| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.010526315789473684, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0010526315789473684, | |
| "grad_norm": 0.022679297253489494, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3788, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010526315789473684, | |
| "eval_loss": 10.377253532409668, | |
| "eval_runtime": 2.6851, | |
| "eval_samples_per_second": 148.972, | |
| "eval_steps_per_second": 74.486, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002105263157894737, | |
| "grad_norm": 0.016693023964762688, | |
| "learning_rate": 4e-05, | |
| "loss": 10.3776, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003157894736842105, | |
| "grad_norm": 0.015842318534851074, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3845, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003157894736842105, | |
| "eval_loss": 10.377248764038086, | |
| "eval_runtime": 2.672, | |
| "eval_samples_per_second": 149.702, | |
| "eval_steps_per_second": 74.851, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004210526315789474, | |
| "grad_norm": 0.01499270461499691, | |
| "learning_rate": 8e-05, | |
| "loss": 10.3793, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005263157894736842, | |
| "grad_norm": 0.017152471467852592, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3772, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00631578947368421, | |
| "grad_norm": 0.014443840831518173, | |
| "learning_rate": 0.00012, | |
| "loss": 10.3754, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00631578947368421, | |
| "eval_loss": 10.377209663391113, | |
| "eval_runtime": 2.6482, | |
| "eval_samples_per_second": 151.046, | |
| "eval_steps_per_second": 75.523, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007368421052631579, | |
| "grad_norm": 0.01774691417813301, | |
| "learning_rate": 0.00014, | |
| "loss": 10.3827, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.008421052631578947, | |
| "grad_norm": 0.014606388285756111, | |
| "learning_rate": 0.00016, | |
| "loss": 10.375, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.009473684210526316, | |
| "grad_norm": 0.018191713839769363, | |
| "learning_rate": 0.00018, | |
| "loss": 10.3804, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.009473684210526316, | |
| "eval_loss": 10.377147674560547, | |
| "eval_runtime": 2.5658, | |
| "eval_samples_per_second": 155.897, | |
| "eval_steps_per_second": 77.949, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.010526315789473684, | |
| "grad_norm": 0.017616568133234978, | |
| "learning_rate": 0.0002, | |
| "loss": 10.3752, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 232756346880.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |