| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02365464222353637, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004730928444707274, | |
| "eval_loss": 3.7715675830841064, | |
| "eval_runtime": 60.1303, | |
| "eval_samples_per_second": 14.801, | |
| "eval_steps_per_second": 7.401, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002365464222353637, | |
| "grad_norm": 4.726196765899658, | |
| "learning_rate": 5e-05, | |
| "loss": 3.9595, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004730928444707274, | |
| "grad_norm": 5.4399495124816895, | |
| "learning_rate": 0.0001, | |
| "loss": 3.7568, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004730928444707274, | |
| "eval_loss": 3.23077654838562, | |
| "eval_runtime": 60.5455, | |
| "eval_samples_per_second": 14.7, | |
| "eval_steps_per_second": 7.35, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007096392667060911, | |
| "grad_norm": 3.918861150741577, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.9987, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.009461856889414548, | |
| "grad_norm": 3.6118011474609375, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.8883, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.009461856889414548, | |
| "eval_loss": 1.7703381776809692, | |
| "eval_runtime": 60.7528, | |
| "eval_samples_per_second": 14.65, | |
| "eval_steps_per_second": 7.325, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.011827321111768185, | |
| "grad_norm": 2.6210219860076904, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.6853, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.014192785334121822, | |
| "grad_norm": 2.8847033977508545, | |
| "learning_rate": 5e-05, | |
| "loss": 1.545, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.014192785334121822, | |
| "eval_loss": 1.4944615364074707, | |
| "eval_runtime": 60.8895, | |
| "eval_samples_per_second": 14.617, | |
| "eval_steps_per_second": 7.308, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01655824955647546, | |
| "grad_norm": 3.2016212940216064, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.4231, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.018923713778829097, | |
| "grad_norm": 2.7728047370910645, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.2891, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.018923713778829097, | |
| "eval_loss": 1.441538691520691, | |
| "eval_runtime": 60.8695, | |
| "eval_samples_per_second": 14.621, | |
| "eval_steps_per_second": 7.311, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.021289178001182733, | |
| "grad_norm": 2.58444881439209, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.2203, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02365464222353637, | |
| "grad_norm": 2.4740593433380127, | |
| "learning_rate": 0.0, | |
| "loss": 1.4042, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02365464222353637, | |
| "eval_loss": 1.433903455734253, | |
| "eval_runtime": 60.7074, | |
| "eval_samples_per_second": 14.66, | |
| "eval_steps_per_second": 7.33, | |
| "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": 9294060346933248.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |