| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.015390534821085032, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00030781069642170063, | |
| "eval_loss": 3.4841344356536865, | |
| "eval_runtime": 98.3902, | |
| "eval_samples_per_second": 13.904, | |
| "eval_steps_per_second": 6.952, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015390534821085034, | |
| "grad_norm": 1.2541712522506714, | |
| "learning_rate": 5e-05, | |
| "loss": 3.3695, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0030781069642170067, | |
| "grad_norm": 1.8117327690124512, | |
| "learning_rate": 0.0001, | |
| "loss": 3.1959, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0030781069642170067, | |
| "eval_loss": 2.695909261703491, | |
| "eval_runtime": 99.0664, | |
| "eval_samples_per_second": 13.809, | |
| "eval_steps_per_second": 6.904, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00461716044632551, | |
| "grad_norm": 2.7991490364074707, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.3309, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0061562139284340135, | |
| "grad_norm": 3.3626081943511963, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.5315, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0061562139284340135, | |
| "eval_loss": 1.2797179222106934, | |
| "eval_runtime": 98.7316, | |
| "eval_samples_per_second": 13.856, | |
| "eval_steps_per_second": 6.928, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007695267410542516, | |
| "grad_norm": 1.0990768671035767, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.1328, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00923432089265102, | |
| "grad_norm": 0.8525949120521545, | |
| "learning_rate": 5e-05, | |
| "loss": 1.085, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00923432089265102, | |
| "eval_loss": 0.8827105760574341, | |
| "eval_runtime": 98.7758, | |
| "eval_samples_per_second": 13.85, | |
| "eval_steps_per_second": 6.925, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.010773374374759523, | |
| "grad_norm": 0.8592066764831543, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.8392, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.012312427856868027, | |
| "grad_norm": 0.8649389147758484, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.7762, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.012312427856868027, | |
| "eval_loss": 0.8062688112258911, | |
| "eval_runtime": 98.5737, | |
| "eval_samples_per_second": 13.878, | |
| "eval_steps_per_second": 6.939, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01385148133897653, | |
| "grad_norm": 0.9955801367759705, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.9317, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.015390534821085032, | |
| "grad_norm": 0.7086855173110962, | |
| "learning_rate": 0.0, | |
| "loss": 0.8363, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.015390534821085032, | |
| "eval_loss": 0.8012153506278992, | |
| "eval_runtime": 98.4951, | |
| "eval_samples_per_second": 13.889, | |
| "eval_steps_per_second": 6.945, | |
| "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": 9710212302766080.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |