| { | |
| "best_metric": 11.762414932250977, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.03203972926428772, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006407945852857543, | |
| "grad_norm": 0.01918589510023594, | |
| "learning_rate": 5e-05, | |
| "loss": 11.7657, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006407945852857543, | |
| "eval_loss": 11.764625549316406, | |
| "eval_runtime": 0.19, | |
| "eval_samples_per_second": 263.216, | |
| "eval_steps_per_second": 68.436, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012815891705715086, | |
| "grad_norm": 0.013567878864705563, | |
| "learning_rate": 0.0001, | |
| "loss": 11.7661, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001922383755857263, | |
| "grad_norm": 0.014705109409987926, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 11.7662, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002563178341143017, | |
| "grad_norm": 0.014921747148036957, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 11.7662, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0032039729264287716, | |
| "grad_norm": 0.014910179190337658, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 11.7663, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003844767511714526, | |
| "grad_norm": 0.015561099164187908, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 11.7656, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00448556209700028, | |
| "grad_norm": 0.016361653804779053, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 11.7657, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.005126356682286034, | |
| "grad_norm": 0.01527388021349907, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 11.7651, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005767151267571789, | |
| "grad_norm": 0.015490738674998283, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 11.7651, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006407945852857543, | |
| "grad_norm": 0.015069335699081421, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 11.7645, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007048740438143298, | |
| "grad_norm": 0.018585877493023872, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 11.765, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.007689535023429052, | |
| "grad_norm": 0.018454791978001595, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 11.7646, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.008330329608714807, | |
| "grad_norm": 0.01986760087311268, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 11.7653, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00897112419400056, | |
| "grad_norm": 0.016353169456124306, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 11.7652, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.009611918779286315, | |
| "grad_norm": 0.01623576134443283, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 11.7649, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010252713364572069, | |
| "grad_norm": 0.019154468551278114, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 11.7654, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.010893507949857825, | |
| "grad_norm": 0.019593609496951103, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 11.7654, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.011534302535143579, | |
| "grad_norm": 0.021537205204367638, | |
| "learning_rate": 7.75e-05, | |
| "loss": 11.764, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.012175097120429332, | |
| "grad_norm": 0.023021511733531952, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 11.7645, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.012815891705715086, | |
| "grad_norm": 0.02351001650094986, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 11.7653, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01345668629100084, | |
| "grad_norm": 0.021814322099089622, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 11.7633, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.014097480876286596, | |
| "grad_norm": 0.01856810972094536, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 11.7641, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01473827546157235, | |
| "grad_norm": 0.023385072126984596, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 11.7632, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.015379070046858104, | |
| "grad_norm": 0.024404870346188545, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 11.7628, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01601986463214386, | |
| "grad_norm": 0.025754794478416443, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 11.7631, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01601986463214386, | |
| "eval_loss": 11.763199806213379, | |
| "eval_runtime": 0.2013, | |
| "eval_samples_per_second": 248.443, | |
| "eval_steps_per_second": 64.595, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.016660659217429614, | |
| "grad_norm": 0.021041374653577805, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 11.7638, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.017301453802715368, | |
| "grad_norm": 0.020159004256129265, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 11.7645, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.01794224838800112, | |
| "grad_norm": 0.02223449945449829, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 11.7643, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.018583042973286876, | |
| "grad_norm": 0.02316456288099289, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 11.7651, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.01922383755857263, | |
| "grad_norm": 0.026051953434944153, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 11.7645, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.019864632143858384, | |
| "grad_norm": 0.02636219933629036, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 11.7633, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.020505426729144138, | |
| "grad_norm": 0.026028776541352272, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 11.7633, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.02114622131442989, | |
| "grad_norm": 0.03129247948527336, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 11.7631, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.02178701589971565, | |
| "grad_norm": 0.030745303258299828, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 11.7637, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.022427810485001403, | |
| "grad_norm": 0.028258973732590675, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 11.7625, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.023068605070287157, | |
| "grad_norm": 0.025046132504940033, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 11.7632, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.02370939965557291, | |
| "grad_norm": 0.02668956108391285, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 11.763, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.024350194240858665, | |
| "grad_norm": 0.035616256296634674, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 11.7639, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.02499098882614442, | |
| "grad_norm": 0.025154443457722664, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 11.7639, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.025631783411430173, | |
| "grad_norm": 0.028521809726953506, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 11.7631, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.026272577996715927, | |
| "grad_norm": 0.03062279336154461, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 11.7638, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.02691337258200168, | |
| "grad_norm": 0.03084789216518402, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 11.7638, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.027554167167287435, | |
| "grad_norm": 0.02840966358780861, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 11.764, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.028194961752573192, | |
| "grad_norm": 0.033411767333745956, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 11.7633, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.028835756337858946, | |
| "grad_norm": 0.034258123487234116, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 11.7631, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0294765509231447, | |
| "grad_norm": 0.027682367712259293, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 11.7631, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.030117345508430454, | |
| "grad_norm": 0.030619610100984573, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 11.7626, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.030758140093716208, | |
| "grad_norm": 0.032262783497571945, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 11.7633, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.03139893467900196, | |
| "grad_norm": 0.033579230308532715, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 11.763, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.03203972926428772, | |
| "grad_norm": 0.03474806621670723, | |
| "learning_rate": 1e-05, | |
| "loss": 11.7618, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03203972926428772, | |
| "eval_loss": 11.762414932250977, | |
| "eval_runtime": 0.1947, | |
| "eval_samples_per_second": 256.82, | |
| "eval_steps_per_second": 66.773, | |
| "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": 164654353481728.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |