| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.8654970760233918, | |
| "eval_steps": 10, | |
| "global_step": 160, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11695906432748537, | |
| "eval_loss": 0.291916161775589, | |
| "eval_runtime": 14.114, | |
| "eval_samples_per_second": 53.635, | |
| "eval_steps_per_second": 6.731, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.23391812865497075, | |
| "grad_norm": 0.9206290389893743, | |
| "learning_rate": 7.692307692307694e-06, | |
| "loss": 0.3086, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.23391812865497075, | |
| "eval_loss": 0.2310570627450943, | |
| "eval_runtime": 13.833, | |
| "eval_samples_per_second": 54.724, | |
| "eval_steps_per_second": 6.868, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3508771929824561, | |
| "eval_loss": 0.2036609798669815, | |
| "eval_runtime": 13.8307, | |
| "eval_samples_per_second": 54.733, | |
| "eval_steps_per_second": 6.869, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4678362573099415, | |
| "grad_norm": 0.6671501778795791, | |
| "learning_rate": 9.908063190205739e-06, | |
| "loss": 0.2113, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4678362573099415, | |
| "eval_loss": 0.1889752596616745, | |
| "eval_runtime": 13.8386, | |
| "eval_samples_per_second": 54.702, | |
| "eval_steps_per_second": 6.865, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5847953216374269, | |
| "eval_loss": 0.1784025877714157, | |
| "eval_runtime": 13.7963, | |
| "eval_samples_per_second": 54.87, | |
| "eval_steps_per_second": 6.886, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7017543859649122, | |
| "grad_norm": 0.6133391984537656, | |
| "learning_rate": 9.465880538792519e-06, | |
| "loss": 0.1774, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.7017543859649122, | |
| "eval_loss": 0.17270329594612122, | |
| "eval_runtime": 13.8427, | |
| "eval_samples_per_second": 54.686, | |
| "eval_steps_per_second": 6.863, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.8187134502923976, | |
| "eval_loss": 0.16722090542316437, | |
| "eval_runtime": 13.8528, | |
| "eval_samples_per_second": 54.646, | |
| "eval_steps_per_second": 6.858, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.935672514619883, | |
| "grad_norm": 0.5734119079085649, | |
| "learning_rate": 8.689603152981262e-06, | |
| "loss": 0.1663, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.935672514619883, | |
| "eval_loss": 0.16241328418254852, | |
| "eval_runtime": 13.8277, | |
| "eval_samples_per_second": 54.745, | |
| "eval_steps_per_second": 6.87, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.0467836257309941, | |
| "eval_loss": 0.16258972883224487, | |
| "eval_runtime": 13.8228, | |
| "eval_samples_per_second": 54.764, | |
| "eval_steps_per_second": 6.873, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.1637426900584795, | |
| "grad_norm": 0.5466652845884847, | |
| "learning_rate": 7.637304728380036e-06, | |
| "loss": 0.1251, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.1637426900584795, | |
| "eval_loss": 0.16274206340312958, | |
| "eval_runtime": 13.8628, | |
| "eval_samples_per_second": 54.607, | |
| "eval_steps_per_second": 6.853, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.280701754385965, | |
| "eval_loss": 0.16260136663913727, | |
| "eval_runtime": 13.8176, | |
| "eval_samples_per_second": 54.785, | |
| "eval_steps_per_second": 6.875, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.3976608187134503, | |
| "grad_norm": 0.6270786548860793, | |
| "learning_rate": 6.387708231181229e-06, | |
| "loss": 0.1108, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.3976608187134503, | |
| "eval_loss": 0.1583063155412674, | |
| "eval_runtime": 13.8218, | |
| "eval_samples_per_second": 54.769, | |
| "eval_steps_per_second": 6.873, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.5146198830409356, | |
| "eval_loss": 0.15549179911613464, | |
| "eval_runtime": 13.7868, | |
| "eval_samples_per_second": 54.907, | |
| "eval_steps_per_second": 6.891, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.631578947368421, | |
| "grad_norm": 0.5175376687666863, | |
| "learning_rate": 5.034296594080849e-06, | |
| "loss": 0.1079, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.631578947368421, | |
| "eval_loss": 0.15371112525463104, | |
| "eval_runtime": 13.8138, | |
| "eval_samples_per_second": 54.8, | |
| "eval_steps_per_second": 6.877, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.7485380116959064, | |
| "eval_loss": 0.15189678966999054, | |
| "eval_runtime": 13.8351, | |
| "eval_samples_per_second": 54.716, | |
| "eval_steps_per_second": 6.867, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.8654970760233918, | |
| "grad_norm": 0.5236246557796638, | |
| "learning_rate": 3.6783192117952427e-06, | |
| "loss": 0.1057, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.8654970760233918, | |
| "eval_loss": 0.15082819759845734, | |
| "eval_runtime": 13.8117, | |
| "eval_samples_per_second": 54.808, | |
| "eval_steps_per_second": 6.878, | |
| "step": 160 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 255, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 20, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 40369975721984.0, | |
| "train_batch_size": 5, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |