| { | |
| "best_metric": 0.6268936991691589, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.40424456796361796, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00808489135927236, | |
| "grad_norm": 1.6052894592285156, | |
| "learning_rate": 5e-05, | |
| "loss": 1.744, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00808489135927236, | |
| "eval_loss": 2.1085262298583984, | |
| "eval_runtime": 3.8396, | |
| "eval_samples_per_second": 13.022, | |
| "eval_steps_per_second": 3.386, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01616978271854472, | |
| "grad_norm": 1.779472827911377, | |
| "learning_rate": 0.0001, | |
| "loss": 1.9097, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02425467407781708, | |
| "grad_norm": 2.0423178672790527, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 1.8782, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03233956543708944, | |
| "grad_norm": 2.7541654109954834, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.709, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0404244567963618, | |
| "grad_norm": 2.0727179050445557, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.23, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04850934815563416, | |
| "grad_norm": 1.5737111568450928, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.1274, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.05659423951490652, | |
| "grad_norm": 1.5571566820144653, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.0106, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06467913087417888, | |
| "grad_norm": 1.84938383102417, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.9096, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07276402223345124, | |
| "grad_norm": 0.7360393404960632, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.8576, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0808489135927236, | |
| "grad_norm": 0.7223778367042542, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.7962, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08893380495199596, | |
| "grad_norm": 0.6078234314918518, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.6922, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.09701869631126832, | |
| "grad_norm": 0.6479470729827881, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.5929, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.10510358767054068, | |
| "grad_norm": 0.4767465889453888, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.7316, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.11318847902981304, | |
| "grad_norm": 0.49146518111228943, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.6829, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.1212733703890854, | |
| "grad_norm": 0.49033933877944946, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.7022, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.12935826174835777, | |
| "grad_norm": 0.4863513112068176, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.826, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1374431531076301, | |
| "grad_norm": 0.4957202970981598, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.8124, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.14552804446690248, | |
| "grad_norm": 0.4850342571735382, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.77, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.15361293582617483, | |
| "grad_norm": 0.47507721185684204, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.7409, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.1616978271854472, | |
| "grad_norm": 0.4847748577594757, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.7319, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.16978271854471955, | |
| "grad_norm": 0.46571776270866394, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.7065, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.17786760990399192, | |
| "grad_norm": 0.46438243985176086, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.7466, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.18595250126326426, | |
| "grad_norm": 0.43673038482666016, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.6795, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.19403739262253664, | |
| "grad_norm": 0.40861475467681885, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.6411, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.20212228398180898, | |
| "grad_norm": 0.4549863040447235, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.6347, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.20212228398180898, | |
| "eval_loss": 0.6450268030166626, | |
| "eval_runtime": 3.4879, | |
| "eval_samples_per_second": 14.335, | |
| "eval_steps_per_second": 3.727, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.21020717534108135, | |
| "grad_norm": 0.5683823823928833, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.7581, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.21829206670035373, | |
| "grad_norm": 0.5637506246566772, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.7071, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.22637695805962607, | |
| "grad_norm": 0.44266441464424133, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.7379, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.23446184941889844, | |
| "grad_norm": 0.3773636519908905, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.7573, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.2425467407781708, | |
| "grad_norm": 0.3675413131713867, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.6714, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.25063163213744316, | |
| "grad_norm": 0.37877586483955383, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.7193, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.25871652349671553, | |
| "grad_norm": 0.41423583030700684, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.6975, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.26680141485598785, | |
| "grad_norm": 0.4509444832801819, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.7055, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.2748863062152602, | |
| "grad_norm": 0.4025251567363739, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.6764, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.2829711975745326, | |
| "grad_norm": 0.4443969428539276, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.6929, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.29105608893380497, | |
| "grad_norm": 0.4087773859500885, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.6093, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.2991409802930773, | |
| "grad_norm": 0.40454772114753723, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.6058, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.30722587165234966, | |
| "grad_norm": 0.34317758679389954, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.5982, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.31531076301162203, | |
| "grad_norm": 0.3430269658565521, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.6715, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.3233956543708944, | |
| "grad_norm": 0.3907616138458252, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.6747, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3314805457301668, | |
| "grad_norm": 0.35974612832069397, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.6912, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3395654370894391, | |
| "grad_norm": 0.47870934009552, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.7493, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.34765032844871147, | |
| "grad_norm": 0.4124900698661804, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.6813, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.35573521980798384, | |
| "grad_norm": 0.3971357047557831, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.7382, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.3638201111672562, | |
| "grad_norm": 0.4053785800933838, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.6815, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3719050025265285, | |
| "grad_norm": 0.42002072930336, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.6561, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.3799898938858009, | |
| "grad_norm": 0.4654466211795807, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.6316, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.3880747852450733, | |
| "grad_norm": 0.4234202802181244, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.6168, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.39615967660434565, | |
| "grad_norm": 0.49169376492500305, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.5986, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.40424456796361796, | |
| "grad_norm": 0.5422549843788147, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5929, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.40424456796361796, | |
| "eval_loss": 0.6268936991691589, | |
| "eval_runtime": 3.4738, | |
| "eval_samples_per_second": 14.393, | |
| "eval_steps_per_second": 3.742, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 5.968083617316864e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |