| { | |
| "best_metric": 11.9251070022583, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.07140307033202428, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0014280614066404856, | |
| "grad_norm": 0.01256503351032734, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 11.932, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0014280614066404856, | |
| "eval_loss": 11.929503440856934, | |
| "eval_runtime": 0.118, | |
| "eval_samples_per_second": 423.6, | |
| "eval_steps_per_second": 110.136, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002856122813280971, | |
| "grad_norm": 0.012207700870931149, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 11.9326, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004284184219921457, | |
| "grad_norm": 0.0168023519217968, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9319, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005712245626561942, | |
| "grad_norm": 0.018574345856904984, | |
| "learning_rate": 9.99571699711836e-05, | |
| "loss": 11.9313, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.007140307033202428, | |
| "grad_norm": 0.017314305528998375, | |
| "learning_rate": 9.982876141412856e-05, | |
| "loss": 11.9315, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008568368439842914, | |
| "grad_norm": 0.021495508030056953, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 11.9314, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009996429846483398, | |
| "grad_norm": 0.021389691159129143, | |
| "learning_rate": 9.931634888554937e-05, | |
| "loss": 11.9309, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.011424491253123885, | |
| "grad_norm": 0.022012054920196533, | |
| "learning_rate": 9.893332032039701e-05, | |
| "loss": 11.9318, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01285255265976437, | |
| "grad_norm": 0.02568540722131729, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 11.9292, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.014280614066404856, | |
| "grad_norm": 0.027455564588308334, | |
| "learning_rate": 9.791726278367022e-05, | |
| "loss": 11.9318, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01570867547304534, | |
| "grad_norm": 0.02765016444027424, | |
| "learning_rate": 9.728616793536588e-05, | |
| "loss": 11.9334, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.017136736879685827, | |
| "grad_norm": 0.030797112733125687, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 11.9288, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.018564798286326314, | |
| "grad_norm": 0.013843487948179245, | |
| "learning_rate": 9.578385041664925e-05, | |
| "loss": 11.933, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.019992859692966797, | |
| "grad_norm": 0.013023129664361477, | |
| "learning_rate": 9.491548749301997e-05, | |
| "loss": 11.9328, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.021420921099607283, | |
| "grad_norm": 0.015522303991019726, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 11.9313, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02284898250624777, | |
| "grad_norm": 0.020236888900399208, | |
| "learning_rate": 9.295261506157986e-05, | |
| "loss": 11.9321, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.024277043912888253, | |
| "grad_norm": 0.01841001957654953, | |
| "learning_rate": 9.186184199300464e-05, | |
| "loss": 11.9309, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.02570510531952874, | |
| "grad_norm": 0.02082350105047226, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 11.9296, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.027133166726169226, | |
| "grad_norm": 0.019161349162459373, | |
| "learning_rate": 8.947199994035401e-05, | |
| "loss": 11.9305, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.028561228132809712, | |
| "grad_norm": 0.03010161966085434, | |
| "learning_rate": 8.817748015645558e-05, | |
| "loss": 11.9298, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.029989289539450195, | |
| "grad_norm": 0.028989531099796295, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 11.9313, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03141735094609068, | |
| "grad_norm": 0.031918078660964966, | |
| "learning_rate": 8.540155934270471e-05, | |
| "loss": 11.9319, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03284541235273117, | |
| "grad_norm": 0.03244626522064209, | |
| "learning_rate": 8.392544243589427e-05, | |
| "loss": 11.9283, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.034273473759371655, | |
| "grad_norm": 0.03859555348753929, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 11.9266, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03570153516601214, | |
| "grad_norm": 0.043594446033239365, | |
| "learning_rate": 8.081093963579707e-05, | |
| "loss": 11.9312, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03570153516601214, | |
| "eval_loss": 11.927620887756348, | |
| "eval_runtime": 0.1194, | |
| "eval_samples_per_second": 418.809, | |
| "eval_steps_per_second": 108.89, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03712959657265263, | |
| "grad_norm": 0.01668129302561283, | |
| "learning_rate": 7.917848237560709e-05, | |
| "loss": 11.9312, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03855765797929311, | |
| "grad_norm": 0.019484911113977432, | |
| "learning_rate": 7.75e-05, | |
| "loss": 11.9326, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.039985719385933594, | |
| "grad_norm": 0.022947635501623154, | |
| "learning_rate": 7.577868759557654e-05, | |
| "loss": 11.9308, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.04141378079257408, | |
| "grad_norm": 0.021383561193943024, | |
| "learning_rate": 7.401782177833148e-05, | |
| "loss": 11.9308, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.042841842199214566, | |
| "grad_norm": 0.024260492995381355, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 11.9303, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04426990360585505, | |
| "grad_norm": 0.028633374720811844, | |
| "learning_rate": 7.03909064496551e-05, | |
| "loss": 11.9292, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.04569796501249554, | |
| "grad_norm": 0.02832259237766266, | |
| "learning_rate": 6.853176097769229e-05, | |
| "loss": 11.9282, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.047126026419136026, | |
| "grad_norm": 0.03353510797023773, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 11.9284, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.048554087825776505, | |
| "grad_norm": 0.04560869559645653, | |
| "learning_rate": 6.473978262721463e-05, | |
| "loss": 11.9314, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.04998214923241699, | |
| "grad_norm": 0.03242092579603195, | |
| "learning_rate": 6.281416799501188e-05, | |
| "loss": 11.9283, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.05141021063905748, | |
| "grad_norm": 0.0488186776638031, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 11.9272, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.052838272045697965, | |
| "grad_norm": 0.052332524210214615, | |
| "learning_rate": 5.8922008423644624e-05, | |
| "loss": 11.9297, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.05426633345233845, | |
| "grad_norm": 0.023282960057258606, | |
| "learning_rate": 5.696287243144013e-05, | |
| "loss": 11.9333, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.05569439485897894, | |
| "grad_norm": 0.019144542515277863, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 11.9337, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.057122456265619424, | |
| "grad_norm": 0.025501970201730728, | |
| "learning_rate": 5.303712756855988e-05, | |
| "loss": 11.9301, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.058550517672259904, | |
| "grad_norm": 0.03369976952672005, | |
| "learning_rate": 5.107799157635538e-05, | |
| "loss": 11.9299, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.05997857907890039, | |
| "grad_norm": 0.03190389275550842, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 11.9294, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.06140664048554088, | |
| "grad_norm": 0.030228126794099808, | |
| "learning_rate": 4.718583200498814e-05, | |
| "loss": 11.9301, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.06283470189218136, | |
| "grad_norm": 0.03605984151363373, | |
| "learning_rate": 4.526021737278538e-05, | |
| "loss": 11.9276, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.06426276329882184, | |
| "grad_norm": 0.040830787271261215, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 11.9279, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.06569082470546234, | |
| "grad_norm": 0.045084644109010696, | |
| "learning_rate": 4.146823902230772e-05, | |
| "loss": 11.9275, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.06711888611210282, | |
| "grad_norm": 0.0474667102098465, | |
| "learning_rate": 3.960909355034491e-05, | |
| "loss": 11.9258, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.06854694751874331, | |
| "grad_norm": 0.05405554547905922, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 11.9259, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.06997500892538379, | |
| "grad_norm": 0.05304645374417305, | |
| "learning_rate": 3.598217822166854e-05, | |
| "loss": 11.9267, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.07140307033202428, | |
| "grad_norm": 0.06828918308019638, | |
| "learning_rate": 3.422131240442349e-05, | |
| "loss": 11.93, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07140307033202428, | |
| "eval_loss": 11.9251070022583, | |
| "eval_runtime": 0.1184, | |
| "eval_samples_per_second": 422.373, | |
| "eval_steps_per_second": 109.817, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1042494259200.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |