| { | |
| "best_metric": 6.717546463012695, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.1951219512195122, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003902439024390244, | |
| "grad_norm": 1.0753778219223022, | |
| "learning_rate": 0.0001, | |
| "loss": 6.8598, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003902439024390244, | |
| "eval_loss": 6.874822616577148, | |
| "eval_runtime": 0.3539, | |
| "eval_samples_per_second": 305.19, | |
| "eval_steps_per_second": 152.595, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007804878048780488, | |
| "grad_norm": 1.0130054950714111, | |
| "learning_rate": 0.0002, | |
| "loss": 6.8847, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.011707317073170732, | |
| "grad_norm": 0.9435489773750305, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 6.8877, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.015609756097560976, | |
| "grad_norm": 1.0122114419937134, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 6.8591, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01951219512195122, | |
| "grad_norm": 1.1082350015640259, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 6.852, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.023414634146341463, | |
| "grad_norm": 1.0150554180145264, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 6.8492, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.027317073170731707, | |
| "grad_norm": 1.0667434930801392, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 6.8208, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03121951219512195, | |
| "grad_norm": 1.1213891506195068, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 6.8285, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0351219512195122, | |
| "grad_norm": 0.9607540965080261, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 6.8272, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03902439024390244, | |
| "grad_norm": 0.8629202246665955, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 6.8256, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.042926829268292686, | |
| "grad_norm": 0.9799481630325317, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 6.8136, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04682926829268293, | |
| "grad_norm": 0.9151404500007629, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 6.8049, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.050731707317073174, | |
| "grad_norm": 0.9145707488059998, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 6.8344, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.054634146341463415, | |
| "grad_norm": 0.8406278491020203, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 6.7926, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.05853658536585366, | |
| "grad_norm": 0.7802610397338867, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 6.7981, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0624390243902439, | |
| "grad_norm": 0.7458345293998718, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 6.7865, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.06634146341463415, | |
| "grad_norm": 0.8287109136581421, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 6.753, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0702439024390244, | |
| "grad_norm": 0.7422548532485962, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 6.7736, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.07414634146341463, | |
| "grad_norm": 0.7774643301963806, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 6.7444, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.07804878048780488, | |
| "grad_norm": 0.7221447825431824, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 6.7524, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08195121951219513, | |
| "grad_norm": 0.7915313243865967, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 6.7579, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.08585365853658537, | |
| "grad_norm": 0.8400879502296448, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 6.7394, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0897560975609756, | |
| "grad_norm": 0.8928730487823486, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 6.7376, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.09365853658536585, | |
| "grad_norm": 0.7348310351371765, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 6.7359, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0975609756097561, | |
| "grad_norm": 0.8059408664703369, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 6.7461, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0975609756097561, | |
| "eval_loss": 6.743670463562012, | |
| "eval_runtime": 0.3602, | |
| "eval_samples_per_second": 299.83, | |
| "eval_steps_per_second": 149.915, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.10146341463414635, | |
| "grad_norm": 0.7409495711326599, | |
| "learning_rate": 0.0001, | |
| "loss": 6.7454, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.10536585365853658, | |
| "grad_norm": 0.7578893899917603, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 6.7515, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.10926829268292683, | |
| "grad_norm": 0.7759184837341309, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 6.7554, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.11317073170731708, | |
| "grad_norm": 0.7387394309043884, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 6.7204, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.11707317073170732, | |
| "grad_norm": 0.705632746219635, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 6.7335, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.12097560975609756, | |
| "grad_norm": 0.6851465106010437, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 6.7493, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.1248780487804878, | |
| "grad_norm": 0.740122377872467, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 6.701, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.12878048780487805, | |
| "grad_norm": 0.638899564743042, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 6.7514, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1326829268292683, | |
| "grad_norm": 0.7418556809425354, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 6.7595, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.13658536585365855, | |
| "grad_norm": 0.6872796416282654, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 6.75, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.1404878048780488, | |
| "grad_norm": 0.6563825011253357, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 6.7437, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.144390243902439, | |
| "grad_norm": 0.7908744215965271, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 6.7463, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.14829268292682926, | |
| "grad_norm": 0.6440786123275757, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 6.7321, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.1521951219512195, | |
| "grad_norm": 0.731747031211853, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 6.7546, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.15609756097560976, | |
| "grad_norm": 0.6230834126472473, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 6.7368, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.7506718635559082, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 6.7426, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.16390243902439025, | |
| "grad_norm": 0.7346739768981934, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 6.7446, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1678048780487805, | |
| "grad_norm": 0.6999073624610901, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 6.7347, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.17170731707317075, | |
| "grad_norm": 0.6503731608390808, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 6.7496, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.17560975609756097, | |
| "grad_norm": 0.6913208365440369, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 6.7058, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1795121951219512, | |
| "grad_norm": 0.7521505355834961, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 6.7188, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.18341463414634146, | |
| "grad_norm": 0.8142408132553101, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 6.7163, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.1873170731707317, | |
| "grad_norm": 0.6648187637329102, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 6.7262, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.19121951219512195, | |
| "grad_norm": 0.8425360321998596, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 6.7683, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.1951219512195122, | |
| "grad_norm": 0.710664689540863, | |
| "learning_rate": 0.0, | |
| "loss": 6.7291, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1951219512195122, | |
| "eval_loss": 6.717546463012695, | |
| "eval_runtime": 0.3537, | |
| "eval_samples_per_second": 305.34, | |
| "eval_steps_per_second": 152.67, | |
| "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": 589302988800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |