| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.0949667616334283, |
| "eval_steps": 25, |
| "global_step": 25, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.003798670465337132, |
| "grad_norm": 5.763856410980225, |
| "learning_rate": 3.3333333333333335e-05, |
| "loss": 1.3805, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.003798670465337132, |
| "eval_loss": 1.6539767980575562, |
| "eval_runtime": 46.0435, |
| "eval_samples_per_second": 4.822, |
| "eval_steps_per_second": 2.411, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.007597340930674264, |
| "grad_norm": 10.064556121826172, |
| "learning_rate": 6.666666666666667e-05, |
| "loss": 1.3331, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.011396011396011397, |
| "grad_norm": 4.493223190307617, |
| "learning_rate": 0.0001, |
| "loss": 1.2743, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.015194681861348529, |
| "grad_norm": 2.946624755859375, |
| "learning_rate": 9.99524110790929e-05, |
| "loss": 0.8182, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.01899335232668566, |
| "grad_norm": 2.3877036571502686, |
| "learning_rate": 9.980973490458728e-05, |
| "loss": 0.4942, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.022792022792022793, |
| "grad_norm": 2.079784631729126, |
| "learning_rate": 9.957224306869053e-05, |
| "loss": 0.3639, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.026590693257359924, |
| "grad_norm": 2.2234725952148438, |
| "learning_rate": 9.924038765061042e-05, |
| "loss": 0.2986, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.030389363722697058, |
| "grad_norm": 2.4654929637908936, |
| "learning_rate": 9.881480035599667e-05, |
| "loss": 0.3149, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.03418803418803419, |
| "grad_norm": 1.5854908227920532, |
| "learning_rate": 9.829629131445342e-05, |
| "loss": 0.2439, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.03798670465337132, |
| "grad_norm": 1.5591164827346802, |
| "learning_rate": 9.768584753741134e-05, |
| "loss": 0.2072, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.04178537511870845, |
| "grad_norm": 1.7570960521697998, |
| "learning_rate": 9.698463103929542e-05, |
| "loss": 0.2455, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.045584045584045586, |
| "grad_norm": 1.3588300943374634, |
| "learning_rate": 9.619397662556435e-05, |
| "loss": 0.2317, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.04938271604938271, |
| "grad_norm": 1.2992509603500366, |
| "learning_rate": 9.53153893518325e-05, |
| "loss": 0.2435, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.05318138651471985, |
| "grad_norm": 1.2096527814865112, |
| "learning_rate": 9.435054165891109e-05, |
| "loss": 0.1905, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.05698005698005698, |
| "grad_norm": 1.542781114578247, |
| "learning_rate": 9.330127018922194e-05, |
| "loss": 0.2319, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.060778727445394115, |
| "grad_norm": 1.497053861618042, |
| "learning_rate": 9.21695722906443e-05, |
| "loss": 0.2579, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.06457739791073125, |
| "grad_norm": 0.8226407766342163, |
| "learning_rate": 9.09576022144496e-05, |
| "loss": 0.1359, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.06837606837606838, |
| "grad_norm": 1.5668431520462036, |
| "learning_rate": 8.966766701456177e-05, |
| "loss": 0.196, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.0721747388414055, |
| "grad_norm": 0.9736147522926331, |
| "learning_rate": 8.83022221559489e-05, |
| "loss": 0.147, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.07597340930674264, |
| "grad_norm": 1.0604015588760376, |
| "learning_rate": 8.68638668405062e-05, |
| "loss": 0.157, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.07977207977207977, |
| "grad_norm": 1.4285651445388794, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 0.1586, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.0835707502374169, |
| "grad_norm": 1.30019211769104, |
| "learning_rate": 8.377951038078302e-05, |
| "loss": 0.1612, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.08736942070275404, |
| "grad_norm": 1.120355248451233, |
| "learning_rate": 8.213938048432697e-05, |
| "loss": 0.1544, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.09116809116809117, |
| "grad_norm": 1.0541555881500244, |
| "learning_rate": 8.043807145043604e-05, |
| "loss": 0.177, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.0949667616334283, |
| "grad_norm": 4.731549263000488, |
| "learning_rate": 7.86788218175523e-05, |
| "loss": 0.1304, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.0949667616334283, |
| "eval_loss": 0.13617277145385742, |
| "eval_runtime": 46.0992, |
| "eval_samples_per_second": 4.816, |
| "eval_steps_per_second": 2.408, |
| "step": 25 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 75, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 25, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4.1446136610816e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
