| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.001867505176490911, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 9.337525882454556e-06, | |
| "eval_loss": 1.8007404804229736, | |
| "eval_runtime": 1427.512, | |
| "eval_samples_per_second": 31.589, | |
| "eval_steps_per_second": 15.795, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 9.337525882454556e-05, | |
| "grad_norm": 15.88760757446289, | |
| "learning_rate": 0.00019967573081342103, | |
| "loss": 4.4098, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0001867505176490911, | |
| "grad_norm": 13.844344139099121, | |
| "learning_rate": 0.0001970941817426052, | |
| "loss": 1.0261, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0002801257764736367, | |
| "grad_norm": 14.212364196777344, | |
| "learning_rate": 0.00019199794436588243, | |
| "loss": 0.852, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0003735010352981822, | |
| "grad_norm": 13.421478271484375, | |
| "learning_rate": 0.0001845190085543795, | |
| "loss": 0.9217, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.00046687629412272777, | |
| "grad_norm": 9.063638687133789, | |
| "learning_rate": 0.00017485107481711012, | |
| "loss": 0.6308, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.00046687629412272777, | |
| "eval_loss": 0.17543035745620728, | |
| "eval_runtime": 1424.7926, | |
| "eval_samples_per_second": 31.649, | |
| "eval_steps_per_second": 15.825, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0005602515529472734, | |
| "grad_norm": 5.191962718963623, | |
| "learning_rate": 0.00016324453755953773, | |
| "loss": 0.7862, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0006536268117718189, | |
| "grad_norm": 4.098013401031494, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.6442, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0007470020705963644, | |
| "grad_norm": 5.904275894165039, | |
| "learning_rate": 0.00013546048870425356, | |
| "loss": 0.5431, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.0008403773294209099, | |
| "grad_norm": 16.334659576416016, | |
| "learning_rate": 0.00012000256937760445, | |
| "loss": 0.4667, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0009337525882454555, | |
| "grad_norm": 10.986539840698242, | |
| "learning_rate": 0.00010402659401094152, | |
| "loss": 0.5034, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0009337525882454555, | |
| "eval_loss": 0.13188250362873077, | |
| "eval_runtime": 1425.5359, | |
| "eval_samples_per_second": 31.632, | |
| "eval_steps_per_second": 15.817, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.001027127847070001, | |
| "grad_norm": 7.501925468444824, | |
| "learning_rate": 8.79463319744677e-05, | |
| "loss": 0.4854, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.0011205031058945467, | |
| "grad_norm": 6.146622657775879, | |
| "learning_rate": 7.217825360835473e-05, | |
| "loss": 0.5185, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.0012138783647190922, | |
| "grad_norm": 16.533327102661133, | |
| "learning_rate": 5.713074385969457e-05, | |
| "loss": 0.5499, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.0013072536235436377, | |
| "grad_norm": 5.197549819946289, | |
| "learning_rate": 4.3193525326884435e-05, | |
| "loss": 0.3846, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.0014006288823681834, | |
| "grad_norm": 4.099363803863525, | |
| "learning_rate": 3.072756464904006e-05, | |
| "loss": 0.3223, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.0014006288823681834, | |
| "eval_loss": 0.1042235940694809, | |
| "eval_runtime": 1425.3406, | |
| "eval_samples_per_second": 31.637, | |
| "eval_steps_per_second": 15.819, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.001494004141192729, | |
| "grad_norm": 5.590132713317871, | |
| "learning_rate": 2.0055723659649904e-05, | |
| "loss": 0.4452, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.0015873794000172744, | |
| "grad_norm": 5.151331424713135, | |
| "learning_rate": 1.1454397434679021e-05, | |
| "loss": 0.3123, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.0016807546588418199, | |
| "grad_norm": 5.607838153839111, | |
| "learning_rate": 5.146355805285452e-06, | |
| "loss": 0.3708, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.0017741299176663656, | |
| "grad_norm": 4.572511196136475, | |
| "learning_rate": 1.2949737362087156e-06, | |
| "loss": 0.2782, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.001867505176490911, | |
| "grad_norm": 4.551802635192871, | |
| "learning_rate": 0.0, | |
| "loss": 0.249, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.001867505176490911, | |
| "eval_loss": 0.0991196408867836, | |
| "eval_runtime": 1426.6404, | |
| "eval_samples_per_second": 31.608, | |
| "eval_steps_per_second": 15.804, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.50534158516224e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |