prune main-v1 step 13200

checkpoints/main-v1/step_0013200/model.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b254b00a4e1641f10fc8fa603d69aec95913d4c272e2919931f997a938afac7c
-size 604159003

checkpoints/main-v1/step_0013200/optim.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5f7756a2649fa92ab37b693441d31eb2a578cf62a8001f227c39d2f7af016cd9
-size 755298763

checkpoints/main-v1/step_0013200/state.json

@@ -1 +0,0 @@
-{"step": 13200, "tokens": 6920601600, "scaler": {"scale": 262144.0, "growth_factor": 2.0, "backoff_factor": 0.5, "growth_interval": 1000, "_growth_tracker": 657}, "loader": {"mixer": {"doc_index": 18300755, "docs_by_src": {"fineweb_edu": 1472266, "wikipedia_en": 592755, "ufw_en_multistyle": 622135, "nem12_fact": 2458805, "cc_math_4plus": 857106, "finemath_4plus": 327870, "infiwebmath_4plus": 299055, "arithmetic_reasoning": 8746416, "math_sft": 145134, "decimal_addition": 40458, "operand_addition": 19601, "decimal_compare": 12742, "orca_math": 6750, "pp2_arxiv": 167, "pp2_web": 660, "pp2_formal": 154, "pp2_python": 564, "pp2_matlab_jupyter": 91, "pp2_tex": 111, "ifm_math_rewrite": 1012, "ifm_math_think_qwen": 824, "ifm_math_think_oss": 1241, "ifm_math_dialogue": 1300, "chat_smoltalk": 206961, "code_python": 844775, "code_java": 387047, "code_javascript": 477872, "code_html": 73221, "code_css": 52938, "code_markdown": 152920, "code_tex": 45288, "nem11_code_concepts": 452516}, "readers": {"fineweb_edu": {"epoch": 1, "file_pos": 2, "row": 13266}, "wikipedia_en": {"epoch": 1, "file_pos": 3, "row": 123890}, "ufw_en_multistyle": {"epoch": 1, "file_pos": 0, "row": 622135}, "nem12_fact": {"epoch": 1, "file_pos": 0, "row": 2458805}, "cc_math_4plus": {"epoch": 1, "file_pos": 0, "row": 857106}, "finemath_4plus": {"epoch": 1, "file_pos": 3, "row": 13832}, "infiwebmath_4plus": {"epoch": 1, "file_pos": 1, "row": 102298}, "arithmetic_reasoning": {"epoch": 1, "file_pos": 3, "row": 1246416}, "math_sft": {"epoch": 1, "byte": 8205481100}, "decimal_addition": {"epoch": 1, "byte": 1009051}, "operand_addition": {"epoch": 1, "byte": 377658}, "decimal_compare": {"epoch": 1, "file_pos": 0, "row": 12742}, "orca_math": {"epoch": 1, "file_pos": 0, "row": 6750}, "pp2_arxiv": {"epoch": 1, "file_pos": 0, "line": 167}, "pp2_web": {"epoch": 1, "file_pos": 0, "line": 660}, "pp2_formal": {"epoch": 1, "file_pos": 0, "line": 154}, "pp2_python": {"epoch": 1, "file_pos": 0, "line": 564}, "pp2_matlab_jupyter": {"epoch": 1, "file_pos": 0, "line": 91}, "pp2_tex": {"epoch": 1, "file_pos": 0, "line": 111}, "ifm_math_rewrite": {"epoch": 1, "file_pos": 0, "row": 1012}, "ifm_math_think_qwen": {"epoch": 1, "file_pos": 0, "row": 824}, "ifm_math_think_oss": {"epoch": 1, "file_pos": 0, "row": 1241}, "ifm_math_dialogue": {"epoch": 1, "file_pos": 0, "row": 1300}, "chat_smoltalk": {"epoch": 1, "file_pos": 1, "row": 90970}, "code_python": {"epoch": 1, "file_pos": 3, "row": 190539}, "code_java": {"epoch": 1, "file_pos": 1, "row": 156337}, "code_javascript": {"epoch": 1, "file_pos": 1, "row": 177191}, "code_html": {"epoch": 1, "file_pos": 0, "row": 73221}, "code_css": {"epoch": 1, "file_pos": 0, "row": 52938}, "code_markdown": {"epoch": 1, "file_pos": 0, "row": 152920}, "code_tex": {"epoch": 1, "file_pos": 0, "row": 45288}, "nem11_code_concepts": {"epoch": 1, "file_pos": 1, "row": 202516}}, "dead": [], "cons": {"1": [1175872346.33, 415009963.94, 276672336.96000004, 207476399.47, 713147410.145, 412168019.94, 343744049.45000005, 482531928.43000007, 71794421.49000001, 2624942.0, 1049301.0, 1050292.0, 1314014.0, 2628611.0, 1059466.0, 1053642.0, 1055187.0, 526172.0, 527798.0, 2102903.0, 2106683.0, 2105183.0, 1577283.0, 207506956.47, 830025595.88, 449595635.185, 484173887.43000007, 200594815.82099998, 83059881.788, 172918887.22500002, 138353785.98000002, 235171974.066], "2": [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0]}, "tgt": {"1": [1175875783.292643, 415012455.985669, 276675946.6570624, 207500316.9928345, 713133924.4303638, 412151747.0358673, 343742125.9942618, 482588140.40462685, 71797330.07315516, 2628515.408887229, 1051406.1635549136, 1051406.1635549136, 1314257.7044436145, 2628515.408887229, 1051406.1635549136, 1051406.1635549136, 1051406.1635549136, 525703.0817774568, 525703.0817774568, 2102812.327109827, 2102812.327109827, 2102812.327109827, 1577109.2453323277, 207507544.9928345, 830030651.971338, 449599076.8177971, 484181443.64986527, 200592787.22640374, 83005956.19712684, 172921987.16069782, 138342784.32853115, 235174498.05854037], "2": [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0]}, "anchor": 5662308734.0, "mix_sig": "283364ab6d6c7ac3", "names": ["fineweb_edu", "wikipedia_en", "ufw_en_multistyle", "nem12_fact", "cc_math_4plus", "finemath_4plus", "infiwebmath_4plus", "arithmetic_reasoning", "math_sft", "decimal_addition", "operand_addition", "decimal_compare", "orca_math", "pp2_arxiv", "pp2_web", "pp2_formal", "pp2_python", "pp2_matlab_jupyter", "pp2_tex", "ifm_math_rewrite", "ifm_math_think_qwen", "ifm_math_think_oss", "ifm_math_dialogue", "chat_smoltalk", "code_python", "code_java", "code_javascript", "code_html", "code_css", "code_markdown", "code_tex", "nem11_code_concepts"]}, "pos": 161, "tokens_by_src": {"fineweb_edu": 1366722086, "wikipedia_en": 376845367, "ufw_en_multistyle": 276671758, "nem12_fact": 169304251, "cc_math_4plus": 713145840, "finemath_4plus": 412165773, "infiwebmath_4plus": 343742477, "arithmetic_reasoning": 520684571, "math_sft": 71793722, "decimal_addition": 2624942, "operand_addition": 1049301, "decimal_compare": 1050292, "orca_math": 1314014, "pp2_arxiv": 2628611, "pp2_web": 1059466, "pp2_formal": 1053642, "pp2_python": 1055187, "pp2_matlab_jupyter": 526172, "pp2_tex": 527798, "ifm_math_rewrite": 2102903, "ifm_math_think_qwen": 2106683, "ifm_math_think_oss": 2105183, "ifm_math_dialogue": 1577283, "chat_smoltalk": 150254353, "code_python": 982696334, "code_java": 373257260, "code_javascript": 407846441, "code_html": 166253437, "code_css": 67792616, "code_markdown": 172917164, "code_tex": 138355953, "nem11_code_concepts": 189368893}}, "cfg": {"vocab": 49152, "d": 768, "layers": 18, "heads": 12, "kv_heads": 4, "head_dim": 64, "ffn": 2048, "rope_theta": 500000.0, "max_seq": 2048, "norm_eps": 1e-05, "init_std": 0.02, "qk_norm": true, "mtp": 0, "recurrent": 1}, "args": {"run": "main-v1", "repo": "Arko007/Zenyx-100M-Base", "tokenizer": "tokenizer_candidates_v3/F-49152-f70/tokenizer.json", "manifest": "data/manifest_z100m.json", "seed": 1234, "vocab": 49152, "d": 768, "layers": 18, "heads": 12, "kv_heads": 4, "ffn": 2048, "recurrent": 1, "mtp": 0, "mtp_weight": 0.3, "seq": 2048, "micro_batch": 8, "global_tokens": 524288, "optimizer": "muon", "lr": 0.002, "muon_lr": 0.012, "muon_wd": 0.0015, "min_lr_ratio": 0.1, "warmup_steps": 400, "wd": 0.1, "clip": 1.0, "total_tokens": 35000000000.0, "decay_start_tokens": 3900000000.0, "decay_end_tokens": 15000000000.0, "phase2_start_tokens": 31000000000.0, "eval_every": 250, "save_every_steps": 100, "session_hours": 11.2, "work_dir": "/kaggle/working/z100", "compile": true, "fsdp": false, "synthetic": false, "bench_steps": 0, "no_hf": false, "sources": ""}}