| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0026579839191972886, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002657983919197289, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.8765, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002657983919197289, | |
| "eval_loss": NaN, | |
| "eval_runtime": 48.5256, | |
| "eval_samples_per_second": 32.663, | |
| "eval_steps_per_second": 16.342, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005315967838394578, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0007973951757591866, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0007973951757591866, | |
| "eval_loss": NaN, | |
| "eval_runtime": 46.5281, | |
| "eval_samples_per_second": 34.065, | |
| "eval_steps_per_second": 17.043, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0010631935676789156, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0013289919595986443, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0015947903515183732, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0015947903515183732, | |
| "eval_loss": NaN, | |
| "eval_runtime": 46.6245, | |
| "eval_samples_per_second": 33.995, | |
| "eval_steps_per_second": 17.008, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0018605887434381021, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014, | |
| "loss": 1.7785, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0021263871353578313, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00239218552727756, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 4.1513, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00239218552727756, | |
| "eval_loss": NaN, | |
| "eval_runtime": 46.4938, | |
| "eval_samples_per_second": 34.091, | |
| "eval_steps_per_second": 17.056, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0026579839191972886, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "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": 1829767848394752.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |