| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0725163161711385, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0014503263234227702, | |
| "eval_loss": 0.2840324938297272, | |
| "eval_runtime": 26.3496, | |
| "eval_samples_per_second": 11.044, | |
| "eval_steps_per_second": 5.541, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007251631617113851, | |
| "grad_norm": 7.322425842285156, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9639, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.014503263234227702, | |
| "grad_norm": 6.449563980102539, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6865, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.014503263234227702, | |
| "eval_loss": 0.18034805357456207, | |
| "eval_runtime": 26.6312, | |
| "eval_samples_per_second": 10.927, | |
| "eval_steps_per_second": 5.482, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.021754894851341553, | |
| "grad_norm": 5.386337757110596, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.966, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.029006526468455404, | |
| "grad_norm": 3.2059736251831055, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.8909, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.029006526468455404, | |
| "eval_loss": 0.16475515067577362, | |
| "eval_runtime": 26.6463, | |
| "eval_samples_per_second": 10.921, | |
| "eval_steps_per_second": 5.479, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03625815808556925, | |
| "grad_norm": 3.6938018798828125, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.5317, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.043509789702683106, | |
| "grad_norm": 3.9650323390960693, | |
| "learning_rate": 5e-05, | |
| "loss": 0.807, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.043509789702683106, | |
| "eval_loss": 0.15476326644420624, | |
| "eval_runtime": 26.8368, | |
| "eval_samples_per_second": 10.843, | |
| "eval_steps_per_second": 5.44, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.050761421319796954, | |
| "grad_norm": 3.7301838397979736, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.7523, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.05801305293691081, | |
| "grad_norm": 2.2021450996398926, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.662, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05801305293691081, | |
| "eval_loss": 0.14993450045585632, | |
| "eval_runtime": 26.8244, | |
| "eval_samples_per_second": 10.848, | |
| "eval_steps_per_second": 5.443, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06526468455402465, | |
| "grad_norm": 2.6724581718444824, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.6567, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0725163161711385, | |
| "grad_norm": 3.068004846572876, | |
| "learning_rate": 0.0, | |
| "loss": 0.8431, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0725163161711385, | |
| "eval_loss": 0.14900246262550354, | |
| "eval_runtime": 26.7705, | |
| "eval_samples_per_second": 10.87, | |
| "eval_steps_per_second": 5.454, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.248777222488064e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |