| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.1, | |
| "eval_steps": 500, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005, | |
| "grad_norm": 29.21416664123535, | |
| "learning_rate": 0.000199, | |
| "loss": 12.1369, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.8678336143493652, | |
| "learning_rate": 0.00019800000000000002, | |
| "loss": 3.0885, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.015, | |
| "grad_norm": 0.6990471482276917, | |
| "learning_rate": 0.00019700000000000002, | |
| "loss": 0.2248, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.3682764768600464, | |
| "learning_rate": 0.000196, | |
| "loss": 0.1795, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.025, | |
| "grad_norm": 0.20672959089279175, | |
| "learning_rate": 0.000195, | |
| "loss": 0.1333, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.19836053252220154, | |
| "learning_rate": 0.000194, | |
| "loss": 0.1045, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.035, | |
| "grad_norm": 0.3058789372444153, | |
| "learning_rate": 0.000193, | |
| "loss": 0.0776, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.20461063086986542, | |
| "learning_rate": 0.000192, | |
| "loss": 0.0537, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.045, | |
| "grad_norm": 0.320773184299469, | |
| "learning_rate": 0.000191, | |
| "loss": 0.0363, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.2853151559829712, | |
| "learning_rate": 0.00019, | |
| "loss": 0.0251, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.055, | |
| "grad_norm": 0.19527700543403625, | |
| "learning_rate": 0.00018899999999999999, | |
| "loss": 0.0164, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.2739509344100952, | |
| "learning_rate": 0.000188, | |
| "loss": 0.0106, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.065, | |
| "grad_norm": 0.1407923698425293, | |
| "learning_rate": 0.00018700000000000002, | |
| "loss": 0.0079, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.10815149545669556, | |
| "learning_rate": 0.00018600000000000002, | |
| "loss": 0.0058, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.075, | |
| "grad_norm": 0.25316667556762695, | |
| "learning_rate": 0.00018500000000000002, | |
| "loss": 0.005, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.0536436066031456, | |
| "learning_rate": 0.00018400000000000003, | |
| "loss": 0.0042, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.085, | |
| "grad_norm": 0.12960447371006012, | |
| "learning_rate": 0.000183, | |
| "loss": 0.0037, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.19423653185367584, | |
| "learning_rate": 0.000182, | |
| "loss": 0.0039, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.095, | |
| "grad_norm": 0.030633121728897095, | |
| "learning_rate": 0.000181, | |
| "loss": 0.0033, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.0728762298822403, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0034, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 2000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 880899155558400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |