| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.8089887640449438, | |
| "eval_steps": 5, | |
| "global_step": 45, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.017977528089887642, | |
| "eval_loss": 11.93013858795166, | |
| "eval_runtime": 0.9844, | |
| "eval_samples_per_second": 95.493, | |
| "eval_steps_per_second": 24.381, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05393258426966292, | |
| "grad_norm": 0.15690268576145172, | |
| "learning_rate": 3e-05, | |
| "loss": 11.9306, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0898876404494382, | |
| "eval_loss": 11.929566383361816, | |
| "eval_runtime": 0.9816, | |
| "eval_samples_per_second": 95.766, | |
| "eval_steps_per_second": 24.451, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.10786516853932585, | |
| "grad_norm": 0.1660546213388443, | |
| "learning_rate": 6e-05, | |
| "loss": 11.9306, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.16179775280898875, | |
| "grad_norm": 0.18455131351947784, | |
| "learning_rate": 9e-05, | |
| "loss": 11.9286, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1797752808988764, | |
| "eval_loss": 11.927314758300781, | |
| "eval_runtime": 0.9797, | |
| "eval_samples_per_second": 95.952, | |
| "eval_steps_per_second": 24.498, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2157303370786517, | |
| "grad_norm": 0.22720609605312347, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 11.9266, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2696629213483146, | |
| "grad_norm": 0.28416040539741516, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 11.9244, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2696629213483146, | |
| "eval_loss": 11.922819137573242, | |
| "eval_runtime": 0.9826, | |
| "eval_samples_per_second": 95.669, | |
| "eval_steps_per_second": 24.426, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3235955056179775, | |
| "grad_norm": 0.3423050045967102, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 11.9214, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3595505617977528, | |
| "eval_loss": 11.91664981842041, | |
| "eval_runtime": 0.9795, | |
| "eval_samples_per_second": 95.969, | |
| "eval_steps_per_second": 24.503, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3775280898876405, | |
| "grad_norm": 0.42053401470184326, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 11.9182, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.4314606741573034, | |
| "grad_norm": 0.44844770431518555, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 11.9144, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.449438202247191, | |
| "eval_loss": 11.909857749938965, | |
| "eval_runtime": 0.9776, | |
| "eval_samples_per_second": 96.152, | |
| "eval_steps_per_second": 24.55, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4853932584269663, | |
| "grad_norm": 0.4792076349258423, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 11.9108, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.5393258426966292, | |
| "grad_norm": 0.4625144898891449, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9055, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5393258426966292, | |
| "eval_loss": 11.904311180114746, | |
| "eval_runtime": 0.9844, | |
| "eval_samples_per_second": 95.493, | |
| "eval_steps_per_second": 24.381, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5932584269662922, | |
| "grad_norm": 0.44238442182540894, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 11.904, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.6292134831460674, | |
| "eval_loss": 11.900728225708008, | |
| "eval_runtime": 0.9786, | |
| "eval_samples_per_second": 96.054, | |
| "eval_steps_per_second": 24.524, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.647191011235955, | |
| "grad_norm": 0.4191032648086548, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 11.9021, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.701123595505618, | |
| "grad_norm": 0.4025208055973053, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 11.8995, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.7191011235955056, | |
| "eval_loss": 11.898837089538574, | |
| "eval_runtime": 0.976, | |
| "eval_samples_per_second": 96.312, | |
| "eval_steps_per_second": 24.59, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.755056179775281, | |
| "grad_norm": 0.3940165936946869, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 11.8986, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.8089887640449438, | |
| "grad_norm": 0.35280826687812805, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 11.899, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.8089887640449438, | |
| "eval_loss": 11.898167610168457, | |
| "eval_runtime": 0.9809, | |
| "eval_samples_per_second": 95.827, | |
| "eval_steps_per_second": 24.466, | |
| "step": 45 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 425438085120.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |