| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.000599970001499925, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000119994000299985, | |
| "grad_norm": 73.9129638671875, | |
| "learning_rate": 1e-05, | |
| "loss": 9.8328, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000119994000299985, | |
| "eval_loss": 0.7179164886474609, | |
| "eval_runtime": 345.794, | |
| "eval_samples_per_second": 40.591, | |
| "eval_steps_per_second": 20.295, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00023998800059997, | |
| "grad_norm": 67.33753204345703, | |
| "learning_rate": 2e-05, | |
| "loss": 10.2671, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00023998800059997, | |
| "eval_loss": 0.6718374490737915, | |
| "eval_runtime": 407.7711, | |
| "eval_samples_per_second": 34.421, | |
| "eval_steps_per_second": 17.211, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.000359982000899955, | |
| "grad_norm": 76.12003326416016, | |
| "learning_rate": 3e-05, | |
| "loss": 9.9913, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00047997600119994, | |
| "grad_norm": 67.31082916259766, | |
| "learning_rate": 4e-05, | |
| "loss": 10.3175, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00047997600119994, | |
| "eval_loss": 0.5318808555603027, | |
| "eval_runtime": 303.022, | |
| "eval_samples_per_second": 46.32, | |
| "eval_steps_per_second": 23.16, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.000599970001499925, | |
| "grad_norm": 46.659603118896484, | |
| "learning_rate": 5e-05, | |
| "loss": 6.912, | |
| "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": 3505343598428160.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |