| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0018620240201098594, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00018620240201098595, | |
| "grad_norm": 4.857226371765137, | |
| "learning_rate": 2e-05, | |
| "loss": 25.7467, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00018620240201098595, | |
| "eval_loss": 5.632566928863525, | |
| "eval_runtime": 122.7597, | |
| "eval_samples_per_second": 18.426, | |
| "eval_steps_per_second": 9.213, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003724048040219719, | |
| "grad_norm": 8.374910354614258, | |
| "learning_rate": 4e-05, | |
| "loss": 32.9321, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0005586072060329579, | |
| "grad_norm": 3.9596030712127686, | |
| "learning_rate": 6e-05, | |
| "loss": 21.4046, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0005586072060329579, | |
| "eval_loss": 5.626686096191406, | |
| "eval_runtime": 122.906, | |
| "eval_samples_per_second": 18.404, | |
| "eval_steps_per_second": 9.202, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0007448096080439438, | |
| "grad_norm": 5.284407138824463, | |
| "learning_rate": 8e-05, | |
| "loss": 26.7912, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0009310120100549297, | |
| "grad_norm": 6.530699253082275, | |
| "learning_rate": 0.0001, | |
| "loss": 28.1877, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0011172144120659157, | |
| "grad_norm": 5.761786937713623, | |
| "learning_rate": 0.00012, | |
| "loss": 25.445, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0011172144120659157, | |
| "eval_loss": 5.563575744628906, | |
| "eval_runtime": 123.0527, | |
| "eval_samples_per_second": 18.382, | |
| "eval_steps_per_second": 9.191, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0013034168140769015, | |
| "grad_norm": 7.088345527648926, | |
| "learning_rate": 0.00014, | |
| "loss": 26.5892, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0014896192160878876, | |
| "grad_norm": 5.727215766906738, | |
| "learning_rate": 0.00016, | |
| "loss": 19.6825, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0016758216180988734, | |
| "grad_norm": 11.316922187805176, | |
| "learning_rate": 0.00018, | |
| "loss": 24.3956, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0016758216180988734, | |
| "eval_loss": 5.0582499504089355, | |
| "eval_runtime": 123.0467, | |
| "eval_samples_per_second": 18.383, | |
| "eval_steps_per_second": 9.192, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0018620240201098594, | |
| "grad_norm": 14.976569175720215, | |
| "learning_rate": 0.0002, | |
| "loss": 23.6391, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3397367365632000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |