gyung commited on
Commit
0c7286f
·
verified ·
1 Parent(s): 8ec82cd

Add files using upload-large-folder tool

Browse files
Files changed (23) hide show
  1. .gitattributes +9 -0
  2. stage3c-local-terminal-repeat2-step680000/all_config.yaml +46 -0
  3. stage3c-local-terminal-repeat2-step680000/carry_step_680000.0.pt +3 -0
  4. stage3c-local-terminal-repeat2-step680000/carry_step_680000.1.pt +3 -0
  5. stage3c-local-terminal-repeat2-step680000/carry_step_680000.2.pt +3 -0
  6. stage3c-local-terminal-repeat2-step680000/carry_step_680000.3.pt +3 -0
  7. stage3c-local-terminal-repeat2-step680000/carry_step_680000.4.pt +3 -0
  8. stage3c-local-terminal-repeat2-step680000/carry_step_680000.5.pt +3 -0
  9. stage3c-local-terminal-repeat2-step680000/carry_step_680000.6.pt +3 -0
  10. stage3c-local-terminal-repeat2-step680000/carry_step_680000.7.pt +3 -0
  11. stage3c-local-terminal-repeat2-step680000/fsdp2_step_680000/.metadata +3 -0
  12. stage3c-local-terminal-repeat2-step680000/fsdp2_step_680000/__0_0.distcp +3 -0
  13. stage3c-local-terminal-repeat2-step680000/fsdp2_step_680000/__1_0.distcp +3 -0
  14. stage3c-local-terminal-repeat2-step680000/fsdp2_step_680000/__2_0.distcp +3 -0
  15. stage3c-local-terminal-repeat2-step680000/fsdp2_step_680000/__3_0.distcp +3 -0
  16. stage3c-local-terminal-repeat2-step680000/fsdp2_step_680000/__4_0.distcp +3 -0
  17. stage3c-local-terminal-repeat2-step680000/fsdp2_step_680000/__5_0.distcp +3 -0
  18. stage3c-local-terminal-repeat2-step680000/fsdp2_step_680000/__6_0.distcp +3 -0
  19. stage3c-local-terminal-repeat2-step680000/fsdp2_step_680000/__7_0.distcp +3 -0
  20. stage3c-local-terminal-repeat2-step680000/latest_checkpoint.txt +1 -0
  21. stage3c-local-terminal-repeat2-step680000/step_680000_info.json +8 -0
  22. stage3c-local-terminal-repeat2-step680000/train_metadata.yaml +13 -0
  23. stage3c-local-terminal-repeat2-step680000/upload_manifest.json +1 -0
.gitattributes CHANGED
@@ -807,3 +807,12 @@ stage3c-local-terminal-repeat2-step670000/fsdp2_step_670000/__7_0.distcp filter=
807
  stage3c-local-terminal-repeat2-step670000/fsdp2_step_670000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
808
  stage3c-local-terminal-repeat2-step670000/fsdp2_step_670000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
809
  stage3c-local-terminal-repeat2-step670000/fsdp2_step_670000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
807
  stage3c-local-terminal-repeat2-step670000/fsdp2_step_670000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
808
  stage3c-local-terminal-repeat2-step670000/fsdp2_step_670000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
809
  stage3c-local-terminal-repeat2-step670000/fsdp2_step_670000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
810
+ stage3c-local-terminal-repeat2-step680000/fsdp2_step_680000/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
811
+ stage3c-local-terminal-repeat2-step680000/fsdp2_step_680000/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
812
+ stage3c-local-terminal-repeat2-step680000/fsdp2_step_680000/.metadata filter=lfs diff=lfs merge=lfs -text
813
+ stage3c-local-terminal-repeat2-step680000/fsdp2_step_680000/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
814
+ stage3c-local-terminal-repeat2-step680000/fsdp2_step_680000/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
815
+ stage3c-local-terminal-repeat2-step680000/fsdp2_step_680000/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
816
+ stage3c-local-terminal-repeat2-step680000/fsdp2_step_680000/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
817
+ stage3c-local-terminal-repeat2-step680000/fsdp2_step_680000/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
818
+ stage3c-local-terminal-repeat2-step680000/fsdp2_step_680000/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
stage3c-local-terminal-repeat2-step680000/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-stage3c-local-terminal-repeat2-gbs180
24
+ checkpoint_step_interval: 10000
25
+ data:
26
+ path: /home/work/.data/hrm_text_prepared/local_terminal_conversations_ctx9k_resp6k_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-stage2c-hrm-full-nocap-repeat2-gbs180
39
+ resume_step: null
40
+ resume_step_offset: 631316
41
+ run_name: KoHRM-Text-1.4B-stage3c-local-terminal-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
stage3c-local-terminal-repeat2-step680000/carry_step_680000.0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dd9503de97916b7b2efa3ae3ca75b769a7e3d54911414792710b2df518f1859
3
+ size 1333
stage3c-local-terminal-repeat2-step680000/carry_step_680000.1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74e5ba23699315debb30b9ff3a354ec7b4ac723e8184b325a9c62c0fba19aea5
3
+ size 1333
stage3c-local-terminal-repeat2-step680000/carry_step_680000.2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:709bc8fd425b2f50a58f82051966f3854ee1a7eaf01689e5b9cd7db593912495
3
+ size 1333
stage3c-local-terminal-repeat2-step680000/carry_step_680000.3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:124b900a016d2d7ca40c4d27bdd98233f738ec2a05cbb756568245260aad985f
3
+ size 1333
stage3c-local-terminal-repeat2-step680000/carry_step_680000.4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db82092c9bf44174fdeabb749c069ff15f414b16eb479ef4802638d0689b47f4
3
+ size 1333
stage3c-local-terminal-repeat2-step680000/carry_step_680000.5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f258dfb73eb212aafc85d14deeda0dd63e875f181184d3ec213c1b3233a8041
3
+ size 1333
stage3c-local-terminal-repeat2-step680000/carry_step_680000.6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82c8d52e8a202e17aa1afeb2c78fec0fbfeaaafc1810417f005120a9b3fb0ff6
3
+ size 1333
stage3c-local-terminal-repeat2-step680000/carry_step_680000.7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61acdb476a0cae29392f6fce2599f412f61f3859e10f2c3fa76fe5778de3de89
3
+ size 1333
stage3c-local-terminal-repeat2-step680000/fsdp2_step_680000/.metadata ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6154ee58a5a7cd07879f6029ef8acd6d15df2501c85a14adcfc555d62373801
3
+ size 983815
stage3c-local-terminal-repeat2-step680000/fsdp2_step_680000/__0_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8304e107d3f65cbc19e485a6d26436b04b83857ce2055c185085e07ea8ee112
3
+ size 2769065329
stage3c-local-terminal-repeat2-step680000/fsdp2_step_680000/__1_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cc314c053601e5bf6c29fa3c9c8d6243ad9db96e00e7661b568e59e263ebd2f
3
+ size 2769090643
stage3c-local-terminal-repeat2-step680000/fsdp2_step_680000/__2_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8c1da631f4ab7c06de7a385afdff2b3682ffcb765314e9776f7c04bf159dac0
3
+ size 2769090643
stage3c-local-terminal-repeat2-step680000/fsdp2_step_680000/__3_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02230d1910ba46e9e0ad44e4ba5e8b971c668ba4702c1519637e6f5e39063966
3
+ size 2769090643
stage3c-local-terminal-repeat2-step680000/fsdp2_step_680000/__4_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:996ae444ffaa75da6e81bc571e2d324be1b57b793abe3e9940c3bdca2ff0888f
3
+ size 2769090643
stage3c-local-terminal-repeat2-step680000/fsdp2_step_680000/__5_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cb77a764df780d0f76f7b4aa4b5d733e21ac44ed5408139d38c8c9e1b984d42
3
+ size 2769090643
stage3c-local-terminal-repeat2-step680000/fsdp2_step_680000/__6_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b39746c5810162a5466eb836886248e46dff19bd58df62271a49d60043b0a06
3
+ size 2769091588
stage3c-local-terminal-repeat2-step680000/fsdp2_step_680000/__7_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd58802e78aef1d16a5bb637a3994972f6b6083667d47cdbcf7fca3037d91262
3
+ size 2769098756
stage3c-local-terminal-repeat2-step680000/latest_checkpoint.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ step_680000
stage3c-local-terminal-repeat2-step680000/step_680000_info.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "tag": "step_680000",
3
+ "global_step": 680000,
4
+ "stage_start_step": 631316,
5
+ "skip_batches_hint": 48684,
6
+ "data_path": "/home/work/.data/hrm_text_prepared/local_terminal_conversations_ctx9k_resp6k_v1",
7
+ "global_batch_size": 180224
8
+ }
stage3c-local-terminal-repeat2-step680000/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/hrm_text_prepared/local_terminal_conversations_ctx9k_resp6k_v1
12
+ total_length: 9386532467
13
+ vocab_size: 131072
stage3c-local-terminal-repeat2-step680000/upload_manifest.json ADDED
@@ -0,0 +1 @@
 
 
1
+ stage3c-local-terminal-repeat2 step_680000 raw resume checkpoint