| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.3591050693854432, | |
| "eval_steps": 354, | |
| "global_step": 1200, | |
| "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 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 1766, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 4.058581317399936e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |