| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 131, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.007633587786259542, | |
| "grad_norm": 177.0453643798828, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 47.6977, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03816793893129771, | |
| "grad_norm": 85.61766815185547, | |
| "learning_rate": 7.142857142857143e-05, | |
| "loss": 43.3804, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07633587786259542, | |
| "grad_norm": 21.188264846801758, | |
| "learning_rate": 0.00014285714285714287, | |
| "loss": 32.4675, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11450381679389313, | |
| "grad_norm": 12.669232368469238, | |
| "learning_rate": 0.00019996395276708856, | |
| "loss": 26.336, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.15267175572519084, | |
| "grad_norm": 6.164061069488525, | |
| "learning_rate": 0.00019870502626379127, | |
| "loss": 23.7885, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.19083969465648856, | |
| "grad_norm": 9.347785949707031, | |
| "learning_rate": 0.00019566964208274254, | |
| "loss": 22.3163, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.22900763358778625, | |
| "grad_norm": 16.819992065429688, | |
| "learning_rate": 0.0001909124299802724, | |
| "loss": 20.7837, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.26717557251908397, | |
| "grad_norm": 27.521188735961914, | |
| "learning_rate": 0.0001845190085543795, | |
| "loss": 17.9141, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3053435114503817, | |
| "grad_norm": 36.15729522705078, | |
| "learning_rate": 0.0001766044443118978, | |
| "loss": 12.8744, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3435114503816794, | |
| "grad_norm": 30.39793586730957, | |
| "learning_rate": 0.00016731118074275704, | |
| "loss": 7.4619, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3816793893129771, | |
| "grad_norm": 13.962003707885742, | |
| "learning_rate": 0.00015680647467311557, | |
| "loss": 4.1925, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4198473282442748, | |
| "grad_norm": 9.878511428833008, | |
| "learning_rate": 0.00014527938603696376, | |
| "loss": 3.5013, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.4580152671755725, | |
| "grad_norm": 4.401936054229736, | |
| "learning_rate": 0.00013293737524320797, | |
| "loss": 2.9085, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.4961832061068702, | |
| "grad_norm": 2.499587297439575, | |
| "learning_rate": 0.00012000256937760445, | |
| "loss": 2.6199, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.5343511450381679, | |
| "grad_norm": 4.096787452697754, | |
| "learning_rate": 0.00010670776443910024, | |
| "loss": 2.4025, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.5725190839694656, | |
| "grad_norm": 2.0821242332458496, | |
| "learning_rate": 9.329223556089975e-05, | |
| "loss": 2.3207, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.6106870229007634, | |
| "grad_norm": 1.016592025756836, | |
| "learning_rate": 7.999743062239557e-05, | |
| "loss": 2.2112, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.648854961832061, | |
| "grad_norm": 2.0435054302215576, | |
| "learning_rate": 6.706262475679205e-05, | |
| "loss": 2.1628, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.6870229007633588, | |
| "grad_norm": 1.766175627708435, | |
| "learning_rate": 5.472061396303629e-05, | |
| "loss": 2.1301, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.7251908396946565, | |
| "grad_norm": 0.9447934031486511, | |
| "learning_rate": 4.3193525326884435e-05, | |
| "loss": 2.0873, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.7633587786259542, | |
| "grad_norm": 1.282375454902649, | |
| "learning_rate": 3.268881925724297e-05, | |
| "loss": 2.0758, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.8015267175572519, | |
| "grad_norm": 1.1836905479431152, | |
| "learning_rate": 2.339555568810221e-05, | |
| "loss": 2.0401, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.8396946564885496, | |
| "grad_norm": 4.228659629821777, | |
| "learning_rate": 1.5480991445620542e-05, | |
| "loss": 2.0129, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.8778625954198473, | |
| "grad_norm": 0.9176464676856995, | |
| "learning_rate": 9.08757001972762e-06, | |
| "loss": 2.0476, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.916030534351145, | |
| "grad_norm": 2.124687433242798, | |
| "learning_rate": 4.3303579172574885e-06, | |
| "loss": 2.017, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.9541984732824428, | |
| "grad_norm": 1.6751036643981934, | |
| "learning_rate": 1.2949737362087156e-06, | |
| "loss": 2.0379, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.9923664122137404, | |
| "grad_norm": 1.4553974866867065, | |
| "learning_rate": 3.60472329114625e-08, | |
| "loss": 2.0437, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.034517288208008, | |
| "eval_runtime": 27.6, | |
| "eval_samples_per_second": 33.37, | |
| "eval_steps_per_second": 1.413, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 131, | |
| "total_flos": 1.997211509414953e+17, | |
| "train_loss": 9.52029996245872, | |
| "train_runtime": 979.0233, | |
| "train_samples_per_second": 8.551, | |
| "train_steps_per_second": 0.134 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 131, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.997211509414953e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |