gyung commited on
Commit
0c84bd6
·
verified ·
1 Parent(s): f27d044

Add files using upload-large-folder tool

Browse files
Files changed (23) hide show
  1. .gitattributes +9 -0
  2. stage2c-hrm-full-nocap-repeat2-step590000/all_config.yaml +46 -0
  3. stage2c-hrm-full-nocap-repeat2-step590000/carry_step_590000.0.pt +3 -0
  4. stage2c-hrm-full-nocap-repeat2-step590000/carry_step_590000.1.pt +3 -0
  5. stage2c-hrm-full-nocap-repeat2-step590000/carry_step_590000.2.pt +3 -0
  6. stage2c-hrm-full-nocap-repeat2-step590000/carry_step_590000.3.pt +3 -0
  7. stage2c-hrm-full-nocap-repeat2-step590000/carry_step_590000.4.pt +3 -0
  8. stage2c-hrm-full-nocap-repeat2-step590000/carry_step_590000.5.pt +3 -0
  9. stage2c-hrm-full-nocap-repeat2-step590000/carry_step_590000.6.pt +3 -0
  10. stage2c-hrm-full-nocap-repeat2-step590000/carry_step_590000.7.pt +3 -0
  11. stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/.metadata +3 -0
  12. stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__0_0.distcp +3 -0
  13. stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__1_0.distcp +3 -0
  14. stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__2_0.distcp +3 -0
  15. stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__3_0.distcp +3 -0
  16. stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__4_0.distcp +3 -0
  17. stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__5_0.distcp +3 -0
  18. stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__6_0.distcp +3 -0
  19. stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__7_0.distcp +3 -0
  20. stage2c-hrm-full-nocap-repeat2-step590000/latest_checkpoint.txt +1 -0
  21. stage2c-hrm-full-nocap-repeat2-step590000/step_590000_info.json +8 -0
  22. stage2c-hrm-full-nocap-repeat2-step590000/train_metadata.yaml +13 -0
  23. stage2c-hrm-full-nocap-repeat2-step590000/upload_manifest.json +1 -0
.gitattributes CHANGED
@@ -708,3 +708,12 @@ stage2c-hrm-full-nocap-repeat2-step580000/fsdp2_step_580000/__1_0.distcp filter=
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
 
 
 
 
 
 
 
 
 
 
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
711
+ stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
712
+ stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
713
+ stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
714
+ stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/.metadata filter=lfs diff=lfs merge=lfs -text
715
+ stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
716
+ stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
717
+ stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
718
+ stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
719
+ stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
stage2c-hrm-full-nocap-repeat2-step590000/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-step590000/carry_step_590000.0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5725b1c387d769870ee247d66d644856de4f414c6028a43b8b831e4f416942f2
3
+ size 1333
stage2c-hrm-full-nocap-repeat2-step590000/carry_step_590000.1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4bc44d89cd6baf153cf40a385fa3a7626c96f54c4383f0904c96e535fe2cdfe
3
+ size 1333
stage2c-hrm-full-nocap-repeat2-step590000/carry_step_590000.2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4e2a1e577fea76e7c3cf73fe2c0db8fd0de37728a2b1a05ded2190bb5c91101
3
+ size 1333
stage2c-hrm-full-nocap-repeat2-step590000/carry_step_590000.3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8206d5c40f00a09247b1e8af38584c630a246352e525ea8d354b14178f3697e4
3
+ size 1333
stage2c-hrm-full-nocap-repeat2-step590000/carry_step_590000.4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c86553a7c52f4228de77b25e21e79723bb967c7fc972bb1c6a46e10e96377c7b
3
+ size 1333
stage2c-hrm-full-nocap-repeat2-step590000/carry_step_590000.5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c776002f3c55db0d1944baa3b5af451d7e841463c6806ddd1b81026cb2042164
3
+ size 1333
stage2c-hrm-full-nocap-repeat2-step590000/carry_step_590000.6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e271413c5f589106bee9d649c01b32299da9396cf7fd241822a7234777442b2
3
+ size 1333
stage2c-hrm-full-nocap-repeat2-step590000/carry_step_590000.7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3a2cde857e21576a0611366c0f11cc8fbced20ecf504ecb80d624d9c9686482
3
+ size 1333
stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/.metadata ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0992f844ba808553761f04e30dc3352e79e54a0d1297f268ead6892d2ae5e735
3
+ size 983815
stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__0_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0f2ea1a8dfd4b42594448ced0753f1b7c71aed6a7deb8c55794c5727e08a76f
3
+ size 2769065329
stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__1_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:626dca18022e89e130c34ba6b433eccc088994e58d13ff4d7748ce00de830dfc
3
+ size 2769090643
stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__2_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bddb19b49d5a6fa6982517b20f0781def9d3cce07d62d195f4fff56e012df655
3
+ size 2769090643
stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__3_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bba7d216474b560ea98c6d821deeb77f5e1ffaadf085062dfab2167b68ca8e4
3
+ size 2769090643
stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__4_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48562f50462dda92664c19ec01e0aff2c697c4a4be870beee41344956e2e4131
3
+ size 2769090643
stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__5_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b542f7d60015e75687969436a41367090ee3ec8e763c673c160481de2128431f
3
+ size 2769090643
stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__6_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d397b5b7925b1458cccbbbbeefb0e53d7e34adcccaa990720bad00dfa580c406
3
+ size 2769091588
stage2c-hrm-full-nocap-repeat2-step590000/fsdp2_step_590000/__7_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54a0dabddce84b6fa33779474874694524a9f631812b2e2d44c8dad647319dbc
3
+ size 2769098756
stage2c-hrm-full-nocap-repeat2-step590000/latest_checkpoint.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ step_590000
stage2c-hrm-full-nocap-repeat2-step590000/step_590000_info.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "tag": "step_590000",
3
+ "global_step": 590000,
4
+ "stage_start_step": 550699,
5
+ "skip_batches_hint": 39301,
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-step590000/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-step590000/upload_manifest.json ADDED
@@ -0,0 +1 @@
 
 
1
+ stage2c-hrm-full-nocap-repeat2 step_590000 raw resume checkpoint