| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.028985507246376812, | |
| "eval_steps": 3, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00322061191626409, | |
| "grad_norm": 4.223480224609375, | |
| "learning_rate": 2e-05, | |
| "loss": 1.2474, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00322061191626409, | |
| "eval_loss": 0.3257923722267151, | |
| "eval_runtime": 5.7867, | |
| "eval_samples_per_second": 22.638, | |
| "eval_steps_per_second": 11.406, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00644122383252818, | |
| "grad_norm": 3.256812810897827, | |
| "learning_rate": 4e-05, | |
| "loss": 0.9454, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00966183574879227, | |
| "grad_norm": 4.940719127655029, | |
| "learning_rate": 6e-05, | |
| "loss": 1.451, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00966183574879227, | |
| "eval_loss": 0.3070842921733856, | |
| "eval_runtime": 5.7854, | |
| "eval_samples_per_second": 22.643, | |
| "eval_steps_per_second": 11.408, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01288244766505636, | |
| "grad_norm": 3.5844881534576416, | |
| "learning_rate": 8e-05, | |
| "loss": 1.3144, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01610305958132045, | |
| "grad_norm": 3.266148805618286, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2428, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01932367149758454, | |
| "grad_norm": 4.981524467468262, | |
| "learning_rate": 0.00012, | |
| "loss": 1.1346, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01932367149758454, | |
| "eval_loss": 0.23133356869220734, | |
| "eval_runtime": 5.8148, | |
| "eval_samples_per_second": 22.529, | |
| "eval_steps_per_second": 11.35, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02254428341384863, | |
| "grad_norm": 4.297223091125488, | |
| "learning_rate": 0.00014, | |
| "loss": 1.1112, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02576489533011272, | |
| "grad_norm": 3.5222208499908447, | |
| "learning_rate": 0.00016, | |
| "loss": 0.6196, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.028985507246376812, | |
| "grad_norm": 4.136260509490967, | |
| "learning_rate": 0.00018, | |
| "loss": 0.878, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.028985507246376812, | |
| "eval_loss": 0.2005186229944229, | |
| "eval_runtime": 5.8322, | |
| "eval_samples_per_second": 22.462, | |
| "eval_steps_per_second": 11.317, | |
| "step": 9 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1752669785948160.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |