| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00027404392924185747, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.7404392924185746e-05, | |
| "grad_norm": 4.900609970092773, | |
| "learning_rate": 2e-05, | |
| "loss": 3.3911, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.7404392924185746e-05, | |
| "eval_loss": 4.010412693023682, | |
| "eval_runtime": 523.024, | |
| "eval_samples_per_second": 29.377, | |
| "eval_steps_per_second": 14.69, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 5.480878584837149e-05, | |
| "grad_norm": 5.804568767547607, | |
| "learning_rate": 4e-05, | |
| "loss": 4.009, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 8.221317877255724e-05, | |
| "grad_norm": 5.007122993469238, | |
| "learning_rate": 6e-05, | |
| "loss": 3.3929, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 8.221317877255724e-05, | |
| "eval_loss": 3.920656681060791, | |
| "eval_runtime": 522.7367, | |
| "eval_samples_per_second": 29.393, | |
| "eval_steps_per_second": 14.698, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00010961757169674298, | |
| "grad_norm": 5.824885845184326, | |
| "learning_rate": 8e-05, | |
| "loss": 3.7096, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00013702196462092874, | |
| "grad_norm": 5.463647365570068, | |
| "learning_rate": 0.0001, | |
| "loss": 3.6884, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0001644263575451145, | |
| "grad_norm": 5.512495517730713, | |
| "learning_rate": 0.00012, | |
| "loss": 3.0868, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0001644263575451145, | |
| "eval_loss": 2.885078191757202, | |
| "eval_runtime": 522.6605, | |
| "eval_samples_per_second": 29.398, | |
| "eval_steps_per_second": 14.7, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00019183075046930024, | |
| "grad_norm": 6.342769622802734, | |
| "learning_rate": 0.00014, | |
| "loss": 2.8191, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00021923514339348597, | |
| "grad_norm": 5.295454025268555, | |
| "learning_rate": 0.00016, | |
| "loss": 2.346, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00024663953631767175, | |
| "grad_norm": 7.578736782073975, | |
| "learning_rate": 0.00018, | |
| "loss": 1.987, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00024663953631767175, | |
| "eval_loss": 1.5399349927902222, | |
| "eval_runtime": 522.9254, | |
| "eval_samples_per_second": 29.383, | |
| "eval_steps_per_second": 14.692, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00027404392924185747, | |
| "grad_norm": 4.2416090965271, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4092, | |
| "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": 1911091416268800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |