| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9335978527249388, | |
| "eval_steps": 250, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2333994631812347, | |
| "grad_norm": 0.46615204215049744, | |
| "learning_rate": 8.959847237666421e-05, | |
| "loss": 0.5497, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.2333994631812347, | |
| "eval_loss": 0.2917565405368805, | |
| "eval_runtime": 12.6905, | |
| "eval_samples_per_second": 6.856, | |
| "eval_steps_per_second": 6.856, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.4667989263624694, | |
| "grad_norm": 0.4836747646331787, | |
| "learning_rate": 5.783666949486448e-05, | |
| "loss": 0.19, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.4667989263624694, | |
| "eval_loss": 0.17282703518867493, | |
| "eval_runtime": 12.6616, | |
| "eval_samples_per_second": 6.871, | |
| "eval_steps_per_second": 6.871, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.7001983895437041, | |
| "grad_norm": 0.414004921913147, | |
| "learning_rate": 2.179828363456768e-05, | |
| "loss": 0.1427, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.7001983895437041, | |
| "eval_loss": 0.14984185993671417, | |
| "eval_runtime": 12.722, | |
| "eval_samples_per_second": 6.839, | |
| "eval_steps_per_second": 6.839, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.9335978527249388, | |
| "grad_norm": 0.44972530007362366, | |
| "learning_rate": 1.149979013737007e-06, | |
| "loss": 0.1258, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.9335978527249388, | |
| "eval_loss": 0.142617329955101, | |
| "eval_runtime": 12.7107, | |
| "eval_samples_per_second": 6.845, | |
| "eval_steps_per_second": 6.845, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 250, | |
| "max_steps": 1071, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 250, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.432776831522816e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |