| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0033751713954224237, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00033751713954224236, | |
| "grad_norm": 0.4469277560710907, | |
| "learning_rate": 1e-05, | |
| "loss": 1.1908, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00033751713954224236, | |
| "eval_loss": 1.1857836246490479, | |
| "eval_runtime": 255.5797, | |
| "eval_samples_per_second": 19.524, | |
| "eval_steps_per_second": 9.762, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006750342790844847, | |
| "grad_norm": 0.40224871039390564, | |
| "learning_rate": 2e-05, | |
| "loss": 1.1118, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0010125514186267272, | |
| "grad_norm": 0.34902000427246094, | |
| "learning_rate": 3e-05, | |
| "loss": 1.0579, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0010125514186267272, | |
| "eval_loss": 1.1678147315979004, | |
| "eval_runtime": 176.6542, | |
| "eval_samples_per_second": 28.247, | |
| "eval_steps_per_second": 14.124, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0013500685581689694, | |
| "grad_norm": 0.41233962774276733, | |
| "learning_rate": 4e-05, | |
| "loss": 1.1444, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0016875856977112118, | |
| "grad_norm": 0.3759932518005371, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1329, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0020251028372534545, | |
| "grad_norm": 0.42395076155662537, | |
| "learning_rate": 6e-05, | |
| "loss": 1.1086, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0020251028372534545, | |
| "eval_loss": 1.1323615312576294, | |
| "eval_runtime": 176.7605, | |
| "eval_samples_per_second": 28.23, | |
| "eval_steps_per_second": 14.115, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0023626199767956967, | |
| "grad_norm": 0.5308507680892944, | |
| "learning_rate": 7e-05, | |
| "loss": 1.2025, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002700137116337939, | |
| "grad_norm": 0.47383561730384827, | |
| "learning_rate": 8e-05, | |
| "loss": 0.9867, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0030376542558801815, | |
| "grad_norm": 0.4871196150779724, | |
| "learning_rate": 9e-05, | |
| "loss": 1.0586, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0030376542558801815, | |
| "eval_loss": 1.0454866886138916, | |
| "eval_runtime": 176.7058, | |
| "eval_samples_per_second": 28.239, | |
| "eval_steps_per_second": 14.12, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0033751713954224237, | |
| "grad_norm": 0.3529665470123291, | |
| "learning_rate": 0.0001, | |
| "loss": 1.029, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.07108490018816e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |