| { | |
| "best_metric": 1.2021186351776123, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 3.0372881355932204, | |
| "eval_steps": 25, | |
| "global_step": 70, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04338983050847458, | |
| "grad_norm": 0.19333525002002716, | |
| "learning_rate": 0.0001, | |
| "loss": 1.4844, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04338983050847458, | |
| "eval_loss": 1.57308030128479, | |
| "eval_runtime": 1.681, | |
| "eval_samples_per_second": 29.744, | |
| "eval_steps_per_second": 7.733, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.08677966101694916, | |
| "grad_norm": 0.22077158093452454, | |
| "learning_rate": 0.0002, | |
| "loss": 1.5603, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.13016949152542373, | |
| "grad_norm": 0.258558452129364, | |
| "learning_rate": 0.00019990396773221354, | |
| "loss": 1.4966, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.17355932203389832, | |
| "grad_norm": 0.2679038345813751, | |
| "learning_rate": 0.00019961607586655312, | |
| "loss": 1.4893, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.21694915254237288, | |
| "grad_norm": 0.2787069082260132, | |
| "learning_rate": 0.00019913693877876847, | |
| "loss": 1.5337, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.26033898305084746, | |
| "grad_norm": 0.21714474260807037, | |
| "learning_rate": 0.00019846757897155117, | |
| "loss": 1.4605, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.303728813559322, | |
| "grad_norm": 0.2101472020149231, | |
| "learning_rate": 0.00019760942489246237, | |
| "loss": 1.4191, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.34711864406779663, | |
| "grad_norm": 0.2357436865568161, | |
| "learning_rate": 0.00019656430788555373, | |
| "loss": 1.3739, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3905084745762712, | |
| "grad_norm": 0.22543178498744965, | |
| "learning_rate": 0.00019533445828318692, | |
| "loss": 1.3078, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.43389830508474575, | |
| "grad_norm": 0.2066933512687683, | |
| "learning_rate": 0.000193922500646392, | |
| "loss": 1.3297, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.47728813559322036, | |
| "grad_norm": 0.2858045995235443, | |
| "learning_rate": 0.0001923314481639219, | |
| "loss": 1.4037, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.5206779661016949, | |
| "grad_norm": 0.3108825385570526, | |
| "learning_rate": 0.00019056469622195563, | |
| "loss": 1.3338, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5640677966101695, | |
| "grad_norm": 0.2868238091468811, | |
| "learning_rate": 0.00018862601515817325, | |
| "loss": 1.3208, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.607457627118644, | |
| "grad_norm": 0.1842653751373291, | |
| "learning_rate": 0.00018651954221566528, | |
| "loss": 1.2517, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.6508474576271186, | |
| "grad_norm": 0.23613254725933075, | |
| "learning_rate": 0.0001842497727138472, | |
| "loss": 1.2301, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6942372881355933, | |
| "grad_norm": 0.27285611629486084, | |
| "learning_rate": 0.00018182155045522159, | |
| "loss": 1.2618, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.7376271186440678, | |
| "grad_norm": 0.28099900484085083, | |
| "learning_rate": 0.00017924005738845914, | |
| "loss": 1.3992, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.7810169491525424, | |
| "grad_norm": 0.20399919152259827, | |
| "learning_rate": 0.00017651080254985933, | |
| "loss": 1.3072, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.8244067796610169, | |
| "grad_norm": 0.21079455316066742, | |
| "learning_rate": 0.00017363961030678927, | |
| "loss": 1.3045, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.8677966101694915, | |
| "grad_norm": 0.19453535974025726, | |
| "learning_rate": 0.00017063260792819014, | |
| "loss": 1.194, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.9111864406779661, | |
| "grad_norm": 0.15201877057552338, | |
| "learning_rate": 0.0001674962125086765, | |
| "loss": 1.214, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.9545762711864407, | |
| "grad_norm": 0.13938187062740326, | |
| "learning_rate": 0.00016423711727413308, | |
| "loss": 1.2856, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.9979661016949153, | |
| "grad_norm": 0.2446557730436325, | |
| "learning_rate": 0.00016086227729803328, | |
| "loss": 1.427, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.0413559322033898, | |
| "grad_norm": 0.4381452202796936, | |
| "learning_rate": 0.00015737889465896202, | |
| "loss": 2.4556, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.0847457627118644, | |
| "grad_norm": 0.13573524355888367, | |
| "learning_rate": 0.00015379440307101706, | |
| "loss": 1.2265, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0847457627118644, | |
| "eval_loss": 1.2588658332824707, | |
| "eval_runtime": 1.6779, | |
| "eval_samples_per_second": 29.799, | |
| "eval_steps_per_second": 7.748, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.128135593220339, | |
| "grad_norm": 0.14407069981098175, | |
| "learning_rate": 0.00015011645201988848, | |
| "loss": 1.1929, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.1715254237288135, | |
| "grad_norm": 0.15989331901073456, | |
| "learning_rate": 0.00014635289043847053, | |
| "loss": 1.1703, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.214915254237288, | |
| "grad_norm": 0.16030077636241913, | |
| "learning_rate": 0.0001425117499568438, | |
| "loss": 1.2557, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.2583050847457626, | |
| "grad_norm": 0.18936704099178314, | |
| "learning_rate": 0.00013860122776237113, | |
| "loss": 1.2149, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.3016949152542372, | |
| "grad_norm": 0.24135200679302216, | |
| "learning_rate": 0.0001346296691064875, | |
| "loss": 1.3461, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.345084745762712, | |
| "grad_norm": 0.17525914311408997, | |
| "learning_rate": 0.00013060554949551208, | |
| "loss": 1.1852, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.3884745762711863, | |
| "grad_norm": 0.13595549762248993, | |
| "learning_rate": 0.00012653745660349134, | |
| "loss": 1.1576, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.431864406779661, | |
| "grad_norm": 0.18319641053676605, | |
| "learning_rate": 0.0001224340719456694, | |
| "loss": 1.1778, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.4752542372881357, | |
| "grad_norm": 0.21508461236953735, | |
| "learning_rate": 0.00011830415235169719, | |
| "loss": 1.3049, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.5186440677966102, | |
| "grad_norm": 0.18303513526916504, | |
| "learning_rate": 0.00011415651127811657, | |
| "loss": 1.1947, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.5620338983050848, | |
| "grad_norm": 0.17415650188922882, | |
| "learning_rate": 0.00011000000000000002, | |
| "loss": 1.2696, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.6054237288135593, | |
| "grad_norm": 0.16625842452049255, | |
| "learning_rate": 0.00010584348872188346, | |
| "loss": 1.1646, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.6488135593220339, | |
| "grad_norm": 0.17237333953380585, | |
| "learning_rate": 0.00010169584764830285, | |
| "loss": 1.1039, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.6922033898305084, | |
| "grad_norm": 0.17974147200584412, | |
| "learning_rate": 9.756592805433063e-05, | |
| "loss": 1.1694, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.735593220338983, | |
| "grad_norm": 0.23319189250469208, | |
| "learning_rate": 9.346254339650866e-05, | |
| "loss": 1.3278, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.7789830508474576, | |
| "grad_norm": 0.219391867518425, | |
| "learning_rate": 8.939445050448795e-05, | |
| "loss": 1.2026, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.8223728813559323, | |
| "grad_norm": 0.23197093605995178, | |
| "learning_rate": 8.537033089351256e-05, | |
| "loss": 1.2161, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.8657627118644067, | |
| "grad_norm": 0.16063331067562103, | |
| "learning_rate": 8.139877223762886e-05, | |
| "loss": 1.1265, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.9091525423728815, | |
| "grad_norm": 0.1530478149652481, | |
| "learning_rate": 7.748825004315625e-05, | |
| "loss": 1.1452, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.9525423728813558, | |
| "grad_norm": 0.19677256047725677, | |
| "learning_rate": 7.364710956152947e-05, | |
| "loss": 1.2146, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.9959322033898306, | |
| "grad_norm": 0.26235055923461914, | |
| "learning_rate": 6.988354798011156e-05, | |
| "loss": 1.3677, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.039322033898305, | |
| "grad_norm": 0.5380977988243103, | |
| "learning_rate": 6.620559692898295e-05, | |
| "loss": 2.2549, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.0827118644067797, | |
| "grad_norm": 0.14503780007362366, | |
| "learning_rate": 6.262110534103797e-05, | |
| "loss": 1.1591, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.1261016949152545, | |
| "grad_norm": 0.13808022439479828, | |
| "learning_rate": 5.913772270196674e-05, | |
| "loss": 1.1382, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.169491525423729, | |
| "grad_norm": 0.1822243332862854, | |
| "learning_rate": 5.5762882725866936e-05, | |
| "loss": 1.1082, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.169491525423729, | |
| "eval_loss": 1.2021186351776123, | |
| "eval_runtime": 1.679, | |
| "eval_samples_per_second": 29.779, | |
| "eval_steps_per_second": 7.743, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.2128813559322036, | |
| "grad_norm": 0.208404541015625, | |
| "learning_rate": 5.250378749132351e-05, | |
| "loss": 1.235, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.256271186440678, | |
| "grad_norm": 0.17768944799900055, | |
| "learning_rate": 4.9367392071809857e-05, | |
| "loss": 1.1382, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.2996610169491527, | |
| "grad_norm": 0.2600400447845459, | |
| "learning_rate": 4.6360389693210735e-05, | |
| "loss": 1.3375, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.343050847457627, | |
| "grad_norm": 0.17488409578800201, | |
| "learning_rate": 4.348919745014069e-05, | |
| "loss": 1.1467, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.386440677966102, | |
| "grad_norm": 0.1583094447851181, | |
| "learning_rate": 4.07599426115409e-05, | |
| "loss": 1.0945, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.429830508474576, | |
| "grad_norm": 0.18399091064929962, | |
| "learning_rate": 3.817844954477845e-05, | |
| "loss": 1.1229, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.473220338983051, | |
| "grad_norm": 0.21471183001995087, | |
| "learning_rate": 3.5750227286152804e-05, | |
| "loss": 1.2722, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.5166101694915253, | |
| "grad_norm": 0.17655105888843536, | |
| "learning_rate": 3.348045778433474e-05, | |
| "loss": 1.1581, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "grad_norm": 0.1815287321805954, | |
| "learning_rate": 3.137398484182675e-05, | |
| "loss": 1.2125, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.6033898305084744, | |
| "grad_norm": 0.14957380294799805, | |
| "learning_rate": 2.9435303778044405e-05, | |
| "loss": 1.1048, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.646779661016949, | |
| "grad_norm": 0.16781945526599884, | |
| "learning_rate": 2.766855183607811e-05, | |
| "loss": 1.0719, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.690169491525424, | |
| "grad_norm": 0.20620030164718628, | |
| "learning_rate": 2.6077499353607988e-05, | |
| "loss": 1.1494, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.7335593220338983, | |
| "grad_norm": 0.2556055784225464, | |
| "learning_rate": 2.4665541716813075e-05, | |
| "loss": 1.2749, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.7769491525423726, | |
| "grad_norm": 0.21309202909469604, | |
| "learning_rate": 2.343569211444629e-05, | |
| "loss": 1.1472, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.8203389830508474, | |
| "grad_norm": 0.18439190089702606, | |
| "learning_rate": 2.2390575107537647e-05, | |
| "loss": 1.2353, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.863728813559322, | |
| "grad_norm": 0.1528278887271881, | |
| "learning_rate": 2.153242102844884e-05, | |
| "loss": 1.118, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.9071186440677965, | |
| "grad_norm": 0.14112654328346252, | |
| "learning_rate": 2.0863061221231545e-05, | |
| "loss": 1.1025, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.9505084745762713, | |
| "grad_norm": 0.17627808451652527, | |
| "learning_rate": 2.03839241334469e-05, | |
| "loss": 1.142, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.9938983050847456, | |
| "grad_norm": 0.2500801682472229, | |
| "learning_rate": 2.0096032267786484e-05, | |
| "loss": 1.3468, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 3.0372881355932204, | |
| "grad_norm": 0.5967485308647156, | |
| "learning_rate": 2e-05, | |
| "loss": 2.3796, | |
| "step": 70 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 70, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 60, | |
| "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": 1.2467356978642944e+18, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |