra_id_94>": 48222,
96
+ "<extra_id_95>": 48223,
97
+ "<extra_id_96>": 48224,
98
+ "<extra_id_97>": 48225,
99
+ "<extra_id_98>": 48226,
100
+ "<extra_id_99>": 48227,
101
+ "<extra_id_9>": 48137
102
+ }
checkpoints/tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,132 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "bos_token": {
105
+ "content": "<s>",
106
+ "lstrip": false,
107
+ "normalized": true,
108
+ "rstrip": false,
109
+ "single_word": false
110
+ },
111
+ "eos_token": {
112
+ "content": "</s>",
113
+ "lstrip": false,
114
+ "normalized": true,
115
+ "rstrip": false,
116
+ "single_word": false
117
+ },
118
+ "pad_token": {
119
+ "content": "<pad>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false
124
+ },
125
+ "unk_token": {
126
+ "content": "<unk>",
127
+ "lstrip": false,
128
+ "normalized": true,
129
+ "rstrip": false,
130
+ "single_word": false
131
+ }
132
+ }
checkpoints/tokenizer/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoints/tokenizer/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:165515d67d17852d3e7c30ec22d7a745330f2cba264f40c3ea9380eddf84396f
3
+ size 1042483
checkpoints/tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,952 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": true,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "3": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "48128": {
39
+ "content": "<extra_id_0>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "48129": {
47
+ "content": "<extra_id_1>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "48130": {
55
+ "content": "<extra_id_2>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "48131": {
63
+ "content": "<extra_id_3>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "48132": {
71
+ "content": "<extra_id_4>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "48133": {
79
+ "content": "<extra_id_5>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "48134": {
87
+ "content": "<extra_id_6>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "48135": {
95
+ "content": "<extra_id_7>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "48136": {
103
+ "content": "<extra_id_8>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "48137": {
111
+ "content": "<extra_id_9>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "48138": {
119
+ "content": "<extra_id_10>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": true
125
+ },
126
+ "48139": {
127
+ "content": "<extra_id_11>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": true
133
+ },
134
+ "48140": {
135
+ "content": "<extra_id_12>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": true
141
+ },
142
+ "48141": {
143
+ "content": "<extra_id_13>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": true
149
+ },
150
+ "48142": {
151
+ "content": "<extra_id_14>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": true
157
+ },
158
+ "48143": {
159
+ "content": "<extra_id_15>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": true
165
+ },
166
+ "48144": {
167
+ "content": "<extra_id_16>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": true
173
+ },
174
+ "48145": {
175
+ "content": "<extra_id_17>",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": true
181
+ },
182
+ "48146": {
183
+ "content": "<extra_id_18>",
184
+ "lstrip": false,
185
+ "normalized": false,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": true
189
+ },
190
+ "48147": {
191
+ "content": "<extra_id_19>",
192
+ "lstrip": false,
193
+ "normalized": false,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": true
197
+ },
198
+ "48148": {
199
+ "content": "<extra_id_20>",
200
+ "lstrip": false,
201
+ "normalized": false,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": true
205
+ },
206
+ "48149": {
207
+ "content": "<extra_id_21>",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": false,
211
+ "single_word": false,
212
+ "special": true
213
+ },
214
+ "48150": {
215
+ "content": "<extra_id_22>",
216
+ "lstrip": false,
217
+ "normalized": false,
218
+ "rstrip": false,
219
+ "single_word": false,
220
+ "special": true
221
+ },
222
+ "48151": {
223
+ "content": "<extra_id_23>",
224
+ "lstrip": false,
225
+ "normalized": false,
226
+ "rstrip": false,
227
+ "single_word": false,
228
+ "special": true
229
+ },
230
+ "48152": {
231
+ "content": "<extra_id_24>",
232
+ "lstrip": false,
233
+ "normalized": false,
234
+ "rstrip": false,
235
+ "single_word": false,
236
+ "special": true
237
+ },
238
+ "48153": {
239
+ "content": "<extra_id_25>",
240
+ "lstrip": false,
241
+ "normalized": false,
242
+ "rstrip": false,
243
+ "single_word": false,
244
+ "special": true
245
+ },
246
+ "48154": {
247
+ "content": "<extra_id_26>",
248
+ "lstrip": false,
249
+ "normalized": false,
250
+ "rstrip": false,
251
+ "single_word": false,
252
+ "special": true
253
+ },
254
+ "48155": {
255
+ "content": "<extra_id_27>",
256
+ "lstrip": false,
257
+ "normalized": false,
258
+ "rstrip": false,
259
+ "single_word": false,
260
+ "special": true
261
+ },
262
+ "48156": {
263
+ "content": "<extra_id_28>",
264
+ "lstrip": false,
265
+ "normalized": false,
266
+ "rstrip": false,
267
+ "single_word": false,
268
+ "special": true
269
+ },
270
+ "48157": {
271
+ "content": "<extra_id_29>",
272
+ "lstrip": false,
273
+ "normalized": false,
274
+ "rstrip": false,
275
+ "single_word": false,
276
+ "special": true
277
+ },
278
+ "48158": {
279
+ "content": "<extra_id_30>",
280
+ "lstrip": false,
281
+ "normalized": false,
282
+ "rstrip": false,
283
+ "single_word": false,
284
+ "special": true
285
+ },
286
+ "48159": {
287
+ "content": "<extra_id_31>",
288
+ "lstrip": false,
289
+ "normalized": false,
290
+ "rstrip": false,
291
+ "single_word": false,
292
+ "special": true
293
+ },
294
+ "48160": {
295
+ "content": "<extra_id_32>",
296
+ "lstrip": false,
297
+ "normalized": false,
298
+ "rstrip": false,
299
+ "single_word": false,
300
+ "special": true
301
+ },
302
+ "48161": {
303
+ "content": "<extra_id_33>",
304
+ "lstrip": false,
305
+ "normalized": false,
306
+ "rstrip": false,
307
+ "single_word": false,
308
+ "special": true
309
+ },
310
+ "48162": {
311
+ "content": "<extra_id_34>",
312
+ "lstrip": false,
313
+ "normalized": false,
314
+ "rstrip": false,
315
+ "single_word": false,
316
+ "special": true
317
+ },
318
+ "48163": {
319
+ "content": "<extra_id_35>",
320
+ "lstrip": false,
321
+ "normalized": false,
322
+ "rstrip": false,
323
+ "single_word": false,
324
+ "special": true
325
+ },
326
+ "48164": {
327
+ "content": "<extra_id_36>",
328
+ "lstrip": false,
329
+ "normalized": false,
330
+ "rstrip": false,
331
+ "single_word": false,
332
+ "special": true
333
+ },
334
+ "48165": {
335
+ "content": "<extra_id_37>",
336
+ "lstrip": false,
337
+ "normalized": false,
338
+ "rstrip": false,
339
+ "single_word": false,
340
+ "special": true
341
+ },
342
+ "48166": {
343
+ "content": "<extra_id_38>",
344
+ "lstrip": false,
345
+ "normalized": false,
346
+ "rstrip": false,
347
+ "single_word": false,
348
+ "special": true
349
+ },
350
+ "48167": {
351
+ "content": "<extra_id_39>",
352
+ "lstrip": false,
353
+ "normalized": false,
354
+ "rstrip": false,
355
+ "single_word": false,
356
+ "special": true
357
+ },
358
+ "48168": {
359
+ "content": "<extra_id_40>",
360
+ "lstrip": false,
361
+ "normalized": false,
362
+ "rstrip": false,
363
+ "single_word": false,
364
+ "special": true
365
+ },
366
+ "48169": {
367
+ "content": "<extra_id_41>",
368
+ "lstrip": false,
369
+ "normalized": false,
370
+ "rstrip": false,
371
+ "single_word": false,
372
+ "special": true
373
+ },
374
+ "48170": {
375
+ "content": "<extra_id_42>",
376
+ "lstrip": false,
377
+ "normalized": false,
378
+ "rstrip": false,
379
+ "single_word": false,
380
+ "special": true
381
+ },
382
+ "48171": {
383
+ "content": "<extra_id_43>",
384
+ "lstrip": false,
385
+ "normalized": false,
386
+ "rstrip": false,
387
+ "single_word": false,
388
+ "special": true
389
+ },
390
+ "48172": {
391
+ "content": "<extra_id_44>",
392
+ "lstrip": false,
393
+ "normalized": false,
394
+ "rstrip": false,
395
+ "single_word": false,
396
+ "special": true
397
+ },
398
+ "48173": {
399
+ "content": "<extra_id_45>",
400
+ "lstrip": false,
401
+ "normalized": false,
402
+ "rstrip": false,
403
+ "single_word": false,
404
+ "special": true
405
+ },
406
+ "48174": {
407
+ "content": "<extra_id_46>",
408
+ "lstrip": false,
409
+ "normalized": false,
410
+ "rstrip": false,
411
+ "single_word": false,
412
+ "special": true
413
+ },
414
+ "48175": {
415
+ "content": "<extra_id_47>",
416
+ "lstrip": false,
417
+ "normalized": false,
418
+ "rstrip": false,
419
+ "single_word": false,
420
+ "special": true
421
+ },
422
+ "48176": {
423
+ "content": "<extra_id_48>",
424
+ "lstrip": false,
425
+ "normalized": false,
426
+ "rstrip": false,
427
+ "single_word": false,
428
+ "special": true
429
+ },
430
+ "48177": {
431
+ "content": "<extra_id_49>",
432
+ "lstrip": false,
433
+ "normalized": false,
434
+ "rstrip": false,
435
+ "single_word": false,
436
+ "special": true
437
+ },
438
+ "48178": {
439
+ "content": "<extra_id_50>",
440
+ "lstrip": false,
441
+ "normalized": false,
442
+ "rstrip": false,
443
+ "single_word": false,
444
+ "special": true
445
+ },
446
+ "48179": {
447
+ "content": "<extra_id_51>",
448
+ "lstrip": false,
449
+ "normalized": false,
450
+ "rstrip": false,
451
+ "single_word": false,
452
+ "special": true
453
+ },
454
+ "48180": {
455
+ "content": "<extra_id_52>",
456
+ "lstrip": false,
457
+ "normalized": false,
458
+ "rstrip": false,
459
+ "single_word": false,
460
+ "special": true
461
+ },
462
+ "48181": {
463
+ "content": "<extra_id_53>",
464
+ "lstrip": false,
465
+ "normalized": false,
466
+ "rstrip": false,
467
+ "single_word": false,
468
+ "special": true
469
+ },
470
+ "48182": {
471
+ "content": "<extra_id_54>",
472
+ "lstrip": false,
473
+ "normalized": false,
474
+ "rstrip": false,
475
+ "single_word": false,
476
+ "special": true
477
+ },
478
+ "48183": {
479
+ "content": "<extra_id_55>",
480
+ "lstrip": false,
481
+ "normalized": false,
482
+ "rstrip": false,
483
+ "single_word": false,
484
+ "special": true
485
+ },
486
+ "48184": {
487
+ "content": "<extra_id_56>",
488
+ "lstrip": false,
489
+ "normalized": false,
490
+ "rstrip": false,
491
+ "single_word": false,
492
+ "special": true
493
+ },
494
+ "48185": {
495
+ "content": "<extra_id_57>",
496
+ "lstrip": false,
497
+ "normalized": false,
498
+ "rstrip": false,
499
+ "single_word": false,
500
+ "special": true
501
+ },
502
+ "48186": {
503
+ "content": "<extra_id_58>",
504
+ "lstrip": false,
505
+ "normalized": false,
506
+ "rstrip": false,
507
+ "single_word": false,
508
+ "special": true
509
+ },
510
+ "48187": {
511
+ "content": "<extra_id_59>",
512
+ "lstrip": false,
513
+ "normalized": false,
514
+ "rstrip": false,
515
+ "single_word": false,
516
+ "special": true
517
+ },
518
+ "48188": {
519
+ "content": "<extra_id_60>",
520
+ "lstrip": false,
521
+ "normalized": false,
522
+ "rstrip": false,
523
+ "single_word": false,
524
+ "special": true
525
+ },
526
+ "48189": {
527
+ "content": "<extra_id_61>",
528
+ "lstrip": false,
529
+ "normalized": false,
530
+ "rstrip": false,
531
+ "single_word": false,
532
+ "special": true
533
+ },
534
+ "48190": {
535
+ "content": "<extra_id_62>",
536
+ "lstrip": false,
537
+ "normalized": false,
538
+ "rstrip": false,
539
+ "single_word": false,
540
+ "special": true
541
+ },
542
+ "48191": {
543
+ "content": "<extra_id_63>",
544
+ "lstrip": false,
545
+ "normalized": false,
546
+ "rstrip": false,
547
+ "single_word": false,
548
+ "special": true
549
+ },
550
+ "48192": {
551
+ "content": "<extra_id_64>",
552
+ "lstrip": false,
553
+ "normalized": false,
554
+ "rstrip": false,
555
+ "single_word": false,
556
+ "special": true
557
+ },
558
+ "48193": {
559
+ "content": "<extra_id_65>",
560
+ "lstrip": false,
561
+ "normalized": false,
562
+ "rstrip": false,
563
+ "single_word": false,
564
+ "special": true
565
+ },
566
+ "48194": {
567
+ "content": "<extra_id_66>",
568
+ "lstrip": false,
569
+ "normalized": false,
570
+ "rstrip": false,
571
+ "single_word": false,
572
+ "special": true
573
+ },
574
+ "48195": {
575
+ "content": "<extra_id_67>",
576
+ "lstrip": false,
577
+ "normalized": false,
578
+ "rstrip": false,
579
+ "single_word": false,
580
+ "special": true
581
+ },
582
+ "48196": {
583
+ "content": "<extra_id_68>",
584
+ "lstrip": false,
585
+ "normalized": false,
586
+ "rstrip": false,
587
+ "single_word": false,
588
+ "special": true
589
+ },
590
+ "48197": {
591
+ "content": "<extra_id_69>",
592
+ "lstrip": false,
593
+ "normalized": false,
594
+ "rstrip": false,
595
+ "single_word": false,
596
+ "special": true
597
+ },
598
+ "48198": {
599
+ "content": "<extra_id_70>",
600
+ "lstrip": false,
601
+ "normalized": false,
602
+ "rstrip": false,
603
+ "single_word": false,
604
+ "special": true
605
+ },
606
+ "48199": {
607
+ "content": "<extra_id_71>",
608
+ "lstrip": false,
609
+ "normalized": false,
610
+ "rstrip": false,
611
+ "single_word": false,
612
+ "special": true
613
+ },
614
+ "48200": {
615
+ "content": "<extra_id_72>",
616
+ "lstrip": false,
617
+ "normalized": false,
618
+ "rstrip": false,
619
+ "single_word": false,
620
+ "special": true
621
+ },
622
+ "48201": {
623
+ "content": "<extra_id_73>",
624
+ "lstrip": false,
625
+ "normalized": false,
626
+ "rstrip": false,
627
+ "single_word": false,
628
+ "special": true
629
+ },
630
+ "48202": {
631
+ "content": "<extra_id_74>",
632
+ "lstrip": false,
633
+ "normalized": false,
634
+ "rstrip": false,
635
+ "single_word": false,
636
+ "special": true
637
+ },
638
+ "48203": {
639
+ "content": "<extra_id_75>",
640
+ "lstrip": false,
641
+ "normalized": false,
642
+ "rstrip": false,
643
+ "single_word": false,
644
+ "special": true
645
+ },
646
+ "48204": {
647
+ "content": "<extra_id_76>",
648
+ "lstrip": false,
649
+ "normalized": false,
650
+ "rstrip": false,
651
+ "single_word": false,
652
+ "special": true
653
+ },
654
+ "48205": {
655
+ "content": "<extra_id_77>",
656
+ "lstrip": false,
657
+ "normalized": false,
658
+ "rstrip": false,
659
+ "single_word": false,
660
+ "special": true
661
+ },
662
+ "48206": {
663
+ "content": "<extra_id_78>",
664
+ "lstrip": false,
665
+ "normalized": false,
666
+ "rstrip": false,
667
+ "single_word": false,
668
+ "special": true
669
+ },
670
+ "48207": {
671
+ "content": "<extra_id_79>",
672
+ "lstrip": false,
673
+ "normalized": false,
674
+ "rstrip": false,
675
+ "single_word": false,
676
+ "special": true
677
+ },
678
+ "48208": {
679
+ "content": "<extra_id_80>",
680
+ "lstrip": false,
681
+ "normalized": false,
682
+ "rstrip": false,
683
+ "single_word": false,
684
+ "special": true
685
+ },
686
+ "48209": {
687
+ "content": "<extra_id_81>",
688
+ "lstrip": false,
689
+ "normalized": false,
690
+ "rstrip": false,
691
+ "single_word": false,
692
+ "special": true
693
+ },
694
+ "48210": {
695
+ "content": "<extra_id_82>",
696
+ "lstrip": false,
697
+ "normalized": false,
698
+ "rstrip": false,
699
+ "single_word": false,
700
+ "special": true
701
+ },
702
+ "48211": {
703
+ "content": "<extra_id_83>",
704
+ "lstrip": false,
705
+ "normalized": false,
706
+ "rstrip": false,
707
+ "single_word": false,
708
+ "special": true
709
+ },
710
+ "48212": {
711
+ "content": "<extra_id_84>",
712
+ "lstrip": false,
713
+ "normalized": false,
714
+ "rstrip": false,
715
+ "single_word": false,
716
+ "special": true
717
+ },
718
+ "48213": {
719
+ "content": "<extra_id_85>",
720
+ "lstrip": false,
721
+ "normalized": false,
722
+ "rstrip": false,
723
+ "single_word": false,
724
+ "special": true
725
+ },
726
+ "48214": {
727
+ "content": "<extra_id_86>",
728
+ "lstrip": false,
729
+ "normalized": false,
730
+ "rstrip": false,
731
+ "single_word": false,
732
+ "special": true
733
+ },
734
+ "48215": {
735
+ "content": "<extra_id_87>",
736
+ "lstrip": false,
737
+ "normalized": false,
738
+ "rstrip": false,
739
+ "single_word": false,
740
+ "special": true
741
+ },
742
+ "48216": {
743
+ "content": "<extra_id_88>",
744
+ "lstrip": false,
745
+ "normalized": false,
746
+ "rstrip": false,
747
+ "single_word": false,
748
+ "special": true
749
+ },
750
+ "48217": {
751
+ "content": "<extra_id_89>",
752
+ "lstrip": false,
753
+ "normalized": false,
754
+ "rstrip": false,
755
+ "single_word": false,
756
+ "special": true
757
+ },
758
+ "48218": {
759
+ "content": "<extra_id_90>",
760
+ "lstrip": false,
761
+ "normalized": false,
762
+ "rstrip": false,
763
+ "single_word": false,
764
+ "special": true
765
+ },
766
+ "48219": {
767
+ "content": "<extra_id_91>",
768
+ "lstrip": false,
769
+ "normalized": false,
770
+ "rstrip": false,
771
+ "single_word": false,
772
+ "special": true
773
+ },
774
+ "48220": {
775
+ "content": "<extra_id_92>",
776
+ "lstrip": false,
777
+ "normalized": false,
778
+ "rstrip": false,
779
+ "single_word": false,
780
+ "special": true
781
+ },
782
+ "48221": {
783
+ "content": "<extra_id_93>",
784
+ "lstrip": false,
785
+ "normalized": false,
786
+ "rstrip": false,
787
+ "single_word": false,
788
+ "special": true
789
+ },
790
+ "48222": {
791
+ "content": "<extra_id_94>",
792
+ "lstrip": false,
793
+ "normalized": false,
794
+ "rstrip": false,
795
+ "single_word": false,
796
+ "special": true
797
+ },
798
+ "48223": {
799
+ "content": "<extra_id_95>",
800
+ "lstrip": false,
801
+ "normalized": false,
802
+ "rstrip": false,
803
+ "single_word": false,
804
+ "special": true
805
+ },
806
+ "48224": {
807
+ "content": "<extra_id_96>",
808
+ "lstrip": false,
809
+ "normalized": false,
810
+ "rstrip": false,
811
+ "single_word": false,
812
+ "special": true
813
+ },
814
+ "48225": {
815
+ "content": "<extra_id_97>",
816
+ "lstrip": false,
817
+ "normalized": false,
818
+ "rstrip": false,
819
+ "single_word": false,
820
+ "special": true
821
+ },
822
+ "48226": {
823
+ "content": "<extra_id_98>",
824
+ "lstrip": false,
825
+ "normalized": false,
826
+ "rstrip": false,
827
+ "single_word": false,
828
+ "special": true
829
+ },
830
+ "48227": {
831
+ "content": "<extra_id_99>",
832
+ "lstrip": false,
833
+ "normalized": false,
834
+ "rstrip": false,
835
+ "single_word": false,
836
+ "special": true
837
+ }
838
+ },
839
+ "additional_special_tokens": [
840
+ "<extra_id_0>",
841
+ "<extra_id_1>",
842
+ "<extra_id_2>",
843
+ "<extra_id_3>",
844
+ "<extra_id_4>",
845
+ "<extra_id_5>",
846
+ "<extra_id_6>",
847
+ "<extra_id_7>",
848
+ "<extra_id_8>",
849
+ "<extra_id_9>",
850
+ "<extra_id_10>",
851
+ "<extra_id_11>",
852
+ "<extra_id_12>",
853
+ "<extra_id_13>",
854
+ "<extra_id_14>",
855
+ "<extra_id_15>",
856
+ "<extra_id_16>",
857
+ "<extra_id_17>",
858
+ "<extra_id_18>",
859
+ "<extra_id_19>",
860
+ "<extra_id_20>",
861
+ "<extra_id_21>",
862
+ "<extra_id_22>",
863
+ "<extra_id_23>",
864
+ "<extra_id_24>",
865
+ "<extra_id_25>",
866
+ "<extra_id_26>",
867
+ "<extra_id_27>",
868
+ "<extra_id_28>",
869
+ "<extra_id_29>",
870
+ "<extra_id_30>",
871
+ "<extra_id_31>",
872
+ "<extra_id_32>",
873
+ "<extra_id_33>",
874
+ "<extra_id_34>",
875
+ "<extra_id_35>",
876
+ "<extra_id_36>",
877
+ "<extra_id_37>",
878
+ "<extra_id_38>",
879
+ "<extra_id_39>",
880
+ "<extra_id_40>",
881
+ "<extra_id_41>",
882
+ "<extra_id_42>",
883
+ "<extra_id_43>",
884
+ "<extra_id_44>",
885
+ "<extra_id_45>",
886
+ "<extra_id_46>",
887
+ "<extra_id_47>",
888
+ "<extra_id_48>",
889
+ "<extra_id_49>",
890
+ "<extra_id_50>",
891
+ "<extra_id_51>",
892
+ "<extra_id_52>",
893
+ "<extra_id_53>",
894
+ "<extra_id_54>",
895
+ "<extra_id_55>",
896
+ "<extra_id_56>",
897
+ "<extra_id_57>",
898
+ "<extra_id_58>",
899
+ "<extra_id_59>",
900
+ "<extra_id_60>",
901
+ "<extra_id_61>",
902
+ "<extra_id_62>",
903
+ "<extra_id_63>",
904
+ "<extra_id_64>",
905
+ "<extra_id_65>",
906
+ "<extra_id_66>",
907
+ "<extra_id_67>",
908
+ "<extra_id_68>",
909
+ "<extra_id_69>",
910
+ "<extra_id_70>",
911
+ "<extra_id_71>",
912
+ "<extra_id_72>",
913
+ "<extra_id_73>",
914
+ "<extra_id_74>",
915
+ "<extra_id_75>",
916
+ "<extra_id_76>",
917
+ "<extra_id_77>",
918
+ "<extra_id_78>",
919
+ "<extra_id_79>",
920
+ "<extra_id_80>",
921
+ "<extra_id_81>",
922
+ "<extra_id_82>",
923
+ "<extra_id_83>",
924
+ "<extra_id_84>",
925
+ "<extra_id_85>",
926
+ "<extra_id_86>",
927
+ "<extra_id_87>",
928
+ "<extra_id_88>",
929
+ "<extra_id_89>",
930
+ "<extra_id_90>",
931
+ "<extra_id_91>",
932
+ "<extra_id_92>",
933
+ "<extra_id_93>",
934
+ "<extra_id_94>",
935
+ "<extra_id_95>",
936
+ "<extra_id_96>",
937
+ "<extra_id_97>",
938
+ "<extra_id_98>",
939
+ "<extra_id_99>"
940
+ ],
941
+ "bos_token": "<s>",
942
+ "clean_up_tokenization_spaces": false,
943
+ "eos_token": "</s>",
944
+ "legacy": false,
945
+ "model_max_length": 1000000000,
946
+ "pad_token": "<pad>",
947
+ "sp_model_kwargs": {},
948
+ "spaces_between_special_tokens": false,
949
+ "tokenizer_class": "LlamaTokenizer",
950
+ "unk_token": "<unk>",
951
+ "use_default_system_prompt": false
952
+ }
checkpoints/wandb/debug-internal.log ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"time":"2024-09-26T05:19:52.292500571Z","level":"INFO","msg":"using version","core version":"0.18.1"}
2
+ {"time":"2024-09-26T05:19:52.292535212Z","level":"INFO","msg":"created symlink","path":"/workspace/nanoT5/outputs/2024-09-26/05-19-51/wandb/run-20240926_051952-6q92wn34/logs/debug-core.log"}
3
+ {"time":"2024-09-26T05:19:52.292605612Z","level":"INFO","msg":"using version","core version":"0.18.1"}
4
+ {"time":"2024-09-26T05:19:52.292620977Z","level":"INFO","msg":"created symlink","path":"/workspace/nanoT5/outputs/2024-09-26/05-19-51/wandb/run-20240926_051952-6q92wn34/logs/debug-core.log"}
5
+ {"time":"2024-09-26T05:19:52.294337676Z","level":"INFO","msg":"created new stream","id":"6q92wn34"}
6
+ {"time":"2024-09-26T05:19:52.294383771Z","level":"INFO","msg":"stream: started","id":"6q92wn34"}
7
+ {"time":"2024-09-26T05:19:52.294425397Z","level":"INFO","msg":"handler: started","stream_id":{"value":"6q92wn34"}}
8
+ {"time":"2024-09-26T05:19:52.29448127Z","level":"INFO","msg":"sender: started","stream_id":{"value":"6q92wn34"}}
9
+ {"time":"2024-09-26T05:19:52.294511441Z","level":"INFO","msg":"writer: Do: started","stream_id":{"value":"6q92wn34"}}
10
+ {"time":"2024-09-26T05:19:52.509267513Z","level":"INFO","msg":"wandb-core","!BADKEY":null}
11
+ {"time":"2024-09-26T05:19:52.511105177Z","level":"INFO","msg":"Starting system monitor"}
12
+ {"time":"2024-09-26T05:19:52.511144288Z","level":"WARN","msg":"handleCodeSave: program relative path is empty"}
13
+ {"time":"2024-09-26T05:19:52.511207425Z","level":"ERROR","msg":"git repo not found","error":"repository does not exist"}
14
+ {"time":"2024-09-26T09:44:43.029621654Z","level":"INFO","msg":"api: retrying HTTP error","status":500,"url":"https://api.wandb.ai/files/pszemraj/nanoT5/6q92wn34/file_stream"}
15
+ {"time":"2024-09-26T09:44:50.617725083Z","level":"INFO","msg":"api: retrying HTTP error","status":500,"url":"https://api.wandb.ai/files/pszemraj/nanoT5/6q92wn34/file_stream"}
16
+ {"time":"2024-09-26T18:09:44.231714248Z","level":"INFO","msg":"api: retrying HTTP request, no error or response"}
17
+ {"time":"2024-09-27T17:10:18.39466019Z","level":"INFO","msg":"Stopping system monitor"}
18
+ {"time":"2024-09-27T17:10:18.397170844Z","level":"INFO","msg":"Stopped system monitor"}
19
+ {"time":"2024-09-27T17:10:18.739166013Z","level":"WARN","msg":"No program path found, not creating job artifact. See https://docs.wandb.ai/guides/launch/create-job"}
20
+ {"time":"2024-09-27T17:10:18.739493149Z","level":"INFO","msg":"sender: sendDefer: no job artifact to save"}
21
+ {"time":"2024-09-27T17:10:20.571908866Z","level":"INFO","msg":"stream: closing","id":"6q92wn34"}
22
+ {"time":"2024-09-27T17:10:20.572950618Z","level":"INFO","msg":"handler: closed","stream_id":{"value":"6q92wn34"}}
23
+ {"time":"2024-09-27T17:10:20.573099241Z","level":"INFO","msg":"sender: closed","stream_id":{"value":"6q92wn34"}}
24
+ {"time":"2024-09-27T17:10:20.573878949Z","level":"INFO","msg":"writer: Close: closed","stream_id":{"value":"6q92wn34"}}
25
+ {"time":"2024-09-27T17:10:20.573995723Z","level":"INFO","msg":"stream: closed","id":"6q92wn34"}
checkpoints/wandb/debug.log ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2024-09-26 05:19:52,278 INFO MainThread:21647 [wandb_setup.py:_flush():77] Current SDK version is 0.18.1
2
+ 2024-09-26 05:19:52,279 INFO MainThread:21647 [wandb_setup.py:_flush():77] Configure stats pid to 21647
3
+ 2024-09-26 05:19:52,279 INFO MainThread:21647 [wandb_setup.py:_flush():77] Loading settings from /root/.config/wandb/settings
4
+ 2024-09-26 05:19:52,279 INFO MainThread:21647 [wandb_setup.py:_flush():77] Loading settings from /workspace/nanoT5/outputs/2024-09-26/05-19-51/wandb/settings
5
+ 2024-09-26 05:19:52,279 INFO MainThread:21647 [wandb_setup.py:_flush():77] Loading settings from environment variables: {'project': 'nanoT5'}
6
+ 2024-09-26 05:19:52,279 INFO MainThread:21647 [wandb_setup.py:_flush():77] Applying setup settings: {'mode': 'online', '_disable_service': None}
7
+ 2024-09-26 05:19:52,279 WARNING MainThread:21647 [wandb_setup.py:_flush():77] Could not find program at -m nanoT5.main
8
+ 2024-09-26 05:19:52,279 INFO MainThread:21647 [wandb_setup.py:_flush():77] Inferring run settings from compute environment: {'program_relpath': None, 'program': '-m nanoT5.main'}
9
+ 2024-09-26 05:19:52,279 INFO MainThread:21647 [wandb_setup.py:_flush():77] Applying login settings: {}
10
+ 2024-09-26 05:19:52,279 INFO MainThread:21647 [wandb_init.py:_log_setup():532] Logging user logs to /workspace/nanoT5/outputs/2024-09-26/05-19-51/wandb/run-20240926_051952-6q92wn34/logs/debug.log
11
+ 2024-09-26 05:19:52,279 INFO MainThread:21647 [wandb_init.py:_log_setup():533] Logging internal logs to /workspace/nanoT5/outputs/2024-09-26/05-19-51/wandb/run-20240926_051952-6q92wn34/logs/debug-internal.log
12
+ 2024-09-26 05:19:52,279 INFO MainThread:21647 [wandb_init.py:init():616] calling init triggers
13
+ 2024-09-26 05:19:52,279 INFO MainThread:21647 [wandb_init.py:init():623] wandb.init called with sweep_config: {}
14
+ config: {'mode': 'pt', 'device': 'gpu', 'precision': 'bf16', 'eval_only': False, 'predict_only': False, 'seed': 34534, 'model': {'klass': 'hf_t5', 'name': 'pszemraj/tFINE-850m-24x24-512ctx', 'overwrite': {'dropout_rate': 0.0}, 'checkpoint_path': '', 'random_init': False, 'compile': True}, 'tokenizer': {'name': 'BEE-spoke-data/slimpajama_tok-48128-BPE-forT5'}, 'data': {'input_length': 1024, 'mlm_probability': 0.15, 'mean_noise_span_length': 3.0, 'num_workers': 16}, 'optim': {'name': 'adamwscale', 'base_lr': 0.01, 'batch_size': 128, 'total_steps': 20000, 'epochs': -1, 'warmup_steps': 5000, 'lr_scheduler': 'cosine', 'weight_decay': 0.0, 'grad_clip': 1.0, 'grad_acc': 8, 'final_cosine': 2e-05}, 'eval': {'every_steps': 1000000000, 'steps': 500}, 'checkpoint': {'every_steps': 2500}, 'logging': {'use_wandb': True, 'wandb_config': {'project': 'nanoT5', 'entity': 'pszemraj', 'tags': ['24x24', '1024'], 'mode': 'online'}, 'every_steps': 25, 'grad_l2': True, 'weights_l2': True}, 'slurm_id': 'none', 'working_dir': '/workspace/nanoT5/outputs/2024-09-26/05-19-51'}
15
+ 2024-09-26 05:19:52,279 INFO MainThread:21647 [wandb_init.py:init():666] starting backend
16
+ 2024-09-26 05:19:52,279 INFO MainThread:21647 [wandb_init.py:init():670] setting up manager
17
+ 2024-09-26 05:19:52,285 INFO MainThread:21647 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
18
+ 2024-09-26 05:19:52,286 INFO MainThread:21647 [wandb_init.py:init():678] backend started and connected
19
+ 2024-09-26 05:19:52,293 INFO MainThread:21647 [wandb_init.py:init():773] updated telemetry
20
+ 2024-09-26 05:19:52,299 INFO MainThread:21647 [wandb_init.py:init():806] communicating run to backend with 90.0 second timeout
21
+ 2024-09-26 05:19:52,503 INFO MainThread:21647 [wandb_init.py:init():857] starting run threads in backend
22
+ 2024-09-26 05:19:52,643 INFO MainThread:21647 [wandb_run.py:_console_start():2459] atexit reg
23
+ 2024-09-26 05:19:52,643 INFO MainThread:21647 [wandb_run.py:_redirect():2307] redirect: wrap_raw
24
+ 2024-09-26 05:19:52,643 INFO MainThread:21647 [wandb_run.py:_redirect():2372] Wrapping output streams.
25
+ 2024-09-26 05:19:52,643 INFO MainThread:21647 [wandb_run.py:_redirect():2397] Redirects installed.
26
+ 2024-09-26 05:19:52,646 INFO MainThread:21647 [wandb_init.py:init():900] run started, returning control to user process
27
+ 2024-09-26 05:20:47,956 INFO MainThread:21647 [wandb_run.py:_config_callback():1388] config_cb None None {'mode': 'pt', 'device': 'gpu', 'precision': 'bf16', 'eval_only': False, 'predict_only': False, 'seed': 34534, 'model': {'klass': 'hf_t5', 'name': 'pszemraj/tFINE-850m-24x24-512ctx', 'overwrite': {'dropout_rate': 0.0}, 'checkpoint_path': '', 'random_init': False, 'compile': True}, 'tokenizer': {'name': 'BEE-spoke-data/slimpajama_tok-48128-BPE-forT5'}, 'data': {'input_length': 1024, 'mlm_probability': 0.15, 'mean_noise_span_length': 3.0, 'num_workers': 16, 'before_mask_input_length': 1137, 'target_length': 229}, 'optim': {'name': 'adamwscale', 'base_lr': 0.01, 'batch_size': 128, 'total_steps': 20000, 'epochs': -1, 'warmup_steps': 5000, 'lr_scheduler': 'cosine', 'weight_decay': 0.0, 'grad_clip': 1.0, 'grad_acc': 8, 'final_cosine': 2e-05}, 'eval': {'every_steps': 1000000000, 'steps': 500, 'corrected_steps': 500}, 'checkpoint': {'every_steps': 2500}, 'logging': {'use_wandb': True, 'wandb_config': {'project': 'nanoT5', 'entity': 'pszemraj', 'tags': ['24x24', '1024'], 'mode': 'online'}, 'every_steps': 25, 'grad_l2': True, 'weights_l2': True}, 'slurm_id': 'none', 'working_dir': '/workspace/nanoT5/outputs/2024-09-26/05-19-51', 'n_all_param': 853929472}
28
+ 2024-09-27 17:10:18,389 INFO MainThread:21647 [wandb_run.py:_finish():2158] finishing run pszemraj/nanoT5/6q92wn34
29
+ 2024-09-27 17:10:18,392 INFO MainThread:21647 [wandb_run.py:_atexit_cleanup():2422] got exitcode: 0
30
+ 2024-09-27 17:10:18,392 INFO MainThread:21647 [wandb_run.py:_restore():2404] restore
31
+ 2024-09-27 17:10:18,393 INFO MainThread:21647 [wandb_run.py:_restore():2410] restore done
32
+ 2024-09-27 17:10:20,554 INFO MainThread:21647 [wandb_run.py:_footer_history_summary_info():4037] rendering history
33
+ 2024-09-27 17:10:20,556 INFO MainThread:21647 [wandb_run.py:_footer_history_summary_info():4069] rendering summary
34
+ 2024-09-27 17:10:20,567 INFO MainThread:21647 [wandb_run.py:_footer_sync_info():3996] logging synced files
checkpoints/wandb/run-20240926_051952-6q92wn34/files/config.yaml ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _wandb:
2
+ value:
3
+ cli_version: 0.18.1
4
+ m: []
5
+ python_version: 3.11.10
6
+ t:
7
+ "1":
8
+ - 1
9
+ - 11
10
+ - 41
11
+ - 49
12
+ - 50
13
+ - 51
14
+ - 55
15
+ - 71
16
+ - 100
17
+ "2":
18
+ - 1
19
+ - 11
20
+ - 41
21
+ - 49
22
+ - 50
23
+ - 51
24
+ - 55
25
+ - 71
26
+ - 100
27
+ "3":
28
+ - 2
29
+ - 15
30
+ - 16
31
+ - 23
32
+ - 55
33
+ - 61
34
+ "4": 3.11.10
35
+ "5": 0.18.1
36
+ "6": 4.44.2
37
+ "8":
38
+ - 5
39
+ "12": 0.18.1
40
+ "13": linux-x86_64
41
+ checkpoint:
42
+ value:
43
+ every_steps: 2500
44
+ data:
45
+ value:
46
+ before_mask_input_length: 1137
47
+ input_length: 1024
48
+ mean_noise_span_length: 3
49
+ mlm_probability: 0.15
50
+ num_workers: 16
51
+ target_length: 229
52
+ device:
53
+ value: gpu
54
+ eval:
55
+ value:
56
+ corrected_steps: 500
57
+ every_steps: 1000000000
58
+ steps: 500
59
+ eval_only:
60
+ value: false
61
+ logging:
62
+ value:
63
+ every_steps: 25
64
+ grad_l2: true
65
+ use_wandb: true
66
+ wandb_config:
67
+ entity: pszemraj
68
+ mode: online
69
+ project: nanoT5
70
+ tags:
71
+ - 24x24
72
+ - "1024"
73
+ weights_l2: true
74
+ mode:
75
+ value: pt
76
+ model:
77
+ value:
78
+ checkpoint_path: ""
79
+ compile: true
80
+ klass: hf_t5
81
+ name: pszemraj/tFINE-850m-24x24-512ctx
82
+ overwrite:
83
+ dropout_rate: 0
84
+ random_init: false
85
+ n_all_param:
86
+ value: 853929472
87
+ optim:
88
+ value:
89
+ base_lr: 0.01
90
+ batch_size: 128
91
+ epochs: -1
92
+ final_cosine: 2e-05
93
+ grad_acc: 8
94
+ grad_clip: 1
95
+ lr_scheduler: cosine
96
+ name: adamwscale
97
+ total_steps: 20000
98
+ warmup_steps: 5000
99
+ weight_decay: 0
100
+ precision:
101
+ value: bf16
102
+ predict_only:
103
+ value: false
104
+ seed:
105
+ value: 34534
106
+ slurm_id:
107
+ value: none
108
+ tokenizer:
109
+ value:
110
+ name: BEE-spoke-data/slimpajama_tok-48128-BPE-forT5
111
+ working_dir:
112
+ value: /workspace/nanoT5/outputs/2024-09-26/05-19-51
checkpoints/wandb/run-20240926_051952-6q92wn34/files/output.log ADDED
The diff for this file is too large to render. See raw diff
 
checkpoints/wandb/run-20240926_051952-6q92wn34/files/requirements.txt ADDED
@@ -0,0 +1,201 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ninja==1.11.1.1
2
+ tqdm==4.66.5
3
+ smmap==5.0.1
4
+ setproctitle==1.3.3
5
+ sentry-sdk==2.14.0
6
+ safetensors==0.4.5
7
+ regex==2024.9.11
8
+ aiohttp==3.10.6
9
+ docker-pycreds==0.4.0
10
+ click==8.1.7
11
+ huggingface-hub==0.25.1
12
+ gitdb==4.0.11
13
+ tokenizers==0.19.1
14
+ GitPython==3.1.43
15
+ wandb==0.18.1
16
+ transformers==4.44.2
17
+ hf_transfer==0.1.8
18
+ sentencepiece==0.2.0
19
+ pytz==2024.2
20
+ pyrepl==0.9.0
21
+ antlr4-python3-runtime==4.9.3
22
+ xxhash==3.5.0
23
+ wmctrl==0.5
24
+ tzdata==2024.2
25
+ pynvml==11.5.3
26
+ pyarrow==17.0.0
27
+ protobuf==3.20.3
28
+ omegaconf==2.3.0
29
+ multidict==6.1.0
30
+ joblib==1.4.2
31
+ frozenlist==1.4.1
32
+ fancycompleter==0.9.1
33
+ dill==0.3.8
34
+ aiohappyeyeballs==2.4.0
35
+ absl-py==2.1.0
36
+ yarl==1.12.1
37
+ pdbpp==0.10.3
38
+ pandas==2.2.3
39
+ nltk==3.9.1
40
+ multiprocess==0.70.16
41
+ hydra-core==1.3.2
42
+ aiosignal==1.3.1
43
+ rouge_score==0.1.2
44
+ accelerate==0.34.2
45
+ datasets==3.0.0
46
+ evaluate==0.4.3
47
+ nvidia-ml-py==12.560.30
48
+ blessed==1.20.0
49
+ gpustat==1.1.1
50
+ termcolor==2.4.0
51
+ fire==0.6.0
52
+ entrypoints==0.4
53
+ jupyter_client==7.4.9
54
+ nbclassic==1.1.0
55
+ notebook==6.5.5
56
+ pyzmq==24.0.1
57
+ PyYAML==6.0.2
58
+ Send2Trash==1.8.3
59
+ anyio==4.6.0
60
+ argon2-cffi==23.1.0
61
+ argon2-cffi-bindings==21.2.0
62
+ arrow==1.3.0
63
+ asttokens==2.4.1
64
+ async-lru==2.0.4
65
+ attrs==24.2.0
66
+ babel==2.16.0
67
+ beautifulsoup4==4.12.3
68
+ bleach==6.1.0
69
+ certifi==2024.8.30
70
+ cffi==1.17.1
71
+ charset-normalizer==3.3.2
72
+ comm==0.2.2
73
+ debugpy==1.8.5
74
+ decorator==5.1.1
75
+ defusedxml==0.7.1
76
+ executing==2.1.0
77
+ fastjsonschema==2.20.0
78
+ fqdn==1.5.1
79
+ h11==0.14.0
80
+ httpcore==1.0.5
81
+ httpx==0.27.2
82
+ idna==3.10
83
+ ipykernel==6.29.5
84
+ ipython==8.27.0
85
+ ipython-genutils==0.2.0
86
+ ipywidgets==8.1.5
87
+ isoduration==20.11.0
88
+ jedi==0.19.1
89
+ json5==0.9.25
90
+ jsonpointer==3.0.0
91
+ jsonschema==4.23.0
92
+ jsonschema-specifications==2023.12.1
93
+ jupyter-archive==3.4.0
94
+ jupyter_contrib_core==0.4.2
95
+ jupyter_contrib_nbextensions==0.7.0
96
+ jupyter_core==5.7.2
97
+ jupyter-events==0.10.0
98
+ jupyter-highlight-selected-word==0.2.0
99
+ jupyter-lsp==2.2.5
100
+ jupyter_nbextensions_configurator==0.6.4
101
+ jupyter_server==2.14.2
102
+ jupyter_server_terminals==0.5.3
103
+ jupyterlab==4.2.5
104
+ jupyterlab_pygments==0.3.0
105
+ jupyterlab_server==2.27.3
106
+ jupyterlab_widgets==3.0.13
107
+ lxml==5.3.0
108
+ matplotlib-inline==0.1.7
109
+ mistune==3.0.2
110
+ nbclient==0.10.0
111
+ nbconvert==7.16.4
112
+ nbformat==5.10.4
113
+ nest-asyncio==1.6.0
114
+ notebook_shim==0.2.4
115
+ overrides==7.7.0
116
+ packaging==24.1
117
+ pandocfilters==1.5.1
118
+ parso==0.8.4
119
+ pexpect==4.9.0
120
+ platformdirs==4.3.6
121
+ prometheus_client==0.21.0
122
+ prompt_toolkit==3.0.47
123
+ psutil==6.0.0
124
+ ptyprocess==0.7.0
125
+ pure_eval==0.2.3
126
+ pycparser==2.22
127
+ Pygments==2.18.0
128
+ python-dateutil==2.9.0.post0
129
+ python-json-logger==2.0.7
130
+ referencing==0.35.1
131
+ requests==2.32.3
132
+ rfc3339-validator==0.1.4
133
+ rfc3986-validator==0.1.1
134
+ rpds-py==0.20.0
135
+ sniffio==1.3.1
136
+ soupsieve==2.6
137
+ stack-data==0.6.3
138
+ terminado==0.18.1
139
+ tinycss2==1.3.0
140
+ tornado==6.4.1
141
+ traitlets==5.14.3
142
+ types-python-dateutil==2.9.0.20240906
143
+ uri-template==1.3.0
144
+ urllib3==2.2.3
145
+ wcwidth==0.2.13
146
+ webcolors==24.8.0
147
+ webencodings==0.5.1
148
+ websocket-client==1.8.0
149
+ widgetsnbextension==4.0.13
150
+ Jinja2==3.1.3
151
+ MarkupSafe==2.1.5
152
+ filelock==3.13.1
153
+ fsspec==2024.2.0
154
+ mpmath==1.3.0
155
+ networkx==3.2.1
156
+ numpy==1.26.3
157
+ nvidia-cublas-cu12==12.4.2.65
158
+ nvidia-cuda-cupti-cu12==12.4.99
159
+ nvidia-cuda-nvrtc-cu12==12.4.99
160
+ nvidia-cuda-runtime-cu12==12.4.99
161
+ nvidia-cudnn-cu12==9.1.0.70
162
+ nvidia-cufft-cu12==11.2.0.44
163
+ nvidia-curand-cu12==10.3.5.119
164
+ nvidia-cusolver-cu12==11.6.0.99
165
+ nvidia-cusparse-cu12==12.3.0.142
166
+ nvidia-nccl-cu12==2.20.5
167
+ nvidia-nvjitlink-cu12==12.4.99
168
+ nvidia-nvtx-cu12==12.4.99
169
+ pillow==10.2.0
170
+ sympy==1.12
171
+ torch==2.4.1+cu124
172
+ torchaudio==2.4.1+cu124
173
+ torchvision==0.19.1+cu124
174
+ triton==3.0.0
175
+ typing_extensions==4.9.0
176
+ pip==24.2
177
+ setuptools==75.1.0
178
+ wheel==0.44.0
179
+ PyGObject==3.42.1
180
+ PyJWT==2.3.0
181
+ SecretStorage==3.3.1
182
+ blinker==1.4
183
+ cryptography==3.4.8
184
+ dbus-python==1.2.18
185
+ distro==1.7.0
186
+ httplib2==0.20.2
187
+ importlib-metadata==4.6.4
188
+ jeepney==0.7.1
189
+ keyring==23.5.0
190
+ launchpadlib==1.10.16
191
+ lazr.restfulclient==0.14.4
192
+ lazr.uri==1.0.6
193
+ more-itertools==8.10.0
194
+ oauthlib==3.2.0
195
+ pyparsing==2.4.7
196
+ python-apt==2.4.0+ubuntu4
197
+ six==1.16.0
198
+ wadllib==1.3.6
199
+ zipp==1.0.0
200
+ PyYAML==5.4.1
201
+ Pygments==2.11.2
checkpoints/wandb/run-20240926_051952-6q92wn34/files/wandb-metadata.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "os": "Linux-6.5.0-41-generic-x86_64-with-glibc2.35",
3
+ "python": "3.11.10",
4
+ "startedAt": "2024-09-26T05:19:52.287085Z",
5
+ "program": "-m nanoT5.main",
6
+ "git": {
7
+ "remote": "https://github.com/pszemraj/nanoT5.git",
8
+ "commit": "58834d398cca39b8344c83490f8b1bec71116423"
9
+ },
10
+ "email": "peterszemraj@gmail.com",
11
+ "root": "/workspace/nanoT5/outputs/2024-09-26/05-19-51",
12
+ "host": "bb66bf20b0ac",
13
+ "username": "root",
14
+ "executable": "/usr/bin/python",
15
+ "cpu_count": 100,
16
+ "cpu_count_logical": 100,
17
+ "gpu": "[NVIDIA A100 80GB PCIe]",
18
+ "gpu_count": 1,
19
+ "disk": {
20
+ "/": {
21
+ "total": "214748364800",
22
+ "used": "1568272384"
23
+ }
24
+ },
25
+ "memory": {
26
+ "total": "718177431552"
27
+ },
28
+ "cpu": {
29
+ "count": 100,
30
+ "countLogical": 100
31
+ },
32
+ "gpu_nvidia": [
33
+ {
34
+ "name": "NVIDIA A100 80GB PCIe",
35
+ "memoryTotal": "85899345920",
36
+ "cudaCores": 6912,
37
+ "architecture": "Ampere"
38
+ }
39
+ ],
40
+ "cudaVersion": "12.4"
41
+ }
checkpoints/wandb/run-20240926_051952-6q92wn34/files/wandb-summary.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eval/loss":2.0331861997252854,"eval/accuracy":0.6101275591823644,"train/loss":1.675020592212677,"eval/time":1042.2864139080048,"_timestamp":1.7274570014725459e+09,"train/seconds_per_step":6.350233516693115,"train/weights_l2":11190.639259593589,"_wandb":{"runtime":129026},"_runtime":129026.107521552,"_step":20001,"train/grad_l2":0.2113957405090332,"train/lr":2e-05}
checkpoints/wandb/run-20240926_051952-6q92wn34/logs/debug-core.log ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"time":"2024-09-26T05:19:51.787487487Z","level":"INFO","msg":"started logging, with flags","port-filename":"/tmp/tmphhqtaqzs/port-21647.txt","pid":21647,"debug":false,"disable-analytics":false}
2
+ {"time":"2024-09-26T05:19:51.78754783Z","level":"INFO","msg":"FeatureState","shutdownOnParentExitEnabled":false}
3
+ {"time":"2024-09-26T05:19:51.792575285Z","level":"INFO","msg":"Will exit if parent process dies.","ppid":21647}
4
+ {"time":"2024-09-26T05:19:51.792521647Z","level":"INFO","msg":"server is running","addr":{"IP":"127.0.0.1","Port":44037,"Zone":""}}
5
+ {"time":"2024-09-26T05:19:51.977929295Z","level":"INFO","msg":"created new connection","id":"127.0.0.1:56670"}
6
+ {"time":"2024-09-26T05:19:52.29226758Z","level":"INFO","msg":"connection init received","streamId":"6q92wn34","id":"127.0.0.1:56670"}
7
+ {"time":"2024-09-26T05:19:52.29256678Z","level":"ERROR","msg":"error creating symlink","error":"symlink /root/.cache/wandb/logs/core-debug-20240926_051951.log /workspace/nanoT5/outputs/2024-09-26/05-19-51/wandb/run-20240926_051952-6q92wn34/logs/debug-core.log: file exists"}
8
+ {"time":"2024-09-26T05:19:52.294397181Z","level":"INFO","msg":"connection init completed","streamId":"6q92wn34","id":"127.0.0.1:56670"}
9
+ {"time":"2024-09-27T17:10:20.57067044Z","level":"INFO","msg":"handle finish received","streamId":"6q92wn34","id":"127.0.0.1:56670"}
10
+ {"time":"2024-09-27T17:10:20.685726134Z","level":"INFO","msg":"connection: teardown","id":"127.0.0.1:56670"}
11
+ {"time":"2024-09-27T17:10:20.686208038Z","level":"INFO","msg":"server is shutting down"}
12
+ {"time":"2024-09-27T17:10:20.68644047Z","level":"INFO","msg":"closed connection","id":"127.0.0.1:56670"}
13
+ {"time":"2024-09-27T17:10:20.686510591Z","level":"INFO","msg":"connection closed","id":"127.0.0.1:56670"}
14
+ {"time":"2024-09-27T17:10:20.686547188Z","level":"INFO","msg":"server is closed"}
checkpoints/wandb/run-20240926_051952-6q92wn34/logs/debug-internal.log ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"time":"2024-09-26T05:19:52.292500571Z","level":"INFO","msg":"using version","core version":"0.18.1"}
2
+ {"time":"2024-09-26T05:19:52.292535212Z","level":"INFO","msg":"created symlink","path":"/workspace/nanoT5/outputs/2024-09-26/05-19-51/wandb/run-20240926_051952-6q92wn34/logs/debug-core.log"}
3
+ {"time":"2024-09-26T05:19:52.292605612Z","level":"INFO","msg":"using version","core version":"0.18.1"}
4
+ {"time":"2024-09-26T05:19:52.292620977Z","level":"INFO","msg":"created symlink","path":"/workspace/nanoT5/outputs/2024-09-26/05-19-51/wandb/run-20240926_051952-6q92wn34/logs/debug-core.log"}
5
+ {"time":"2024-09-26T05:19:52.294337676Z","level":"INFO","msg":"created new stream","id":"6q92wn34"}
6
+ {"time":"2024-09-26T05:19:52.294383771Z","level":"INFO","msg":"stream: started","id":"6q92wn34"}
7
+ {"time":"2024-09-26T05:19:52.294425397Z","level":"INFO","msg":"handler: started","stream_id":{"value":"6q92wn34"}}
8
+ {"time":"2024-09-26T05:19:52.29448127Z","level":"INFO","msg":"sender: started","stream_id":{"value":"6q92wn34"}}
9
+ {"time":"2024-09-26T05:19:52.294511441Z","level":"INFO","msg":"writer: Do: started","stream_id":{"value":"6q92wn34"}}
10
+ {"time":"2024-09-26T05:19:52.509267513Z","level":"INFO","msg":"wandb-core","!BADKEY":null}
11
+ {"time":"2024-09-26T05:19:52.511105177Z","level":"INFO","msg":"Starting system monitor"}
12
+ {"time":"2024-09-26T05:19:52.511144288Z","level":"WARN","msg":"handleCodeSave: program relative path is empty"}
13
+ {"time":"2024-09-26T05:19:52.511207425Z","level":"ERROR","msg":"git repo not found","error":"repository does not exist"}
14
+ {"time":"2024-09-26T09:44:43.029621654Z","level":"INFO","msg":"api: retrying HTTP error","status":500,"url":"https://api.wandb.ai/files/pszemraj/nanoT5/6q92wn34/file_stream"}
15
+ {"time":"2024-09-26T09:44:50.617725083Z","level":"INFO","msg":"api: retrying HTTP error","status":500,"url":"https://api.wandb.ai/files/pszemraj/nanoT5/6q92wn34/file_stream"}
16
+ {"time":"2024-09-26T18:09:44.231714248Z","level":"INFO","msg":"api: retrying HTTP request, no error or response"}
17
+ {"time":"2024-09-27T17:10:18.39466019Z","level":"INFO","msg":"Stopping system monitor"}
18
+ {"time":"2024-09-27T17:10:18.397170844Z","level":"INFO","msg":"Stopped system monitor"}
19
+ {"time":"2024-09-27T17:10:18.739166013Z","level":"WARN","msg":"No program path found, not creating job artifact. See https://docs.wandb.ai/guides/launch/create-job"}
20
+ {"time":"2024-09-27T17:10:18.739493149Z","level":"INFO","msg":"sender: sendDefer: no job artifact to save"}
21
+ {"time":"2024-09-27T17:10:20.571908866Z","level":"INFO","msg":"stream: closing","id":"6q92wn34"}
22
+ {"time":"2024-09-27T17:10:20.572950618Z","level":"INFO","msg":"handler: closed","stream_id":{"value":"6q92wn34"}}
23
+ {"time":"2024-09-27T17:10:20.573099241Z","level":"INFO","msg":"sender: closed","stream_id":{"value":"6q92wn34"}}
24
+ {"time":"2024-09-27T17:10:20.573878949Z","level":"INFO","msg":"writer: Close: closed","stream_id":{"value":"6q92wn34"}}
25
+ {"time":"2024-09-27T17:10:20.573995723Z","level":"INFO","msg":"stream: closed","id":"6q92wn34"}
checkpoints/wandb/run-20240926_051952-6q92wn34/logs/debug.log ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2024-09-26 05:19:52,278 INFO MainThread:21647 [wandb_setup.py:_flush():77] Current SDK version is 0.18.1
2
+ 2024-09-26 05:19:52,279 INFO MainThread:21647 [wandb_setup.py:_flush():77] Configure stats pid to 21647
3
+ 2024-09-26 05:19:52,279 INFO MainThread:21647 [wandb_setup.py:_flush():77] Loading settings from /root/.config/wandb/settings
4
+ 2024-09-26 05:19:52,279 INFO MainThread:21647 [wandb_setup.py:_flush():77] Loading settings from /workspace/nanoT5/outputs/2024-09-26/05-19-51/wandb/settings
5
+ 2024-09-26 05:19:52,279 INFO MainThread:21647 [wandb_setup.py:_flush():77] Loading settings from environment variables: {'project': 'nanoT5'}
6
+ 2024-09-26 05:19:52,279 INFO MainThread:21647 [wandb_setup.py:_flush():77] Applying setup settings: {'mode': 'online', '_disable_service': None}
7
+ 2024-09-26 05:19:52,279 WARNING MainThread:21647 [wandb_setup.py:_flush():77] Could not find program at -m nanoT5.main
8
+ 2024-09-26 05:19:52,279 INFO MainThread:21647 [wandb_setup.py:_flush():77] Inferring run settings from compute environment: {'program_relpath': None, 'program': '-m nanoT5.main'}
9
+ 2024-09-26 05:19:52,279 INFO MainThread:21647 [wandb_setup.py:_flush():77] Applying login settings: {}
10
+ 2024-09-26 05:19:52,279 INFO MainThread:21647 [wandb_init.py:_log_setup():532] Logging user logs to /workspace/nanoT5/outputs/2024-09-26/05-19-51/wandb/run-20240926_051952-6q92wn34/logs/debug.log
11
+ 2024-09-26 05:19:52,279 INFO MainThread:21647 [wandb_init.py:_log_setup():533] Logging internal logs to /workspace/nanoT5/outputs/2024-09-26/05-19-51/wandb/run-20240926_051952-6q92wn34/logs/debug-internal.log
12
+ 2024-09-26 05:19:52,279 INFO MainThread:21647 [wandb_init.py:init():616] calling init triggers
13
+ 2024-09-26 05:19:52,279 INFO MainThread:21647 [wandb_init.py:init():623] wandb.init called with sweep_config: {}
14
+ config: {'mode': 'pt', 'device': 'gpu', 'precision': 'bf16', 'eval_only': False, 'predict_only': False, 'seed': 34534, 'model': {'klass': 'hf_t5', 'name': 'pszemraj/tFINE-850m-24x24-512ctx', 'overwrite': {'dropout_rate': 0.0}, 'checkpoint_path': '', 'random_init': False, 'compile': True}, 'tokenizer': {'name': 'BEE-spoke-data/slimpajama_tok-48128-BPE-forT5'}, 'data': {'input_length': 1024, 'mlm_probability': 0.15, 'mean_noise_span_length': 3.0, 'num_workers': 16}, 'optim': {'name': 'adamwscale', 'base_lr': 0.01, 'batch_size': 128, 'total_steps': 20000, 'epochs': -1, 'warmup_steps': 5000, 'lr_scheduler': 'cosine', 'weight_decay': 0.0, 'grad_clip': 1.0, 'grad_acc': 8, 'final_cosine': 2e-05}, 'eval': {'every_steps': 1000000000, 'steps': 500}, 'checkpoint': {'every_steps': 2500}, 'logging': {'use_wandb': True, 'wandb_config': {'project': 'nanoT5', 'entity': 'pszemraj', 'tags': ['24x24', '1024'], 'mode': 'online'}, 'every_steps': 25, 'grad_l2': True, 'weights_l2': True}, 'slurm_id': 'none', 'working_dir': '/workspace/nanoT5/outputs/2024-09-26/05-19-51'}
15
+ 2024-09-26 05:19:52,279 INFO MainThread:21647 [wandb_init.py:init():666] starting backend
16
+ 2024-09-26 05:19:52,279 INFO MainThread:21647 [wandb_init.py:init():670] setting up manager
17
+ 2024-09-26 05:19:52,285 INFO MainThread:21647 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
18
+ 2024-09-26 05:19:52,286 INFO MainThread:21647 [wandb_init.py:init():678] backend started and connected
19
+ 2024-09-26 05:19:52,293 INFO MainThread:21647 [wandb_init.py:init():773] updated telemetry
20
+ 2024-09-26 05:19:52,299 INFO MainThread:21647 [wandb_init.py:init():806] communicating run to backend with 90.0 second timeout
21
+ 2024-09-26 05:19:52,503 INFO MainThread:21647 [wandb_init.py:init():857] starting run threads in backend
22
+ 2024-09-26 05:19:52,643 INFO MainThread:21647 [wandb_run.py:_console_start():2459] atexit reg
23
+ 2024-09-26 05:19:52,643 INFO MainThread:21647 [wandb_run.py:_redirect():2307] redirect: wrap_raw
24
+ 2024-09-26 05:19:52,643 INFO MainThread:21647 [wandb_run.py:_redirect():2372] Wrapping output streams.
25
+ 2024-09-26 05:19:52,643 INFO MainThread:21647 [wandb_run.py:_redirect():2397] Redirects installed.
26
+ 2024-09-26 05:19:52,646 INFO MainThread:21647 [wandb_init.py:init():900] run started, returning control to user process
27
+ 2024-09-26 05:20:47,956 INFO MainThread:21647 [wandb_run.py:_config_callback():1388] config_cb None None {'mode': 'pt', 'device': 'gpu', 'precision': 'bf16', 'eval_only': False, 'predict_only': False, 'seed': 34534, 'model': {'klass': 'hf_t5', 'name': 'pszemraj/tFINE-850m-24x24-512ctx', 'overwrite': {'dropout_rate': 0.0}, 'checkpoint_path': '', 'random_init': False, 'compile': True}, 'tokenizer': {'name': 'BEE-spoke-data/slimpajama_tok-48128-BPE-forT5'}, 'data': {'input_length': 1024, 'mlm_probability': 0.15, 'mean_noise_span_length': 3.0, 'num_workers': 16, 'before_mask_input_length': 1137, 'target_length': 229}, 'optim': {'name': 'adamwscale', 'base_lr': 0.01, 'batch_size': 128, 'total_steps': 20000, 'epochs': -1, 'warmup_steps': 5000, 'lr_scheduler': 'cosine', 'weight_decay': 0.0, 'grad_clip': 1.0, 'grad_acc': 8, 'final_cosine': 2e-05}, 'eval': {'every_steps': 1000000000, 'steps': 500, 'corrected_steps': 500}, 'checkpoint': {'every_steps': 2500}, 'logging': {'use_wandb': True, 'wandb_config': {'project': 'nanoT5', 'entity': 'pszemraj', 'tags': ['24x24', '1024'], 'mode': 'online'}, 'every_steps': 25, 'grad_l2': True, 'weights_l2': True}, 'slurm_id': 'none', 'working_dir': '/workspace/nanoT5/outputs/2024-09-26/05-19-51', 'n_all_param': 853929472}
28
+ 2024-09-27 17:10:18,389 INFO MainThread:21647 [wandb_run.py:_finish():2158] finishing run pszemraj/nanoT5/6q92wn34
29
+ 2024-09-27 17:10:18,392 INFO MainThread:21647 [wandb_run.py:_atexit_cleanup():2422] got exitcode: 0
30
+ 2024-09-27 17:10:18,392 INFO MainThread:21647 [wandb_run.py:_restore():2404] restore
31
+ 2024-09-27 17:10:18,393 INFO MainThread:21647 [wandb_run.py:_restore():2410] restore done
32
+ 2024-09-27 17:10:20,554 INFO MainThread:21647 [wandb_run.py:_footer_history_summary_info():4037] rendering history
33
+ 2024-09-27 17:10:20,556 INFO MainThread:21647 [wandb_run.py:_footer_history_summary_info():4069] rendering summary
34
+ 2024-09-27 17:10:20,567 INFO MainThread:21647 [wandb_run.py:_footer_sync_info():3996] logging synced files
checkpoints/wandb/run-20240926_051952-6q92wn34/run-6q92wn34.wandb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27a9cf5061a75d3086caaf09c6f4383664f2e8d2f186e75b5c2e0a5979fc4ac4
3
+ size 61571591