| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0006015339114742594, | |
| "eval_steps": 10, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.542394644805793e-05, | |
| "eval_loss": 2.4720304012298584, | |
| "eval_runtime": 1761.9842, | |
| "eval_samples_per_second": 15.493, | |
| "eval_steps_per_second": 7.747, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.711973224028966e-05, | |
| "grad_norm": 43.3646354675293, | |
| "learning_rate": 5e-05, | |
| "loss": 9.7773, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00015423946448057932, | |
| "grad_norm": 55.31428146362305, | |
| "learning_rate": 0.0001, | |
| "loss": 8.8598, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00015423946448057932, | |
| "eval_loss": 1.8692532777786255, | |
| "eval_runtime": 1755.9634, | |
| "eval_samples_per_second": 15.546, | |
| "eval_steps_per_second": 7.774, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.000231359196720869, | |
| "grad_norm": 39.72648239135742, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 6.9835, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00030847892896115864, | |
| "grad_norm": 37.37489700317383, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 6.4763, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00030847892896115864, | |
| "eval_loss": 1.598610758781433, | |
| "eval_runtime": 1752.1892, | |
| "eval_samples_per_second": 15.58, | |
| "eval_steps_per_second": 7.79, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0003855986612014483, | |
| "grad_norm": 30.88212776184082, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 6.7263, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.000462718393441738, | |
| "grad_norm": 23.838863372802734, | |
| "learning_rate": 5e-05, | |
| "loss": 6.4899, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.000462718393441738, | |
| "eval_loss": 1.5319379568099976, | |
| "eval_runtime": 1746.7495, | |
| "eval_samples_per_second": 15.628, | |
| "eval_steps_per_second": 7.815, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0005398381256820277, | |
| "grad_norm": 30.91422462463379, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 6.0831, | |
| "step": 35 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6835420016934912.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |