| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.564102564102564, | |
| "eval_steps": 100, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.5128205128205128, | |
| "grad_norm": 485.6934509277344, | |
| "learning_rate": 9.9907e-06, | |
| "loss": 3.7897, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5128205128205128, | |
| "eval_loss": 2.913217067718506, | |
| "eval_runtime": 36.1065, | |
| "eval_samples_per_second": 10.884, | |
| "eval_steps_per_second": 1.385, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.0256410256410255, | |
| "grad_norm": 35.502872467041016, | |
| "learning_rate": 9.980700000000001e-06, | |
| "loss": 2.6449, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.0256410256410255, | |
| "eval_loss": 2.1936488151550293, | |
| "eval_runtime": 35.8618, | |
| "eval_samples_per_second": 10.959, | |
| "eval_steps_per_second": 1.394, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.5384615384615383, | |
| "grad_norm": 44.5572624206543, | |
| "learning_rate": 9.970700000000001e-06, | |
| "loss": 2.123, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.5384615384615383, | |
| "eval_loss": 1.9975601434707642, | |
| "eval_runtime": 36.0033, | |
| "eval_samples_per_second": 10.916, | |
| "eval_steps_per_second": 1.389, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.051282051282051, | |
| "grad_norm": 91.06848907470703, | |
| "learning_rate": 9.960700000000001e-06, | |
| "loss": 1.9616, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.051282051282051, | |
| "eval_loss": 1.9457911252975464, | |
| "eval_runtime": 35.8591, | |
| "eval_samples_per_second": 10.96, | |
| "eval_steps_per_second": 1.394, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.564102564102564, | |
| "grad_norm": 62.52458953857422, | |
| "learning_rate": 9.950700000000001e-06, | |
| "loss": 1.9329, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.564102564102564, | |
| "eval_loss": 1.8983820676803589, | |
| "eval_runtime": 35.7607, | |
| "eval_samples_per_second": 10.99, | |
| "eval_steps_per_second": 1.398, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 100000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 513, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.91121583104e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |