| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 4.0, |
| "eval_steps": 500, |
| "global_step": 17560, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.11389521640091116, |
| "grad_norm": 12.961915016174316, |
| "learning_rate": 2.2733485193621873e-05, |
| "loss": 2.138, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.22779043280182232, |
| "grad_norm": 20.78866958618164, |
| "learning_rate": 4.5512528473804106e-05, |
| "loss": 0.8384, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.3416856492027335, |
| "grad_norm": 15.086663246154785, |
| "learning_rate": 6.829157175398633e-05, |
| "loss": 0.6629, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.45558086560364464, |
| "grad_norm": 34.28147888183594, |
| "learning_rate": 7.99533422493134e-05, |
| "loss": 0.6011, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.5694760820045558, |
| "grad_norm": 42.04814529418945, |
| "learning_rate": 7.95645044782997e-05, |
| "loss": 0.5135, |
| "step": 2500 |
| }, |
| { |
| "epoch": 0.683371298405467, |
| "grad_norm": 2.5099027156829834, |
| "learning_rate": 7.878513717033947e-05, |
| "loss": 0.49, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.7972665148063781, |
| "grad_norm": 4.545470237731934, |
| "learning_rate": 7.762293322991625e-05, |
| "loss": 0.4222, |
| "step": 3500 |
| }, |
| { |
| "epoch": 0.9111617312072893, |
| "grad_norm": 3.895155668258667, |
| "learning_rate": 7.608936442882838e-05, |
| "loss": 0.4221, |
| "step": 4000 |
| }, |
| { |
| "epoch": 1.0250569476082005, |
| "grad_norm": 2.197298288345337, |
| "learning_rate": 7.419956817171832e-05, |
| "loss": 0.4035, |
| "step": 4500 |
| }, |
| { |
| "epoch": 1.1389521640091116, |
| "grad_norm": 4.543397426605225, |
| "learning_rate": 7.19721980792226e-05, |
| "loss": 0.3188, |
| "step": 5000 |
| }, |
| { |
| "epoch": 1.2528473804100229, |
| "grad_norm": 1.2027770280838013, |
| "learning_rate": 6.942923986359271e-05, |
| "loss": 0.301, |
| "step": 5500 |
| }, |
| { |
| "epoch": 1.366742596810934, |
| "grad_norm": 5.7361955642700195, |
| "learning_rate": 6.659579431422354e-05, |
| "loss": 0.3052, |
| "step": 6000 |
| }, |
| { |
| "epoch": 1.4806378132118452, |
| "grad_norm": 60.32481002807617, |
| "learning_rate": 6.349982953517576e-05, |
| "loss": 0.2945, |
| "step": 6500 |
| }, |
| { |
| "epoch": 1.5945330296127562, |
| "grad_norm": 24.024532318115234, |
| "learning_rate": 6.017190488028201e-05, |
| "loss": 0.262, |
| "step": 7000 |
| }, |
| { |
| "epoch": 1.7084282460136673, |
| "grad_norm": 5.258288860321045, |
| "learning_rate": 5.664486931079191e-05, |
| "loss": 0.2964, |
| "step": 7500 |
| }, |
| { |
| "epoch": 1.8223234624145785, |
| "grad_norm": 22.747085571289062, |
| "learning_rate": 5.295353715297871e-05, |
| "loss": 0.2934, |
| "step": 8000 |
| }, |
| { |
| "epoch": 1.9362186788154898, |
| "grad_norm": 1.9899779558181763, |
| "learning_rate": 4.913434445620825e-05, |
| "loss": 0.2535, |
| "step": 8500 |
| }, |
| { |
| "epoch": 2.050113895216401, |
| "grad_norm": 0.44854220747947693, |
| "learning_rate": 4.522498934345834e-05, |
| "loss": 0.1939, |
| "step": 9000 |
| }, |
| { |
| "epoch": 2.164009111617312, |
| "grad_norm": 12.502466201782227, |
| "learning_rate": 4.126405990428233e-05, |
| "loss": 0.161, |
| "step": 9500 |
| }, |
| { |
| "epoch": 2.277904328018223, |
| "grad_norm": 0.9645262360572815, |
| "learning_rate": 3.7290653303175396e-05, |
| "loss": 0.1656, |
| "step": 10000 |
| }, |
| { |
| "epoch": 2.3917995444191344, |
| "grad_norm": 0.041170768439769745, |
| "learning_rate": 3.334398986301262e-05, |
| "loss": 0.1394, |
| "step": 10500 |
| }, |
| { |
| "epoch": 2.5056947608200457, |
| "grad_norm": 56.7460823059082, |
| "learning_rate": 2.9463025932826876e-05, |
| "loss": 0.1377, |
| "step": 11000 |
| }, |
| { |
| "epoch": 2.619589977220957, |
| "grad_norm": 1.695715069770813, |
| "learning_rate": 2.5686069361194757e-05, |
| "loss": 0.1274, |
| "step": 11500 |
| }, |
| { |
| "epoch": 2.733485193621868, |
| "grad_norm": 0.49590688943862915, |
| "learning_rate": 2.205040137077874e-05, |
| "loss": 0.1508, |
| "step": 12000 |
| }, |
| { |
| "epoch": 2.847380410022779, |
| "grad_norm": 2.330212116241455, |
| "learning_rate": 1.8591908566390646e-05, |
| "loss": 0.13, |
| "step": 12500 |
| }, |
| { |
| "epoch": 2.9612756264236904, |
| "grad_norm": 0.003335492219775915, |
| "learning_rate": 1.5344728708915906e-05, |
| "loss": 0.1254, |
| "step": 13000 |
| }, |
| { |
| "epoch": 3.075170842824601, |
| "grad_norm": 0.9676417112350464, |
| "learning_rate": 1.2340913751559621e-05, |
| "loss": 0.0922, |
| "step": 13500 |
| }, |
| { |
| "epoch": 3.1890660592255125, |
| "grad_norm": 0.6340539455413818, |
| "learning_rate": 9.610113464484163e-06, |
| "loss": 0.0876, |
| "step": 14000 |
| }, |
| { |
| "epoch": 3.3029612756264237, |
| "grad_norm": 1.2587453126907349, |
| "learning_rate": 7.179282770685981e-06, |
| "loss": 0.0827, |
| "step": 14500 |
| }, |
| { |
| "epoch": 3.416856492027335, |
| "grad_norm": 2.4137210845947266, |
| "learning_rate": 5.072415681912745e-06, |
| "loss": 0.0827, |
| "step": 15000 |
| }, |
| { |
| "epoch": 3.5307517084282463, |
| "grad_norm": 1.391802191734314, |
| "learning_rate": 3.3103084608609646e-06, |
| "loss": 0.0803, |
| "step": 15500 |
| }, |
| { |
| "epoch": 3.644646924829157, |
| "grad_norm": 0.5722363591194153, |
| "learning_rate": 1.910354347409693e-06, |
| "loss": 0.0777, |
| "step": 16000 |
| }, |
| { |
| "epoch": 3.7585421412300684, |
| "grad_norm": 1.3810276985168457, |
| "learning_rate": 8.863718750874395e-07, |
| "loss": 0.0846, |
| "step": 16500 |
| }, |
| { |
| "epoch": 3.8724373576309796, |
| "grad_norm": 0.8889294862747192, |
| "learning_rate": 2.484684724094999e-07, |
| "loss": 0.0867, |
| "step": 17000 |
| }, |
| { |
| "epoch": 3.9863325740318905, |
| "grad_norm": 1.0857609510421753, |
| "learning_rate": 2.940695436648433e-09, |
| "loss": 0.0769, |
| "step": 17500 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 17560, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 4, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 7.393629300129792e+16, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
