| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0008227067050596463, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.227067050596462e-05, | |
| "grad_norm": 3.5702157020568848, | |
| "learning_rate": 2e-05, | |
| "loss": 5.4978, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.227067050596462e-05, | |
| "eval_loss": 1.5088768005371094, | |
| "eval_runtime": 82.5962, | |
| "eval_samples_per_second": 61.964, | |
| "eval_steps_per_second": 30.982, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00016454134101192923, | |
| "grad_norm": 5.58140230178833, | |
| "learning_rate": 4e-05, | |
| "loss": 7.0481, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00024681201151789385, | |
| "grad_norm": 2.470630645751953, | |
| "learning_rate": 6e-05, | |
| "loss": 6.1498, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00024681201151789385, | |
| "eval_loss": 1.5051883459091187, | |
| "eval_runtime": 80.4444, | |
| "eval_samples_per_second": 63.622, | |
| "eval_steps_per_second": 31.811, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00032908268202385847, | |
| "grad_norm": 2.8296210765838623, | |
| "learning_rate": 8e-05, | |
| "loss": 5.7146, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00041135335252982314, | |
| "grad_norm": 2.789170503616333, | |
| "learning_rate": 0.0001, | |
| "loss": 6.3515, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0004936240230357877, | |
| "grad_norm": 2.5471551418304443, | |
| "learning_rate": 0.00012, | |
| "loss": 6.3627, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0004936240230357877, | |
| "eval_loss": 1.4900403022766113, | |
| "eval_runtime": 80.3863, | |
| "eval_samples_per_second": 63.668, | |
| "eval_steps_per_second": 31.834, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005758946935417523, | |
| "grad_norm": 2.0789339542388916, | |
| "learning_rate": 0.00014, | |
| "loss": 6.2217, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0006581653640477169, | |
| "grad_norm": 2.911343812942505, | |
| "learning_rate": 0.00016, | |
| "loss": 6.6005, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0007404360345536817, | |
| "grad_norm": 2.5469303131103516, | |
| "learning_rate": 0.00018, | |
| "loss": 5.929, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0007404360345536817, | |
| "eval_loss": 1.4770768880844116, | |
| "eval_runtime": 80.4032, | |
| "eval_samples_per_second": 63.654, | |
| "eval_steps_per_second": 31.827, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0008227067050596463, | |
| "grad_norm": 3.311828374862671, | |
| "learning_rate": 0.0002, | |
| "loss": 6.8176, | |
| "step": 10 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 410802758615040.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |