| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.013846819558632626, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0013846819558632627, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013846819558632627, | |
| "eval_loss": NaN, | |
| "eval_runtime": 270.0853, | |
| "eval_samples_per_second": 4.506, | |
| "eval_steps_per_second": 2.255, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0027693639117265254, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004154045867589788, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004154045867589788, | |
| "eval_loss": NaN, | |
| "eval_runtime": 117.8854, | |
| "eval_samples_per_second": 10.324, | |
| "eval_steps_per_second": 5.166, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005538727823453051, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006923409779316313, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008308091735179575, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008308091735179575, | |
| "eval_loss": NaN, | |
| "eval_runtime": 117.5313, | |
| "eval_samples_per_second": 10.355, | |
| "eval_steps_per_second": 5.182, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00969277369104284, | |
| "grad_norm": NaN, | |
| "learning_rate": 7e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.011077455646906102, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.012462137602769364, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.012462137602769364, | |
| "eval_loss": NaN, | |
| "eval_runtime": 117.5745, | |
| "eval_samples_per_second": 10.351, | |
| "eval_steps_per_second": 5.18, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.013846819558632626, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "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": 1.3049588952858624e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |