| { | |
| "best_metric": 2.8746941089630127, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.03696345238645289, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007392690477290579, | |
| "grad_norm": 0.5899631381034851, | |
| "learning_rate": 5e-05, | |
| "loss": 3.1577, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007392690477290579, | |
| "eval_loss": 4.195895195007324, | |
| "eval_runtime": 865.6969, | |
| "eval_samples_per_second": 10.527, | |
| "eval_steps_per_second": 1.317, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0014785380954581157, | |
| "grad_norm": 0.9179840087890625, | |
| "learning_rate": 0.0001, | |
| "loss": 3.4383, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0022178071431871735, | |
| "grad_norm": 0.5260173082351685, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 3.5455, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0029570761909162315, | |
| "grad_norm": 0.7313174605369568, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.5409, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0036963452386452895, | |
| "grad_norm": 0.979415774345398, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.6271, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004435614286374347, | |
| "grad_norm": 1.1546862125396729, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 3.6092, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0051748833341034054, | |
| "grad_norm": 1.218363881111145, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 3.6873, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.005914152381832463, | |
| "grad_norm": 1.4240988492965698, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.6761, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.006653421429561521, | |
| "grad_norm": 1.612452745437622, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 3.6272, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007392690477290579, | |
| "grad_norm": 1.4315338134765625, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 3.6157, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008131959525019637, | |
| "grad_norm": 1.5918232202529907, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 3.85, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.008871228572748694, | |
| "grad_norm": 2.2506461143493652, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 3.8784, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.009610497620477753, | |
| "grad_norm": 0.939863920211792, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.7675, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.010349766668206811, | |
| "grad_norm": 0.9917090535163879, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.8671, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.011089035715935868, | |
| "grad_norm": 0.8895948529243469, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.8104, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.011828304763664926, | |
| "grad_norm": 0.5161738991737366, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.875, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.012567573811393984, | |
| "grad_norm": 0.44667163491249084, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 2.9779, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.013306842859123043, | |
| "grad_norm": 1.2807832956314087, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.9311, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0140461119068521, | |
| "grad_norm": 1.3295377492904663, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.9182, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.014785380954581158, | |
| "grad_norm": 3.2571310997009277, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 3.0558, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.015524650002310215, | |
| "grad_norm": 2.760071039199829, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 3.1078, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.016263919050039273, | |
| "grad_norm": 1.915663480758667, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 3.1278, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01700318809776833, | |
| "grad_norm": 3.2026872634887695, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 3.2755, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.017742457145497388, | |
| "grad_norm": 2.9645938873291016, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 3.3173, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.018481726193226446, | |
| "grad_norm": 2.4532947540283203, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 3.4003, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.018481726193226446, | |
| "eval_loss": 2.9501051902770996, | |
| "eval_runtime": 722.8366, | |
| "eval_samples_per_second": 12.607, | |
| "eval_steps_per_second": 1.577, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.019220995240955507, | |
| "grad_norm": 1.693276286125183, | |
| "learning_rate": 5e-05, | |
| "loss": 2.6401, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.019960264288684564, | |
| "grad_norm": 1.0544100999832153, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 2.6809, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.020699533336413622, | |
| "grad_norm": 0.579472541809082, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 2.7445, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.02143880238414268, | |
| "grad_norm": 0.3539687395095825, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 2.787, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.022178071431871737, | |
| "grad_norm": 0.556016206741333, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 2.8372, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.022917340479600794, | |
| "grad_norm": 1.2517012357711792, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 2.8282, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.023656609527329852, | |
| "grad_norm": 0.893120527267456, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.8801, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.02439587857505891, | |
| "grad_norm": 0.5094900131225586, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 2.9071, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.025135147622787967, | |
| "grad_norm": 0.5577306151390076, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 3.0599, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.025874416670517025, | |
| "grad_norm": 0.7083209753036499, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 3.0671, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.026613685718246086, | |
| "grad_norm": 0.6681864261627197, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 3.06, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.027352954765975143, | |
| "grad_norm": 1.5164320468902588, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 3.1144, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0280922238137042, | |
| "grad_norm": 0.5328857898712158, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.5182, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.02883149286143326, | |
| "grad_norm": 0.5679588913917542, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 2.6474, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.029570761909162316, | |
| "grad_norm": 0.572334885597229, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 2.6516, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.030310030956891373, | |
| "grad_norm": 0.49107661843299866, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 2.713, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.03104930000462043, | |
| "grad_norm": 0.5361040234565735, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 2.7698, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.03178856905234949, | |
| "grad_norm": 0.3799886405467987, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 2.8387, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.032527838100078546, | |
| "grad_norm": 0.5287345051765442, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.8234, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.033267107147807604, | |
| "grad_norm": 0.40399202704429626, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 2.9415, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03400637619553666, | |
| "grad_norm": 0.46025046706199646, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 3.0313, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.03474564524326572, | |
| "grad_norm": 0.6588468551635742, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 2.9097, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.035484914290994776, | |
| "grad_norm": 0.8728823065757751, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 3.0909, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.036224183338723834, | |
| "grad_norm": 0.7503541111946106, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 3.1122, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.03696345238645289, | |
| "grad_norm": 2.220900774002075, | |
| "learning_rate": 0.0, | |
| "loss": 3.272, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03696345238645289, | |
| "eval_loss": 2.8746941089630127, | |
| "eval_runtime": 430.3227, | |
| "eval_samples_per_second": 21.177, | |
| "eval_steps_per_second": 2.649, | |
| "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": 1.0228361536208896e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |