| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.022632968691059976, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007544322897019992, | |
| "eval_loss": NaN, | |
| "eval_runtime": 37.917, | |
| "eval_samples_per_second": 58.892, | |
| "eval_steps_per_second": 14.743, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002263296869105998, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004526593738211996, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006035458317615994, | |
| "eval_loss": NaN, | |
| "eval_runtime": 36.7755, | |
| "eval_samples_per_second": 60.72, | |
| "eval_steps_per_second": 15.2, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0067898906073179935, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.009053187476423991, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.011316484345529988, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.012070916635231988, | |
| "eval_loss": NaN, | |
| "eval_runtime": 36.8059, | |
| "eval_samples_per_second": 60.67, | |
| "eval_steps_per_second": 15.188, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.013579781214635987, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.015843078083741986, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.018106374952847983, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.018106374952847983, | |
| "eval_loss": NaN, | |
| "eval_runtime": 36.7863, | |
| "eval_samples_per_second": 60.702, | |
| "eval_steps_per_second": 15.196, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02036967182195398, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.022632968691059976, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "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": 2189898688757760.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |