| { | |
| "best_metric": 9.034330368041992, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.16420361247947454, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003284072249589491, | |
| "grad_norm": 5.3590240478515625, | |
| "learning_rate": 5e-05, | |
| "loss": 10.1534, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003284072249589491, | |
| "eval_loss": 10.289729118347168, | |
| "eval_runtime": 0.7387, | |
| "eval_samples_per_second": 67.686, | |
| "eval_steps_per_second": 17.598, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006568144499178982, | |
| "grad_norm": 4.474542617797852, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3179, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.009852216748768473, | |
| "grad_norm": 4.106955051422119, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 10.4482, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.013136288998357963, | |
| "grad_norm": 4.247164726257324, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 10.4086, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.016420361247947456, | |
| "grad_norm": 3.9687907695770264, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 10.2262, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.019704433497536946, | |
| "grad_norm": 3.725856065750122, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 10.2195, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.022988505747126436, | |
| "grad_norm": 3.8966777324676514, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 10.0756, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.026272577996715927, | |
| "grad_norm": 3.410893678665161, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 9.971, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.029556650246305417, | |
| "grad_norm": 3.335947275161743, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 9.6592, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03284072249589491, | |
| "grad_norm": 3.607198715209961, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 9.6826, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0361247947454844, | |
| "grad_norm": 3.303114891052246, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 9.4414, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03940886699507389, | |
| "grad_norm": 3.736102819442749, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 9.4726, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.042692939244663386, | |
| "grad_norm": 3.406010866165161, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 9.4421, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04597701149425287, | |
| "grad_norm": 3.1484105587005615, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 9.6238, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04926108374384237, | |
| "grad_norm": 2.822091817855835, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 9.581, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.052545155993431854, | |
| "grad_norm": 2.6720054149627686, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 9.5221, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05582922824302135, | |
| "grad_norm": 2.5903782844543457, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 9.5968, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.059113300492610835, | |
| "grad_norm": 2.503328323364258, | |
| "learning_rate": 7.75e-05, | |
| "loss": 9.5633, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.06239737274220033, | |
| "grad_norm": 2.564364433288574, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 9.557, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06568144499178982, | |
| "grad_norm": 2.438037157058716, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 9.4081, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06896551724137931, | |
| "grad_norm": 2.637592077255249, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 9.3861, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0722495894909688, | |
| "grad_norm": 2.672288656234741, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 9.1602, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0755336617405583, | |
| "grad_norm": 3.1129045486450195, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 9.1205, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.07881773399014778, | |
| "grad_norm": 3.575244426727295, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 9.2012, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.08210180623973727, | |
| "grad_norm": 4.282357692718506, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 9.263, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08210180623973727, | |
| "eval_loss": 9.286540985107422, | |
| "eval_runtime": 0.744, | |
| "eval_samples_per_second": 67.207, | |
| "eval_steps_per_second": 17.474, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08538587848932677, | |
| "grad_norm": 2.6121907234191895, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 9.0977, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.08866995073891626, | |
| "grad_norm": 2.2141213417053223, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 9.1782, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.09195402298850575, | |
| "grad_norm": 2.1672656536102295, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 9.2533, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.09523809523809523, | |
| "grad_norm": 2.1206374168395996, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 9.4548, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.09852216748768473, | |
| "grad_norm": 2.081202268600464, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 9.3319, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10180623973727422, | |
| "grad_norm": 2.0032904148101807, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 9.1952, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.10509031198686371, | |
| "grad_norm": 2.0835368633270264, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 9.1689, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.10837438423645321, | |
| "grad_norm": 2.2021350860595703, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 9.1592, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1116584564860427, | |
| "grad_norm": 2.3087997436523438, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 9.127, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.11494252873563218, | |
| "grad_norm": 2.4689571857452393, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 8.8672, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.11822660098522167, | |
| "grad_norm": 3.0260496139526367, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 8.9765, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.12151067323481117, | |
| "grad_norm": 3.4635651111602783, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 8.9259, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.12479474548440066, | |
| "grad_norm": 2.264085531234741, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 8.8283, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.12807881773399016, | |
| "grad_norm": 2.1152355670928955, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 9.0926, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.13136288998357964, | |
| "grad_norm": 1.843088984489441, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 9.0987, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.13464696223316913, | |
| "grad_norm": 1.9147875308990479, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 9.2151, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.13793103448275862, | |
| "grad_norm": 1.868973970413208, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 9.1413, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1412151067323481, | |
| "grad_norm": 1.8492201566696167, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 9.1159, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.1444991789819376, | |
| "grad_norm": 1.908602237701416, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 9.0776, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1477832512315271, | |
| "grad_norm": 1.9235059022903442, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 9.0402, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1510673234811166, | |
| "grad_norm": 2.0559000968933105, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 8.9646, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.15435139573070608, | |
| "grad_norm": 2.4485461711883545, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 8.8393, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.15763546798029557, | |
| "grad_norm": 2.6814403533935547, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 8.8943, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.16091954022988506, | |
| "grad_norm": 3.552027940750122, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 9.0081, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.16420361247947454, | |
| "grad_norm": 4.193510055541992, | |
| "learning_rate": 1e-05, | |
| "loss": 8.7117, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.16420361247947454, | |
| "eval_loss": 9.034330368041992, | |
| "eval_runtime": 0.7358, | |
| "eval_samples_per_second": 67.95, | |
| "eval_steps_per_second": 17.667, | |
| "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": 232013797785600.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |