| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.146131805157593, | |
| "eval_steps": 50, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05730659025787966, | |
| "grad_norm": 13.612731012431626, | |
| "learning_rate": 5e-07, | |
| "loss": 1.2694, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.11461318051575932, | |
| "grad_norm": 8.505429082267508, | |
| "learning_rate": 1e-06, | |
| "loss": 1.1723, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.17191977077363896, | |
| "grad_norm": 5.229519278318145, | |
| "learning_rate": 9.990212076323586e-07, | |
| "loss": 1.0671, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.22922636103151864, | |
| "grad_norm": 3.9947603670699965, | |
| "learning_rate": 9.9608866266743e-07, | |
| "loss": 1.0138, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.28653295128939826, | |
| "grad_norm": 3.900371267559279, | |
| "learning_rate": 9.912138465157323e-07, | |
| "loss": 1.0129, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3438395415472779, | |
| "grad_norm": 3.587740265290173, | |
| "learning_rate": 9.84415844908637e-07, | |
| "loss": 0.9834, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.40114613180515757, | |
| "grad_norm": 3.5465531180374383, | |
| "learning_rate": 9.757212731744973e-07, | |
| "loss": 0.9669, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4584527220630373, | |
| "grad_norm": 3.5868905869199557, | |
| "learning_rate": 9.65164172035126e-07, | |
| "loss": 0.9694, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5157593123209169, | |
| "grad_norm": 3.42949608727936, | |
| "learning_rate": 9.527858743306018e-07, | |
| "loss": 0.9532, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5730659025787965, | |
| "grad_norm": 3.4836706161476148, | |
| "learning_rate": 9.386348431941952e-07, | |
| "loss": 0.9471, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5730659025787965, | |
| "eval_loss": 0.9284318089485168, | |
| "eval_runtime": 42.6858, | |
| "eval_samples_per_second": 58.076, | |
| "eval_steps_per_second": 0.914, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6303724928366762, | |
| "grad_norm": 3.5475576331396113, | |
| "learning_rate": 9.227664823109882e-07, | |
| "loss": 0.939, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.6876790830945558, | |
| "grad_norm": 3.4823932284730343, | |
| "learning_rate": 9.052429190030588e-07, | |
| "loss": 0.9422, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.7449856733524355, | |
| "grad_norm": 3.504161586419209, | |
| "learning_rate": 8.861327609904857e-07, | |
| "loss": 0.9429, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.8022922636103151, | |
| "grad_norm": 3.5831153273903444, | |
| "learning_rate": 8.655108277804975e-07, | |
| "loss": 0.9253, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.8595988538681948, | |
| "grad_norm": 3.4849359586215187, | |
| "learning_rate": 8.434578577364217e-07, | |
| "loss": 0.9285, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.9169054441260746, | |
| "grad_norm": 3.945566817790106, | |
| "learning_rate": 8.200601919733105e-07, | |
| "loss": 0.8995, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.9742120343839542, | |
| "grad_norm": 4.241462484260481, | |
| "learning_rate": 7.954094363178421e-07, | |
| "loss": 0.8951, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.0315186246418337, | |
| "grad_norm": 4.381193820973214, | |
| "learning_rate": 7.696021026559849e-07, | |
| "loss": 0.8507, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.0888252148997135, | |
| "grad_norm": 4.079439442006685, | |
| "learning_rate": 7.427392310726087e-07, | |
| "loss": 0.7966, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.146131805157593, | |
| "grad_norm": 3.9309034286484152, | |
| "learning_rate": 7.149259942624286e-07, | |
| "loss": 0.7921, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.146131805157593, | |
| "eval_loss": 0.8878535032272339, | |
| "eval_runtime": 42.2111, | |
| "eval_samples_per_second": 58.729, | |
| "eval_steps_per_second": 0.924, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 261, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 589411381149696.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |