| { | |
| "best_metric": 3.9065983295440674, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.06749915626054674, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0013499831252109348, | |
| "grad_norm": 151.8303985595703, | |
| "learning_rate": 5e-05, | |
| "loss": 55.2222, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013499831252109348, | |
| "eval_loss": 110.49451446533203, | |
| "eval_runtime": 367.2894, | |
| "eval_samples_per_second": 13.586, | |
| "eval_steps_per_second": 1.699, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0026999662504218697, | |
| "grad_norm": 194.731689453125, | |
| "learning_rate": 0.0001, | |
| "loss": 73.7774, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004049949375632805, | |
| "grad_norm": 177.084716796875, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 72.807, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005399932500843739, | |
| "grad_norm": 225.96267700195312, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 65.2273, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006749915626054675, | |
| "grad_norm": 313.0947570800781, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 51.4295, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00809989875126561, | |
| "grad_norm": 407.1618957519531, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 40.1723, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009449881876476544, | |
| "grad_norm": 409.1275939941406, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 19.4778, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.010799865001687479, | |
| "grad_norm": 57.939823150634766, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 6.0572, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.012149848126898413, | |
| "grad_norm": 17.780284881591797, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 5.6456, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01349983125210935, | |
| "grad_norm": 99.7518539428711, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 6.3322, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.014849814377320284, | |
| "grad_norm": 94.86551666259766, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 6.2899, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.01619979750253122, | |
| "grad_norm": 22.37548065185547, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 6.2246, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.017549780627742154, | |
| "grad_norm": 13.087552070617676, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 4.3783, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01889976375295309, | |
| "grad_norm": 14.338868141174316, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 4.2968, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.020249746878164023, | |
| "grad_norm": 9.942703247070312, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 4.1482, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.021599730003374958, | |
| "grad_norm": 7.916289806365967, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 4.1814, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.022949713128585892, | |
| "grad_norm": 10.01076889038086, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 4.447, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.024299696253796826, | |
| "grad_norm": 11.480803489685059, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 4.6677, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02564967937900776, | |
| "grad_norm": 10.52211856842041, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 4.6511, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0269996625042187, | |
| "grad_norm": 9.410900115966797, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 4.5054, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.028349645629429633, | |
| "grad_norm": 41.73292922973633, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 4.9315, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.029699628754640568, | |
| "grad_norm": 45.694610595703125, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 4.6239, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.031049611879851502, | |
| "grad_norm": 26.50372886657715, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 4.7849, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03239959500506244, | |
| "grad_norm": 9.058126449584961, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 4.9841, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03374957813027337, | |
| "grad_norm": 11.410837173461914, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 4.813, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03374957813027337, | |
| "eval_loss": 4.240368366241455, | |
| "eval_runtime": 367.5136, | |
| "eval_samples_per_second": 13.578, | |
| "eval_steps_per_second": 1.698, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03509956125548431, | |
| "grad_norm": 7.853964805603027, | |
| "learning_rate": 5e-05, | |
| "loss": 3.1521, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03644954438069524, | |
| "grad_norm": 9.705148696899414, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 3.802, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03779952750590618, | |
| "grad_norm": 8.01811408996582, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 3.889, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03914951063111711, | |
| "grad_norm": 7.757350444793701, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 3.7606, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.040499493756328046, | |
| "grad_norm": 6.41825532913208, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 3.892, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.041849476881538984, | |
| "grad_norm": 5.245662212371826, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 4.0991, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.043199460006749915, | |
| "grad_norm": 4.809782981872559, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 4.0009, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.04454944313196085, | |
| "grad_norm": 8.199280738830566, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 4.3727, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.045899426257171784, | |
| "grad_norm": 7.22475528717041, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 4.4786, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.04724940938238272, | |
| "grad_norm": 7.309934139251709, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 4.5763, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04859939250759365, | |
| "grad_norm": 11.301559448242188, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 4.7936, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04994937563280459, | |
| "grad_norm": 11.125042915344238, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 4.9451, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.05129935875801552, | |
| "grad_norm": 3.797098398208618, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 3.1034, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.05264934188322646, | |
| "grad_norm": 5.1125168800354, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 3.3206, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0539993250084374, | |
| "grad_norm": 5.015714645385742, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 3.3168, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05534930813364833, | |
| "grad_norm": 5.0353875160217285, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 3.6131, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.056699291258859266, | |
| "grad_norm": 4.461076259613037, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 3.4785, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0580492743840702, | |
| "grad_norm": 4.7747626304626465, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 3.9127, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.059399257509281135, | |
| "grad_norm": 4.582426071166992, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 3.8955, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.060749240634492066, | |
| "grad_norm": 4.616299152374268, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 3.9779, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.062099223759703004, | |
| "grad_norm": 5.402363300323486, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 4.2335, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.06344920688491394, | |
| "grad_norm": 5.3311238288879395, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 4.329, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.06479919001012488, | |
| "grad_norm": 5.6566057205200195, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 4.4042, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0661491731353358, | |
| "grad_norm": 7.9716796875, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 4.7986, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.06749915626054674, | |
| "grad_norm": 8.92253303527832, | |
| "learning_rate": 0.0, | |
| "loss": 4.7756, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06749915626054674, | |
| "eval_loss": 3.9065983295440674, | |
| "eval_runtime": 367.5364, | |
| "eval_samples_per_second": 13.577, | |
| "eval_steps_per_second": 1.698, | |
| "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": 6.174479344467968e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |