| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00565171317555634, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011303426351112682, | |
| "grad_norm": 8.859309196472168, | |
| "learning_rate": 1e-05, | |
| "loss": 177.625, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011303426351112682, | |
| "eval_loss": 11.10067081451416, | |
| "eval_runtime": 14.3176, | |
| "eval_samples_per_second": 104.067, | |
| "eval_steps_per_second": 52.034, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0022606852702225363, | |
| "grad_norm": 9.065450668334961, | |
| "learning_rate": 2e-05, | |
| "loss": 177.375, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0022606852702225363, | |
| "eval_loss": 11.100335121154785, | |
| "eval_runtime": 5.819, | |
| "eval_samples_per_second": 256.06, | |
| "eval_steps_per_second": 128.03, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0033910279053338045, | |
| "grad_norm": 10.572774887084961, | |
| "learning_rate": 3e-05, | |
| "loss": 177.5625, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004521370540445073, | |
| "grad_norm": 9.449956893920898, | |
| "learning_rate": 4e-05, | |
| "loss": 177.8125, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004521370540445073, | |
| "eval_loss": 11.09874153137207, | |
| "eval_runtime": 5.9864, | |
| "eval_samples_per_second": 248.899, | |
| "eval_steps_per_second": 124.45, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00565171317555634, | |
| "grad_norm": 8.789073944091797, | |
| "learning_rate": 5e-05, | |
| "loss": 177.5625, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 192896040960.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |