| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.111111111111111, | |
| "eval_steps": 25, | |
| "global_step": 14, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2222222222222222, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.874639560909117e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.7483, | |
| "eval_samples_per_second": 17.159, | |
| "eval_steps_per_second": 2.288, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.504844339512095e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.90915741234015e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.117449009293668e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 1.1111111111111112, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.169418695587791e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.112604669781572e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.5555555555555556, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.887395330218429e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8305813044122097e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8825509907063327e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.4444444444444446, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.090842587659851e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.951556604879048e-06, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 2.888888888888889, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2536043909088191e-06, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 3.111111111111111, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 14 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 14, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.4725502391759667e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |