| { | |
| "best_metric": 1.5111960172653198, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 2.6058631921824107, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05211726384364821, | |
| "grad_norm": 0.2591265141963959, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5446, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05211726384364821, | |
| "eval_loss": 1.7352440357208252, | |
| "eval_runtime": 1.5465, | |
| "eval_samples_per_second": 84.06, | |
| "eval_steps_per_second": 10.992, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.10423452768729642, | |
| "grad_norm": 0.3195701241493225, | |
| "learning_rate": 0.0001, | |
| "loss": 1.67, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.1563517915309446, | |
| "grad_norm": 0.37172287702560425, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.7673, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.20846905537459284, | |
| "grad_norm": 0.4107956886291504, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.7723, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.26058631921824105, | |
| "grad_norm": 0.305014431476593, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.6542, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.3127035830618892, | |
| "grad_norm": 0.23137179017066956, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.519, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.36482084690553745, | |
| "grad_norm": 0.27529802918434143, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.5625, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.4169381107491857, | |
| "grad_norm": 0.29970821738243103, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.6496, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.46905537459283386, | |
| "grad_norm": 0.3417079448699951, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.6382, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.5211726384364821, | |
| "grad_norm": 0.23188437521457672, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.5449, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5732899022801303, | |
| "grad_norm": 0.22860518097877502, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.4941, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.6254071661237784, | |
| "grad_norm": 0.23443861305713654, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.5574, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.6775244299674267, | |
| "grad_norm": 0.2669665217399597, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.6183, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.7296416938110749, | |
| "grad_norm": 0.3732811510562897, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.6219, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.7817589576547231, | |
| "grad_norm": 0.19876886904239655, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.5135, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.8338762214983714, | |
| "grad_norm": 0.1795257329940796, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.5132, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.8859934853420195, | |
| "grad_norm": 0.17552366852760315, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.5645, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.9381107491856677, | |
| "grad_norm": 0.20799390971660614, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.5952, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.990228013029316, | |
| "grad_norm": 0.2864566445350647, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.5729, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.0423452768729642, | |
| "grad_norm": 0.37049034237861633, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.7564, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.0944625407166124, | |
| "grad_norm": 0.16121427714824677, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.4912, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.1465798045602607, | |
| "grad_norm": 0.17705480754375458, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.5317, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.1986970684039089, | |
| "grad_norm": 0.20234566926956177, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.5432, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.2508143322475571, | |
| "grad_norm": 0.1751578152179718, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.1263, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.3029315960912053, | |
| "grad_norm": 0.18956966698169708, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.8535, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.3029315960912053, | |
| "eval_loss": 1.5221261978149414, | |
| "eval_runtime": 1.5434, | |
| "eval_samples_per_second": 84.228, | |
| "eval_steps_per_second": 11.014, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.3550488599348534, | |
| "grad_norm": 0.1639164388179779, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4846, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.4071661237785016, | |
| "grad_norm": 0.18915408849716187, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.5516, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.4592833876221498, | |
| "grad_norm": 0.21086834371089935, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.5759, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.511400651465798, | |
| "grad_norm": 0.15464426577091217, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.303, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.5635179153094463, | |
| "grad_norm": 0.16771115362644196, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.6029, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.6156351791530945, | |
| "grad_norm": 0.16686154901981354, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.4701, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.6677524429967425, | |
| "grad_norm": 0.19988751411437988, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.545, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.7198697068403908, | |
| "grad_norm": 0.23184122145175934, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.5683, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.771986970684039, | |
| "grad_norm": 0.15493892133235931, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.3687, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.8241042345276872, | |
| "grad_norm": 0.16259148716926575, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.5158, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.8762214983713354, | |
| "grad_norm": 0.17531201243400574, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.4868, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.9283387622149837, | |
| "grad_norm": 0.19777899980545044, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.5352, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.980456026058632, | |
| "grad_norm": 0.2821734547615051, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.5323, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.03257328990228, | |
| "grad_norm": 0.37536874413490295, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 2.6423, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.0846905537459284, | |
| "grad_norm": 0.1467260718345642, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.3896, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.1368078175895766, | |
| "grad_norm": 0.16421370208263397, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.4957, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.188925081433225, | |
| "grad_norm": 0.19313547015190125, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.4973, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.241042345276873, | |
| "grad_norm": 0.19032856822013855, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.0895, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.2931596091205213, | |
| "grad_norm": 0.20216412842273712, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.87, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.3452768729641695, | |
| "grad_norm": 0.15414832532405853, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.4545, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.3973941368078178, | |
| "grad_norm": 0.17168298363685608, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.4898, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.449511400651466, | |
| "grad_norm": 0.20633788406848907, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.5513, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.5016286644951142, | |
| "grad_norm": 0.17030811309814453, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.0551, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.5537459283387625, | |
| "grad_norm": 0.1883995532989502, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.8285, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.6058631921824107, | |
| "grad_norm": 0.1657257378101349, | |
| "learning_rate": 0.0, | |
| "loss": 1.4567, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.6058631921824107, | |
| "eval_loss": 1.5111960172653198, | |
| "eval_runtime": 1.5423, | |
| "eval_samples_per_second": 84.287, | |
| "eval_steps_per_second": 11.022, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 1.059536353886208e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |