| { | |
| "best_metric": 2.0190470218658447, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.11555683952043912, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0023111367904087824, | |
| "grad_norm": 4.737668037414551, | |
| "learning_rate": 5e-05, | |
| "loss": 8.8266, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0023111367904087824, | |
| "eval_loss": 10.756378173828125, | |
| "eval_runtime": 88.4893, | |
| "eval_samples_per_second": 32.942, | |
| "eval_steps_per_second": 4.125, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004622273580817565, | |
| "grad_norm": 4.769935131072998, | |
| "learning_rate": 0.0001, | |
| "loss": 8.5569, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006933410371226347, | |
| "grad_norm": 5.380407810211182, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 8.9336, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00924454716163513, | |
| "grad_norm": 12.746003150939941, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 8.4446, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.011555683952043911, | |
| "grad_norm": 8.30001449584961, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 7.601, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.013866820742452693, | |
| "grad_norm": 7.933149337768555, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 5.6546, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.016177957532861477, | |
| "grad_norm": 6.780417442321777, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 5.0568, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01848909432327026, | |
| "grad_norm": 6.728231430053711, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 4.211, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02080023111367904, | |
| "grad_norm": 7.113791465759277, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 3.9294, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.023111367904087823, | |
| "grad_norm": 4.8951311111450195, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 3.1353, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.025422504694496605, | |
| "grad_norm": 8.186279296875, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 3.0856, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.027733641484905387, | |
| "grad_norm": 8.730195045471191, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 3.2603, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03004477827531417, | |
| "grad_norm": 10.195311546325684, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.8125, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.032355915065722954, | |
| "grad_norm": 5.314338207244873, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.3914, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03466705185613173, | |
| "grad_norm": 3.3374502658843994, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.2778, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03697818864654052, | |
| "grad_norm": 6.324762344360352, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.4252, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.039289325436949296, | |
| "grad_norm": 4.7701239585876465, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 2.4389, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04160046222735808, | |
| "grad_norm": 2.40031361579895, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.0299, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04391159901776687, | |
| "grad_norm": 4.168339729309082, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.0835, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.046222735808175645, | |
| "grad_norm": 2.804626941680908, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.9547, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04853387259858443, | |
| "grad_norm": 2.20493745803833, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.9779, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05084500938899321, | |
| "grad_norm": 1.6454471349716187, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 2.051, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.053156146179401995, | |
| "grad_norm": 1.7552924156188965, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 2.1951, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.05546728296981077, | |
| "grad_norm": 1.9301644563674927, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 2.3227, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05777841976021956, | |
| "grad_norm": 2.2262816429138184, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 2.5943, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05777841976021956, | |
| "eval_loss": 2.122105836868286, | |
| "eval_runtime": 88.3962, | |
| "eval_samples_per_second": 32.977, | |
| "eval_steps_per_second": 4.129, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06008955655062834, | |
| "grad_norm": 2.3176376819610596, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7672, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.06240069334103712, | |
| "grad_norm": 1.6695570945739746, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.7331, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06471183013144591, | |
| "grad_norm": 1.470428705215454, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.8564, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0670229669218547, | |
| "grad_norm": 1.9413001537322998, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 2.0338, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.06933410371226346, | |
| "grad_norm": 1.4334675073623657, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.9684, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07164524050267225, | |
| "grad_norm": 1.4908390045166016, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.7507, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.07395637729308104, | |
| "grad_norm": 1.3455537557601929, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.818, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.07626751408348982, | |
| "grad_norm": 1.1437408924102783, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.7837, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.07857865087389859, | |
| "grad_norm": 1.5162749290466309, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.8623, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.08088978766430738, | |
| "grad_norm": 1.4613982439041138, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 2.086, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08320092445471616, | |
| "grad_norm": 0.9104688763618469, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 2.151, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.08551206124512495, | |
| "grad_norm": 1.7871757745742798, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 2.235, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.08782319803553373, | |
| "grad_norm": 1.5214916467666626, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.9367, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0901343348259425, | |
| "grad_norm": 2.2295875549316406, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.7298, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.09244547161635129, | |
| "grad_norm": 1.6196082830429077, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.7052, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09475660840676008, | |
| "grad_norm": 1.135953664779663, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.8029, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.09706774519716886, | |
| "grad_norm": 0.9740651845932007, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.9533, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.09937888198757763, | |
| "grad_norm": 1.0038777589797974, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.7188, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.10169001877798642, | |
| "grad_norm": 1.0359888076782227, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.746, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1040011555683952, | |
| "grad_norm": 1.179372787475586, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.8965, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.10631229235880399, | |
| "grad_norm": 1.2560983896255493, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.8588, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.10862342914921277, | |
| "grad_norm": 1.3571735620498657, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.9218, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.11093456593962155, | |
| "grad_norm": 1.9261860847473145, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 2.1027, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.11324570273003033, | |
| "grad_norm": 1.3769975900650024, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 2.0781, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.11555683952043912, | |
| "grad_norm": 1.6940319538116455, | |
| "learning_rate": 0.0, | |
| "loss": 2.5252, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11555683952043912, | |
| "eval_loss": 2.0190470218658447, | |
| "eval_runtime": 88.4389, | |
| "eval_samples_per_second": 32.961, | |
| "eval_steps_per_second": 4.127, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 5.968083617316864e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |