| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 45, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06666666666666667, | |
| "grad_norm": 98.21532030503785, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 1.8595, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 30.800740243895696, | |
| "learning_rate": 2e-05, | |
| "loss": 1.3856, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 15.616799282095581, | |
| "learning_rate": 1.9238795325112867e-05, | |
| "loss": 0.8256, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 4.893885987624207, | |
| "learning_rate": 1.7071067811865477e-05, | |
| "loss": 0.612, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.566252589225769, | |
| "eval_runtime": 4.2539, | |
| "eval_samples_per_second": 46.78, | |
| "eval_steps_per_second": 0.94, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 3.3286961705391014, | |
| "learning_rate": 1.3826834323650899e-05, | |
| "loss": 0.5009, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.6666666666666665, | |
| "grad_norm": 1.3920639558462544, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4407, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 1.3655223364170395, | |
| "learning_rate": 6.173165676349103e-06, | |
| "loss": 0.4089, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.429166316986084, | |
| "eval_runtime": 4.1164, | |
| "eval_samples_per_second": 48.343, | |
| "eval_steps_per_second": 0.972, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.3333333333333335, | |
| "grad_norm": 1.2577240969960297, | |
| "learning_rate": 2.9289321881345257e-06, | |
| "loss": 0.3299, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 0.9884829876056015, | |
| "learning_rate": 7.612046748871327e-07, | |
| "loss": 0.3136, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 1.4077416282701332, | |
| "learning_rate": 0.0, | |
| "loss": 0.3032, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.4109707474708557, | |
| "eval_runtime": 4.1074, | |
| "eval_samples_per_second": 48.449, | |
| "eval_steps_per_second": 0.974, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 45, | |
| "total_flos": 18844169011200.0, | |
| "train_loss": 0.5794603930579292, | |
| "train_runtime": 365.3228, | |
| "train_samples_per_second": 14.765, | |
| "train_steps_per_second": 0.123 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 45, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 18844169011200.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |