| { | |
| "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": 177.04702758789062, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 47.6977, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03816793893129771, | |
| "grad_norm": 85.58233642578125, | |
| "learning_rate": 7.142857142857143e-05, | |
| "loss": 43.384, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07633587786259542, | |
| "grad_norm": 22.778974533081055, | |
| "learning_rate": 0.00014285714285714287, | |
| "loss": 32.4846, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11450381679389313, | |
| "grad_norm": 12.44094181060791, | |
| "learning_rate": 0.00019996395276708856, | |
| "loss": 26.3676, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.15267175572519084, | |
| "grad_norm": 6.125822067260742, | |
| "learning_rate": 0.00019870502626379127, | |
| "loss": 23.7984, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.19083969465648856, | |
| "grad_norm": 9.35146427154541, | |
| "learning_rate": 0.00019566964208274254, | |
| "loss": 22.3143, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.22900763358778625, | |
| "grad_norm": 16.801265716552734, | |
| "learning_rate": 0.0001909124299802724, | |
| "loss": 20.7786, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.26717557251908397, | |
| "grad_norm": 27.962474822998047, | |
| "learning_rate": 0.0001845190085543795, | |
| "loss": 17.8884, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3053435114503817, | |
| "grad_norm": 36.50389099121094, | |
| "learning_rate": 0.0001766044443118978, | |
| "loss": 12.7762, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3435114503816794, | |
| "grad_norm": 29.48056983947754, | |
| "learning_rate": 0.00016731118074275704, | |
| "loss": 7.3657, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3816793893129771, | |
| "grad_norm": 13.53995418548584, | |
| "learning_rate": 0.00015680647467311557, | |
| "loss": 4.1446, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4198473282442748, | |
| "grad_norm": 9.89051342010498, | |
| "learning_rate": 0.00014527938603696376, | |
| "loss": 3.4783, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.4580152671755725, | |
| "grad_norm": 4.344300270080566, | |
| "learning_rate": 0.00013293737524320797, | |
| "loss": 2.8938, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.4961832061068702, | |
| "grad_norm": 1.8051707744598389, | |
| "learning_rate": 0.00012000256937760445, | |
| "loss": 2.6057, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.5343511450381679, | |
| "grad_norm": 3.4716169834136963, | |
| "learning_rate": 0.00010670776443910024, | |
| "loss": 2.3928, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.5725190839694656, | |
| "grad_norm": 2.3160088062286377, | |
| "learning_rate": 9.329223556089975e-05, | |
| "loss": 2.3088, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.6106870229007634, | |
| "grad_norm": 1.0746971368789673, | |
| "learning_rate": 7.999743062239557e-05, | |
| "loss": 2.1992, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.648854961832061, | |
| "grad_norm": 1.997909665107727, | |
| "learning_rate": 6.706262475679205e-05, | |
| "loss": 2.152, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.6870229007633588, | |
| "grad_norm": 1.3188209533691406, | |
| "learning_rate": 5.472061396303629e-05, | |
| "loss": 2.1218, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.7251908396946565, | |
| "grad_norm": 0.9503675699234009, | |
| "learning_rate": 4.3193525326884435e-05, | |
| "loss": 2.0813, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.7633587786259542, | |
| "grad_norm": 1.3065646886825562, | |
| "learning_rate": 3.268881925724297e-05, | |
| "loss": 2.0714, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.8015267175572519, | |
| "grad_norm": 1.3419970273971558, | |
| "learning_rate": 2.339555568810221e-05, | |
| "loss": 2.0359, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.8396946564885496, | |
| "grad_norm": 2.586273670196533, | |
| "learning_rate": 1.5480991445620542e-05, | |
| "loss": 2.0068, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.8778625954198473, | |
| "grad_norm": 0.914634108543396, | |
| "learning_rate": 9.08757001972762e-06, | |
| "loss": 2.0416, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.916030534351145, | |
| "grad_norm": 2.010348081588745, | |
| "learning_rate": 4.3303579172574885e-06, | |
| "loss": 2.0116, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.9541984732824428, | |
| "grad_norm": 1.2241454124450684, | |
| "learning_rate": 1.2949737362087156e-06, | |
| "loss": 2.032, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.9923664122137404, | |
| "grad_norm": 1.092801809310913, | |
| "learning_rate": 3.60472329114625e-08, | |
| "loss": 2.0377, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.032930850982666, | |
| "eval_runtime": 23.8518, | |
| "eval_samples_per_second": 38.614, | |
| "eval_steps_per_second": 1.216, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 131, | |
| "total_flos": 1.997211509414953e+17, | |
| "train_loss": 9.506409932638853, | |
| "train_runtime": 976.3941, | |
| "train_samples_per_second": 8.574, | |
| "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 | |
| } | |