| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 183, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.16632016632016633, |
| "grad_norm": 2.801249331241931, |
| "learning_rate": 9.99291347838381e-06, |
| "loss": 1.0972, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.33264033264033266, |
| "grad_norm": 2.000785262889263, |
| "learning_rate": 9.867488905171934e-06, |
| "loss": 0.1818, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.498960498960499, |
| "grad_norm": 2.2565786899065334, |
| "learning_rate": 9.589125507238234e-06, |
| "loss": 0.166, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.6652806652806653, |
| "grad_norm": 1.649823236531967, |
| "learning_rate": 9.166569595412576e-06, |
| "loss": 0.1528, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.8316008316008316, |
| "grad_norm": 1.4354975090312643, |
| "learning_rate": 8.613098078136436e-06, |
| "loss": 0.1562, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.997920997920998, |
| "grad_norm": 1.2478891763319888, |
| "learning_rate": 7.946101294662418e-06, |
| "loss": 0.144, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.1496881496881497, |
| "grad_norm": 1.0160991470086236, |
| "learning_rate": 7.186536602294278e-06, |
| "loss": 0.0878, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.316008316008316, |
| "grad_norm": 1.3584013564688255, |
| "learning_rate": 6.3582698862171945e-06, |
| "loss": 0.0777, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.4823284823284824, |
| "grad_norm": 1.0503121306228607, |
| "learning_rate": 5.4873256819937325e-06, |
| "loss": 0.07, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.6486486486486487, |
| "grad_norm": 1.0487942926311893, |
| "learning_rate": 4.601069472234584e-06, |
| "loss": 0.0757, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.814968814968815, |
| "grad_norm": 1.0247148210847015, |
| "learning_rate": 3.727347850073012e-06, |
| "loss": 0.0752, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.9812889812889813, |
| "grad_norm": 1.000581984958329, |
| "learning_rate": 2.8936135659170217e-06, |
| "loss": 0.0782, |
| "step": 120 |
| }, |
| { |
| "epoch": 2.133056133056133, |
| "grad_norm": 0.7098493516244677, |
| "learning_rate": 2.1260629489279662e-06, |
| "loss": 0.0487, |
| "step": 130 |
| }, |
| { |
| "epoch": 2.2993762993762994, |
| "grad_norm": 0.7480560793826878, |
| "learning_rate": 1.44881280585441e-06, |
| "loss": 0.034, |
| "step": 140 |
| }, |
| { |
| "epoch": 2.4656964656964657, |
| "grad_norm": 0.8970057694708895, |
| "learning_rate": 8.831426594527976e-07, |
| "loss": 0.034, |
| "step": 150 |
| }, |
| { |
| "epoch": 2.632016632016632, |
| "grad_norm": 0.7017367503301483, |
| "learning_rate": 4.468261357254339e-07, |
| "loss": 0.0319, |
| "step": 160 |
| }, |
| { |
| "epoch": 2.7983367983367984, |
| "grad_norm": 0.8643222958979049, |
| "learning_rate": 1.5357250810788316e-07, |
| "loss": 0.0312, |
| "step": 170 |
| }, |
| { |
| "epoch": 2.9646569646569647, |
| "grad_norm": 0.7302961131892796, |
| "learning_rate": 1.2595945553992572e-08, |
| "loss": 0.0336, |
| "step": 180 |
| }, |
| { |
| "epoch": 3.0, |
| "step": 183, |
| "total_flos": 62619912962048.0, |
| "train_loss": 0.14141920302572147, |
| "train_runtime": 2521.8463, |
| "train_samples_per_second": 9.149, |
| "train_steps_per_second": 0.073 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 183, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 62619912962048.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
