| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.2429906542056073, | |
| "eval_steps": 25, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.14953271028037382, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.94459753267812e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.14953271028037382, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.7354, | |
| "eval_samples_per_second": 13.385, | |
| "eval_steps_per_second": 3.48, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.29906542056074764, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.779754323328192e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.4485981308411215, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.509529358847655e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.5981308411214953, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.140576474687264e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.7476635514018691, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.897196261682243, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.14503363531613e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.1308411214953271, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.542957248827961e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 1.280373831775701, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.890576474687263e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.4299065420560748, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.203955092681039e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.5794392523364484, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.7289719626168223, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.7960449073189606e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.8785046728971961, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.109423525312738e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 2.1121495327102804, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.45704275117204e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 2.2616822429906542, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.854966364683872e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 2.411214953271028, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 2.560747663551402, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8594235253127375e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 2.710280373831776, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.490470641152345e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 2.8598130841121496, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2202456766718093e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 3.0934579439252334, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0554024673218807e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 3.2429906542056073, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 20, | |
| "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": 2.323895134715904e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |