| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0010077851402081077, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.0155702804162153e-05, | |
| "eval_loss": 1.8410059213638306, | |
| "eval_runtime": 1886.297, | |
| "eval_samples_per_second": 11.075, | |
| "eval_steps_per_second": 5.537, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00010077851402081077, | |
| "grad_norm": 1.935125470161438, | |
| "learning_rate": 5e-05, | |
| "loss": 1.8486, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00020155702804162154, | |
| "grad_norm": 1.3043996095657349, | |
| "learning_rate": 0.0001, | |
| "loss": 1.658, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00020155702804162154, | |
| "eval_loss": 1.4670926332473755, | |
| "eval_runtime": 1890.2781, | |
| "eval_samples_per_second": 11.051, | |
| "eval_steps_per_second": 5.526, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0003023355420624323, | |
| "grad_norm": 1.296493411064148, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.1661, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0004031140560832431, | |
| "grad_norm": 0.7659422755241394, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.3867, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0004031140560832431, | |
| "eval_loss": 1.1846641302108765, | |
| "eval_runtime": 1888.6218, | |
| "eval_samples_per_second": 11.061, | |
| "eval_steps_per_second": 5.53, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0005038925701040538, | |
| "grad_norm": 1.5011175870895386, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.3181, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0006046710841248646, | |
| "grad_norm": 1.0637823343276978, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1796, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0006046710841248646, | |
| "eval_loss": 1.128209114074707, | |
| "eval_runtime": 1884.6643, | |
| "eval_samples_per_second": 11.084, | |
| "eval_steps_per_second": 5.542, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0007054495981456754, | |
| "grad_norm": 0.5737879276275635, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.3374, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0008062281121664861, | |
| "grad_norm": 1.3823490142822266, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.8899, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0008062281121664861, | |
| "eval_loss": 1.1056840419769287, | |
| "eval_runtime": 1887.14, | |
| "eval_samples_per_second": 11.07, | |
| "eval_steps_per_second": 5.535, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0009070066261872969, | |
| "grad_norm": 0.7595813274383545, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.1041, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0010077851402081077, | |
| "grad_norm": 1.2080858945846558, | |
| "learning_rate": 0.0, | |
| "loss": 1.1336, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0010077851402081077, | |
| "eval_loss": 1.1016148328781128, | |
| "eval_runtime": 1885.738, | |
| "eval_samples_per_second": 11.078, | |
| "eval_steps_per_second": 5.539, | |
| "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": 1.2761993312206848e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |