| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 44.44444444444444, | |
| "eval_steps": 500, | |
| "global_step": 150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.4814814814814814, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.995066821070679e-05, | |
| "loss": 3.9182, | |
| "num_input_tokens_seen": 11376, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 2.962962962962963, | |
| "grad_norm": 4.32528018951416, | |
| "learning_rate": 4.964990092676263e-05, | |
| "loss": 2.9902, | |
| "num_input_tokens_seen": 23120, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 4.444444444444445, | |
| "grad_norm": 3.1273458003997803, | |
| "learning_rate": 4.907906416994146e-05, | |
| "loss": 2.0558, | |
| "num_input_tokens_seen": 34960, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 5.925925925925926, | |
| "grad_norm": 3.0323095321655273, | |
| "learning_rate": 4.8244412147206284e-05, | |
| "loss": 1.5538, | |
| "num_input_tokens_seen": 46368, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 7.407407407407407, | |
| "grad_norm": 1.668092131614685, | |
| "learning_rate": 4.715508948078037e-05, | |
| "loss": 1.2808, | |
| "num_input_tokens_seen": 58112, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 8.88888888888889, | |
| "grad_norm": 1.1815176010131836, | |
| "learning_rate": 4.5823031017752485e-05, | |
| "loss": 1.0824, | |
| "num_input_tokens_seen": 69600, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 10.37037037037037, | |
| "grad_norm": 1.2929940223693848, | |
| "learning_rate": 4.426283106939474e-05, | |
| "loss": 0.9639, | |
| "num_input_tokens_seen": 81392, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 11.851851851851851, | |
| "grad_norm": 0.8027080297470093, | |
| "learning_rate": 4.249158351283414e-05, | |
| "loss": 0.8585, | |
| "num_input_tokens_seen": 92784, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 13.333333333333334, | |
| "grad_norm": 0.9231483936309814, | |
| "learning_rate": 4.052869450695776e-05, | |
| "loss": 0.7936, | |
| "num_input_tokens_seen": 104656, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 14.814814814814815, | |
| "grad_norm": 0.8608518838882446, | |
| "learning_rate": 3.8395669874474915e-05, | |
| "loss": 0.6884, | |
| "num_input_tokens_seen": 116352, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 16.296296296296298, | |
| "grad_norm": 1.0098791122436523, | |
| "learning_rate": 3.611587947962319e-05, | |
| "loss": 0.6035, | |
| "num_input_tokens_seen": 127968, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 17.77777777777778, | |
| "grad_norm": 0.9739498496055603, | |
| "learning_rate": 3.3714301183045385e-05, | |
| "loss": 0.5181, | |
| "num_input_tokens_seen": 139184, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 19.25925925925926, | |
| "grad_norm": 1.0032066106796265, | |
| "learning_rate": 3.121724717912138e-05, | |
| "loss": 0.4617, | |
| "num_input_tokens_seen": 150848, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 20.74074074074074, | |
| "grad_norm": 0.943274974822998, | |
| "learning_rate": 2.8652075714060295e-05, | |
| "loss": 0.3967, | |
| "num_input_tokens_seen": 162544, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 22.22222222222222, | |
| "grad_norm": 1.0475025177001953, | |
| "learning_rate": 2.604689134322999e-05, | |
| "loss": 0.3591, | |
| "num_input_tokens_seen": 174128, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 23.703703703703702, | |
| "grad_norm": 0.9079996943473816, | |
| "learning_rate": 2.3430237011767167e-05, | |
| "loss": 0.2662, | |
| "num_input_tokens_seen": 185968, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 25.185185185185187, | |
| "grad_norm": 1.1758606433868408, | |
| "learning_rate": 2.0830781332097446e-05, | |
| "loss": 0.2432, | |
| "num_input_tokens_seen": 197680, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 26.666666666666668, | |
| "grad_norm": 1.1381499767303467, | |
| "learning_rate": 1.827700448461836e-05, | |
| "loss": 0.2029, | |
| "num_input_tokens_seen": 209504, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 28.14814814814815, | |
| "grad_norm": 0.9022475481033325, | |
| "learning_rate": 1.5796886182883053e-05, | |
| "loss": 0.1476, | |
| "num_input_tokens_seen": 220880, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 29.62962962962963, | |
| "grad_norm": 1.102629542350769, | |
| "learning_rate": 1.3417599122003464e-05, | |
| "loss": 0.1575, | |
| "num_input_tokens_seen": 232544, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 31.11111111111111, | |
| "grad_norm": 0.8161982297897339, | |
| "learning_rate": 1.11652112689164e-05, | |
| "loss": 0.1061, | |
| "num_input_tokens_seen": 244144, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 32.592592592592595, | |
| "grad_norm": 0.6333702802658081, | |
| "learning_rate": 9.064400256282757e-06, | |
| "loss": 0.1196, | |
| "num_input_tokens_seen": 255952, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 34.074074074074076, | |
| "grad_norm": 0.6209620833396912, | |
| "learning_rate": 7.138183009179922e-06, | |
| "loss": 0.0896, | |
| "num_input_tokens_seen": 267328, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 35.55555555555556, | |
| "grad_norm": 0.5725650787353516, | |
| "learning_rate": 5.4076635668540075e-06, | |
| "loss": 0.1, | |
| "num_input_tokens_seen": 279264, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 37.03703703703704, | |
| "grad_norm": 0.5420427918434143, | |
| "learning_rate": 3.891801862449629e-06, | |
| "loss": 0.0777, | |
| "num_input_tokens_seen": 290736, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 38.51851851851852, | |
| "grad_norm": 0.608285129070282, | |
| "learning_rate": 2.6072059940146775e-06, | |
| "loss": 0.0705, | |
| "num_input_tokens_seen": 302128, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "grad_norm": 0.6441460251808167, | |
| "learning_rate": 1.5679502627027136e-06, | |
| "loss": 0.0845, | |
| "num_input_tokens_seen": 314000, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 41.48148148148148, | |
| "grad_norm": 0.6497734189033508, | |
| "learning_rate": 7.854209717842231e-07, | |
| "loss": 0.0748, | |
| "num_input_tokens_seen": 325600, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 42.96296296296296, | |
| "grad_norm": 0.6788354516029358, | |
| "learning_rate": 2.681916759252917e-07, | |
| "loss": 0.0746, | |
| "num_input_tokens_seen": 337232, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 44.44444444444444, | |
| "grad_norm": 0.6091296076774597, | |
| "learning_rate": 2.192924752854042e-08, | |
| "loss": 0.0824, | |
| "num_input_tokens_seen": 349136, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 44.44444444444444, | |
| "num_input_tokens_seen": 349136, | |
| "step": 150, | |
| "total_flos": 5843993170542592.0, | |
| "train_loss": 0.6807288352648417, | |
| "train_runtime": 762.8508, | |
| "train_samples_per_second": 7.079, | |
| "train_steps_per_second": 0.197 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 150, | |
| "num_input_tokens_seen": 349136, | |
| "num_train_epochs": 50, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5843993170542592.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |