| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.07628734901462174, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0025429116338207248, | |
| "eval_loss": 2.1195061206817627, | |
| "eval_runtime": 8.9136, | |
| "eval_samples_per_second": 18.623, | |
| "eval_steps_per_second": 9.312, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007628734901462174, | |
| "grad_norm": 15.621068954467773, | |
| "learning_rate": 6e-05, | |
| "loss": 2.0799, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.015257469802924348, | |
| "grad_norm": 2.5891709327697754, | |
| "learning_rate": 0.00012, | |
| "loss": 2.0585, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.020343293070565798, | |
| "eval_loss": 1.9666500091552734, | |
| "eval_runtime": 8.9529, | |
| "eval_samples_per_second": 18.541, | |
| "eval_steps_per_second": 9.271, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02288620470438652, | |
| "grad_norm": 0.7750437259674072, | |
| "learning_rate": 0.00018, | |
| "loss": 2.1303, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.030514939605848695, | |
| "grad_norm": 0.8389137387275696, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 2.0045, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03814367450731087, | |
| "grad_norm": 0.7117744088172913, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.889, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.040686586141131596, | |
| "eval_loss": 1.8759232759475708, | |
| "eval_runtime": 8.9673, | |
| "eval_samples_per_second": 18.512, | |
| "eval_steps_per_second": 9.256, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04577240940877304, | |
| "grad_norm": 0.6732363700866699, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.9495, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05340114431023522, | |
| "grad_norm": 0.6290881037712097, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 1.9134, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.06102987921169739, | |
| "grad_norm": 0.541335940361023, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 1.7863, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06102987921169739, | |
| "eval_loss": 1.8515095710754395, | |
| "eval_runtime": 8.9814, | |
| "eval_samples_per_second": 18.483, | |
| "eval_steps_per_second": 9.241, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06865861411315957, | |
| "grad_norm": 0.6374207139015198, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 1.9475, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07628734901462174, | |
| "grad_norm": 0.6173187494277954, | |
| "learning_rate": 0.0, | |
| "loss": 1.8881, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3116424700624896.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |