| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.5361930294906166, | |
| "eval_steps": 200, | |
| "global_step": 600, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.17873100983020554, | |
| "grad_norm": 0.5410762429237366, | |
| "learning_rate": 9.999142157322298e-05, | |
| "loss": 0.5394, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.17873100983020554, | |
| "eval_loss": 0.2514195740222931, | |
| "eval_runtime": 56.7459, | |
| "eval_samples_per_second": 3.19, | |
| "eval_steps_per_second": 1.604, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.3574620196604111, | |
| "grad_norm": 0.3244825303554535, | |
| "learning_rate": 9.95497608932715e-05, | |
| "loss": 0.2114, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.3574620196604111, | |
| "eval_loss": 0.19941778481006622, | |
| "eval_runtime": 56.7365, | |
| "eval_samples_per_second": 3.19, | |
| "eval_steps_per_second": 1.604, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.5361930294906166, | |
| "grad_norm": 0.23322512209415436, | |
| "learning_rate": 9.844466810070319e-05, | |
| "loss": 0.184, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.5361930294906166, | |
| "eval_loss": 0.1872645616531372, | |
| "eval_runtime": 56.8389, | |
| "eval_samples_per_second": 3.184, | |
| "eval_steps_per_second": 1.601, | |
| "step": 600 | |
| } | |
| ], | |
| "logging_steps": 200, | |
| "max_steps": 5595, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.71879841804288e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |