| { | |
| "best_metric": 0.4871082007884979, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.146131805157593, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.022922636103151862, | |
| "grad_norm": 31.6502742767334, | |
| "learning_rate": 5e-05, | |
| "loss": 5.3734, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.022922636103151862, | |
| "eval_loss": 5.7447590827941895, | |
| "eval_runtime": 2.6003, | |
| "eval_samples_per_second": 113.065, | |
| "eval_steps_per_second": 14.229, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.045845272206303724, | |
| "grad_norm": 32.82808303833008, | |
| "learning_rate": 0.0001, | |
| "loss": 4.9718, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06876790830945559, | |
| "grad_norm": 28.511812210083008, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 4.209, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.09169054441260745, | |
| "grad_norm": 13.637245178222656, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.7987, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.11461318051575932, | |
| "grad_norm": 4.1366658210754395, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.9741, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.13753581661891118, | |
| "grad_norm": 2.514648199081421, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.8654, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.16045845272206305, | |
| "grad_norm": 3.5103213787078857, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.9549, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.1833810888252149, | |
| "grad_norm": 6.054518222808838, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.0575, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.20630372492836677, | |
| "grad_norm": 5.0815815925598145, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.7392, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.22922636103151864, | |
| "grad_norm": 4.686445236206055, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.5844, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2521489971346705, | |
| "grad_norm": 4.0975565910339355, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.7778, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.27507163323782235, | |
| "grad_norm": 6.624898433685303, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.8382, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2979942693409742, | |
| "grad_norm": 4.663875102996826, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.6117, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.3209169054441261, | |
| "grad_norm": 5.501865386962891, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.5617, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3438395415472779, | |
| "grad_norm": 3.0963211059570312, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.5292, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3667621776504298, | |
| "grad_norm": 3.279914379119873, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.5894, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.38968481375358166, | |
| "grad_norm": 2.7416744232177734, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.522, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.41260744985673353, | |
| "grad_norm": 3.031243324279785, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.5461, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.4355300859598854, | |
| "grad_norm": 3.002058506011963, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.5502, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.4584527220630373, | |
| "grad_norm": 2.168818473815918, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.5598, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.4813753581661891, | |
| "grad_norm": 2.2690036296844482, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.4805, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.504297994269341, | |
| "grad_norm": 3.7220213413238525, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.8447, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.5272206303724928, | |
| "grad_norm": 2.7926387786865234, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.6777, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.5501432664756447, | |
| "grad_norm": 5.17102575302124, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.5588, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5730659025787965, | |
| "grad_norm": 2.3544936180114746, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.4681, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5730659025787965, | |
| "eval_loss": 0.5292229652404785, | |
| "eval_runtime": 2.599, | |
| "eval_samples_per_second": 113.121, | |
| "eval_steps_per_second": 14.236, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5959885386819485, | |
| "grad_norm": 2.372102975845337, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5179, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.6189111747851003, | |
| "grad_norm": 1.839175820350647, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.443, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.6418338108882522, | |
| "grad_norm": 2.125877857208252, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.5021, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.664756446991404, | |
| "grad_norm": 1.3504488468170166, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.4931, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.6876790830945558, | |
| "grad_norm": 2.0473389625549316, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.5186, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.7106017191977078, | |
| "grad_norm": 3.015089273452759, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.5055, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.7335243553008596, | |
| "grad_norm": 3.7230453491210938, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.5307, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.7564469914040115, | |
| "grad_norm": 3.5798141956329346, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.9552, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.7793696275071633, | |
| "grad_norm": 3.0358645915985107, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.673, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.8022922636103151, | |
| "grad_norm": 3.3272151947021484, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.5957, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.8252148997134671, | |
| "grad_norm": 1.9087271690368652, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.4367, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.8481375358166189, | |
| "grad_norm": 1.8877273797988892, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.4389, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.8710601719197708, | |
| "grad_norm": 1.7177760601043701, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.4901, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.8939828080229226, | |
| "grad_norm": 1.89617121219635, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.4447, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.9169054441260746, | |
| "grad_norm": 1.4989944696426392, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.5251, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.9398280802292264, | |
| "grad_norm": 1.7579575777053833, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.4943, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.9627507163323782, | |
| "grad_norm": 1.385714054107666, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.53, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.9856733524355301, | |
| "grad_norm": 1.1276830434799194, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.4551, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.008595988538682, | |
| "grad_norm": 4.495203495025635, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.1086, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.0315186246418337, | |
| "grad_norm": 1.7150007486343384, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.6485, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.0544412607449858, | |
| "grad_norm": 0.8887443542480469, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.4886, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.0773638968481376, | |
| "grad_norm": 1.4859352111816406, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.4817, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.1002865329512894, | |
| "grad_norm": 1.5945063829421997, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.4495, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.1232091690544412, | |
| "grad_norm": 1.5430727005004883, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.4143, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.146131805157593, | |
| "grad_norm": 2.9990031719207764, | |
| "learning_rate": 0.0, | |
| "loss": 0.3694, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.146131805157593, | |
| "eval_loss": 0.4871082007884979, | |
| "eval_runtime": 2.604, | |
| "eval_samples_per_second": 112.904, | |
| "eval_steps_per_second": 14.209, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.879368894316544e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |