| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 2339, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04275331338178709, | |
| "grad_norm": 0.15714330971240997, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 2.323, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.08550662676357418, | |
| "grad_norm": 0.22236719727516174, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 2.2818, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.12825994014536127, | |
| "grad_norm": 0.4057689309120178, | |
| "learning_rate": 2e-05, | |
| "loss": 2.1665, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.17101325352714836, | |
| "grad_norm": 0.6240995526313782, | |
| "learning_rate": 1.9881538840448035e-05, | |
| "loss": 2.0323, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.21376656690893545, | |
| "grad_norm": 1.0177165269851685, | |
| "learning_rate": 1.9528961971056615e-05, | |
| "loss": 1.9214, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.25651988029072254, | |
| "grad_norm": 0.8750305771827698, | |
| "learning_rate": 1.8950622724781605e-05, | |
| "loss": 1.8745, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.2992731936725096, | |
| "grad_norm": 1.0784953832626343, | |
| "learning_rate": 1.816022324916863e-05, | |
| "loss": 1.8557, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.3420265070542967, | |
| "grad_norm": 1.0847351551055908, | |
| "learning_rate": 1.717648987189577e-05, | |
| "loss": 1.7955, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.3847798204360838, | |
| "grad_norm": 1.1327402591705322, | |
| "learning_rate": 1.6022729432275364e-05, | |
| "loss": 1.7167, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.4275331338178709, | |
| "grad_norm": 1.1066670417785645, | |
| "learning_rate": 1.4726277090211945e-05, | |
| "loss": 1.6959, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.47028644719965795, | |
| "grad_norm": 1.1382914781570435, | |
| "learning_rate": 1.3317848695254441e-05, | |
| "loss": 1.634, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.5130397605814451, | |
| "grad_norm": 1.3232320547103882, | |
| "learning_rate": 1.1830813059565374e-05, | |
| "loss": 1.6383, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.5557930739632322, | |
| "grad_norm": 1.2707828283309937, | |
| "learning_rate": 1.0300401376284509e-05, | |
| "loss": 1.662, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.5985463873450192, | |
| "grad_norm": 1.1388013362884521, | |
| "learning_rate": 8.762872513930507e-06, | |
| "loss": 1.6272, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.6412997007268063, | |
| "grad_norm": 1.339849829673767, | |
| "learning_rate": 7.254653962879187e-06, | |
| "loss": 1.6351, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.6840530141085934, | |
| "grad_norm": 1.3893671035766602, | |
| "learning_rate": 5.8114787868136125e-06, | |
| "loss": 1.5628, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.7268063274903805, | |
| "grad_norm": 1.172720193862915, | |
| "learning_rate": 4.4675390266924536e-06, | |
| "loss": 1.6123, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.7695596408721675, | |
| "grad_norm": 1.1993151903152466, | |
| "learning_rate": 3.2546756149860935e-06, | |
| "loss": 1.5979, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.8123129542539547, | |
| "grad_norm": 1.6297610998153687, | |
| "learning_rate": 2.2016239929203174e-06, | |
| "loss": 1.6089, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.8550662676357418, | |
| "grad_norm": 1.2422642707824707, | |
| "learning_rate": 1.3333333037387176e-06, | |
| "loss": 1.5803, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.8978195810175289, | |
| "grad_norm": 1.5311039686203003, | |
| "learning_rate": 6.703752918150241e-07, | |
| "loss": 1.6131, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.9405728943993159, | |
| "grad_norm": 1.3912514448165894, | |
| "learning_rate": 2.2845691211458298e-07, | |
| "loss": 1.5255, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.983326207781103, | |
| "grad_norm": 1.408026099205017, | |
| "learning_rate": 1.8048197374724852e-08, | |
| "loss": 1.5973, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 2339, | |
| "total_flos": 4.259518857216e+16, | |
| "train_loss": 1.7606283989458218, | |
| "train_runtime": 1228.9387, | |
| "train_samples_per_second": 3.806, | |
| "train_steps_per_second": 1.903 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 2339, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.259518857216e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |