| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0490075961774075, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00098015192354815, | |
| "eval_loss": 1.9742891788482666, | |
| "eval_runtime": 25.489, | |
| "eval_samples_per_second": 16.87, | |
| "eval_steps_per_second": 8.435, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00490075961774075, | |
| "grad_norm": 0.8985056281089783, | |
| "learning_rate": 5e-05, | |
| "loss": 1.8776, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0098015192354815, | |
| "grad_norm": 0.8799164295196533, | |
| "learning_rate": 0.0001, | |
| "loss": 1.7926, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0098015192354815, | |
| "eval_loss": 1.7347216606140137, | |
| "eval_runtime": 25.8727, | |
| "eval_samples_per_second": 16.62, | |
| "eval_steps_per_second": 8.31, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.014702278853222249, | |
| "grad_norm": 0.8822070956230164, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.5342, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.019603038470963, | |
| "grad_norm": 1.0811736583709717, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.196, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.019603038470963, | |
| "eval_loss": 1.078147530555725, | |
| "eval_runtime": 26.0768, | |
| "eval_samples_per_second": 16.49, | |
| "eval_steps_per_second": 8.245, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02450379808870375, | |
| "grad_norm": 0.7334229946136475, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.9801, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.029404557706444498, | |
| "grad_norm": 0.7310940623283386, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9216, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.029404557706444498, | |
| "eval_loss": 0.8484925031661987, | |
| "eval_runtime": 26.0131, | |
| "eval_samples_per_second": 16.53, | |
| "eval_steps_per_second": 8.265, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03430531732418525, | |
| "grad_norm": 0.9621075391769409, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.9208, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.039206076941926, | |
| "grad_norm": 0.5775378346443176, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.7803, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.039206076941926, | |
| "eval_loss": 0.7931650280952454, | |
| "eval_runtime": 26.2018, | |
| "eval_samples_per_second": 16.411, | |
| "eval_steps_per_second": 8.206, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04410683655966675, | |
| "grad_norm": 0.8775522708892822, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.8029, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0490075961774075, | |
| "grad_norm": 0.6940584778785706, | |
| "learning_rate": 0.0, | |
| "loss": 0.7945, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0490075961774075, | |
| "eval_loss": 0.7870774865150452, | |
| "eval_runtime": 25.6678, | |
| "eval_samples_per_second": 16.752, | |
| "eval_steps_per_second": 8.376, | |
| "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": 8256900235788288.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |