| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0009567546880979717, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00019135093761959434, | |
| "grad_norm": 2.1792891025543213, | |
| "learning_rate": 1e-05, | |
| "loss": 4.9394, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00019135093761959434, | |
| "eval_loss": 5.939249515533447, | |
| "eval_runtime": 1412.6334, | |
| "eval_samples_per_second": 6.231, | |
| "eval_steps_per_second": 3.115, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003827018752391887, | |
| "grad_norm": 2.1776986122131348, | |
| "learning_rate": 2e-05, | |
| "loss": 5.4852, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0003827018752391887, | |
| "eval_loss": 5.804806709289551, | |
| "eval_runtime": 1877.6298, | |
| "eval_samples_per_second": 4.688, | |
| "eval_steps_per_second": 2.344, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.000574052812858783, | |
| "grad_norm": 2.1300365924835205, | |
| "learning_rate": 3e-05, | |
| "loss": 5.1781, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0007654037504783774, | |
| "grad_norm": 2.2785775661468506, | |
| "learning_rate": 4e-05, | |
| "loss": 5.3314, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0007654037504783774, | |
| "eval_loss": 5.707258701324463, | |
| "eval_runtime": 1939.9153, | |
| "eval_samples_per_second": 4.537, | |
| "eval_steps_per_second": 2.269, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0009567546880979717, | |
| "grad_norm": 2.329453468322754, | |
| "learning_rate": 5e-05, | |
| "loss": 4.4398, | |
| "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": 5968528457859072.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |