| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.012948336138806164, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00025896672277612325, | |
| "eval_loss": 1.5784907341003418, | |
| "eval_runtime": 108.2393, | |
| "eval_samples_per_second": 15.022, | |
| "eval_steps_per_second": 7.511, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012948336138806163, | |
| "grad_norm": 1.6027204990386963, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5852, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0025896672277612325, | |
| "grad_norm": 1.9320919513702393, | |
| "learning_rate": 0.0001, | |
| "loss": 1.4257, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0025896672277612325, | |
| "eval_loss": 1.176233172416687, | |
| "eval_runtime": 108.8069, | |
| "eval_samples_per_second": 14.944, | |
| "eval_steps_per_second": 7.472, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003884500841641849, | |
| "grad_norm": 1.5479215383529663, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.8012, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005179334455522465, | |
| "grad_norm": 1.6621352434158325, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.4485, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005179334455522465, | |
| "eval_loss": 0.3972953259944916, | |
| "eval_runtime": 109.0312, | |
| "eval_samples_per_second": 14.913, | |
| "eval_steps_per_second": 7.457, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006474168069403082, | |
| "grad_norm": 1.189834713935852, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.385, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.007769001683283698, | |
| "grad_norm": 1.0969147682189941, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3264, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.007769001683283698, | |
| "eval_loss": 0.32326599955558777, | |
| "eval_runtime": 109.206, | |
| "eval_samples_per_second": 14.889, | |
| "eval_steps_per_second": 7.445, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.009063835297164315, | |
| "grad_norm": 0.8971261978149414, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.2954, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01035866891104493, | |
| "grad_norm": 0.755368709564209, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.2693, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01035866891104493, | |
| "eval_loss": 0.28383180499076843, | |
| "eval_runtime": 109.5571, | |
| "eval_samples_per_second": 14.842, | |
| "eval_steps_per_second": 7.421, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.011653502524925547, | |
| "grad_norm": 0.9192548394203186, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.2735, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.012948336138806164, | |
| "grad_norm": 1.1631362438201904, | |
| "learning_rate": 0.0, | |
| "loss": 0.2861, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.012948336138806164, | |
| "eval_loss": 0.2751847803592682, | |
| "eval_runtime": 109.3309, | |
| "eval_samples_per_second": 14.872, | |
| "eval_steps_per_second": 7.436, | |
| "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": 9294060346933248.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |