| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.002345267323830115, | |
| "eval_steps": 2, | |
| "global_step": 4, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005863168309575287, | |
| "grad_norm": 0.4483147859573364, | |
| "learning_rate": 1e-05, | |
| "loss": 1.9425, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005863168309575287, | |
| "eval_loss": 1.927413821220398, | |
| "eval_runtime": 242.503, | |
| "eval_samples_per_second": 11.847, | |
| "eval_steps_per_second": 5.926, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011726336619150575, | |
| "grad_norm": 0.5081765651702881, | |
| "learning_rate": 2e-05, | |
| "loss": 1.9406, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0011726336619150575, | |
| "eval_loss": 1.907767653465271, | |
| "eval_runtime": 107.2886, | |
| "eval_samples_per_second": 26.778, | |
| "eval_steps_per_second": 13.394, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001758950492872586, | |
| "grad_norm": 0.41233697533607483, | |
| "learning_rate": 3e-05, | |
| "loss": 1.9427, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002345267323830115, | |
| "grad_norm": 0.368813693523407, | |
| "learning_rate": 4e-05, | |
| "loss": 1.8687, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002345267323830115, | |
| "eval_loss": 1.8932936191558838, | |
| "eval_runtime": 136.1899, | |
| "eval_samples_per_second": 21.096, | |
| "eval_steps_per_second": 10.551, | |
| "step": 4 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1886111929466880.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |