| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 29.62962962962963, | |
| "eval_steps": 500, | |
| "global_step": 2400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.6172839506172839, | |
| "grad_norm": 14.113041877746582, | |
| "learning_rate": 9.953000000000001e-06, | |
| "loss": 9.3136, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.2345679012345678, | |
| "grad_norm": 11.032143592834473, | |
| "learning_rate": 9.903e-06, | |
| "loss": 8.8439, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.8518518518518519, | |
| "grad_norm": 21.83379554748535, | |
| "learning_rate": 9.853e-06, | |
| "loss": 8.9582, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.4691358024691357, | |
| "grad_norm": 13.823728561401367, | |
| "learning_rate": 9.803e-06, | |
| "loss": 8.5429, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.0864197530864197, | |
| "grad_norm": 14.090177536010742, | |
| "learning_rate": 9.753e-06, | |
| "loss": 8.0873, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.7037037037037037, | |
| "grad_norm": 16.695327758789062, | |
| "learning_rate": 9.703000000000002e-06, | |
| "loss": 7.5718, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.320987654320987, | |
| "grad_norm": 12.39268970489502, | |
| "learning_rate": 9.653e-06, | |
| "loss": 7.2107, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "grad_norm": 20.64848518371582, | |
| "learning_rate": 9.603000000000001e-06, | |
| "loss": 6.633, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 5.555555555555555, | |
| "grad_norm": 10.930610656738281, | |
| "learning_rate": 9.553000000000002e-06, | |
| "loss": 6.3085, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 6.172839506172839, | |
| "grad_norm": 7.421260833740234, | |
| "learning_rate": 9.503e-06, | |
| "loss": 5.9761, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 6.790123456790123, | |
| "grad_norm": 19.653493881225586, | |
| "learning_rate": 9.453e-06, | |
| "loss": 6.0252, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 7.407407407407407, | |
| "grad_norm": 10.195016860961914, | |
| "learning_rate": 9.403000000000001e-06, | |
| "loss": 5.9531, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 8.024691358024691, | |
| "grad_norm": 15.588345527648926, | |
| "learning_rate": 9.353000000000002e-06, | |
| "loss": 5.979, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 8.641975308641975, | |
| "grad_norm": 11.010184288024902, | |
| "learning_rate": 9.303e-06, | |
| "loss": 5.9684, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 9.25925925925926, | |
| "grad_norm": 12.536541938781738, | |
| "learning_rate": 9.253000000000001e-06, | |
| "loss": 6.0309, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 9.876543209876543, | |
| "grad_norm": 10.15280818939209, | |
| "learning_rate": 9.203000000000002e-06, | |
| "loss": 5.7873, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 10.493827160493828, | |
| "grad_norm": 18.81814956665039, | |
| "learning_rate": 9.153e-06, | |
| "loss": 5.7782, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 11.11111111111111, | |
| "grad_norm": 21.824844360351562, | |
| "learning_rate": 9.103e-06, | |
| "loss": 5.9619, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 11.728395061728396, | |
| "grad_norm": 14.213790893554688, | |
| "learning_rate": 9.053000000000001e-06, | |
| "loss": 5.7755, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 12.345679012345679, | |
| "grad_norm": 16.542211532592773, | |
| "learning_rate": 9.003e-06, | |
| "loss": 5.837, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 12.962962962962964, | |
| "grad_norm": 20.188156127929688, | |
| "learning_rate": 8.953e-06, | |
| "loss": 5.7611, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 13.580246913580247, | |
| "grad_norm": 14.349571228027344, | |
| "learning_rate": 8.903000000000001e-06, | |
| "loss": 5.8904, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 14.197530864197532, | |
| "grad_norm": 22.795913696289062, | |
| "learning_rate": 8.853e-06, | |
| "loss": 5.7211, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 14.814814814814815, | |
| "grad_norm": 10.970526695251465, | |
| "learning_rate": 8.803e-06, | |
| "loss": 5.7186, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 15.432098765432098, | |
| "grad_norm": 22.462017059326172, | |
| "learning_rate": 8.753e-06, | |
| "loss": 5.6172, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 16.049382716049383, | |
| "grad_norm": 15.98877239227295, | |
| "learning_rate": 8.703e-06, | |
| "loss": 5.7045, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 16.666666666666668, | |
| "grad_norm": 10.7304048538208, | |
| "learning_rate": 8.653e-06, | |
| "loss": 5.77, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 17.28395061728395, | |
| "grad_norm": 14.929125785827637, | |
| "learning_rate": 8.603e-06, | |
| "loss": 5.6916, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 17.901234567901234, | |
| "grad_norm": 12.337247848510742, | |
| "learning_rate": 8.553000000000001e-06, | |
| "loss": 5.6017, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 18.51851851851852, | |
| "grad_norm": 10.826752662658691, | |
| "learning_rate": 8.503e-06, | |
| "loss": 5.5774, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 19.135802469135804, | |
| "grad_norm": 31.670007705688477, | |
| "learning_rate": 8.453000000000002e-06, | |
| "loss": 5.6931, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 19.753086419753085, | |
| "grad_norm": 11.033102989196777, | |
| "learning_rate": 8.403e-06, | |
| "loss": 5.6504, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 20.37037037037037, | |
| "grad_norm": 12.53508472442627, | |
| "learning_rate": 8.353000000000001e-06, | |
| "loss": 5.7015, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 20.987654320987655, | |
| "grad_norm": 13.549042701721191, | |
| "learning_rate": 8.304e-06, | |
| "loss": 5.6826, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 21.604938271604937, | |
| "grad_norm": 13.270482063293457, | |
| "learning_rate": 8.254000000000001e-06, | |
| "loss": 5.5371, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 22.22222222222222, | |
| "grad_norm": 15.088618278503418, | |
| "learning_rate": 8.204000000000001e-06, | |
| "loss": 5.6817, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 22.839506172839506, | |
| "grad_norm": 12.706061363220215, | |
| "learning_rate": 8.154e-06, | |
| "loss": 5.6142, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 23.45679012345679, | |
| "grad_norm": 12.286702156066895, | |
| "learning_rate": 8.104e-06, | |
| "loss": 5.4426, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 24.074074074074073, | |
| "grad_norm": 19.067840576171875, | |
| "learning_rate": 8.054000000000001e-06, | |
| "loss": 5.5586, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 24.691358024691358, | |
| "grad_norm": 17.961570739746094, | |
| "learning_rate": 8.004e-06, | |
| "loss": 5.5784, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 25.308641975308642, | |
| "grad_norm": 15.893245697021484, | |
| "learning_rate": 7.954e-06, | |
| "loss": 5.4392, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 25.925925925925927, | |
| "grad_norm": 20.282608032226562, | |
| "learning_rate": 7.904000000000001e-06, | |
| "loss": 5.6877, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 26.54320987654321, | |
| "grad_norm": 10.545083045959473, | |
| "learning_rate": 7.854e-06, | |
| "loss": 5.5013, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 27.160493827160494, | |
| "grad_norm": 14.949348449707031, | |
| "learning_rate": 7.804e-06, | |
| "loss": 5.5302, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 27.77777777777778, | |
| "grad_norm": 12.412175178527832, | |
| "learning_rate": 7.754e-06, | |
| "loss": 5.4353, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 28.395061728395063, | |
| "grad_norm": 45.30052185058594, | |
| "learning_rate": 7.704000000000001e-06, | |
| "loss": 5.4165, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 29.012345679012345, | |
| "grad_norm": 17.286645889282227, | |
| "learning_rate": 7.654e-06, | |
| "loss": 5.5977, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 29.62962962962963, | |
| "grad_norm": 19.336837768554688, | |
| "learning_rate": 7.604e-06, | |
| "loss": 5.546, | |
| "step": 2400 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 10000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 124, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9.173835988992e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |