| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.9933774834437086, |
| "eval_steps": 50, |
| "global_step": 75, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.06622516556291391, |
| "grad_norm": 7.145169734954834, |
| "learning_rate": 5e-05, |
| "loss": 2.9784, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.13245033112582782, |
| "grad_norm": 2.2012343406677246, |
| "learning_rate": 9.994504457428558e-05, |
| "loss": 0.8648, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.1986754966887417, |
| "grad_norm": 5.701715469360352, |
| "learning_rate": 9.8034259378842e-05, |
| "loss": 0.677, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.26490066225165565, |
| "grad_norm": 0.7785886526107788, |
| "learning_rate": 9.349531862043952e-05, |
| "loss": 0.6025, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.33112582781456956, |
| "grad_norm": 0.4165729880332947, |
| "learning_rate": 8.657656676318346e-05, |
| "loss": 0.4445, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.3973509933774834, |
| "grad_norm": 1.1374096870422363, |
| "learning_rate": 7.765655770625997e-05, |
| "loss": 0.4018, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.46357615894039733, |
| "grad_norm": 0.6517850160598755, |
| "learning_rate": 6.722334251421665e-05, |
| "loss": 0.4919, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.5298013245033113, |
| "grad_norm": 0.3663589060306549, |
| "learning_rate": 5.584776609860414e-05, |
| "loss": 0.4198, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.5960264900662252, |
| "grad_norm": 0.34794583916664124, |
| "learning_rate": 4.415223390139588e-05, |
| "loss": 0.398, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.6622516556291391, |
| "grad_norm": 0.3982546031475067, |
| "learning_rate": 3.277665748578336e-05, |
| "loss": 0.4235, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.7284768211920529, |
| "grad_norm": 0.32591888308525085, |
| "learning_rate": 2.234344229374003e-05, |
| "loss": 0.4253, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.7947019867549668, |
| "grad_norm": 0.3768315017223358, |
| "learning_rate": 1.3423433236816563e-05, |
| "loss": 0.4094, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.8609271523178808, |
| "grad_norm": 0.4178403317928314, |
| "learning_rate": 6.50468137956049e-06, |
| "loss": 0.4191, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.9271523178807947, |
| "grad_norm": 0.3431091904640198, |
| "learning_rate": 1.9657406211579966e-06, |
| "loss": 0.4236, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.9933774834437086, |
| "grad_norm": 0.37446972727775574, |
| "learning_rate": 5.4955425714431353e-08, |
| "loss": 0.431, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.9933774834437086, |
| "step": 75, |
| "total_flos": 1.0406942485905408e+16, |
| "train_loss": 0.6540391174952189, |
| "train_runtime": 272.6059, |
| "train_samples_per_second": 1.108, |
| "train_steps_per_second": 0.275 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 75, |
| "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": 1.0406942485905408e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
