| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0009239724656205245, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.079908218735082e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 41.2646, | |
| "eval_samples_per_second": 331.301, | |
| "eval_steps_per_second": 165.662, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 9.239724656205245e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00015399541093675409, | |
| "eval_loss": NaN, | |
| "eval_runtime": 40.5, | |
| "eval_samples_per_second": 337.556, | |
| "eval_steps_per_second": 168.79, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0001847944931241049, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00027719173968615736, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00030799082187350817, | |
| "eval_loss": NaN, | |
| "eval_runtime": 40.2936, | |
| "eval_samples_per_second": 339.285, | |
| "eval_steps_per_second": 169.655, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0003695889862482098, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00046198623281026223, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00046198623281026223, | |
| "eval_loss": NaN, | |
| "eval_runtime": 40.3088, | |
| "eval_samples_per_second": 339.157, | |
| "eval_steps_per_second": 169.591, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0005543834793723147, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0006159816437470163, | |
| "eval_loss": NaN, | |
| "eval_runtime": 40.1737, | |
| "eval_samples_per_second": 340.298, | |
| "eval_steps_per_second": 170.161, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0006467807259343672, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0007391779724964196, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0007699770546837705, | |
| "eval_loss": NaN, | |
| "eval_runtime": 40.2752, | |
| "eval_samples_per_second": 339.44, | |
| "eval_steps_per_second": 169.732, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0008315752190584721, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0009239724656205245, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0009239724656205245, | |
| "eval_loss": NaN, | |
| "eval_runtime": 40.133, | |
| "eval_samples_per_second": 340.642, | |
| "eval_steps_per_second": 170.334, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 15, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1550057472000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |