| { | |
| "best_metric": 0.01057486142963171, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.012738853503184714, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00025477707006369424, | |
| "grad_norm": 1.0286307334899902, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 0.269, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00025477707006369424, | |
| "eval_loss": 0.5101139545440674, | |
| "eval_runtime": 1.5196, | |
| "eval_samples_per_second": 32.903, | |
| "eval_steps_per_second": 4.606, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005095541401273885, | |
| "grad_norm": 1.556894063949585, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 0.3567, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0007643312101910828, | |
| "grad_norm": 2.283867359161377, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 0.4087, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001019108280254777, | |
| "grad_norm": 2.4171900749206543, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 0.363, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0012738853503184713, | |
| "grad_norm": 12.618427276611328, | |
| "learning_rate": 0.00015, | |
| "loss": 0.3981, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0015286624203821656, | |
| "grad_norm": 2.4185802936553955, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 0.4004, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0017834394904458599, | |
| "grad_norm": 5.5376715660095215, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 0.2874, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002038216560509554, | |
| "grad_norm": 0.9478390216827393, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 0.1853, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0022929936305732482, | |
| "grad_norm": 56.32394027709961, | |
| "learning_rate": 0.00027, | |
| "loss": 0.3149, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0025477707006369425, | |
| "grad_norm": 16.362091064453125, | |
| "learning_rate": 0.0003, | |
| "loss": 0.1729, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002802547770700637, | |
| "grad_norm": 0.7184139490127563, | |
| "learning_rate": 0.0002999794957488703, | |
| "loss": 0.1242, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.003057324840764331, | |
| "grad_norm": 0.5045642256736755, | |
| "learning_rate": 0.0002999179886011389, | |
| "loss": 0.1038, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0033121019108280254, | |
| "grad_norm": 0.310913622379303, | |
| "learning_rate": 0.0002998154953722457, | |
| "loss": 0.0685, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0035668789808917197, | |
| "grad_norm": 0.2581654191017151, | |
| "learning_rate": 0.00029967204408281613, | |
| "loss": 0.0829, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.003821656050955414, | |
| "grad_norm": 0.3674789369106293, | |
| "learning_rate": 0.00029948767395100045, | |
| "loss": 0.0568, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004076433121019108, | |
| "grad_norm": 0.39360904693603516, | |
| "learning_rate": 0.0002992624353817517, | |
| "loss": 0.0528, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004331210191082803, | |
| "grad_norm": 0.1805201917886734, | |
| "learning_rate": 0.0002989963899530457, | |
| "loss": 0.04, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0045859872611464965, | |
| "grad_norm": 0.1762702465057373, | |
| "learning_rate": 0.00029868961039904624, | |
| "loss": 0.0367, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.004840764331210191, | |
| "grad_norm": 0.13610054552555084, | |
| "learning_rate": 0.00029834218059022024, | |
| "loss": 0.025, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.005095541401273885, | |
| "grad_norm": 0.19703835248947144, | |
| "learning_rate": 0.00029795419551040833, | |
| "loss": 0.0246, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00535031847133758, | |
| "grad_norm": 0.09786652028560638, | |
| "learning_rate": 0.00029752576123085736, | |
| "loss": 0.0268, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.005605095541401274, | |
| "grad_norm": 0.14086395502090454, | |
| "learning_rate": 0.0002970569948812214, | |
| "loss": 0.0264, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.005859872611464968, | |
| "grad_norm": 0.17169000208377838, | |
| "learning_rate": 0.0002965480246175399, | |
| "loss": 0.0196, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.006114649681528662, | |
| "grad_norm": 0.09433834254741669, | |
| "learning_rate": 0.0002959989895872009, | |
| "loss": 0.0189, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.006369426751592357, | |
| "grad_norm": 0.16031892597675323, | |
| "learning_rate": 0.0002954100398908995, | |
| "loss": 0.0108, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006369426751592357, | |
| "eval_loss": 0.010693784803152084, | |
| "eval_runtime": 1.1107, | |
| "eval_samples_per_second": 45.016, | |
| "eval_steps_per_second": 6.302, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006624203821656051, | |
| "grad_norm": 0.11191248893737793, | |
| "learning_rate": 0.0002947813365416023, | |
| "loss": 0.0238, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.006878980891719746, | |
| "grad_norm": 0.10025566816329956, | |
| "learning_rate": 0.0002941130514205272, | |
| "loss": 0.0235, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0071337579617834395, | |
| "grad_norm": 0.07389934360980988, | |
| "learning_rate": 0.0002934053672301536, | |
| "loss": 0.0243, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.007388535031847133, | |
| "grad_norm": 0.091887466609478, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 0.0129, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.007643312101910828, | |
| "grad_norm": 0.12741683423519135, | |
| "learning_rate": 0.00029187258625509513, | |
| "loss": 0.0103, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.007898089171974522, | |
| "grad_norm": 0.05791885778307915, | |
| "learning_rate": 0.00029104790851742417, | |
| "loss": 0.0159, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.008152866242038216, | |
| "grad_norm": 0.024696996435523033, | |
| "learning_rate": 0.0002901846696899191, | |
| "loss": 0.0102, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.008407643312101911, | |
| "grad_norm": 0.11524629592895508, | |
| "learning_rate": 0.00028928310577345606, | |
| "loss": 0.0152, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.008662420382165605, | |
| "grad_norm": 0.059739116579294205, | |
| "learning_rate": 0.0002883434632466077, | |
| "loss": 0.0144, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.008917197452229299, | |
| "grad_norm": 0.10027167946100235, | |
| "learning_rate": 0.00028736599899825856, | |
| "loss": 0.0126, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.009171974522292993, | |
| "grad_norm": 0.12271470576524734, | |
| "learning_rate": 0.00028635098025737434, | |
| "loss": 0.013, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.009426751592356689, | |
| "grad_norm": 0.06018821895122528, | |
| "learning_rate": 0.00028529868451994384, | |
| "loss": 0.0046, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.009681528662420382, | |
| "grad_norm": 0.04106978327035904, | |
| "learning_rate": 0.0002842093994731145, | |
| "loss": 0.0141, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.009936305732484076, | |
| "grad_norm": 0.08049760013818741, | |
| "learning_rate": 0.00028308342291654174, | |
| "loss": 0.0091, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.01019108280254777, | |
| "grad_norm": 0.07265523076057434, | |
| "learning_rate": 0.00028192106268097334, | |
| "loss": 0.0135, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.010445859872611466, | |
| "grad_norm": 0.10459401458501816, | |
| "learning_rate": 0.00028072263654409154, | |
| "loss": 0.0146, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.01070063694267516, | |
| "grad_norm": 0.19710560142993927, | |
| "learning_rate": 0.0002794884721436361, | |
| "loss": 0.0117, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.010955414012738853, | |
| "grad_norm": 0.04603102430701256, | |
| "learning_rate": 0.00027821890688783083, | |
| "loss": 0.0207, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.011210191082802547, | |
| "grad_norm": 0.04048272594809532, | |
| "learning_rate": 0.0002769142878631403, | |
| "loss": 0.0051, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.011464968152866241, | |
| "grad_norm": 0.10804333537817001, | |
| "learning_rate": 0.00027557497173937923, | |
| "loss": 0.0253, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.011719745222929937, | |
| "grad_norm": 0.10464876145124435, | |
| "learning_rate": 0.000274201324672203, | |
| "loss": 0.0167, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.01197452229299363, | |
| "grad_norm": 0.05495596304535866, | |
| "learning_rate": 0.00027279372220300385, | |
| "loss": 0.0113, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.012229299363057325, | |
| "grad_norm": 0.19954094290733337, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 0.0109, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.012484076433121018, | |
| "grad_norm": 0.34227123856544495, | |
| "learning_rate": 0.00026987819953423867, | |
| "loss": 0.0267, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.012738853503184714, | |
| "grad_norm": 0.4878714680671692, | |
| "learning_rate": 0.00026837107640945905, | |
| "loss": 0.0323, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.012738853503184714, | |
| "eval_loss": 0.01057486142963171, | |
| "eval_runtime": 1.1123, | |
| "eval_samples_per_second": 44.951, | |
| "eval_steps_per_second": 6.293, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "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": 1.0991728418881536e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |