| { | |
| "best_metric": 1.0271567106246948, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.0028107652308340947, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.621530461668189e-05, | |
| "grad_norm": 1.0037671327590942, | |
| "learning_rate": 0.0001, | |
| "loss": 4.8903, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 5.621530461668189e-05, | |
| "eval_loss": 1.4244569540023804, | |
| "eval_runtime": 7759.2914, | |
| "eval_samples_per_second": 0.965, | |
| "eval_steps_per_second": 0.483, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00011243060923336378, | |
| "grad_norm": 0.9153568744659424, | |
| "learning_rate": 0.0002, | |
| "loss": 4.4247, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00016864591385004567, | |
| "grad_norm": 1.173575520515442, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 5.1528, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00022486121846672757, | |
| "grad_norm": 1.2566075325012207, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 4.5673, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00028107652308340944, | |
| "grad_norm": 1.372121810913086, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 4.9937, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00033729182770009133, | |
| "grad_norm": 1.0780651569366455, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 4.4226, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00039350713231677323, | |
| "grad_norm": 0.942474901676178, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 4.4456, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00044972243693345513, | |
| "grad_norm": 1.527437686920166, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 4.7015, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.000505937741550137, | |
| "grad_norm": 2.087895631790161, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 4.1849, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0005621530461668189, | |
| "grad_norm": 0.8344571590423584, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 3.8176, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0006183683507835008, | |
| "grad_norm": 0.8567643761634827, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 4.0602, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0006745836554001827, | |
| "grad_norm": 1.0290203094482422, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 3.8269, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0007307989600168646, | |
| "grad_norm": 1.0773515701293945, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 4.0728, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0007870142646335465, | |
| "grad_norm": 0.9667721390724182, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 3.9006, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0008432295692502284, | |
| "grad_norm": 1.1101466417312622, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 4.1819, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0008994448738669103, | |
| "grad_norm": 1.3487257957458496, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 4.6194, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0009556601784835922, | |
| "grad_norm": 1.091251015663147, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 4.0581, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.001011875483100274, | |
| "grad_norm": 1.0720723867416382, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 3.7407, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.001068090787716956, | |
| "grad_norm": 1.1119567155838013, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 4.1069, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0011243060923336377, | |
| "grad_norm": 1.2740784883499146, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 3.5911, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0011805213969503198, | |
| "grad_norm": 1.1338714361190796, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 3.7111, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0012367367015670015, | |
| "grad_norm": 1.1218507289886475, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 3.8789, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0012929520061836835, | |
| "grad_norm": 1.2838630676269531, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 3.9582, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0013491673108003653, | |
| "grad_norm": 1.4839881658554077, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 4.4876, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0014053826154170473, | |
| "grad_norm": 1.1227571964263916, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 4.0313, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0014053826154170473, | |
| "eval_loss": 1.0495991706848145, | |
| "eval_runtime": 7778.5368, | |
| "eval_samples_per_second": 0.963, | |
| "eval_steps_per_second": 0.481, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0014615979200337291, | |
| "grad_norm": 1.109177589416504, | |
| "learning_rate": 0.0001, | |
| "loss": 4.4231, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0015178132246504111, | |
| "grad_norm": 1.3502737283706665, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 4.1029, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.001574028529267093, | |
| "grad_norm": 1.2638400793075562, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 4.4384, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.001630243833883775, | |
| "grad_norm": 1.253785490989685, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 3.7949, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0016864591385004567, | |
| "grad_norm": 1.2122159004211426, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 4.5219, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0017426744431171387, | |
| "grad_norm": 1.1317585706710815, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 4.0376, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0017988897477338205, | |
| "grad_norm": 3.269996404647827, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 4.1345, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0018551050523505025, | |
| "grad_norm": 2.4214236736297607, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 3.9074, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0019113203569671843, | |
| "grad_norm": 1.186686635017395, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 3.9877, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.001967535661583866, | |
| "grad_norm": 1.3781710863113403, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 4.4423, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.002023750966200548, | |
| "grad_norm": 1.2803940773010254, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 4.1471, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.00207996627081723, | |
| "grad_norm": 1.5898265838623047, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 4.409, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.002136181575433912, | |
| "grad_norm": 1.3593076467514038, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 3.7433, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0021923968800505937, | |
| "grad_norm": 1.3938697576522827, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 4.0942, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0022486121846672755, | |
| "grad_norm": 1.291236162185669, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 4.0084, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0023048274892839577, | |
| "grad_norm": 1.3661845922470093, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 4.1608, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0023610427939006395, | |
| "grad_norm": 1.5577927827835083, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 4.073, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0024172580985173213, | |
| "grad_norm": 1.5352163314819336, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 4.3885, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.002473473403134003, | |
| "grad_norm": 1.6036438941955566, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 4.3737, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0025296887077506853, | |
| "grad_norm": 1.6673026084899902, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 4.0295, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.002585904012367367, | |
| "grad_norm": 1.7688616514205933, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 4.6062, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.002642119316984049, | |
| "grad_norm": 1.910326600074768, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 5.2657, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0026983346216007307, | |
| "grad_norm": 2.360198736190796, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 4.7428, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.002754549926217413, | |
| "grad_norm": 1.9681812524795532, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 4.1981, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0028107652308340947, | |
| "grad_norm": 3.8947713375091553, | |
| "learning_rate": 0.0, | |
| "loss": 5.1876, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0028107652308340947, | |
| "eval_loss": 1.0271567106246948, | |
| "eval_runtime": 7776.1879, | |
| "eval_samples_per_second": 0.963, | |
| "eval_steps_per_second": 0.482, | |
| "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": 1.361684987904e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |