| { | |
| "best_metric": 4.9084954261779785, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.1693480101608806, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003386960203217612, | |
| "grad_norm": 13.740797996520996, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 3.1754, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003386960203217612, | |
| "eval_loss": 4.746492385864258, | |
| "eval_runtime": 6.8487, | |
| "eval_samples_per_second": 7.301, | |
| "eval_steps_per_second": 1.022, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006773920406435224, | |
| "grad_norm": 15.781672477722168, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 3.1112, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.010160880609652836, | |
| "grad_norm": 13.645687103271484, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 3.0881, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.013547840812870448, | |
| "grad_norm": 9.539155960083008, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 1.7159, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01693480101608806, | |
| "grad_norm": 4.083582878112793, | |
| "learning_rate": 0.00015, | |
| "loss": 0.4898, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02032176121930567, | |
| "grad_norm": 2.5189051628112793, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 0.2539, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.023708721422523286, | |
| "grad_norm": 6.38540506362915, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 0.3516, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.027095681625740897, | |
| "grad_norm": 13.505107879638672, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 0.5986, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03048264182895851, | |
| "grad_norm": 3.495882987976074, | |
| "learning_rate": 0.00027, | |
| "loss": 0.2681, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03386960203217612, | |
| "grad_norm": 4.064078330993652, | |
| "learning_rate": 0.0003, | |
| "loss": 0.1063, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03725656223539373, | |
| "grad_norm": 5.738462924957275, | |
| "learning_rate": 0.0002999794957488703, | |
| "loss": 0.0551, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04064352243861134, | |
| "grad_norm": 11.198445320129395, | |
| "learning_rate": 0.0002999179886011389, | |
| "loss": 0.5952, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04403048264182896, | |
| "grad_norm": 10.263776779174805, | |
| "learning_rate": 0.0002998154953722457, | |
| "loss": 0.4714, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04741744284504657, | |
| "grad_norm": 13.766398429870605, | |
| "learning_rate": 0.00029967204408281613, | |
| "loss": 0.615, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.05080440304826418, | |
| "grad_norm": 6.041114330291748, | |
| "learning_rate": 0.00029948767395100045, | |
| "loss": 0.6127, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05419136325148179, | |
| "grad_norm": 3.049060583114624, | |
| "learning_rate": 0.0002992624353817517, | |
| "loss": 0.5814, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.057578323454699404, | |
| "grad_norm": 2.864790678024292, | |
| "learning_rate": 0.0002989963899530457, | |
| "loss": 0.4473, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.06096528365791702, | |
| "grad_norm": 6.220133304595947, | |
| "learning_rate": 0.00029868961039904624, | |
| "loss": 0.4051, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.06435224386113463, | |
| "grad_norm": 2.263486862182617, | |
| "learning_rate": 0.00029834218059022024, | |
| "loss": 0.2403, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06773920406435224, | |
| "grad_norm": 4.127490520477295, | |
| "learning_rate": 0.00029795419551040833, | |
| "loss": 0.2728, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07112616426756986, | |
| "grad_norm": 3.9908688068389893, | |
| "learning_rate": 0.00029752576123085736, | |
| "loss": 0.2682, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.07451312447078746, | |
| "grad_norm": 9.111742973327637, | |
| "learning_rate": 0.0002970569948812214, | |
| "loss": 0.2637, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.07790008467400508, | |
| "grad_norm": 3.493535280227661, | |
| "learning_rate": 0.0002965480246175399, | |
| "loss": 0.2798, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.08128704487722269, | |
| "grad_norm": 2.2693541049957275, | |
| "learning_rate": 0.0002959989895872009, | |
| "loss": 0.2922, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0846740050804403, | |
| "grad_norm": 3.484853744506836, | |
| "learning_rate": 0.0002954100398908995, | |
| "loss": 0.2737, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0846740050804403, | |
| "eval_loss": 1.9888197183609009, | |
| "eval_runtime": 6.9843, | |
| "eval_samples_per_second": 7.159, | |
| "eval_steps_per_second": 1.002, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08806096528365792, | |
| "grad_norm": 2.42002534866333, | |
| "learning_rate": 0.0002947813365416023, | |
| "loss": 0.1555, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.09144792548687553, | |
| "grad_norm": 4.468302249908447, | |
| "learning_rate": 0.0002941130514205272, | |
| "loss": 0.2272, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.09483488569009314, | |
| "grad_norm": 4.684446334838867, | |
| "learning_rate": 0.0002934053672301536, | |
| "loss": 0.5432, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.09822184589331075, | |
| "grad_norm": 11.514558792114258, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 0.4408, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.10160880609652836, | |
| "grad_norm": 4.456749439239502, | |
| "learning_rate": 0.00029187258625509513, | |
| "loss": 0.3308, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10499576629974598, | |
| "grad_norm": 6.331120491027832, | |
| "learning_rate": 0.00029104790851742417, | |
| "loss": 0.7949, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.10838272650296359, | |
| "grad_norm": 29.455829620361328, | |
| "learning_rate": 0.0002901846696899191, | |
| "loss": 4.6651, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1117696867061812, | |
| "grad_norm": 11.79928970336914, | |
| "learning_rate": 0.00028928310577345606, | |
| "loss": 1.6663, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.11515664690939881, | |
| "grad_norm": 6.791766166687012, | |
| "learning_rate": 0.0002883434632466077, | |
| "loss": 0.6458, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.11854360711261643, | |
| "grad_norm": 9.273675918579102, | |
| "learning_rate": 0.00028736599899825856, | |
| "loss": 0.6169, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.12193056731583404, | |
| "grad_norm": 1.2118967771530151, | |
| "learning_rate": 0.00028635098025737434, | |
| "loss": 0.315, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.12531752751905165, | |
| "grad_norm": 3.5652599334716797, | |
| "learning_rate": 0.00028529868451994384, | |
| "loss": 0.3108, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.12870448772226925, | |
| "grad_norm": 1.0388684272766113, | |
| "learning_rate": 0.0002842093994731145, | |
| "loss": 0.3072, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.13209144792548688, | |
| "grad_norm": 1.3198330402374268, | |
| "learning_rate": 0.00028308342291654174, | |
| "loss": 0.2595, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1354784081287045, | |
| "grad_norm": 9.642812728881836, | |
| "learning_rate": 0.00028192106268097334, | |
| "loss": 0.4847, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1388653683319221, | |
| "grad_norm": 8.038244247436523, | |
| "learning_rate": 0.00028072263654409154, | |
| "loss": 0.4086, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.14225232853513972, | |
| "grad_norm": 2.3692054748535156, | |
| "learning_rate": 0.0002794884721436361, | |
| "loss": 0.3204, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.14563928873835733, | |
| "grad_norm": 0.9498773217201233, | |
| "learning_rate": 0.00027821890688783083, | |
| "loss": 0.2721, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.14902624894157493, | |
| "grad_norm": 0.9654709100723267, | |
| "learning_rate": 0.0002769142878631403, | |
| "loss": 0.1986, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.15241320914479256, | |
| "grad_norm": 3.0386719703674316, | |
| "learning_rate": 0.00027557497173937923, | |
| "loss": 0.2193, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.15580016934801016, | |
| "grad_norm": 4.969003200531006, | |
| "learning_rate": 0.000274201324672203, | |
| "loss": 0.296, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.15918712955122777, | |
| "grad_norm": 5.841146945953369, | |
| "learning_rate": 0.00027279372220300385, | |
| "loss": 0.5754, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.16257408975444537, | |
| "grad_norm": 4.163698196411133, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 0.3311, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.165961049957663, | |
| "grad_norm": 0.9581086039543152, | |
| "learning_rate": 0.00026987819953423867, | |
| "loss": 0.1751, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.1693480101608806, | |
| "grad_norm": 0.8359802961349487, | |
| "learning_rate": 0.00026837107640945905, | |
| "loss": 0.1348, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1693480101608806, | |
| "eval_loss": 4.9084954261779785, | |
| "eval_runtime": 6.9763, | |
| "eval_samples_per_second": 7.167, | |
| "eval_steps_per_second": 1.003, | |
| "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": 8.75088325902336e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |