| { | |
| "best_metric": 0.8585520386695862, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.0476190476190474, | |
| "eval_steps": 25, | |
| "global_step": 40, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0761904761904762, | |
| "grad_norm": 14.026223182678223, | |
| "learning_rate": 5e-05, | |
| "loss": 7.5144, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0761904761904762, | |
| "eval_loss": 7.233830451965332, | |
| "eval_runtime": 1.8952, | |
| "eval_samples_per_second": 46.961, | |
| "eval_steps_per_second": 6.332, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1523809523809524, | |
| "grad_norm": 14.973212242126465, | |
| "learning_rate": 0.0001, | |
| "loss": 7.9078, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.22857142857142856, | |
| "grad_norm": 13.781585693359375, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 7.1847, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.3047619047619048, | |
| "grad_norm": 12.180188179016113, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 5.6694, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.38095238095238093, | |
| "grad_norm": 9.784143447875977, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 4.3383, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.45714285714285713, | |
| "grad_norm": 9.046195983886719, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 3.3229, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.5333333333333333, | |
| "grad_norm": 7.573584079742432, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 2.4241, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.6095238095238096, | |
| "grad_norm": 7.039599418640137, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 1.9458, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.6857142857142857, | |
| "grad_norm": 4.332740306854248, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 1.2798, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.7619047619047619, | |
| "grad_norm": 2.105264663696289, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 1.0346, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.8380952380952381, | |
| "grad_norm": 4.982356071472168, | |
| "learning_rate": 8.678619553365659e-05, | |
| "loss": 1.011, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.9142857142857143, | |
| "grad_norm": 2.1526806354522705, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 0.9524, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.9904761904761905, | |
| "grad_norm": 1.4837459325790405, | |
| "learning_rate": 8.07106356344834e-05, | |
| "loss": 0.9343, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 3.639598846435547, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 1.7018, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.1428571428571428, | |
| "grad_norm": 1.631341814994812, | |
| "learning_rate": 7.379736965185368e-05, | |
| "loss": 0.9145, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.2190476190476192, | |
| "grad_norm": 1.466554045677185, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 0.9415, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.2952380952380953, | |
| "grad_norm": 5.518876075744629, | |
| "learning_rate": 6.623497346023418e-05, | |
| "loss": 0.8771, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.3714285714285714, | |
| "grad_norm": 1.651365876197815, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 0.9171, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.4476190476190476, | |
| "grad_norm": 1.233325719833374, | |
| "learning_rate": 5.8229729514036705e-05, | |
| "loss": 0.9414, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.5238095238095237, | |
| "grad_norm": 1.4162348508834839, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 0.8752, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 1.5792149305343628, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9103, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.6761904761904762, | |
| "grad_norm": 1.1879042387008667, | |
| "learning_rate": 4.5871032726383386e-05, | |
| "loss": 0.9003, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.7523809523809524, | |
| "grad_norm": 0.9944649338722229, | |
| "learning_rate": 4.17702704859633e-05, | |
| "loss": 0.8776, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.8285714285714287, | |
| "grad_norm": 3.7743890285491943, | |
| "learning_rate": 3.772572564296005e-05, | |
| "loss": 0.911, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.9047619047619047, | |
| "grad_norm": 0.7919507622718811, | |
| "learning_rate": 3.3765026539765834e-05, | |
| "loss": 0.891, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.9047619047619047, | |
| "eval_loss": 0.8585520386695862, | |
| "eval_runtime": 1.8941, | |
| "eval_samples_per_second": 46.988, | |
| "eval_steps_per_second": 6.335, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.980952380952381, | |
| "grad_norm": 0.9605194330215454, | |
| "learning_rate": 2.991522876735154e-05, | |
| "loss": 0.887, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.057142857142857, | |
| "grad_norm": 2.160217523574829, | |
| "learning_rate": 2.6202630348146324e-05, | |
| "loss": 1.6403, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.1333333333333333, | |
| "grad_norm": 1.0214014053344727, | |
| "learning_rate": 2.2652592093878666e-05, | |
| "loss": 0.9062, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.2095238095238097, | |
| "grad_norm": 1.190313458442688, | |
| "learning_rate": 1.928936436551661e-05, | |
| "loss": 0.853, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.2857142857142856, | |
| "grad_norm": 1.1187245845794678, | |
| "learning_rate": 1.6135921418712956e-05, | |
| "loss": 0.8842, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.361904761904762, | |
| "grad_norm": 0.9486127495765686, | |
| "learning_rate": 1.3213804466343421e-05, | |
| "loss": 0.8989, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.4380952380952383, | |
| "grad_norm": 1.1477197408676147, | |
| "learning_rate": 1.0542974530180327e-05, | |
| "loss": 0.8428, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.5142857142857142, | |
| "grad_norm": 0.8318337798118591, | |
| "learning_rate": 8.141676086873572e-06, | |
| "loss": 0.8689, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.5904761904761906, | |
| "grad_norm": 0.9033652544021606, | |
| "learning_rate": 6.026312439675552e-06, | |
| "loss": 0.8886, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 1.3068876266479492, | |
| "learning_rate": 4.2113336672471245e-06, | |
| "loss": 0.8713, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.742857142857143, | |
| "grad_norm": 1.5723620653152466, | |
| "learning_rate": 2.7091379149682685e-06, | |
| "loss": 0.8887, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.819047619047619, | |
| "grad_norm": 0.7510371804237366, | |
| "learning_rate": 1.5299867030334814e-06, | |
| "loss": 0.8693, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.895238095238095, | |
| "grad_norm": 0.9378589987754822, | |
| "learning_rate": 6.819348298638839e-07, | |
| "loss": 0.8705, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.9714285714285715, | |
| "grad_norm": 1.0388190746307373, | |
| "learning_rate": 1.7077534966650766e-07, | |
| "loss": 0.8689, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 3.0476190476190474, | |
| "grad_norm": 2.3041744232177734, | |
| "learning_rate": 0.0, | |
| "loss": 1.5959, | |
| "step": 40 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 40, | |
| "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": 1.2528685890404352e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |