| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.002372085300187395, |
| "eval_steps": 10, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 4.74417060037479e-05, |
| "eval_loss": 1.785589575767517, |
| "eval_runtime": 614.2354, |
| "eval_samples_per_second": 14.45, |
| "eval_steps_per_second": 7.225, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.00023720853001873946, |
| "grad_norm": 18.565052032470703, |
| "learning_rate": 5e-05, |
| "loss": 7.3014, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.00047441706003747893, |
| "grad_norm": 11.056122779846191, |
| "learning_rate": 0.0001, |
| "loss": 6.3042, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.00047441706003747893, |
| "eval_loss": 1.4843670129776, |
| "eval_runtime": 616.7874, |
| "eval_samples_per_second": 14.391, |
| "eval_steps_per_second": 7.195, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.0007116255900562184, |
| "grad_norm": 12.173872947692871, |
| "learning_rate": 9.619397662556435e-05, |
| "loss": 5.5322, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.0009488341200749579, |
| "grad_norm": 10.90223503112793, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 5.7847, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.0009488341200749579, |
| "eval_loss": 1.3738691806793213, |
| "eval_runtime": 615.8096, |
| "eval_samples_per_second": 14.414, |
| "eval_steps_per_second": 7.207, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.0011860426500936974, |
| "grad_norm": 8.575257301330566, |
| "learning_rate": 6.91341716182545e-05, |
| "loss": 5.618, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.0014232511801124368, |
| "grad_norm": 8.83657169342041, |
| "learning_rate": 5e-05, |
| "loss": 5.6481, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.0014232511801124368, |
| "eval_loss": 1.3377556800842285, |
| "eval_runtime": 616.2304, |
| "eval_samples_per_second": 14.404, |
| "eval_steps_per_second": 7.202, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.0016604597101311763, |
| "grad_norm": 9.329240798950195, |
| "learning_rate": 3.086582838174551e-05, |
| "loss": 5.3622, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.0018976682401499157, |
| "grad_norm": 7.63873815536499, |
| "learning_rate": 1.4644660940672627e-05, |
| "loss": 5.4219, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.0018976682401499157, |
| "eval_loss": 1.3230457305908203, |
| "eval_runtime": 617.3808, |
| "eval_samples_per_second": 14.377, |
| "eval_steps_per_second": 7.188, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.0021348767701686554, |
| "grad_norm": 6.972021102905273, |
| "learning_rate": 3.8060233744356633e-06, |
| "loss": 4.7516, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.002372085300187395, |
| "grad_norm": 8.430161476135254, |
| "learning_rate": 0.0, |
| "loss": 4.741, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.002372085300187395, |
| "eval_loss": 1.3194341659545898, |
| "eval_runtime": 616.3452, |
| "eval_samples_per_second": 14.401, |
| "eval_steps_per_second": 7.201, |
| "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": 9771313639981056.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
