| { | |
| "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": 1408.1902, | |
| "eval_samples_per_second": 32.022, | |
| "eval_steps_per_second": 16.011, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 9.337525882454556e-05, | |
| "grad_norm": 16.06702423095703, | |
| "learning_rate": 0.00019967573081342103, | |
| "loss": 4.4126, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0001867505176490911, | |
| "grad_norm": 20.935449600219727, | |
| "learning_rate": 0.0001970941817426052, | |
| "loss": 1.0184, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0002801257764736367, | |
| "grad_norm": 15.171615600585938, | |
| "learning_rate": 0.00019199794436588243, | |
| "loss": 0.8537, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0003735010352981822, | |
| "grad_norm": 10.143608093261719, | |
| "learning_rate": 0.0001845190085543795, | |
| "loss": 0.8855, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.00046687629412272777, | |
| "grad_norm": 11.451573371887207, | |
| "learning_rate": 0.00017485107481711012, | |
| "loss": 0.6427, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.00046687629412272777, | |
| "eval_loss": 0.1703098565340042, | |
| "eval_runtime": 1404.613, | |
| "eval_samples_per_second": 32.104, | |
| "eval_steps_per_second": 16.052, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0005602515529472734, | |
| "grad_norm": 6.204837799072266, | |
| "learning_rate": 0.00016324453755953773, | |
| "loss": 0.8176, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0006536268117718189, | |
| "grad_norm": 4.421334743499756, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.6348, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0007470020705963644, | |
| "grad_norm": 5.26912260055542, | |
| "learning_rate": 0.00013546048870425356, | |
| "loss": 0.5701, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.0008403773294209099, | |
| "grad_norm": 12.316139221191406, | |
| "learning_rate": 0.00012000256937760445, | |
| "loss": 0.4992, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0009337525882454555, | |
| "grad_norm": 7.5016350746154785, | |
| "learning_rate": 0.00010402659401094152, | |
| "loss": 0.4787, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0009337525882454555, | |
| "eval_loss": 0.13443197309970856, | |
| "eval_runtime": 1402.4134, | |
| "eval_samples_per_second": 32.154, | |
| "eval_steps_per_second": 16.077, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.001027127847070001, | |
| "grad_norm": 7.565667629241943, | |
| "learning_rate": 8.79463319744677e-05, | |
| "loss": 0.4692, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.0011205031058945467, | |
| "grad_norm": 7.207690238952637, | |
| "learning_rate": 7.217825360835473e-05, | |
| "loss": 0.494, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.0012138783647190922, | |
| "grad_norm": 20.8629093170166, | |
| "learning_rate": 5.713074385969457e-05, | |
| "loss": 0.5744, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.0013072536235436377, | |
| "grad_norm": 6.1960625648498535, | |
| "learning_rate": 4.3193525326884435e-05, | |
| "loss": 0.3863, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.0014006288823681834, | |
| "grad_norm": 4.858926296234131, | |
| "learning_rate": 3.072756464904006e-05, | |
| "loss": 0.3115, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.0014006288823681834, | |
| "eval_loss": 0.10407046973705292, | |
| "eval_runtime": 1402.3656, | |
| "eval_samples_per_second": 32.155, | |
| "eval_steps_per_second": 16.078, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.001494004141192729, | |
| "grad_norm": 6.014227390289307, | |
| "learning_rate": 2.0055723659649904e-05, | |
| "loss": 0.4751, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.0015873794000172744, | |
| "grad_norm": 6.426490306854248, | |
| "learning_rate": 1.1454397434679021e-05, | |
| "loss": 0.317, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.0016807546588418199, | |
| "grad_norm": 6.19764518737793, | |
| "learning_rate": 5.146355805285452e-06, | |
| "loss": 0.3526, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.0017741299176663656, | |
| "grad_norm": 4.254812240600586, | |
| "learning_rate": 1.2949737362087156e-06, | |
| "loss": 0.278, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.001867505176490911, | |
| "grad_norm": 5.536872863769531, | |
| "learning_rate": 0.0, | |
| "loss": 0.2585, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.001867505176490911, | |
| "eval_loss": 0.09946458041667938, | |
| "eval_runtime": 1400.9431, | |
| "eval_samples_per_second": 32.188, | |
| "eval_steps_per_second": 16.094, | |
| "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 | |
| } | |