| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.88, | |
| "eval_steps": 500, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.096, | |
| "grad_norm": 1.9259725061038635, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 0.7587, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.192, | |
| "grad_norm": 2.049268420650378, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.7674, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.288, | |
| "grad_norm": 1.8747063256034509, | |
| "learning_rate": 1e-05, | |
| "loss": 0.7241, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.384, | |
| "grad_norm": 1.292446480570027, | |
| "learning_rate": 9.966191788709716e-06, | |
| "loss": 0.7884, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 1.102369937824534, | |
| "learning_rate": 9.86522435289912e-06, | |
| "loss": 0.6799, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.576, | |
| "grad_norm": 1.1156530710500372, | |
| "learning_rate": 9.698463103929542e-06, | |
| "loss": 0.7124, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.672, | |
| "grad_norm": 1.289873608779737, | |
| "learning_rate": 9.468163201617063e-06, | |
| "loss": 0.6514, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.768, | |
| "grad_norm": 1.062347962718082, | |
| "learning_rate": 9.177439057064684e-06, | |
| "loss": 0.622, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.864, | |
| "grad_norm": 0.8359897864349394, | |
| "learning_rate": 8.83022221559489e-06, | |
| "loss": 0.6111, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.6822054477942913, | |
| "learning_rate": 8.43120818934367e-06, | |
| "loss": 0.5754, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.056, | |
| "grad_norm": 1.1449236868526296, | |
| "learning_rate": 7.985792958513932e-06, | |
| "loss": 0.8793, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.152, | |
| "grad_norm": 0.6194240012412793, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 0.5532, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.248, | |
| "grad_norm": 0.6415102621935532, | |
| "learning_rate": 6.980398830195785e-06, | |
| "loss": 0.5669, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.3439999999999999, | |
| "grad_norm": 0.7201896144485234, | |
| "learning_rate": 6.434016163555452e-06, | |
| "loss": 0.6219, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 0.6037727593926941, | |
| "learning_rate": 5.8682408883346535e-06, | |
| "loss": 0.5092, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.536, | |
| "grad_norm": 0.5540675036066202, | |
| "learning_rate": 5.290724144552379e-06, | |
| "loss": 0.5177, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.6320000000000001, | |
| "grad_norm": 0.5152284803827317, | |
| "learning_rate": 4.7092758554476215e-06, | |
| "loss": 0.5007, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.728, | |
| "grad_norm": 0.5215068211046744, | |
| "learning_rate": 4.131759111665349e-06, | |
| "loss": 0.5342, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.8239999999999998, | |
| "grad_norm": 0.4688306236480946, | |
| "learning_rate": 3.5659838364445505e-06, | |
| "loss": 0.4718, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 0.5581232863519313, | |
| "learning_rate": 3.019601169804216e-06, | |
| "loss": 0.6043, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.016, | |
| "grad_norm": 0.9249445167553337, | |
| "learning_rate": 2.5000000000000015e-06, | |
| "loss": 0.838, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 2.112, | |
| "grad_norm": 0.4441044859173903, | |
| "learning_rate": 2.0142070414860704e-06, | |
| "loss": 0.443, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.208, | |
| "grad_norm": 0.4716134582182365, | |
| "learning_rate": 1.5687918106563326e-06, | |
| "loss": 0.5071, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.304, | |
| "grad_norm": 0.4825901207173238, | |
| "learning_rate": 1.1697777844051105e-06, | |
| "loss": 0.5188, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 0.4740847334344184, | |
| "learning_rate": 8.225609429353187e-07, | |
| "loss": 0.4816, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.496, | |
| "grad_norm": 0.46603655925006804, | |
| "learning_rate": 5.318367983829393e-07, | |
| "loss": 0.4424, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.592, | |
| "grad_norm": 0.45444530803024485, | |
| "learning_rate": 3.015368960704584e-07, | |
| "loss": 0.4778, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.6879999999999997, | |
| "grad_norm": 0.4364104500267912, | |
| "learning_rate": 1.3477564710088097e-07, | |
| "loss": 0.4417, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.784, | |
| "grad_norm": 0.43550990569382114, | |
| "learning_rate": 3.3808211290284886e-08, | |
| "loss": 0.4643, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "grad_norm": 0.7865657852577704, | |
| "learning_rate": 0.0, | |
| "loss": 0.4885, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "step": 30, | |
| "total_flos": 2.2758181499305984e+16, | |
| "train_loss": 0.591774974266688, | |
| "train_runtime": 2448.0606, | |
| "train_samples_per_second": 0.613, | |
| "train_steps_per_second": 0.012 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.2758181499305984e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |