| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 219, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0045662100456621, | |
| "grad_norm": 23.25, | |
| "learning_rate": 4.5454545454545457e-07, | |
| "loss": 1.6483, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.045662100456621, | |
| "grad_norm": 11.5, | |
| "learning_rate": 4.5454545454545455e-06, | |
| "loss": 1.6309, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.091324200913242, | |
| "grad_norm": 3.015625, | |
| "learning_rate": 9.090909090909091e-06, | |
| "loss": 1.4979, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.136986301369863, | |
| "grad_norm": 2.96875, | |
| "learning_rate": 9.959365197965824e-06, | |
| "loss": 1.3794, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.182648401826484, | |
| "grad_norm": 2.78125, | |
| "learning_rate": 9.795417628509857e-06, | |
| "loss": 1.316, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.228310502283105, | |
| "grad_norm": 2.421875, | |
| "learning_rate": 9.50977494371594e-06, | |
| "loss": 1.2561, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.273972602739726, | |
| "grad_norm": 2.421875, | |
| "learning_rate": 9.109686005344258e-06, | |
| "loss": 1.2691, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.319634703196347, | |
| "grad_norm": 2.328125, | |
| "learning_rate": 8.60530402074241e-06, | |
| "loss": 1.2524, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.365296803652968, | |
| "grad_norm": 2.296875, | |
| "learning_rate": 8.009428881086836e-06, | |
| "loss": 1.2188, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.410958904109589, | |
| "grad_norm": 2.25, | |
| "learning_rate": 7.33718233373407e-06, | |
| "loss": 1.2069, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.45662100456621, | |
| "grad_norm": 2.21875, | |
| "learning_rate": 6.6056242319551315e-06, | |
| "loss": 1.2022, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.502283105022831, | |
| "grad_norm": 2.3125, | |
| "learning_rate": 5.8333196006277536e-06, | |
| "loss": 1.2224, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.547945205479452, | |
| "grad_norm": 2.265625, | |
| "learning_rate": 5.039867504623084e-06, | |
| "loss": 1.2076, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.593607305936073, | |
| "grad_norm": 2.265625, | |
| "learning_rate": 4.245403675970877e-06, | |
| "loss": 1.2082, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.639269406392694, | |
| "grad_norm": 2.234375, | |
| "learning_rate": 3.4700895218205026e-06, | |
| "loss": 1.1879, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.684931506849315, | |
| "grad_norm": 2.359375, | |
| "learning_rate": 2.7336004808348094e-06, | |
| "loss": 1.2127, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.730593607305936, | |
| "grad_norm": 2.21875, | |
| "learning_rate": 2.0546267121888863e-06, | |
| "loss": 1.2206, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.776255707762557, | |
| "grad_norm": 2.34375, | |
| "learning_rate": 1.4503987883766857e-06, | |
| "loss": 1.2045, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.821917808219178, | |
| "grad_norm": 2.453125, | |
| "learning_rate": 9.362504284973683e-07, | |
| "loss": 1.2108, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.867579908675799, | |
| "grad_norm": 2.25, | |
| "learning_rate": 5.252293687031196e-07, | |
| "loss": 1.1964, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.91324200913242, | |
| "grad_norm": 2.390625, | |
| "learning_rate": 2.2776624489530664e-07, | |
| "loss": 1.209, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.958904109589041, | |
| "grad_norm": 2.390625, | |
| "learning_rate": 5.1409890557246876e-08, | |
| "loss": 1.2177, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 219, | |
| "total_flos": 2.2271578481885184e+16, | |
| "train_loss": 1.2611416202701935, | |
| "train_runtime": 537.6163, | |
| "train_samples_per_second": 3.259, | |
| "train_steps_per_second": 0.407 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 219, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.2271578481885184e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |