prune pilot-d-f-m03 step 1200

checkpoints/pilot-d-f-m03/step_0001200/model.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3b875e174629762024c34e2fe36b5d3fb291a5d59bc92279b5a5cf69578f0aba
-size 604159003

checkpoints/pilot-d-f-m03/step_0001200/optim.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:38f1da0b542508a4235e2e78ffcc4fa1a50267e91921dbf723a1cb55f8062eab
-size 755298763

checkpoints/pilot-d-f-m03/step_0001200/state.json

@@ -1 +0,0 @@
-{"step": 1200, "tokens": 314572800, "scaler": {"scale": 65536.0, "growth_factor": 2.0, "backoff_factor": 0.5, "growth_interval": 1000, "_growth_tracker": 200}, "loader": {"mixer": {"doc_index": 838511, "docs_by_src": {"fineweb_edu": 74647, "wikipedia_en": 24337, "ufw_en_multistyle": 28708, "nem12_fact": 92466, "cc_math_4plus": 43317, "finemath_4plus": 15286, "infiwebmath_4plus": 13863, "arithmetic_reasoning": 427925, "math_sft": 6608, "chat_smoltalk": 6517, "code_python": 41148, "code_java": 15855, "code_javascript": 16955, "code_html": 2597, "code_css": 1863, "code_markdown": 7689, "code_tex": 2153, "nem11_code_concepts": 16577}, "readers": {"fineweb_edu": {"epoch": 1, "file_pos": 0, "row": 74647}, "wikipedia_en": {"epoch": 1, "file_pos": 0, "row": 24337}, "ufw_en_multistyle": {"epoch": 1, "file_pos": 0, "row": 28708}, "nem12_fact": {"epoch": 1, "file_pos": 0, "row": 92466}, "cc_math_4plus": {"epoch": 1, "file_pos": 0, "row": 43317}, "finemath_4plus": {"epoch": 1, "file_pos": 0, "row": 15286}, "infiwebmath_4plus": {"epoch": 1, "file_pos": 0, "row": 13863}, "arithmetic_reasoning": {"epoch": 1, "file_pos": 0, "row": 427925}, "math_sft": {"epoch": 1, "byte": 332661346}, "chat_smoltalk": {"epoch": 1, "file_pos": 0, "row": 6517}, "code_python": {"epoch": 1, "file_pos": 0, "row": 41148}, "code_java": {"epoch": 1, "file_pos": 0, "row": 15855}, "code_javascript": {"epoch": 1, "file_pos": 0, "row": 16955}, "code_html": {"epoch": 1, "file_pos": 0, "row": 2597}, "code_css": {"epoch": 1, "file_pos": 0, "row": 1863}, "code_markdown": {"epoch": 1, "file_pos": 0, "row": 7689}, "code_tex": {"epoch": 1, "file_pos": 0, "row": 2153}, "nem11_code_concepts": {"epoch": 1, "file_pos": 0, "row": 16577}}, "dead": [], "cons": {"1": [69204056.0, 15727531.0, 12580981.0, 6287687.0, 33029200.0, 18888311.0, 15730901.0, 25149428.0, 3145555.0, 4720166.0, 50330154.0, 14154769.0, 15727235.0, 6291825.0, 2519885.0, 7863401.0, 6301174.0, 6920497.0], "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]}}, "pos": 44, "tokens_by_src": {"fineweb_edu": 69204056, "wikipedia_en": 15727531, "ufw_en_multistyle": 12580981, "nem12_fact": 6287687, "cc_math_4plus": 33029200, "finemath_4plus": 18888311, "infiwebmath_4plus": 15730901, "arithmetic_reasoning": 25149428, "math_sft": 3145555, "chat_smoltalk": 4720166, "code_python": 50330154, "code_java": 14154769, "code_javascript": 15727235, "code_html": 6291825, "code_css": 2519885, "code_markdown": 7863401, "code_tex": 6301174, "nem11_code_concepts": 6920497}}, "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, "recurrent": 1}, "args": {"run": "pilot-d-f-m03", "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, "seq": 2048, "micro_batch": 8, "global_tokens": 262144, "optimizer": "muon", "lr": 0.002, "muon_lr": 0.03, "muon_wd": 0.0015, "min_lr_ratio": 0.1, "warmup_steps": 100, "wd": 0.1, "clip": 1.0, "total_tokens": 400000000.0, "decay_start_tokens": -1, "phase2_start_tokens": -1, "eval_every": 100, "save_every_steps": 200, "session_hours": 11.2, "work_dir": "/kaggle/working/z100", "compile": true, "fsdp": false, "synthetic": false, "bench_steps": 0, "no_hf": false, "sources": ""}}