| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0008699907563482138, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00017399815126964275, | |
| "grad_norm": 1.2253239154815674, | |
| "learning_rate": 1e-05, | |
| "loss": 1.333, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00017399815126964275, | |
| "eval_loss": 1.4384846687316895, | |
| "eval_runtime": 335.2219, | |
| "eval_samples_per_second": 28.876, | |
| "eval_steps_per_second": 14.438, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003479963025392855, | |
| "grad_norm": 1.2080564498901367, | |
| "learning_rate": 2e-05, | |
| "loss": 1.4199, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0003479963025392855, | |
| "eval_loss": 1.4256417751312256, | |
| "eval_runtime": 297.2533, | |
| "eval_samples_per_second": 32.565, | |
| "eval_steps_per_second": 16.282, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0005219944538089283, | |
| "grad_norm": 1.2211428880691528, | |
| "learning_rate": 3e-05, | |
| "loss": 1.356, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000695992605078571, | |
| "grad_norm": 1.1242731809616089, | |
| "learning_rate": 4e-05, | |
| "loss": 1.2467, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.000695992605078571, | |
| "eval_loss": 1.3928427696228027, | |
| "eval_runtime": 156.1547, | |
| "eval_samples_per_second": 61.99, | |
| "eval_steps_per_second": 30.995, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008699907563482138, | |
| "grad_norm": 1.270448088645935, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4384, | |
| "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": 1505144214650880.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |