| { | |
| "best_metric": 0.0494825541973114, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.32102728731942215, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.012841091492776886, | |
| "grad_norm": 2.98820424079895, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7501, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012841091492776886, | |
| "eval_loss": 4.6158623695373535, | |
| "eval_runtime": 2.1584, | |
| "eval_samples_per_second": 23.165, | |
| "eval_steps_per_second": 6.023, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.025682182985553772, | |
| "grad_norm": 3.726931095123291, | |
| "learning_rate": 0.0001, | |
| "loss": 2.2293, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.038523274478330656, | |
| "grad_norm": 3.8018789291381836, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 2.317, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.051364365971107544, | |
| "grad_norm": 4.310789585113525, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.9756, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06420545746388442, | |
| "grad_norm": 5.516280174255371, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.5689, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07704654895666131, | |
| "grad_norm": 4.980829238891602, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.0627, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0898876404494382, | |
| "grad_norm": 5.193998336791992, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.7698, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.10272873194221509, | |
| "grad_norm": 3.3907129764556885, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.4906, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.11556982343499198, | |
| "grad_norm": 2.7564470767974854, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.1924, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.12841091492776885, | |
| "grad_norm": 1.1876503229141235, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.1494, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14125200642054575, | |
| "grad_norm": 2.6727466583251953, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.2081, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.15409309791332262, | |
| "grad_norm": 0.9418500065803528, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.117, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.16693418940609953, | |
| "grad_norm": 0.27055737376213074, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.0342, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1797752808988764, | |
| "grad_norm": 0.29577669501304626, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.0389, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.1926163723916533, | |
| "grad_norm": 0.1944814771413803, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.0505, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.20545746388443017, | |
| "grad_norm": 0.30078575015068054, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.043, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.21829855537720708, | |
| "grad_norm": 0.28765007853507996, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.0478, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.23113964686998395, | |
| "grad_norm": 0.4925723671913147, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.0432, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.24398073836276082, | |
| "grad_norm": 0.3609505593776703, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.0644, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2568218298555377, | |
| "grad_norm": 0.45685964822769165, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.056, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2696629213483146, | |
| "grad_norm": 0.4444729685783386, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.0824, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.2825040128410915, | |
| "grad_norm": 0.47437188029289246, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.0743, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.2953451043338684, | |
| "grad_norm": 0.44289061427116394, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.0703, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.30818619582664525, | |
| "grad_norm": 0.7908194065093994, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.0685, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.32102728731942215, | |
| "grad_norm": 0.45595434308052063, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.0865, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.32102728731942215, | |
| "eval_loss": 0.0494825541973114, | |
| "eval_runtime": 1.423, | |
| "eval_samples_per_second": 35.138, | |
| "eval_steps_per_second": 9.136, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.812028905324544e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |