| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00023621256768966393, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.3621256768966393e-05, | |
| "grad_norm": 0.8610138297080994, | |
| "learning_rate": 2e-05, | |
| "loss": 7.4129, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.3621256768966393e-05, | |
| "eval_loss": 1.6822291612625122, | |
| "eval_runtime": 1332.7448, | |
| "eval_samples_per_second": 13.375, | |
| "eval_steps_per_second": 6.688, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.7242513537932786e-05, | |
| "grad_norm": 0.8238146901130676, | |
| "learning_rate": 4e-05, | |
| "loss": 5.8307, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 7.086377030689917e-05, | |
| "grad_norm": 0.8232203722000122, | |
| "learning_rate": 6e-05, | |
| "loss": 6.8934, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 7.086377030689917e-05, | |
| "eval_loss": 1.6812478303909302, | |
| "eval_runtime": 1335.3673, | |
| "eval_samples_per_second": 13.349, | |
| "eval_steps_per_second": 6.675, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 9.448502707586557e-05, | |
| "grad_norm": 0.8889926075935364, | |
| "learning_rate": 8e-05, | |
| "loss": 6.5514, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00011810628384483197, | |
| "grad_norm": 0.7885150909423828, | |
| "learning_rate": 0.0001, | |
| "loss": 7.3438, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00014172754061379835, | |
| "grad_norm": 1.099139928817749, | |
| "learning_rate": 0.00012, | |
| "loss": 7.3883, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00014172754061379835, | |
| "eval_loss": 1.644141674041748, | |
| "eval_runtime": 1335.6064, | |
| "eval_samples_per_second": 13.347, | |
| "eval_steps_per_second": 6.673, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00016534879738276475, | |
| "grad_norm": 1.1097192764282227, | |
| "learning_rate": 0.00014, | |
| "loss": 6.9015, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00018897005415173114, | |
| "grad_norm": 0.9701343774795532, | |
| "learning_rate": 0.00016, | |
| "loss": 6.123, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00021259131092069754, | |
| "grad_norm": 1.2156624794006348, | |
| "learning_rate": 0.00018, | |
| "loss": 7.6541, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00021259131092069754, | |
| "eval_loss": 1.5384564399719238, | |
| "eval_runtime": 1335.5235, | |
| "eval_samples_per_second": 13.348, | |
| "eval_steps_per_second": 6.674, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00023621256768966393, | |
| "grad_norm": 1.4620938301086426, | |
| "learning_rate": 0.0002, | |
| "loss": 6.1339, | |
| "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": 6196217134448640.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |