| { | |
| "best_metric": 0.38506779074668884, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.03388681802778719, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0013554727211114877, | |
| "grad_norm": 3.3763315677642822, | |
| "learning_rate": 5e-05, | |
| "loss": 2.1424, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013554727211114877, | |
| "eval_loss": 2.15142822265625, | |
| "eval_runtime": 99.9108, | |
| "eval_samples_per_second": 49.744, | |
| "eval_steps_per_second": 6.226, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0027109454422229754, | |
| "grad_norm": 4.00703239440918, | |
| "learning_rate": 0.0001, | |
| "loss": 1.9617, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004066418163334463, | |
| "grad_norm": 4.4005446434021, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.9565, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005421890884445951, | |
| "grad_norm": 2.728137969970703, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.2676, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006777363605557438, | |
| "grad_norm": 2.65754771232605, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.9894, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008132836326668925, | |
| "grad_norm": 2.2339353561401367, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.8164, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009488309047780414, | |
| "grad_norm": 1.3696885108947754, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.609, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.010843781768891902, | |
| "grad_norm": 1.4017082452774048, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.5677, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.012199254490003388, | |
| "grad_norm": 0.6293935775756836, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.1703, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.013554727211114876, | |
| "grad_norm": 0.6255472302436829, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.0563, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.014910199932226365, | |
| "grad_norm": 0.46427881717681885, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.0557, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.01626567265333785, | |
| "grad_norm": 1.1536684036254883, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.3666, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01762114537444934, | |
| "grad_norm": 3.3044023513793945, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.1331, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.018976618095560827, | |
| "grad_norm": 1.8147028684616089, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.7374, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.020332090816672314, | |
| "grad_norm": 0.7124860286712646, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.587, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.021687563537783804, | |
| "grad_norm": 0.8253095149993896, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.5289, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.02304303625889529, | |
| "grad_norm": 0.9700387120246887, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.588, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.024398508980006776, | |
| "grad_norm": 0.7491101622581482, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.5031, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.025753981701118266, | |
| "grad_norm": 0.658585250377655, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.371, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.027109454422229753, | |
| "grad_norm": 0.5979881286621094, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.3764, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02846492714334124, | |
| "grad_norm": 0.3236429989337921, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.1499, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02982039986445273, | |
| "grad_norm": 0.1420210599899292, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.0144, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.031175872585564215, | |
| "grad_norm": 0.09472154825925827, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.0173, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0325313453066757, | |
| "grad_norm": 0.2316225916147232, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.1172, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03388681802778719, | |
| "grad_norm": 0.8157581090927124, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.3354, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03388681802778719, | |
| "eval_loss": 0.38506779074668884, | |
| "eval_runtime": 100.9968, | |
| "eval_samples_per_second": 49.209, | |
| "eval_steps_per_second": 6.159, | |
| "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": 1.1718929936285696e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |