| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.309914642153644, | |
| "eval_steps": 250, | |
| "global_step": 250, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05252790544977019, | |
| "grad_norm": 5.0390625, | |
| "learning_rate": 4.9989743168950524e-05, | |
| "loss": 5.2565, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10505581089954039, | |
| "grad_norm": 5.2265625, | |
| "learning_rate": 4.9979486337901046e-05, | |
| "loss": 4.5589, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.15758371634931057, | |
| "grad_norm": 4.55078125, | |
| "learning_rate": 4.996922950685157e-05, | |
| "loss": 4.4762, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.21011162179908077, | |
| "grad_norm": 4.44140625, | |
| "learning_rate": 4.995897267580208e-05, | |
| "loss": 4.3738, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.262639527248851, | |
| "grad_norm": 4.71484375, | |
| "learning_rate": 4.9948715844752605e-05, | |
| "loss": 4.4801, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.31516743269862113, | |
| "grad_norm": 5.0703125, | |
| "learning_rate": 4.993845901370313e-05, | |
| "loss": 4.5073, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.36769533814839134, | |
| "grad_norm": 4.61328125, | |
| "learning_rate": 4.992820218265365e-05, | |
| "loss": 4.3882, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.42022324359816154, | |
| "grad_norm": 4.5625, | |
| "learning_rate": 4.991794535160417e-05, | |
| "loss": 4.425, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.4727511490479317, | |
| "grad_norm": 5.1484375, | |
| "learning_rate": 4.990768852055469e-05, | |
| "loss": 4.4183, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.525279054497702, | |
| "grad_norm": 5.8515625, | |
| "learning_rate": 4.9897431689505215e-05, | |
| "loss": 4.4666, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5778069599474721, | |
| "grad_norm": 6.51953125, | |
| "learning_rate": 4.988717485845573e-05, | |
| "loss": 4.3722, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.6303348653972423, | |
| "grad_norm": 5.44140625, | |
| "learning_rate": 4.987691802740626e-05, | |
| "loss": 4.2972, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.6828627708470125, | |
| "grad_norm": 5.1796875, | |
| "learning_rate": 4.986666119635678e-05, | |
| "loss": 4.3687, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.7353906762967827, | |
| "grad_norm": 6.51953125, | |
| "learning_rate": 4.9856404365307296e-05, | |
| "loss": 4.3723, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.7879185817465528, | |
| "grad_norm": 4.8359375, | |
| "learning_rate": 4.984614753425782e-05, | |
| "loss": 4.3499, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.8404464871963231, | |
| "grad_norm": 5.3203125, | |
| "learning_rate": 4.983589070320834e-05, | |
| "loss": 4.3462, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.8929743926460932, | |
| "grad_norm": 5.921875, | |
| "learning_rate": 4.982563387215886e-05, | |
| "loss": 4.2716, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.9455022980958634, | |
| "grad_norm": 5.59375, | |
| "learning_rate": 4.9815377041109377e-05, | |
| "loss": 4.34, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.9980302035456337, | |
| "grad_norm": 6.84765625, | |
| "learning_rate": 4.9805120210059905e-05, | |
| "loss": 4.3273, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.0472751149047932, | |
| "grad_norm": 4.859375, | |
| "learning_rate": 4.979486337901043e-05, | |
| "loss": 4.2688, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.0998030203545635, | |
| "grad_norm": 5.921875, | |
| "learning_rate": 4.978460654796094e-05, | |
| "loss": 4.2825, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.1523309258043335, | |
| "grad_norm": 5.28515625, | |
| "learning_rate": 4.9774349716911464e-05, | |
| "loss": 4.2489, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.2048588312541038, | |
| "grad_norm": 5.34765625, | |
| "learning_rate": 4.9764092885861986e-05, | |
| "loss": 4.1895, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.2573867367038738, | |
| "grad_norm": 5.87109375, | |
| "learning_rate": 4.975383605481251e-05, | |
| "loss": 4.194, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.309914642153644, | |
| "grad_norm": 4.7734375, | |
| "learning_rate": 4.974357922376302e-05, | |
| "loss": 4.2085, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.309914642153644, | |
| "eval_loss": 0.26515865325927734, | |
| "eval_runtime": 7.1414, | |
| "eval_samples_per_second": 1400.28, | |
| "eval_steps_per_second": 21.984, | |
| "step": 250 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 380, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 250, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.967181164570214e+17, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |