| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.5109034267912773, | |
| "eval_steps": 354, | |
| "global_step": 3100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05664117813650524, | |
| "grad_norm": 0.7603653073310852, | |
| "learning_rate": 0.0001978110599078341, | |
| "loss": 0.9425, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11328235627301048, | |
| "grad_norm": 0.6873273849487305, | |
| "learning_rate": 0.00019205069124423964, | |
| "loss": 0.6078, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.16992353440951571, | |
| "grad_norm": 0.6323167085647583, | |
| "learning_rate": 0.00018629032258064517, | |
| "loss": 0.6748, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.22656471254602095, | |
| "grad_norm": 1.0095610618591309, | |
| "learning_rate": 0.0001805299539170507, | |
| "loss": 0.6594, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.2832058906825262, | |
| "grad_norm": 0.5822212100028992, | |
| "learning_rate": 0.00017476958525345623, | |
| "loss": 0.6317, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.33984706881903143, | |
| "grad_norm": 0.8490907549858093, | |
| "learning_rate": 0.00016900921658986176, | |
| "loss": 0.5742, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.3964882469555367, | |
| "grad_norm": 0.6252707242965698, | |
| "learning_rate": 0.0001632488479262673, | |
| "loss": 0.5502, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.4010195412064571, | |
| "eval_loss": 0.6019027233123779, | |
| "eval_runtime": 159.9351, | |
| "eval_samples_per_second": 9.81, | |
| "eval_steps_per_second": 2.457, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 0.4531294250920419, | |
| "grad_norm": 0.656812310218811, | |
| "learning_rate": 0.00015748847926267282, | |
| "loss": 0.5686, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.5097706032285472, | |
| "grad_norm": 0.7391073703765869, | |
| "learning_rate": 0.00015172811059907835, | |
| "loss": 0.5701, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.5664117813650524, | |
| "grad_norm": 0.9210707545280457, | |
| "learning_rate": 0.00014596774193548388, | |
| "loss": 0.6397, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.6230529595015576, | |
| "grad_norm": 0.8228403329849243, | |
| "learning_rate": 0.00014020737327188939, | |
| "loss": 0.5822, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.6796941376380629, | |
| "grad_norm": 0.716748833656311, | |
| "learning_rate": 0.00013444700460829494, | |
| "loss": 0.5881, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.7363353157745681, | |
| "grad_norm": 0.7144941091537476, | |
| "learning_rate": 0.00012868663594470047, | |
| "loss": 0.6032, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.7929764939110734, | |
| "grad_norm": 1.016291618347168, | |
| "learning_rate": 0.000122926267281106, | |
| "loss": 0.6377, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.8020390824129142, | |
| "eval_loss": 0.5828524827957153, | |
| "eval_runtime": 150.8754, | |
| "eval_samples_per_second": 10.399, | |
| "eval_steps_per_second": 2.605, | |
| "step": 708 | |
| }, | |
| { | |
| "epoch": 0.8496176720475785, | |
| "grad_norm": 1.0243154764175415, | |
| "learning_rate": 0.00011716589861751153, | |
| "loss": 0.6005, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.9062588501840838, | |
| "grad_norm": 0.6541144251823425, | |
| "learning_rate": 0.00011140552995391706, | |
| "loss": 0.5723, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.9629000283205891, | |
| "grad_norm": 1.0017038583755493, | |
| "learning_rate": 0.00010564516129032258, | |
| "loss": 0.5801, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.0192580005664118, | |
| "grad_norm": 0.7527189254760742, | |
| "learning_rate": 9.988479262672812e-05, | |
| "loss": 0.5511, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.075899178702917, | |
| "grad_norm": 0.7966899871826172, | |
| "learning_rate": 9.412442396313365e-05, | |
| "loss": 0.49, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.1325403568394223, | |
| "grad_norm": 0.7110822796821594, | |
| "learning_rate": 8.836405529953917e-05, | |
| "loss": 0.4725, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.1891815349759276, | |
| "grad_norm": 0.7837777733802795, | |
| "learning_rate": 8.26036866359447e-05, | |
| "loss": 0.527, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.2027754177286887, | |
| "eval_loss": 0.5833637714385986, | |
| "eval_runtime": 150.6223, | |
| "eval_samples_per_second": 10.417, | |
| "eval_steps_per_second": 2.609, | |
| "step": 1062 | |
| }, | |
| { | |
| "epoch": 1.2458227131124326, | |
| "grad_norm": 0.8119267821311951, | |
| "learning_rate": 7.684331797235024e-05, | |
| "loss": 0.4892, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.302463891248938, | |
| "grad_norm": 0.8631129860877991, | |
| "learning_rate": 7.108294930875576e-05, | |
| "loss": 0.5124, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.3591050693854432, | |
| "grad_norm": 0.8685782551765442, | |
| "learning_rate": 6.532258064516129e-05, | |
| "loss": 0.4927, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.4157462475219484, | |
| "grad_norm": 0.8397710919380188, | |
| "learning_rate": 5.956221198156682e-05, | |
| "loss": 0.5125, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.4723874256584537, | |
| "grad_norm": 0.7606781721115112, | |
| "learning_rate": 5.3801843317972355e-05, | |
| "loss": 0.4826, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.529028603794959, | |
| "grad_norm": 1.1354798078536987, | |
| "learning_rate": 4.8041474654377885e-05, | |
| "loss": 0.5101, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 1.5856697819314642, | |
| "grad_norm": 1.28499174118042, | |
| "learning_rate": 4.228110599078341e-05, | |
| "loss": 0.4687, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.603794958935146, | |
| "eval_loss": 0.5791710615158081, | |
| "eval_runtime": 150.7437, | |
| "eval_samples_per_second": 10.408, | |
| "eval_steps_per_second": 2.607, | |
| "step": 1416 | |
| }, | |
| { | |
| "epoch": 1.6423109600679693, | |
| "grad_norm": 0.7527874708175659, | |
| "learning_rate": 3.6520737327188945e-05, | |
| "loss": 0.4992, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 1.6989521382044748, | |
| "grad_norm": 0.9351261854171753, | |
| "learning_rate": 3.076036866359447e-05, | |
| "loss": 0.4873, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.7555933163409798, | |
| "grad_norm": 1.0196998119354248, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.4946, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 1.812234494477485, | |
| "grad_norm": 0.9896508455276489, | |
| "learning_rate": 1.923963133640553e-05, | |
| "loss": 0.4895, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.8688756726139903, | |
| "grad_norm": 1.150964617729187, | |
| "learning_rate": 1.3479262672811061e-05, | |
| "loss": 0.5164, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 1.9255168507504956, | |
| "grad_norm": 0.8384917378425598, | |
| "learning_rate": 7.71889400921659e-06, | |
| "loss": 0.4914, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.9821580288870009, | |
| "grad_norm": 0.9231545329093933, | |
| "learning_rate": 1.9585253456221198e-06, | |
| "loss": 0.4939, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 2.0045312942509206, | |
| "eval_loss": 0.5844214558601379, | |
| "eval_runtime": 166.1298, | |
| "eval_samples_per_second": 9.444, | |
| "eval_steps_per_second": 2.366, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 2.0385160011328236, | |
| "grad_norm": 0.9673134088516235, | |
| "learning_rate": 0.00014248089741505446, | |
| "loss": 0.4303, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.0951571792693287, | |
| "grad_norm": 1.33237624168396, | |
| "learning_rate": 0.00014085514550479596, | |
| "loss": 0.4594, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 2.151798357405834, | |
| "grad_norm": 1.068943738937378, | |
| "learning_rate": 0.0001392293935945375, | |
| "loss": 0.4939, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.208439535542339, | |
| "grad_norm": 1.1625093221664429, | |
| "learning_rate": 0.00013760364168427899, | |
| "loss": 0.4757, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 2.2650807136788447, | |
| "grad_norm": 1.080735683441162, | |
| "learning_rate": 0.00013597788977402048, | |
| "loss": 0.4724, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.3217218918153497, | |
| "grad_norm": 0.8823259472846985, | |
| "learning_rate": 0.00013435213786376198, | |
| "loss": 0.4821, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 2.378363069951855, | |
| "grad_norm": 1.0513312816619873, | |
| "learning_rate": 0.0001327263859535035, | |
| "loss": 0.479, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.4055508354573774, | |
| "eval_loss": 0.6049736738204956, | |
| "eval_runtime": 156.3245, | |
| "eval_samples_per_second": 10.037, | |
| "eval_steps_per_second": 2.514, | |
| "step": 2124 | |
| }, | |
| { | |
| "epoch": 2.4350042480883602, | |
| "grad_norm": 1.0902981758117676, | |
| "learning_rate": 0.000131100634043245, | |
| "loss": 0.4749, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 2.4916454262248653, | |
| "grad_norm": 0.9050194025039673, | |
| "learning_rate": 0.0001294748821329865, | |
| "loss": 0.4346, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 2.5482866043613708, | |
| "grad_norm": 1.0356699228286743, | |
| "learning_rate": 0.00012784913022272803, | |
| "loss": 0.4685, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 2.604927782497876, | |
| "grad_norm": 1.0071344375610352, | |
| "learning_rate": 0.00012622337831246953, | |
| "loss": 0.5, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 2.6615689606343813, | |
| "grad_norm": 1.0409235954284668, | |
| "learning_rate": 0.00012459762640221103, | |
| "loss": 0.4908, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 2.7182101387708864, | |
| "grad_norm": 0.8756324052810669, | |
| "learning_rate": 0.00012297187449195252, | |
| "loss": 0.4765, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 2.774851316907392, | |
| "grad_norm": 0.6662527918815613, | |
| "learning_rate": 0.00012134612258169405, | |
| "loss": 0.4524, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 2.8065703766638346, | |
| "eval_loss": 0.5904644727706909, | |
| "eval_runtime": 157.1505, | |
| "eval_samples_per_second": 9.984, | |
| "eval_steps_per_second": 2.501, | |
| "step": 2478 | |
| }, | |
| { | |
| "epoch": 2.831492495043897, | |
| "grad_norm": 1.0368993282318115, | |
| "learning_rate": 0.00011972037067143556, | |
| "loss": 0.4661, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.888133673180402, | |
| "grad_norm": 1.0678080320358276, | |
| "learning_rate": 0.00011809461876117705, | |
| "loss": 0.4812, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 2.9447748513169074, | |
| "grad_norm": 1.2212059497833252, | |
| "learning_rate": 0.00011646886685091856, | |
| "loss": 0.482, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 3.00113282356273, | |
| "grad_norm": 0.757663369178772, | |
| "learning_rate": 0.00011484311494066007, | |
| "loss": 0.5062, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 3.057774001699235, | |
| "grad_norm": 0.8512151837348938, | |
| "learning_rate": 0.00011321736303040155, | |
| "loss": 0.3651, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 3.1144151798357407, | |
| "grad_norm": 0.9610685706138611, | |
| "learning_rate": 0.00011159161112014307, | |
| "loss": 0.3626, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 3.1710563579722457, | |
| "grad_norm": 1.0879671573638916, | |
| "learning_rate": 0.00010996585920988458, | |
| "loss": 0.3637, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 3.207306711979609, | |
| "eval_loss": 0.6150493025779724, | |
| "eval_runtime": 157.6799, | |
| "eval_samples_per_second": 9.951, | |
| "eval_steps_per_second": 2.492, | |
| "step": 2832 | |
| }, | |
| { | |
| "epoch": 3.227697536108751, | |
| "grad_norm": 1.1237863302230835, | |
| "learning_rate": 0.00010834010729962609, | |
| "loss": 0.4015, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 3.2843387142452563, | |
| "grad_norm": 0.7940804958343506, | |
| "learning_rate": 0.00010671435538936759, | |
| "loss": 0.3572, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 3.3409798923817613, | |
| "grad_norm": 1.7029999494552612, | |
| "learning_rate": 0.0001050886034791091, | |
| "loss": 0.3902, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 3.397621070518267, | |
| "grad_norm": 0.8232925534248352, | |
| "learning_rate": 0.00010346285156885061, | |
| "loss": 0.3814, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3.454262248654772, | |
| "grad_norm": 0.9208984375, | |
| "learning_rate": 0.0001018370996585921, | |
| "loss": 0.377, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 3.5109034267912773, | |
| "grad_norm": 1.1689094305038452, | |
| "learning_rate": 0.00010021134774833361, | |
| "loss": 0.3887, | |
| "step": 3100 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 6181, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 7, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.0467108033589094e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |