| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0013505118439888718, | |
| "eval_steps": 9, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.402047375955487e-05, | |
| "grad_norm": 1.061699628829956, | |
| "learning_rate": 1e-05, | |
| "loss": 2.3561, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 5.402047375955487e-05, | |
| "eval_loss": 2.3112149238586426, | |
| "eval_runtime": 3362.2667, | |
| "eval_samples_per_second": 4.636, | |
| "eval_steps_per_second": 0.58, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00010804094751910974, | |
| "grad_norm": 1.3118318319320679, | |
| "learning_rate": 2e-05, | |
| "loss": 2.3782, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00016206142127866461, | |
| "grad_norm": 1.1144564151763916, | |
| "learning_rate": 3e-05, | |
| "loss": 2.2446, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00021608189503821948, | |
| "grad_norm": 1.174940824508667, | |
| "learning_rate": 4e-05, | |
| "loss": 2.2652, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00027010236879777437, | |
| "grad_norm": 1.4532380104064941, | |
| "learning_rate": 5e-05, | |
| "loss": 2.5352, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00032412284255732923, | |
| "grad_norm": 1.2197051048278809, | |
| "learning_rate": 6e-05, | |
| "loss": 2.2264, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0003781433163168841, | |
| "grad_norm": 1.1164822578430176, | |
| "learning_rate": 7e-05, | |
| "loss": 2.142, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00043216379007643895, | |
| "grad_norm": 1.55741548538208, | |
| "learning_rate": 8e-05, | |
| "loss": 2.4181, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0004861842638359938, | |
| "grad_norm": 1.3686168193817139, | |
| "learning_rate": 9e-05, | |
| "loss": 2.3264, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0004861842638359938, | |
| "eval_loss": 1.989229440689087, | |
| "eval_runtime": 3370.5193, | |
| "eval_samples_per_second": 4.625, | |
| "eval_steps_per_second": 0.578, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0005402047375955487, | |
| "grad_norm": 1.062412142753601, | |
| "learning_rate": 0.0001, | |
| "loss": 1.8345, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0005942252113551035, | |
| "grad_norm": 1.1697839498519897, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 1.9388, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0006482456851146585, | |
| "grad_norm": 1.3678555488586426, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 2.0119, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0007022661588742134, | |
| "grad_norm": 1.381777048110962, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 1.6446, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0007562866326337682, | |
| "grad_norm": 1.0860157012939453, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 1.6745, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0008103071063933231, | |
| "grad_norm": 1.466055154800415, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 1.8303, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0008643275801528779, | |
| "grad_norm": 1.3503963947296143, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 1.7245, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0009183480539124328, | |
| "grad_norm": 1.4205446243286133, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 1.7683, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0009723685276719876, | |
| "grad_norm": 1.3751708269119263, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 1.7489, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0009723685276719876, | |
| "eval_loss": 1.6231409311294556, | |
| "eval_runtime": 3370.1387, | |
| "eval_samples_per_second": 4.626, | |
| "eval_steps_per_second": 0.578, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0010263890014315425, | |
| "grad_norm": 1.411476969718933, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 1.5006, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0010804094751910975, | |
| "grad_norm": 1.5040185451507568, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 1.743, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0011344299489506524, | |
| "grad_norm": 1.4046059846878052, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 1.7263, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.001188450422710207, | |
| "grad_norm": 1.1052309274673462, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 1.5053, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.001242470896469762, | |
| "grad_norm": 0.9669276475906372, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 1.5642, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.001296491370229317, | |
| "grad_norm": 1.1981260776519775, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 1.572, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0013505118439888718, | |
| "grad_norm": 1.1273926496505737, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.6082, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "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": 3.635247689446195e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |