| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004256526674233825, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00014188422247446084, | |
| "eval_loss": NaN, | |
| "eval_runtime": 348.9821, | |
| "eval_samples_per_second": 8.505, | |
| "eval_steps_per_second": 4.252, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004256526674233825, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0007094211123723042, | |
| "eval_loss": NaN, | |
| "eval_runtime": 349.7349, | |
| "eval_samples_per_second": 8.486, | |
| "eval_steps_per_second": 4.243, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.000851305334846765, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0012769580022701475, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0014188422247446084, | |
| "eval_loss": NaN, | |
| "eval_runtime": 350.175, | |
| "eval_samples_per_second": 8.476, | |
| "eval_steps_per_second": 4.238, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00170261066969353, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0021282633371169125, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0021282633371169125, | |
| "eval_loss": NaN, | |
| "eval_runtime": 350.4467, | |
| "eval_samples_per_second": 8.469, | |
| "eval_steps_per_second": 4.235, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002553916004540295, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0028376844494892167, | |
| "eval_loss": NaN, | |
| "eval_runtime": 350.5368, | |
| "eval_samples_per_second": 8.467, | |
| "eval_steps_per_second": 4.234, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0029795686719636776, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00340522133938706, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.003547105561861521, | |
| "eval_loss": NaN, | |
| "eval_runtime": 350.594, | |
| "eval_samples_per_second": 8.466, | |
| "eval_steps_per_second": 4.233, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0038308740068104426, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.004256526674233825, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004256526674233825, | |
| "eval_loss": NaN, | |
| "eval_runtime": 350.4824, | |
| "eval_samples_per_second": 8.468, | |
| "eval_steps_per_second": 4.234, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9888465609031680.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |