| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.0505836575875485, | |
| "eval_steps": 25, | |
| "global_step": 49, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0622568093385214, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0622568093385214, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.9863, | |
| "eval_samples_per_second": 36.165, | |
| "eval_steps_per_second": 4.688, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1245136186770428, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.1867704280155642, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.988834393115767e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.2490272373540856, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.9553874407739e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.311284046692607, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.899808525182935e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.3735408560311284, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.822345875271883e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.4357976653696498, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.723345458039594e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.4980544747081712, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.603249433382144e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5603112840466926, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.462594179299406e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.622568093385214, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.302007896300698e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6848249027237354, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.122207801708802e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.7470817120622568, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.923996926393305e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.8093385214007782, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.708260528239788e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.8715953307392996, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.475962138373213e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.933852140077821, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.228139257794012e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.9961089494163424, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.965898723646776e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.0583657587548638, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.690411765816864e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.1206225680933852, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.402908775933419e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.1828793774319066, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.104673812141675e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.245136186770428, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.797038864187564e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.3073929961089494, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.481377904428171e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.3696498054474708, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.159100751337642e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.4319066147859922, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.831646772915651e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.4941634241245136, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.5004784581204927e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.556420233463035, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.167074885038373e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.556420233463035, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.9859, | |
| "eval_samples_per_second": 36.17, | |
| "eval_steps_per_second": 4.689, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.6186770428015564, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.832925114961629e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.6809338521400778, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.4995215418795085e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.7431906614785992, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.1683532270843504e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.8054474708171206, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.840899248662358e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.867704280155642, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5186220955718306e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.9299610894941635, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.202961135812437e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.9922178988326849, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.895326187858326e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.054474708171206, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5970912240665813e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.1167315175097277, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3095882341831372e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.178988326848249, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0341012763532243e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.2412451361867705, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.771860742205988e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.3035019455252916, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5240378616267886e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.3657587548638133, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2917394717602121e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.4280155642023344, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0760030736066951e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.490272373540856, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.777921982911996e-06, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.5525291828793772, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.979921036993042e-06, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.614785992217899, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.374058207005944e-06, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.6770428015564205, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.967505666178556e-06, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.7392996108949417, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7665454196040664e-06, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.801556420233463, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7765412472811771e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.8638132295719845, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0019147481706625e-06, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.926070038910506, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.461255922609986e-07, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.9883268482490273, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1165606884234181e-07, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 3.0505836575875485, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 49 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 49, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.5448672251202765e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |