| { | |
| "best_metric": 0.06989976763725281, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.3410214168039538, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.026359143327841845, | |
| "grad_norm": 3.2261435985565186, | |
| "learning_rate": 5e-05, | |
| "loss": 2.8904, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.026359143327841845, | |
| "eval_loss": 4.496891498565674, | |
| "eval_runtime": 2.6493, | |
| "eval_samples_per_second": 18.873, | |
| "eval_steps_per_second": 4.907, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05271828665568369, | |
| "grad_norm": 3.7886242866516113, | |
| "learning_rate": 0.0001, | |
| "loss": 3.2601, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.07907742998352553, | |
| "grad_norm": 4.198616027832031, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 3.3531, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.10543657331136738, | |
| "grad_norm": 4.185900688171387, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.7364, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.13179571663920922, | |
| "grad_norm": 3.605696439743042, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.3579, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.15815485996705106, | |
| "grad_norm": 3.8062736988067627, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.147, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.18451400329489293, | |
| "grad_norm": 4.500556945800781, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 2.0153, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.21087314662273476, | |
| "grad_norm": 4.745126724243164, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.7782, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.2372322899505766, | |
| "grad_norm": 5.740296363830566, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.9259, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.26359143327841844, | |
| "grad_norm": 7.462158203125, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.8581, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2899505766062603, | |
| "grad_norm": 4.397566318511963, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.0152, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.3163097199341021, | |
| "grad_norm": 2.9855945110321045, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.7193, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.342668863261944, | |
| "grad_norm": 2.0212604999542236, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.6057, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.36902800658978585, | |
| "grad_norm": 1.7968220710754395, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.538, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3953871499176277, | |
| "grad_norm": 1.760416865348816, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.7498, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.42174629324546953, | |
| "grad_norm": 1.9944193363189697, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.7176, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.44810543657331137, | |
| "grad_norm": 1.9517091512680054, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.7564, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.4744645799011532, | |
| "grad_norm": 2.649627685546875, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.7469, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.500823723228995, | |
| "grad_norm": 3.311579704284668, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.7729, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.5271828665568369, | |
| "grad_norm": 1.6942845582962036, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.3132, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5535420098846787, | |
| "grad_norm": 1.6794170141220093, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.2377, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.5799011532125206, | |
| "grad_norm": 1.4418450593948364, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.2117, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.6062602965403624, | |
| "grad_norm": 1.11506986618042, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.2163, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.6326194398682042, | |
| "grad_norm": 1.2152330875396729, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.211, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.6589785831960461, | |
| "grad_norm": 1.5132273435592651, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.2629, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6589785831960461, | |
| "eval_loss": 0.22433076798915863, | |
| "eval_runtime": 2.0455, | |
| "eval_samples_per_second": 24.444, | |
| "eval_steps_per_second": 6.355, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.685337726523888, | |
| "grad_norm": 1.986502766609192, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.2799, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.7116968698517299, | |
| "grad_norm": 1.9361213445663452, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.3052, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.7380560131795717, | |
| "grad_norm": 3.370849370956421, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.4228, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.7644151565074135, | |
| "grad_norm": 3.750485420227051, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.2901, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.7907742998352554, | |
| "grad_norm": 2.9256770610809326, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.1042, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.8171334431630972, | |
| "grad_norm": 2.44817852973938, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.1124, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.8434925864909391, | |
| "grad_norm": 1.4348925352096558, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.1066, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.8698517298187809, | |
| "grad_norm": 1.0853517055511475, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.0853, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.8962108731466227, | |
| "grad_norm": 2.7698771953582764, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.127, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.9225700164744646, | |
| "grad_norm": 2.3615007400512695, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.2138, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.9489291598023064, | |
| "grad_norm": 2.252959966659546, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.2065, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.9752883031301482, | |
| "grad_norm": 4.12150239944458, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.2188, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.0247116968698518, | |
| "grad_norm": 5.144357681274414, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.3064, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.0510708401976936, | |
| "grad_norm": 0.48973578214645386, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.0159, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.0774299835255354, | |
| "grad_norm": 0.3477337658405304, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.0171, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.1037891268533773, | |
| "grad_norm": 0.7385883927345276, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.0308, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.130148270181219, | |
| "grad_norm": 0.7831564545631409, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.0379, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.156507413509061, | |
| "grad_norm": 0.731144368648529, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.0718, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.1828665568369028, | |
| "grad_norm": 1.3186781406402588, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.0928, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.2092257001647446, | |
| "grad_norm": 1.7480039596557617, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.1888, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.2355848434925865, | |
| "grad_norm": 1.843854546546936, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.1448, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.2619439868204283, | |
| "grad_norm": 0.9175070524215698, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.0842, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.2883031301482701, | |
| "grad_norm": 0.22026900947093964, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.0107, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.314662273476112, | |
| "grad_norm": 0.20567184686660767, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.0084, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.3410214168039538, | |
| "grad_norm": 0.2838402986526489, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0205, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.3410214168039538, | |
| "eval_loss": 0.06989976763725281, | |
| "eval_runtime": 2.0408, | |
| "eval_samples_per_second": 24.501, | |
| "eval_steps_per_second": 6.37, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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 | |
| } | |