{ "best_metric": 10.302132606506348, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 1.0256410256410255, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.020512820512820513, "grad_norm": 0.27070486545562744, "learning_rate": 5e-05, "loss": 10.3777, "step": 1 }, { "epoch": 0.020512820512820513, "eval_loss": 10.361001014709473, "eval_runtime": 0.1067, "eval_samples_per_second": 468.596, "eval_steps_per_second": 121.835, "step": 1 }, { "epoch": 0.041025641025641026, "grad_norm": 0.2512279748916626, "learning_rate": 0.0001, "loss": 10.3865, "step": 2 }, { "epoch": 0.06153846153846154, "grad_norm": 0.26547926664352417, "learning_rate": 9.990365154573717e-05, "loss": 10.3909, "step": 3 }, { "epoch": 0.08205128205128205, "grad_norm": 0.26054540276527405, "learning_rate": 9.961501876182148e-05, "loss": 10.377, "step": 4 }, { "epoch": 0.10256410256410256, "grad_norm": 0.26316037774086, "learning_rate": 9.913533761814537e-05, "loss": 10.3617, "step": 5 }, { "epoch": 0.12307692307692308, "grad_norm": 0.26677894592285156, "learning_rate": 9.846666218300807e-05, "loss": 10.3726, "step": 6 }, { "epoch": 0.14358974358974358, "grad_norm": 0.25949233770370483, "learning_rate": 9.761185582727977e-05, "loss": 10.3627, "step": 7 }, { "epoch": 0.1641025641025641, "grad_norm": 0.2796414792537689, "learning_rate": 9.657457896300791e-05, "loss": 10.3536, "step": 8 }, { "epoch": 0.18461538461538463, "grad_norm": 0.2990741431713104, "learning_rate": 9.535927336897098e-05, "loss": 10.3424, "step": 9 }, { "epoch": 0.20512820512820512, "grad_norm": 0.29780325293540955, "learning_rate": 9.397114317029975e-05, "loss": 10.3536, "step": 10 }, { "epoch": 0.22564102564102564, "grad_norm": 0.3147619962692261, "learning_rate": 9.241613255361455e-05, "loss": 10.3439, "step": 11 }, { "epoch": 0.24615384615384617, "grad_norm": 0.3716137111186981, "learning_rate": 9.070090031310558e-05, "loss": 10.3582, "step": 12 }, { "epoch": 0.26666666666666666, "grad_norm": 0.28069737553596497, "learning_rate": 8.883279133655399e-05, "loss": 10.3686, "step": 13 }, { "epoch": 0.28717948717948716, "grad_norm": 0.2844381034374237, "learning_rate": 8.681980515339464e-05, "loss": 10.3814, "step": 14 }, { "epoch": 0.3076923076923077, "grad_norm": 0.2878939211368561, "learning_rate": 8.467056167950311e-05, "loss": 10.3661, "step": 15 }, { "epoch": 0.3282051282051282, "grad_norm": 0.31458649039268494, "learning_rate": 8.239426430539243e-05, "loss": 10.3666, "step": 16 }, { "epoch": 0.3487179487179487, "grad_norm": 0.3024202585220337, "learning_rate": 8.000066048588211e-05, "loss": 10.354, "step": 17 }, { "epoch": 0.36923076923076925, "grad_norm": 0.3125394284725189, "learning_rate": 7.75e-05, "loss": 10.3361, "step": 18 }, { "epoch": 0.38974358974358975, "grad_norm": 0.33549174666404724, "learning_rate": 7.490299105985507e-05, "loss": 10.3418, "step": 19 }, { "epoch": 0.41025641025641024, "grad_norm": 0.3704705536365509, "learning_rate": 7.222075445642904e-05, "loss": 10.3256, "step": 20 }, { "epoch": 0.4307692307692308, "grad_norm": 0.3914016783237457, "learning_rate": 6.946477593864228e-05, "loss": 10.3287, "step": 21 }, { "epoch": 0.4512820512820513, "grad_norm": 0.4021913707256317, "learning_rate": 6.664685702961344e-05, "loss": 10.3277, "step": 22 }, { "epoch": 0.4717948717948718, "grad_norm": 0.4114139974117279, "learning_rate": 6.377906449072578e-05, "loss": 10.316, "step": 23 }, { "epoch": 0.49230769230769234, "grad_norm": 0.46048444509506226, "learning_rate": 6.087367864990233e-05, "loss": 10.3339, "step": 24 }, { "epoch": 0.5128205128205128, "grad_norm": 0.371286541223526, "learning_rate": 5.794314081535644e-05, "loss": 10.3481, "step": 25 }, { "epoch": 0.5128205128205128, "eval_loss": 10.323739051818848, "eval_runtime": 0.0956, "eval_samples_per_second": 523.14, "eval_steps_per_second": 136.016, "step": 25 }, { "epoch": 0.5333333333333333, "grad_norm": 0.3629811704158783, "learning_rate": 5.500000000000001e-05, "loss": 10.3643, "step": 26 }, { "epoch": 0.5538461538461539, "grad_norm": 0.38693100214004517, "learning_rate": 5.205685918464356e-05, "loss": 10.3506, "step": 27 }, { "epoch": 0.5743589743589743, "grad_norm": 0.3990083932876587, "learning_rate": 4.912632135009769e-05, "loss": 10.3487, "step": 28 }, { "epoch": 0.5948717948717949, "grad_norm": 0.4057125151157379, "learning_rate": 4.6220935509274235e-05, "loss": 10.3388, "step": 29 }, { "epoch": 0.6153846153846154, "grad_norm": 0.4252845346927643, "learning_rate": 4.3353142970386564e-05, "loss": 10.3212, "step": 30 }, { "epoch": 0.6358974358974359, "grad_norm": 0.4381605386734009, "learning_rate": 4.053522406135775e-05, "loss": 10.3197, "step": 31 }, { "epoch": 0.6564102564102564, "grad_norm": 0.4398859441280365, "learning_rate": 3.777924554357096e-05, "loss": 10.3138, "step": 32 }, { "epoch": 0.676923076923077, "grad_norm": 0.48066049814224243, "learning_rate": 3.509700894014496e-05, "loss": 10.3216, "step": 33 }, { "epoch": 0.6974358974358974, "grad_norm": 0.48158058524131775, "learning_rate": 3.250000000000001e-05, "loss": 10.3172, "step": 34 }, { "epoch": 0.717948717948718, "grad_norm": 0.492822527885437, "learning_rate": 2.9999339514117912e-05, "loss": 10.3043, "step": 35 }, { "epoch": 0.7384615384615385, "grad_norm": 0.5400839447975159, "learning_rate": 2.760573569460757e-05, "loss": 10.3198, "step": 36 }, { "epoch": 0.7589743589743589, "grad_norm": 0.4561348855495453, "learning_rate": 2.53294383204969e-05, "loss": 10.3269, "step": 37 }, { "epoch": 0.7794871794871795, "grad_norm": 0.4233783185482025, "learning_rate": 2.3180194846605367e-05, "loss": 10.3418, "step": 38 }, { "epoch": 0.8, "grad_norm": 0.45299649238586426, "learning_rate": 2.1167208663446025e-05, "loss": 10.3455, "step": 39 }, { "epoch": 0.8205128205128205, "grad_norm": 0.4731706976890564, "learning_rate": 1.9299099686894423e-05, "loss": 10.3285, "step": 40 }, { "epoch": 0.841025641025641, "grad_norm": 0.46432170271873474, "learning_rate": 1.758386744638546e-05, "loss": 10.318, "step": 41 }, { "epoch": 0.8615384615384616, "grad_norm": 0.4683786630630493, "learning_rate": 1.602885682970026e-05, "loss": 10.3266, "step": 42 }, { "epoch": 0.882051282051282, "grad_norm": 0.4873765707015991, "learning_rate": 1.464072663102903e-05, "loss": 10.3033, "step": 43 }, { "epoch": 0.9025641025641026, "grad_norm": 0.5106824636459351, "learning_rate": 1.3425421036992098e-05, "loss": 10.3023, "step": 44 }, { "epoch": 0.9230769230769231, "grad_norm": 0.546622633934021, "learning_rate": 1.2388144172720251e-05, "loss": 10.2991, "step": 45 }, { "epoch": 0.9435897435897436, "grad_norm": 0.5175260901451111, "learning_rate": 1.1533337816991932e-05, "loss": 10.2922, "step": 46 }, { "epoch": 0.9641025641025641, "grad_norm": 0.5443073511123657, "learning_rate": 1.0864662381854632e-05, "loss": 10.2989, "step": 47 }, { "epoch": 0.9846153846153847, "grad_norm": 0.5688486099243164, "learning_rate": 1.0384981238178534e-05, "loss": 10.3112, "step": 48 }, { "epoch": 1.005128205128205, "grad_norm": 0.6074473857879639, "learning_rate": 1.0096348454262845e-05, "loss": 12.8749, "step": 49 }, { "epoch": 1.0256410256410255, "grad_norm": 0.48072201013565063, "learning_rate": 1e-05, "loss": 10.1882, "step": 50 }, { "epoch": 1.0256410256410255, "eval_loss": 10.302132606506348, "eval_runtime": 0.1235, "eval_samples_per_second": 404.986, "eval_steps_per_second": 105.296, "step": 50 } ], "logging_steps": 1, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 2, "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": 42768059596800.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }