gyung commited on
Commit
f27d044
·
verified ·
1 Parent(s): 90b7c64

Add files using upload-large-folder tool

Browse files
Files changed (23) hide show
  1. .gitattributes +9 -0
  2. stage2c-hrm-full-nocap-repeat2-step580000/all_config.yaml +46 -0
  3. stage2c-hrm-full-nocap-repeat2-step580000/carry_step_580000.0.pt +3 -0
  4. stage2c-hrm-full-nocap-repeat2-step580000/carry_step_580000.1.pt +3 -0
  5. stage2c-hrm-full-nocap-repeat2-step580000/carry_step_580000.2.pt +3 -0
  6. stage2c-hrm-full-nocap-repeat2-step580000/carry_step_580000.3.pt +3 -0
  7. stage2c-hrm-full-nocap-repeat2-step580000/carry_step_580000.4.pt +3 -0
  8. stage2c-hrm-full-nocap-repeat2-step580000/carry_step_580000.5.pt +3 -0
  9. stage2c-hrm-full-nocap-repeat2-step580000/carry_step_580000.6.pt +3 -0
  10. stage2c-hrm-full-nocap-repeat2-step580000/carry_step_580000.7.pt +3 -0
  11. stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/.metadata +3 -0
  12. stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__0_0.distcp +3 -0
  13. stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__1_0.distcp +3 -0
  14. stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__2_0.distcp +3 -0
  15. stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__3_0.distcp +3 -0
  16. stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__4_0.distcp +3 -0
  17. stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__5_0.distcp +3 -0
  18. stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__6_0.distcp +3 -0
  19. stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__7_0.distcp +3 -0
  20. stage2c-hrm-full-nocap-repeat2-step580000/latest_checkpoint.txt +1 -0
  21. stage2c-hrm-full-nocap-repeat2-step580000/step_580000_info.json +8 -0
  22. stage2c-hrm-full-nocap-repeat2-step580000/train_metadata.yaml +13 -0
  23. stage2c-hrm-full-nocap-repeat2-step580000/upload_manifest.json +1 -0
.gitattributes CHANGED
@@ -699,3 +699,12 @@ stage2c-hrm-full-nocap-repeat2-step570000/fsdp2_step_570000/__4_0.distcp filter=
699
  stage2c-hrm-full-nocap-repeat2-step570000/fsdp2_step_570000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
700
  stage2c-hrm-full-nocap-repeat2-step570000/fsdp2_step_570000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
701
  stage2c-hrm-full-nocap-repeat2-step570000/fsdp2_step_570000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
699
  stage2c-hrm-full-nocap-repeat2-step570000/fsdp2_step_570000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
700
  stage2c-hrm-full-nocap-repeat2-step570000/fsdp2_step_570000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
701
  stage2c-hrm-full-nocap-repeat2-step570000/fsdp2_step_570000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
702
+ stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
703
+ stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
704
+ stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/.metadata filter=lfs diff=lfs merge=lfs -text
705
+ stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
706
+ stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
707
+ stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
708
+ stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
709
+ stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
710
+ stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
stage2c-hrm-full-nocap-repeat2-step580000/all_config.yaml ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ arch:
2
+ H_cycles: 2
3
+ H_override: {}
4
+ L_cycles: 3
5
+ bp_max_steps: 5
6
+ bp_warmup_ratio: 0.2
7
+ expansion: 4
8
+ half_layers: true
9
+ head: lm_head@LMHead
10
+ hidden_size: 1536
11
+ init_type: lecun_normal
12
+ n_layers: 32
13
+ name: baselines.hrm_nocarry_bp_warmup@HierarchicalReasoningModel
14
+ norm_eps: 1.0e-06
15
+ norm_type: pre
16
+ num_heads: 12
17
+ pos_emb_type: rope
18
+ rope_theta: 10000.0
19
+ beta1: 0.9
20
+ beta2: 0.95
21
+ checkpoint_interval: 1
22
+ checkpoint_keep_last: 2
23
+ checkpoint_path: /home/work/.data/hrm_text_checkpoints/KoHRM-Text-1.4B-stage2c-hrm-full-nocap-repeat2-gbs180
24
+ checkpoint_step_interval: 10000
25
+ data:
26
+ path: /home/work/.data/hrm_text_prepared/koterm_hrm_cleaned_full_nocap_v1
27
+ target_only: true
28
+ ema: 0.9999
29
+ epochs: 1
30
+ fwd_bwd_dtype: bfloat16
31
+ global_batch_size: 180224
32
+ log_interval: 5
33
+ lr: 0.00022
34
+ lr_min_ratio: 1.0
35
+ lr_warmup_steps: 2000
36
+ project_name: KoHRM-Text
37
+ resume_epoch: null
38
+ resume_from: /home/work/.data/hrm_text_checkpoints/KoHRM-Text-1.4B-stage1c-hrm-fastcap-repeat2-gbs180
39
+ resume_step: null
40
+ resume_step_offset: 550699
41
+ run_name: KoHRM-Text-1.4B-stage2c-hrm-full-nocap-repeat2
42
+ seed: 0
43
+ skip_batches: 0
44
+ total_steps_override: 700000
45
+ weight_decay: 0.1
46
+ weights_only_resume_from_ema: false
stage2c-hrm-full-nocap-repeat2-step580000/carry_step_580000.0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a9895594d496487455846598fa83d899165393a4ac5b0f80f1c068558afc626
3
+ size 1333
stage2c-hrm-full-nocap-repeat2-step580000/carry_step_580000.1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfa55f89ae381c724efe0d23cee12e200402630e2c265c428275ee84ba804792
3
+ size 1333
stage2c-hrm-full-nocap-repeat2-step580000/carry_step_580000.2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01db223a23443f249b3834afcb1edf7661feb6f697088d5ad5ef6d4176d30ff1
3
+ size 1333
stage2c-hrm-full-nocap-repeat2-step580000/carry_step_580000.3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d173bb52e06289a3d3d262de543f41688701636b6a447ba69867789ddfe5658
3
+ size 1333
stage2c-hrm-full-nocap-repeat2-step580000/carry_step_580000.4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61ae520fb82e85b584bc70f11b475793f43b41037e8fc769a6d78b4e880d3f82
3
+ size 1333
stage2c-hrm-full-nocap-repeat2-step580000/carry_step_580000.5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f6be86ddd69c2e789193b167a071db3b1a495748b2ddac7a922286ca7872df9
3
+ size 1333
stage2c-hrm-full-nocap-repeat2-step580000/carry_step_580000.6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aad98caf77797b33dc50f3a179bfa5ab5328df0b231e11f53a2e4b71a2788154
3
+ size 1333
stage2c-hrm-full-nocap-repeat2-step580000/carry_step_580000.7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d2821347776181c41e9115d3d3edd7326a7a5052cbcbc87a927c6c79c4bb7bb
3
+ size 1333
stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/.metadata ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:139fe7898d021b4570d46c29c37125e987d0deea3b078e307dc3159070470725
3
+ size 983815
stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__0_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9402ef8f3950c9820c5cc0a1c31c3bc3dd31fa4fde24eec4f48f9a2cc3537f54
3
+ size 2769065329
stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__1_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cd34d8ec137c9870cb076731761ea9c1a256d2bbba9ee9d0906503df0075518
3
+ size 2769090643
stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__2_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbc69cb22b0e18cc10b8d06a9be3b072c64c27b535b9b7d16d2438d895dfecda
3
+ size 2769090643
stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__3_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0308a2f49b13ded4b7f7e99fed3745f55c2d77e78ebf3087e3632abcbd8ae514
3
+ size 2769090643
stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__4_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fee568c4a579bc5e68c7b5c298c7a4c18a31859471ecd95873acdc1083a9086d
3
+ size 2769090643
stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__5_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b796bdf82e8036db5a1f646b9e1767b0cd6c7cdf1318c6a6c2f7c7a8968eff70
3
+ size 2769090643
stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__6_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fac67a69b14369d248d6fda6951a54eb6df68784a31aa9eac532c13516ea309a
3
+ size 2769091588
stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__7_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97ae880ece3774b4b300a974e7b27cd9dd805e8d56d354fa3d46e2b08f66945e
3
+ size 2769098756
stage2c-hrm-full-nocap-repeat2-step580000/latest_checkpoint.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ step_580000
stage2c-hrm-full-nocap-repeat2-step580000/step_580000_info.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "tag": "step_580000",
3
+ "global_step": 580000,
4
+ "stage_start_step": 550699,
5
+ "skip_batches_hint": 29301,
6
+ "data_path": "/home/work/.data/hrm_text_prepared/koterm_hrm_cleaned_full_nocap_v1",
7
+ "global_batch_size": 180224
8
+ }
stage2c-hrm-full-nocap-repeat2-step580000/train_metadata.yaml ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ max_seq_len: 4096
2
+ tokenizer_info:
3
+ boq: <|im_start|>
4
+ condition_mapping:
5
+ cot: <|object_ref_end|>
6
+ direct: <|object_ref_start|>
7
+ noisy: <|quad_start|>
8
+ synth: <|quad_end|>
9
+ eoa: <|box_end|>
10
+ eoq: <|im_end|>
11
+ tokenizer_path: /home/work/.data/huggingface/trained_tokenizers/hrm-ko-terminal-131k-v1/tokenizer.json
12
+ total_length: 14553653061
13
+ vocab_size: 131072
stage2c-hrm-full-nocap-repeat2-step580000/upload_manifest.json ADDED
@@ -0,0 +1 @@
 
 
1
+ stage2c-hrm-full-nocap-repeat2 step_580000 raw resume checkpoint