| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 18.51851851851852, | |
| "eval_steps": 500, | |
| "global_step": 1500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.6172839506172839, | |
| "grad_norm": 62.88630294799805, | |
| "learning_rate": 9.916000000000001e-06, | |
| "loss": 6.6856, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.2345679012345678, | |
| "grad_norm": 387.6339111328125, | |
| "learning_rate": 9.818000000000002e-06, | |
| "loss": 5.5869, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.8518518518518519, | |
| "grad_norm": 245.18975830078125, | |
| "learning_rate": 9.718e-06, | |
| "loss": 5.159, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.4691358024691357, | |
| "grad_norm": 330.3158264160156, | |
| "learning_rate": 9.618e-06, | |
| "loss": 4.0494, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.0864197530864197, | |
| "grad_norm": 138.14215087890625, | |
| "learning_rate": 9.518000000000001e-06, | |
| "loss": 3.6313, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.7037037037037037, | |
| "grad_norm": 166.69479370117188, | |
| "learning_rate": 9.418e-06, | |
| "loss": 3.3391, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.320987654320987, | |
| "grad_norm": 107.54407501220703, | |
| "learning_rate": 9.318e-06, | |
| "loss": 3.3295, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "grad_norm": 293.8923034667969, | |
| "learning_rate": 9.218e-06, | |
| "loss": 3.0956, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 5.555555555555555, | |
| "grad_norm": 226.05360412597656, | |
| "learning_rate": 9.118000000000001e-06, | |
| "loss": 3.0271, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 6.172839506172839, | |
| "grad_norm": 352.8487854003906, | |
| "learning_rate": 9.018e-06, | |
| "loss": 3.0627, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 6.790123456790123, | |
| "grad_norm": 97.6641616821289, | |
| "learning_rate": 8.918000000000002e-06, | |
| "loss": 3.0312, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 7.407407407407407, | |
| "grad_norm": 90.92312622070312, | |
| "learning_rate": 8.818000000000001e-06, | |
| "loss": 3.0228, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 8.024691358024691, | |
| "grad_norm": 241.7625732421875, | |
| "learning_rate": 8.718e-06, | |
| "loss": 3.0873, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 8.641975308641975, | |
| "grad_norm": 162.14071655273438, | |
| "learning_rate": 8.618000000000001e-06, | |
| "loss": 2.9582, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 9.25925925925926, | |
| "grad_norm": 128.74766540527344, | |
| "learning_rate": 8.518e-06, | |
| "loss": 2.9787, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 9.876543209876543, | |
| "grad_norm": 164.0232391357422, | |
| "learning_rate": 8.418000000000001e-06, | |
| "loss": 2.969, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 10.493827160493828, | |
| "grad_norm": 110.58142852783203, | |
| "learning_rate": 8.318e-06, | |
| "loss": 2.884, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 11.11111111111111, | |
| "grad_norm": 111.70948791503906, | |
| "learning_rate": 8.218e-06, | |
| "loss": 2.8216, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 11.728395061728396, | |
| "grad_norm": 111.31181335449219, | |
| "learning_rate": 8.118000000000001e-06, | |
| "loss": 2.8621, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 12.345679012345679, | |
| "grad_norm": 84.1104507446289, | |
| "learning_rate": 8.018e-06, | |
| "loss": 2.7653, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 12.962962962962964, | |
| "grad_norm": 85.67730712890625, | |
| "learning_rate": 7.918e-06, | |
| "loss": 2.8418, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 13.580246913580247, | |
| "grad_norm": 567.8911743164062, | |
| "learning_rate": 7.818e-06, | |
| "loss": 2.789, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 14.197530864197532, | |
| "grad_norm": 98.47197723388672, | |
| "learning_rate": 7.718000000000001e-06, | |
| "loss": 2.7996, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 14.814814814814815, | |
| "grad_norm": 86.87311553955078, | |
| "learning_rate": 7.618000000000001e-06, | |
| "loss": 2.7087, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 15.432098765432098, | |
| "grad_norm": 115.806640625, | |
| "learning_rate": 7.518000000000001e-06, | |
| "loss": 2.6898, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 16.049382716049383, | |
| "grad_norm": 108.76448059082031, | |
| "learning_rate": 7.418000000000001e-06, | |
| "loss": 2.7533, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 16.666666666666668, | |
| "grad_norm": 137.66285705566406, | |
| "learning_rate": 7.318000000000001e-06, | |
| "loss": 2.6817, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 17.28395061728395, | |
| "grad_norm": 167.23983764648438, | |
| "learning_rate": 7.218e-06, | |
| "loss": 2.6612, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 17.901234567901234, | |
| "grad_norm": 80.27250671386719, | |
| "learning_rate": 7.118e-06, | |
| "loss": 2.7053, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 18.51851851851852, | |
| "grad_norm": 87.89417266845703, | |
| "learning_rate": 7.018e-06, | |
| "loss": 2.6016, | |
| "step": 1500 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 5000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 62, | |
| "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": 5.73364749312e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |