| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.012313521193464362, | |
| "eval_steps": 13, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00031573131265293233, | |
| "eval_loss": 1.742234706878662, | |
| "eval_runtime": 73.1163, | |
| "eval_samples_per_second": 18.245, | |
| "eval_steps_per_second": 9.122, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0031573131265293236, | |
| "grad_norm": 1.9547810554504395, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 6.5173, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004104507064488121, | |
| "eval_loss": 1.267353892326355, | |
| "eval_runtime": 73.0095, | |
| "eval_samples_per_second": 18.272, | |
| "eval_steps_per_second": 9.136, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.006314626253058647, | |
| "grad_norm": 2.692767858505249, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 4.9838, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.008209014128976242, | |
| "eval_loss": 1.0512802600860596, | |
| "eval_runtime": 73.3113, | |
| "eval_samples_per_second": 18.196, | |
| "eval_steps_per_second": 9.098, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.00947193937958797, | |
| "grad_norm": 2.5398614406585693, | |
| "learning_rate": 8.263518223330697e-05, | |
| "loss": 4.1562, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.012313521193464362, | |
| "eval_loss": 0.9882316589355469, | |
| "eval_runtime": 73.217, | |
| "eval_samples_per_second": 18.22, | |
| "eval_steps_per_second": 9.11, | |
| "step": 39 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.242743039852544e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |