| { | |
| "best_metric": 1.7563599348068237, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.04181913225300575, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000836382645060115, | |
| "grad_norm": 3.9804325103759766, | |
| "learning_rate": 1e-05, | |
| "loss": 3.7687, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000836382645060115, | |
| "eval_loss": 4.0373005867004395, | |
| "eval_runtime": 593.6163, | |
| "eval_samples_per_second": 3.393, | |
| "eval_steps_per_second": 1.696, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00167276529012023, | |
| "grad_norm": 4.442862510681152, | |
| "learning_rate": 2e-05, | |
| "loss": 3.6342, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002509147935180345, | |
| "grad_norm": 3.8639018535614014, | |
| "learning_rate": 3e-05, | |
| "loss": 3.548, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00334553058024046, | |
| "grad_norm": 3.7547290325164795, | |
| "learning_rate": 4e-05, | |
| "loss": 3.7124, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004181913225300575, | |
| "grad_norm": 3.4392964839935303, | |
| "learning_rate": 5e-05, | |
| "loss": 3.4752, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00501829587036069, | |
| "grad_norm": 2.760049343109131, | |
| "learning_rate": 6e-05, | |
| "loss": 3.0996, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005854678515420805, | |
| "grad_norm": 2.3333864212036133, | |
| "learning_rate": 7e-05, | |
| "loss": 3.0418, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00669106116048092, | |
| "grad_norm": 2.4886162281036377, | |
| "learning_rate": 8e-05, | |
| "loss": 3.1069, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.007527443805541035, | |
| "grad_norm": 2.3361315727233887, | |
| "learning_rate": 9e-05, | |
| "loss": 2.7407, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00836382645060115, | |
| "grad_norm": 2.600538969039917, | |
| "learning_rate": 0.0001, | |
| "loss": 2.7452, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009200209095661264, | |
| "grad_norm": 2.1821160316467285, | |
| "learning_rate": 9.98458666866564e-05, | |
| "loss": 2.4587, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.01003659174072138, | |
| "grad_norm": 2.185742139816284, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 2.3698, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.010872974385781496, | |
| "grad_norm": 2.1610116958618164, | |
| "learning_rate": 9.861849601988383e-05, | |
| "loss": 2.2467, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01170935703084161, | |
| "grad_norm": 2.028902292251587, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 2.3435, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.012545739675901725, | |
| "grad_norm": 2.0603365898132324, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.3123, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01338212232096184, | |
| "grad_norm": 1.7492470741271973, | |
| "learning_rate": 9.45503262094184e-05, | |
| "loss": 2.1589, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.014218504966021955, | |
| "grad_norm": 1.9020344018936157, | |
| "learning_rate": 9.263200821770461e-05, | |
| "loss": 1.8803, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01505488761108207, | |
| "grad_norm": 1.9692450761795044, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 2.1115, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.015891270256142186, | |
| "grad_norm": 1.976115107536316, | |
| "learning_rate": 8.802029828000156e-05, | |
| "loss": 1.9854, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0167276529012023, | |
| "grad_norm": 2.1534483432769775, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.197, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.017564035546262416, | |
| "grad_norm": 1.8315283060073853, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 1.9446, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.01840041819132253, | |
| "grad_norm": 2.2477147579193115, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 2.239, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.019236800836382646, | |
| "grad_norm": 1.718516230583191, | |
| "learning_rate": 7.612492823579745e-05, | |
| "loss": 1.955, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.02007318348144276, | |
| "grad_norm": 1.8015698194503784, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 1.9577, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.020909566126502875, | |
| "grad_norm": 1.7671033143997192, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.795, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.020909566126502875, | |
| "eval_loss": 1.9391679763793945, | |
| "eval_runtime": 595.9573, | |
| "eval_samples_per_second": 3.379, | |
| "eval_steps_per_second": 1.69, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02174594877156299, | |
| "grad_norm": 1.694573998451233, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.9518, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.022582331416623105, | |
| "grad_norm": 2.0041921138763428, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 1.9553, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.02341871406168322, | |
| "grad_norm": 1.6085962057113647, | |
| "learning_rate": 5.782172325201155e-05, | |
| "loss": 1.6961, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.024255096706743334, | |
| "grad_norm": 2.1220922470092773, | |
| "learning_rate": 5.392295478639225e-05, | |
| "loss": 1.9733, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.02509147935180345, | |
| "grad_norm": 1.6805081367492676, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7083, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.025927861996863564, | |
| "grad_norm": 1.8382118940353394, | |
| "learning_rate": 4.607704521360776e-05, | |
| "loss": 1.7664, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.02676424464192368, | |
| "grad_norm": 1.6417231559753418, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 1.6639, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.027600627286983793, | |
| "grad_norm": 2.0312328338623047, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 1.7982, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.02843700993204391, | |
| "grad_norm": 1.7858235836029053, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 1.8593, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.029273392577104027, | |
| "grad_norm": 1.8406282663345337, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.8249, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03010977522216414, | |
| "grad_norm": 1.838815450668335, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 1.8452, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.030946157867224256, | |
| "grad_norm": 1.991115927696228, | |
| "learning_rate": 2.3875071764202563e-05, | |
| "loss": 1.7201, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.03178254051228437, | |
| "grad_norm": 1.6236730813980103, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 1.5592, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.032618923157344486, | |
| "grad_norm": 1.7485631704330444, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 1.5686, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0334553058024046, | |
| "grad_norm": 1.8818488121032715, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.7336, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03429168844746471, | |
| "grad_norm": 1.9881000518798828, | |
| "learning_rate": 1.1979701719998453e-05, | |
| "loss": 1.8232, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.03512807109252483, | |
| "grad_norm": 2.0539233684539795, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 1.8541, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.035964453737584945, | |
| "grad_norm": 2.123443365097046, | |
| "learning_rate": 7.367991782295391e-06, | |
| "loss": 1.8711, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.03680083638264506, | |
| "grad_norm": 1.6884969472885132, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 1.5576, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.03763721902770518, | |
| "grad_norm": 1.9117013216018677, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.6863, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03847360167276529, | |
| "grad_norm": 1.8388051986694336, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 1.7621, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.039309984317825404, | |
| "grad_norm": 1.8650563955307007, | |
| "learning_rate": 1.3815039801161721e-06, | |
| "loss": 1.6786, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.04014636696288552, | |
| "grad_norm": 1.9526333808898926, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 1.7661, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.04098274960794564, | |
| "grad_norm": 2.419896364212036, | |
| "learning_rate": 1.5413331334360182e-07, | |
| "loss": 2.1558, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.04181913225300575, | |
| "grad_norm": 1.8293265104293823, | |
| "learning_rate": 0.0, | |
| "loss": 1.7244, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04181913225300575, | |
| "eval_loss": 1.7563599348068237, | |
| "eval_runtime": 596.0962, | |
| "eval_samples_per_second": 3.379, | |
| "eval_steps_per_second": 1.689, | |
| "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": 1.65784546443264e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |