| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00018017206432142696, | |
| "eval_steps": 3, | |
| "global_step": 6, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.0028677386904494e-05, | |
| "grad_norm": 0.19791345298290253, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3476, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.0028677386904494e-05, | |
| "eval_loss": 0.3906751573085785, | |
| "eval_runtime": 1090.9151, | |
| "eval_samples_per_second": 12.853, | |
| "eval_steps_per_second": 6.427, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.005735477380899e-05, | |
| "grad_norm": 0.3280632793903351, | |
| "learning_rate": 4e-05, | |
| "loss": 0.5332, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 9.008603216071348e-05, | |
| "grad_norm": 0.1621210128068924, | |
| "learning_rate": 6e-05, | |
| "loss": 0.2819, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 9.008603216071348e-05, | |
| "eval_loss": 0.38882192969322205, | |
| "eval_runtime": 1090.3311, | |
| "eval_samples_per_second": 12.86, | |
| "eval_steps_per_second": 6.43, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00012011470954761798, | |
| "grad_norm": 0.27617770433425903, | |
| "learning_rate": 8e-05, | |
| "loss": 0.3775, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00015014338693452247, | |
| "grad_norm": 0.33552882075309753, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3013, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00018017206432142696, | |
| "grad_norm": 0.31797710061073303, | |
| "learning_rate": 0.00012, | |
| "loss": 0.4089, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00018017206432142696, | |
| "eval_loss": 0.3593178689479828, | |
| "eval_runtime": 1091.0548, | |
| "eval_samples_per_second": 12.852, | |
| "eval_steps_per_second": 6.426, | |
| "step": 6 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3324514381332480.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |