| { | |
| "best_metric": 1.6380741596221924, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.0020764981934465717, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.1529963868931435e-05, | |
| "grad_norm": 0.9986630082130432, | |
| "learning_rate": 0.0001, | |
| "loss": 1.6028, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.1529963868931435e-05, | |
| "eval_loss": 2.0671894550323486, | |
| "eval_runtime": 2877.7983, | |
| "eval_samples_per_second": 3.523, | |
| "eval_steps_per_second": 1.762, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.305992773786287e-05, | |
| "grad_norm": 1.202799916267395, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8974, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0001245898916067943, | |
| "grad_norm": 0.9093121886253357, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 1.2838, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00016611985547572574, | |
| "grad_norm": 1.2698150873184204, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 1.7091, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00020764981934465716, | |
| "grad_norm": 0.9846441149711609, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 1.4853, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0002491797832135886, | |
| "grad_norm": 1.0469404458999634, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 1.3653, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00029070974708252003, | |
| "grad_norm": 1.0189703702926636, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 1.2868, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0003322397109514515, | |
| "grad_norm": 0.8890460133552551, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 1.2044, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00037376967482038293, | |
| "grad_norm": 0.8418606519699097, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 1.4194, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0004152996386893143, | |
| "grad_norm": 0.9206029772758484, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 1.4633, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00045682960255824577, | |
| "grad_norm": 0.9704146981239319, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 1.4132, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0004983595664271772, | |
| "grad_norm": 1.2635133266448975, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 1.6172, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0005398895302961087, | |
| "grad_norm": 0.8380823135375977, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 1.2886, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0005814194941650401, | |
| "grad_norm": 1.2381993532180786, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.8191, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0006229494580339715, | |
| "grad_norm": 0.8839138150215149, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 1.6391, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.000664479421902903, | |
| "grad_norm": 0.8810262084007263, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 1.4926, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0007060093857718344, | |
| "grad_norm": 1.0955041646957397, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 1.4371, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0007475393496407659, | |
| "grad_norm": 1.037914514541626, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.455, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0007890693135096973, | |
| "grad_norm": 1.3941214084625244, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 1.4295, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0008305992773786286, | |
| "grad_norm": 0.9463165402412415, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 1.4374, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0008721292412475601, | |
| "grad_norm": 1.1351900100708008, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 1.4526, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0009136592051164915, | |
| "grad_norm": 1.1594353914260864, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 1.8897, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0009551891689854229, | |
| "grad_norm": 1.3010016679763794, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 1.6954, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0009967191328543543, | |
| "grad_norm": 1.2132692337036133, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 1.5817, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0010382490967232858, | |
| "grad_norm": 1.2086621522903442, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 1.8013, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0010382490967232858, | |
| "eval_loss": 1.6744242906570435, | |
| "eval_runtime": 2888.5531, | |
| "eval_samples_per_second": 3.51, | |
| "eval_steps_per_second": 1.755, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0010797790605922173, | |
| "grad_norm": 1.1037122011184692, | |
| "learning_rate": 0.0001, | |
| "loss": 1.8685, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0011213090244611486, | |
| "grad_norm": 1.222785472869873, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 1.675, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0011628389883300801, | |
| "grad_norm": 1.1607424020767212, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 1.846, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0012043689521990116, | |
| "grad_norm": 1.2256293296813965, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 1.9248, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.001245898916067943, | |
| "grad_norm": 1.4635818004608154, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 1.6617, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0012874288799368744, | |
| "grad_norm": 1.4820843935012817, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 1.6852, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.001328958843805806, | |
| "grad_norm": 1.3600713014602661, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 1.654, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0013704888076747374, | |
| "grad_norm": 1.2553255558013916, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 1.5762, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0014120187715436687, | |
| "grad_norm": 1.3980979919433594, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.7855, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0014535487354126002, | |
| "grad_norm": 1.4510493278503418, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 1.8295, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0014950786992815317, | |
| "grad_norm": 1.461298942565918, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 1.8186, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.001536608663150463, | |
| "grad_norm": 1.4678010940551758, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 1.47, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0015781386270193945, | |
| "grad_norm": 1.473757266998291, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 1.8708, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.001619668590888326, | |
| "grad_norm": 1.4809536933898926, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 1.8925, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0016611985547572573, | |
| "grad_norm": 1.5196596384048462, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 2.0163, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0017027285186261888, | |
| "grad_norm": 1.8574073314666748, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 2.1846, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0017442584824951203, | |
| "grad_norm": 1.62294602394104, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 1.7325, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0017857884463640516, | |
| "grad_norm": 1.677263617515564, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 2.0305, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.001827318410232983, | |
| "grad_norm": 1.917270541191101, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 1.8953, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0018688483741019146, | |
| "grad_norm": 2.308164358139038, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 1.7661, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0019103783379708459, | |
| "grad_norm": 2.1109867095947266, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 2.2393, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0019519083018397774, | |
| "grad_norm": 2.27052640914917, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 1.7348, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0019934382657087087, | |
| "grad_norm": 2.7785375118255615, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 1.8744, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.00203496822957764, | |
| "grad_norm": 3.298647165298462, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 2.0428, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0020764981934465717, | |
| "grad_norm": 5.072795391082764, | |
| "learning_rate": 0.0, | |
| "loss": 2.6198, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0020764981934465717, | |
| "eval_loss": 1.6380741596221924, | |
| "eval_runtime": 2888.5077, | |
| "eval_samples_per_second": 3.51, | |
| "eval_steps_per_second": 1.755, | |
| "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": 7.456096693046477e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |