| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0881863560732112, | |
| "eval_steps": 25, | |
| "global_step": 29, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1064891846921797, | |
| "grad_norm": 0.2210182100534439, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5738, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1064891846921797, | |
| "eval_loss": 0.6764118671417236, | |
| "eval_runtime": 2.922, | |
| "eval_samples_per_second": 17.111, | |
| "eval_steps_per_second": 4.449, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.2129783693843594, | |
| "grad_norm": 0.2817445397377014, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6376, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.3194675540765391, | |
| "grad_norm": 0.22999179363250732, | |
| "learning_rate": 9.969572609838744e-05, | |
| "loss": 0.5983, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.4259567387687188, | |
| "grad_norm": 0.20780327916145325, | |
| "learning_rate": 9.878701917609207e-05, | |
| "loss": 0.6238, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.5324459234608985, | |
| "grad_norm": 0.18925385177135468, | |
| "learning_rate": 9.728616793536588e-05, | |
| "loss": 0.5685, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.6389351081530782, | |
| "grad_norm": 0.3107340335845947, | |
| "learning_rate": 9.521346881455356e-05, | |
| "loss": 0.5353, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.7454242928452579, | |
| "grad_norm": 0.2847810387611389, | |
| "learning_rate": 9.259695151358214e-05, | |
| "loss": 0.6103, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.8519134775374376, | |
| "grad_norm": 0.14824841916561127, | |
| "learning_rate": 8.947199994035401e-05, | |
| "loss": 0.5314, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.9584026622296173, | |
| "grad_norm": 0.12647435069084167, | |
| "learning_rate": 8.588087370409303e-05, | |
| "loss": 0.6292, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.064891846921797, | |
| "grad_norm": 0.1318836510181427, | |
| "learning_rate": 8.187213662662538e-05, | |
| "loss": 0.8062, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.1713810316139768, | |
| "grad_norm": 0.09517844766378403, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.6232, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.2778702163061564, | |
| "grad_norm": 0.08089004456996918, | |
| "learning_rate": 7.282358947176207e-05, | |
| "loss": 0.4146, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.3843594009983362, | |
| "grad_norm": 0.09264088422060013, | |
| "learning_rate": 6.790614547199907e-05, | |
| "loss": 0.5849, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.4908485856905158, | |
| "grad_norm": 0.06309893727302551, | |
| "learning_rate": 6.281416799501188e-05, | |
| "loss": 0.3409, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.5973377703826954, | |
| "grad_norm": 0.0876927301287651, | |
| "learning_rate": 5.761651730097142e-05, | |
| "loss": 0.6784, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.7038269550748752, | |
| "grad_norm": 0.06547556817531586, | |
| "learning_rate": 5.23834826990286e-05, | |
| "loss": 0.473, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.8103161397670549, | |
| "grad_norm": 0.08073204755783081, | |
| "learning_rate": 4.718583200498814e-05, | |
| "loss": 0.5896, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.9168053244592347, | |
| "grad_norm": 0.08649210631847382, | |
| "learning_rate": 4.209385452800095e-05, | |
| "loss": 0.5938, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 2.0232945091514143, | |
| "grad_norm": 0.11379551887512207, | |
| "learning_rate": 3.717641052823795e-05, | |
| "loss": 0.8089, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 2.129783693843594, | |
| "grad_norm": 0.07528755068778992, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.5308, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.2362728785357735, | |
| "grad_norm": 0.056557416915893555, | |
| "learning_rate": 2.8127863373374635e-05, | |
| "loss": 0.4656, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 2.3427620632279536, | |
| "grad_norm": 0.07839695364236832, | |
| "learning_rate": 2.4119126295906998e-05, | |
| "loss": 0.6126, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.449251247920133, | |
| "grad_norm": 0.05538203939795494, | |
| "learning_rate": 2.0528000059645997e-05, | |
| "loss": 0.4561, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.5557404326123128, | |
| "grad_norm": 0.0652206763625145, | |
| "learning_rate": 1.740304848641787e-05, | |
| "loss": 0.5319, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.6622296173044924, | |
| "grad_norm": 0.054131075739860535, | |
| "learning_rate": 1.4786531185446454e-05, | |
| "loss": 0.4677, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.6622296173044924, | |
| "eval_loss": 0.5396596193313599, | |
| "eval_runtime": 2.8224, | |
| "eval_samples_per_second": 17.716, | |
| "eval_steps_per_second": 4.606, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.7687188019966724, | |
| "grad_norm": 0.05989672616124153, | |
| "learning_rate": 1.2713832064634126e-05, | |
| "loss": 0.5111, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.875207986688852, | |
| "grad_norm": 0.06187813729047775, | |
| "learning_rate": 1.1212980823907931e-05, | |
| "loss": 0.5551, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.9816971713810316, | |
| "grad_norm": 0.08973059058189392, | |
| "learning_rate": 1.0304273901612566e-05, | |
| "loss": 0.7605, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 3.0881863560732112, | |
| "grad_norm": 0.0628635361790657, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5706, | |
| "step": 29 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 29, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 60, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.217251561273557e+18, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |