| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.002545598024615933, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.0911960492318656e-05, | |
| "eval_loss": 3.2041211128234863, | |
| "eval_runtime": 273.0403, | |
| "eval_samples_per_second": 30.292, | |
| "eval_steps_per_second": 15.148, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002545598024615933, | |
| "grad_norm": 3.1962180137634277, | |
| "learning_rate": 5e-05, | |
| "loss": 2.8082, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0005091196049231866, | |
| "grad_norm": 2.8137855529785156, | |
| "learning_rate": 0.0001, | |
| "loss": 3.1394, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0005091196049231866, | |
| "eval_loss": 2.8642525672912598, | |
| "eval_runtime": 273.8633, | |
| "eval_samples_per_second": 30.201, | |
| "eval_steps_per_second": 15.102, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0007636794073847798, | |
| "grad_norm": 2.929637908935547, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.3929, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0010182392098463731, | |
| "grad_norm": 2.667923927307129, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.5685, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0010182392098463731, | |
| "eval_loss": 2.4445629119873047, | |
| "eval_runtime": 275.6971, | |
| "eval_samples_per_second": 30.0, | |
| "eval_steps_per_second": 15.002, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0012727990123079665, | |
| "grad_norm": 2.50893235206604, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.3904, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0015273588147695597, | |
| "grad_norm": 2.2464773654937744, | |
| "learning_rate": 5e-05, | |
| "loss": 2.2897, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0015273588147695597, | |
| "eval_loss": 2.3795933723449707, | |
| "eval_runtime": 274.5051, | |
| "eval_samples_per_second": 30.131, | |
| "eval_steps_per_second": 15.067, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.001781918617231153, | |
| "grad_norm": 2.3766283988952637, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.1278, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0020364784196927463, | |
| "grad_norm": 2.2886879444122314, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.3362, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0020364784196927463, | |
| "eval_loss": 2.364809274673462, | |
| "eval_runtime": 274.0939, | |
| "eval_samples_per_second": 30.176, | |
| "eval_steps_per_second": 15.09, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0022910382221543396, | |
| "grad_norm": 2.241990327835083, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.2436, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.002545598024615933, | |
| "grad_norm": 2.4210216999053955, | |
| "learning_rate": 0.0, | |
| "loss": 2.616, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.002545598024615933, | |
| "eval_loss": 2.3626749515533447, | |
| "eval_runtime": 272.513, | |
| "eval_samples_per_second": 30.351, | |
| "eval_steps_per_second": 15.177, | |
| "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": 445190819020800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |