| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.005858230814294083, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005858230814294083, | |
| "grad_norm": 9.5940523147583, | |
| "learning_rate": 2e-05, | |
| "loss": 15.9668, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005858230814294083, | |
| "eval_loss": 16.182086944580078, | |
| "eval_runtime": 23.0092, | |
| "eval_samples_per_second": 31.248, | |
| "eval_steps_per_second": 15.646, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011716461628588166, | |
| "grad_norm": 8.103241920471191, | |
| "learning_rate": 4e-05, | |
| "loss": 15.8215, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0017574692442882249, | |
| "grad_norm": 8.939263343811035, | |
| "learning_rate": 6e-05, | |
| "loss": 15.952, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0017574692442882249, | |
| "eval_loss": 16.123308181762695, | |
| "eval_runtime": 21.6338, | |
| "eval_samples_per_second": 33.235, | |
| "eval_steps_per_second": 16.641, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0023432923257176333, | |
| "grad_norm": 9.193857192993164, | |
| "learning_rate": 8e-05, | |
| "loss": 16.0648, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0029291154071470417, | |
| "grad_norm": 9.71928596496582, | |
| "learning_rate": 0.0001, | |
| "loss": 16.0317, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0035149384885764497, | |
| "grad_norm": 10.246051788330078, | |
| "learning_rate": 0.00012, | |
| "loss": 15.2528, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0035149384885764497, | |
| "eval_loss": 14.887479782104492, | |
| "eval_runtime": 21.7432, | |
| "eval_samples_per_second": 33.068, | |
| "eval_steps_per_second": 16.557, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004100761570005858, | |
| "grad_norm": 13.074706077575684, | |
| "learning_rate": 0.00014, | |
| "loss": 15.5862, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0046865846514352666, | |
| "grad_norm": 14.782737731933594, | |
| "learning_rate": 0.00016, | |
| "loss": 13.6667, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005272407732864675, | |
| "grad_norm": 14.997851371765137, | |
| "learning_rate": 0.00018, | |
| "loss": 12.6867, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005272407732864675, | |
| "eval_loss": 10.434623718261719, | |
| "eval_runtime": 21.7497, | |
| "eval_samples_per_second": 33.058, | |
| "eval_steps_per_second": 16.552, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005858230814294083, | |
| "grad_norm": 17.834928512573242, | |
| "learning_rate": 0.0002, | |
| "loss": 10.6756, | |
| "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": 1849564248145920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |