| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.1936785474108944, | |
| "eval_steps": 50, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02151983860121049, | |
| "grad_norm": 82.97300720214844, | |
| "learning_rate": 7.499999999999999e-06, | |
| "loss": 84.1949, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02151983860121049, | |
| "eval_loss": 2.7060768604278564, | |
| "eval_runtime": 26.5108, | |
| "eval_samples_per_second": 5.922, | |
| "eval_steps_per_second": 2.98, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04303967720242098, | |
| "grad_norm": 78.80287170410156, | |
| "learning_rate": 1.4999999999999999e-05, | |
| "loss": 86.2387, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06455951580363148, | |
| "grad_norm": 89.162841796875, | |
| "learning_rate": 2.2499999999999998e-05, | |
| "loss": 90.0082, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.08607935440484196, | |
| "grad_norm": 86.92474365234375, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 84.1448, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.10759919300605246, | |
| "grad_norm": 91.07469940185547, | |
| "learning_rate": 3.75e-05, | |
| "loss": 83.3763, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.12911903160726296, | |
| "grad_norm": 104.43302917480469, | |
| "learning_rate": 4.4999999999999996e-05, | |
| "loss": 81.3885, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.15063887020847344, | |
| "grad_norm": 87.57577514648438, | |
| "learning_rate": 5.2499999999999995e-05, | |
| "loss": 74.0475, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.17215870880968392, | |
| "grad_norm": 62.191646575927734, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 73.151, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1936785474108944, | |
| "grad_norm": 46.43473815917969, | |
| "learning_rate": 6.75e-05, | |
| "loss": 65.2091, | |
| "step": 9 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 9, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.733240683895194e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |