| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0026319252533228057, | |
| "eval_steps": 8, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001315962626661403, | |
| "eval_loss": NaN, | |
| "eval_runtime": 113.1561, | |
| "eval_samples_per_second": 28.28, | |
| "eval_steps_per_second": 14.14, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00039478878799842083, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0007895775759968417, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0010527701013291224, | |
| "eval_loss": NaN, | |
| "eval_runtime": 112.0638, | |
| "eval_samples_per_second": 28.555, | |
| "eval_steps_per_second": 14.278, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0011843663639952626, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0015791551519936833, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0019739439399921043, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0021055402026582447, | |
| "eval_loss": NaN, | |
| "eval_runtime": 111.9631, | |
| "eval_samples_per_second": 28.581, | |
| "eval_steps_per_second": 14.29, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.002368732727990525, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.0, | |
| "step": 18 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2829778465849344.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |