| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.4750593824228028, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009501187648456057, | |
| "grad_norm": 0.0, | |
| "learning_rate": 5e-06, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009501187648456057, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.3329, | |
| "eval_samples_per_second": 19.29, | |
| "eval_steps_per_second": 9.859, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.019002375296912115, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.028503562945368172, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03800475059382423, | |
| "grad_norm": 0.0, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.047505938242280284, | |
| "grad_norm": 0.0, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.057007125890736345, | |
| "grad_norm": 0.0, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0665083135391924, | |
| "grad_norm": 0.0, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07600950118764846, | |
| "grad_norm": 0.0, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0855106888361045, | |
| "grad_norm": 0.0, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.09501187648456057, | |
| "grad_norm": 0.0, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10451306413301663, | |
| "grad_norm": 0.0, | |
| "learning_rate": 4.99229333433282e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.11401425178147269, | |
| "grad_norm": 0.0, | |
| "learning_rate": 4.9692208514878444e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.12351543942992874, | |
| "grad_norm": 0.0, | |
| "learning_rate": 4.9309248009941914e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.12351543942992874, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.3034, | |
| "eval_samples_per_second": 34.524, | |
| "eval_steps_per_second": 17.646, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1330166270783848, | |
| "grad_norm": 0.0, | |
| "learning_rate": 4.877641290737884e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.14251781472684086, | |
| "grad_norm": 0.0, | |
| "learning_rate": 4.8096988312782174e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.15201900237529692, | |
| "grad_norm": 0.0, | |
| "learning_rate": 4.72751631047092e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.16152019002375298, | |
| "grad_norm": 0.0, | |
| "learning_rate": 4.6316004108852305e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.171021377672209, | |
| "grad_norm": 0.0, | |
| "learning_rate": 4.522542485937369e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.18052256532066507, | |
| "grad_norm": 0.0, | |
| "learning_rate": 4.401014914000078e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.19002375296912113, | |
| "grad_norm": 0.0, | |
| "learning_rate": 4.267766952966369e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1995249406175772, | |
| "grad_norm": 0.0, | |
| "learning_rate": 4.123620120825459e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.20902612826603326, | |
| "grad_norm": 0.0, | |
| "learning_rate": 3.969463130731183e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.21852731591448932, | |
| "grad_norm": 0.0, | |
| "learning_rate": 3.8062464117898724e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.22802850356294538, | |
| "grad_norm": 0.0, | |
| "learning_rate": 3.634976249348867e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2375296912114014, | |
| "grad_norm": 0.0, | |
| "learning_rate": 3.456708580912725e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.24703087885985747, | |
| "grad_norm": 0.0, | |
| "learning_rate": 3.272542485937369e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.24703087885985747, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.3166, | |
| "eval_samples_per_second": 34.18, | |
| "eval_steps_per_second": 17.47, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.25653206650831356, | |
| "grad_norm": 0.0, | |
| "learning_rate": 3.083613409639764e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.2660332541567696, | |
| "grad_norm": 0.0, | |
| "learning_rate": 2.8910861626005776e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.2755344418052256, | |
| "grad_norm": 0.0, | |
| "learning_rate": 2.6961477393196126e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.2850356294536817, | |
| "grad_norm": 0.0, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.29453681710213775, | |
| "grad_norm": 0.0, | |
| "learning_rate": 2.303852260680388e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.30403800475059384, | |
| "grad_norm": 0.0, | |
| "learning_rate": 2.1089138373994223e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.31353919239904987, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.9163865903602374e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.32304038004750596, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.7274575140626318e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.332541567695962, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.5432914190872757e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.342042755344418, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.3650237506511331e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.3515439429928741, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.1937535882101281e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.36104513064133015, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.0305368692688174e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.37054631828978624, | |
| "grad_norm": 0.0, | |
| "learning_rate": 8.763798791745411e-06, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.37054631828978624, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.2992, | |
| "eval_samples_per_second": 34.637, | |
| "eval_steps_per_second": 17.704, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.38004750593824227, | |
| "grad_norm": 0.0, | |
| "learning_rate": 7.3223304703363135e-06, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.38954869358669836, | |
| "grad_norm": 0.0, | |
| "learning_rate": 5.989850859999227e-06, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3990498812351544, | |
| "grad_norm": 0.0, | |
| "learning_rate": 4.7745751406263165e-06, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.4085510688836104, | |
| "grad_norm": 0.0, | |
| "learning_rate": 3.6839958911476957e-06, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.4180522565320665, | |
| "grad_norm": 0.0, | |
| "learning_rate": 2.7248368952908053e-06, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.42755344418052255, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.9030116872178316e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.43705463182897863, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.2235870926211619e-06, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.44655581947743467, | |
| "grad_norm": 0.0, | |
| "learning_rate": 6.907519900580861e-07, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.45605700712589076, | |
| "grad_norm": 0.0, | |
| "learning_rate": 3.077914851215585e-07, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.4655581947743468, | |
| "grad_norm": 0.0, | |
| "learning_rate": 7.706665667180091e-08, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.4750593824228028, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8713180230451200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |