| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.01360451669954425, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000272090333990885, | |
| "eval_loss": NaN, | |
| "eval_runtime": 106.9407, | |
| "eval_samples_per_second": 14.475, | |
| "eval_steps_per_second": 7.238, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013604516699544248, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0027209033399088495, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0027209033399088495, | |
| "eval_loss": NaN, | |
| "eval_runtime": 201.4387, | |
| "eval_samples_per_second": 7.685, | |
| "eval_steps_per_second": 3.842, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004081355009863274, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005441806679817699, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005441806679817699, | |
| "eval_loss": NaN, | |
| "eval_runtime": 226.5754, | |
| "eval_samples_per_second": 6.832, | |
| "eval_steps_per_second": 3.416, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006802258349772125, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.008162710019726549, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008162710019726549, | |
| "eval_loss": NaN, | |
| "eval_runtime": 116.6895, | |
| "eval_samples_per_second": 13.266, | |
| "eval_steps_per_second": 6.633, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.009523161689680974, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.010883613359635398, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.010883613359635398, | |
| "eval_loss": NaN, | |
| "eval_runtime": 124.9683, | |
| "eval_samples_per_second": 12.387, | |
| "eval_steps_per_second": 6.194, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.012244065029589824, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.01360451669954425, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01360451669954425, | |
| "eval_loss": NaN, | |
| "eval_runtime": 174.5149, | |
| "eval_samples_per_second": 8.87, | |
| "eval_steps_per_second": 4.435, | |
| "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": 1.007785126920192e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |