| { | |
| "best_metric": 0.0001311919477302581, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.15822784810126583, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0031645569620253164, | |
| "grad_norm": 39.122718811035156, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 4.7862, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0031645569620253164, | |
| "eval_loss": 5.090167999267578, | |
| "eval_runtime": 4.6691, | |
| "eval_samples_per_second": 10.709, | |
| "eval_steps_per_second": 1.499, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006329113924050633, | |
| "grad_norm": 38.526920318603516, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 4.8726, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00949367088607595, | |
| "grad_norm": 35.14896011352539, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 4.2408, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.012658227848101266, | |
| "grad_norm": 18.20745086669922, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 2.5564, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.015822784810126583, | |
| "grad_norm": 14.840872764587402, | |
| "learning_rate": 0.00015, | |
| "loss": 1.0869, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0189873417721519, | |
| "grad_norm": 6.644170761108398, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 0.283, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.022151898734177215, | |
| "grad_norm": 42.69538497924805, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 0.5808, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02531645569620253, | |
| "grad_norm": 16.369243621826172, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 0.5497, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.028481012658227847, | |
| "grad_norm": 19.000972747802734, | |
| "learning_rate": 0.00027, | |
| "loss": 0.5608, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03164556962025317, | |
| "grad_norm": 11.529747009277344, | |
| "learning_rate": 0.0003, | |
| "loss": 0.3618, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03481012658227848, | |
| "grad_norm": 15.791008949279785, | |
| "learning_rate": 0.0002999794957488703, | |
| "loss": 0.5098, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0379746835443038, | |
| "grad_norm": 3.0417582988739014, | |
| "learning_rate": 0.0002999179886011389, | |
| "loss": 0.0882, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04113924050632911, | |
| "grad_norm": 3.213977336883545, | |
| "learning_rate": 0.0002998154953722457, | |
| "loss": 0.0588, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04430379746835443, | |
| "grad_norm": 0.42049989104270935, | |
| "learning_rate": 0.00029967204408281613, | |
| "loss": 0.0048, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04746835443037975, | |
| "grad_norm": 0.010697176679968834, | |
| "learning_rate": 0.00029948767395100045, | |
| "loss": 0.0002, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05063291139240506, | |
| "grad_norm": 0.08972659707069397, | |
| "learning_rate": 0.0002992624353817517, | |
| "loss": 0.0003, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05379746835443038, | |
| "grad_norm": 90.54857635498047, | |
| "learning_rate": 0.0002989963899530457, | |
| "loss": 0.2488, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.056962025316455694, | |
| "grad_norm": 0.0011396000627428293, | |
| "learning_rate": 0.00029868961039904624, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.060126582278481014, | |
| "grad_norm": 32.987918853759766, | |
| "learning_rate": 0.00029834218059022024, | |
| "loss": 0.3497, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06329113924050633, | |
| "grad_norm": 0.0006623624940402806, | |
| "learning_rate": 0.00029795419551040833, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06645569620253164, | |
| "grad_norm": 0.002704908140003681, | |
| "learning_rate": 0.00029752576123085736, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.06962025316455696, | |
| "grad_norm": 0.074082151055336, | |
| "learning_rate": 0.0002970569948812214, | |
| "loss": 0.0003, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.07278481012658228, | |
| "grad_norm": 0.051233161240816116, | |
| "learning_rate": 0.0002965480246175399, | |
| "loss": 0.0002, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0759493670886076, | |
| "grad_norm": 0.002620099810883403, | |
| "learning_rate": 0.0002959989895872009, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.07911392405063292, | |
| "grad_norm": 0.002381028374657035, | |
| "learning_rate": 0.0002954100398908995, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07911392405063292, | |
| "eval_loss": 1.5358215023297817e-05, | |
| "eval_runtime": 4.2105, | |
| "eval_samples_per_second": 11.875, | |
| "eval_steps_per_second": 1.663, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08227848101265822, | |
| "grad_norm": 0.0008074412471614778, | |
| "learning_rate": 0.0002947813365416023, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.08544303797468354, | |
| "grad_norm": 80.40802001953125, | |
| "learning_rate": 0.0002941130514205272, | |
| "loss": 0.216, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.08860759493670886, | |
| "grad_norm": 0.0007025494705885649, | |
| "learning_rate": 0.0002934053672301536, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.09177215189873418, | |
| "grad_norm": 0.16022445261478424, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 0.0004, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0949367088607595, | |
| "grad_norm": 0.00044286646880209446, | |
| "learning_rate": 0.00029187258625509513, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0981012658227848, | |
| "grad_norm": 0.0007045658421702683, | |
| "learning_rate": 0.00029104790851742417, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.10126582278481013, | |
| "grad_norm": 4.665228366851807, | |
| "learning_rate": 0.0002901846696899191, | |
| "loss": 0.2712, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.10443037974683544, | |
| "grad_norm": 35.976463317871094, | |
| "learning_rate": 0.00028928310577345606, | |
| "loss": 2.2757, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.10759493670886076, | |
| "grad_norm": 3.145080089569092, | |
| "learning_rate": 0.0002883434632466077, | |
| "loss": 0.0429, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.11075949367088607, | |
| "grad_norm": 0.7390124201774597, | |
| "learning_rate": 0.00028736599899825856, | |
| "loss": 0.0082, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.11392405063291139, | |
| "grad_norm": 56.273048400878906, | |
| "learning_rate": 0.00028635098025737434, | |
| "loss": 0.5411, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.11708860759493671, | |
| "grad_norm": 0.016222132369875908, | |
| "learning_rate": 0.00028529868451994384, | |
| "loss": 0.0002, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.12025316455696203, | |
| "grad_norm": 0.00250585051253438, | |
| "learning_rate": 0.0002842093994731145, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.12341772151898735, | |
| "grad_norm": 0.0014803847298026085, | |
| "learning_rate": 0.00028308342291654174, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.12658227848101267, | |
| "grad_norm": 0.0008740597986616194, | |
| "learning_rate": 0.00028192106268097334, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.12974683544303797, | |
| "grad_norm": 0.0006211165455169976, | |
| "learning_rate": 0.00028072263654409154, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.13291139240506328, | |
| "grad_norm": 0.000527973985299468, | |
| "learning_rate": 0.0002794884721436361, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1360759493670886, | |
| "grad_norm": 0.0007822936167940497, | |
| "learning_rate": 0.00027821890688783083, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.13924050632911392, | |
| "grad_norm": 14.17163372039795, | |
| "learning_rate": 0.0002769142878631403, | |
| "loss": 0.0377, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.14240506329113925, | |
| "grad_norm": 37.15114974975586, | |
| "learning_rate": 0.00027557497173937923, | |
| "loss": 1.6189, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.14556962025316456, | |
| "grad_norm": 0.1055205836892128, | |
| "learning_rate": 0.000274201324672203, | |
| "loss": 0.0009, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.14873417721518986, | |
| "grad_norm": 15.12343978881836, | |
| "learning_rate": 0.00027279372220300385, | |
| "loss": 0.1632, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.1518987341772152, | |
| "grad_norm": 0.004173843655735254, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 0.0001, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1550632911392405, | |
| "grad_norm": 0.010756113566458225, | |
| "learning_rate": 0.00026987819953423867, | |
| "loss": 0.0001, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.15822784810126583, | |
| "grad_norm": 0.014636156149208546, | |
| "learning_rate": 0.00026837107640945905, | |
| "loss": 0.0001, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.15822784810126583, | |
| "eval_loss": 0.0001311919477302581, | |
| "eval_runtime": 4.2069, | |
| "eval_samples_per_second": 11.885, | |
| "eval_steps_per_second": 1.664, | |
| "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": 7.88255238782976e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |