| { | |
| "best_metric": 0.6269358396530151, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.01925900960543104, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00038518019210862084, | |
| "grad_norm": 0.44770216941833496, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6071, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00038518019210862084, | |
| "eval_loss": 0.9548915028572083, | |
| "eval_runtime": 219.8705, | |
| "eval_samples_per_second": 79.547, | |
| "eval_steps_per_second": 9.947, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007703603842172417, | |
| "grad_norm": 0.5682094097137451, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6854, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0011555405763258625, | |
| "grad_norm": 0.5557950139045715, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.7279, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0015407207684344833, | |
| "grad_norm": 0.4635084271430969, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.7289, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0019259009605431042, | |
| "grad_norm": 0.4467443823814392, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.7582, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002311081152651725, | |
| "grad_norm": 0.5062403678894043, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.7018, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002696261344760346, | |
| "grad_norm": 0.5500010848045349, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.7409, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0030814415368689667, | |
| "grad_norm": 0.2866744101047516, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.7095, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0034666217289775875, | |
| "grad_norm": 0.3707396686077118, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.6949, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0038518019210862084, | |
| "grad_norm": 0.3686576783657074, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.7288, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004236982113194829, | |
| "grad_norm": 0.316371351480484, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.7156, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00462216230530345, | |
| "grad_norm": 0.2654811143875122, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.6706, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00500734249741207, | |
| "grad_norm": 0.15250834822654724, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.5479, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.005392522689520692, | |
| "grad_norm": 0.13013990223407745, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.5675, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.005777702881629312, | |
| "grad_norm": 0.13996998965740204, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.6059, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006162883073737933, | |
| "grad_norm": 0.14754410088062286, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.6048, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.006548063265846554, | |
| "grad_norm": 0.14224006235599518, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.6735, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.006933243457955175, | |
| "grad_norm": 0.14491607248783112, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.6682, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0073184236500637954, | |
| "grad_norm": 0.1512575000524521, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.6293, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.007703603842172417, | |
| "grad_norm": 0.1506996601819992, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.7009, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.008088784034281036, | |
| "grad_norm": 0.16476863622665405, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.6853, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.008473964226389658, | |
| "grad_norm": 0.18840517103672028, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.7323, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.008859144418498279, | |
| "grad_norm": 0.19789254665374756, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.7102, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0092443246106069, | |
| "grad_norm": 0.20008715987205505, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.6355, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00962950480271552, | |
| "grad_norm": 0.2522077262401581, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.5746, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00962950480271552, | |
| "eval_loss": 0.6335539221763611, | |
| "eval_runtime": 219.4912, | |
| "eval_samples_per_second": 79.684, | |
| "eval_steps_per_second": 9.964, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01001468499482414, | |
| "grad_norm": 0.10044869780540466, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5081, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.010399865186932762, | |
| "grad_norm": 0.10237814486026764, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.5458, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.010785045379041383, | |
| "grad_norm": 0.10642737150192261, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.5832, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.011170225571150003, | |
| "grad_norm": 0.11753972619771957, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.581, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.011555405763258624, | |
| "grad_norm": 0.1386200189590454, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.6931, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.011940585955367245, | |
| "grad_norm": 0.1426922082901001, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.6748, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.012325766147475867, | |
| "grad_norm": 0.1488451063632965, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.679, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.012710946339584486, | |
| "grad_norm": 0.15228937566280365, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.6274, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.013096126531693108, | |
| "grad_norm": 0.17436490952968597, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.6178, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.013481306723801729, | |
| "grad_norm": 0.181550994515419, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.6855, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01386648691591035, | |
| "grad_norm": 0.17439498007297516, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.6966, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.01425166710801897, | |
| "grad_norm": 0.1905146837234497, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.5829, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.014636847300127591, | |
| "grad_norm": 0.14072227478027344, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.5333, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.015022027492236212, | |
| "grad_norm": 0.09869525581598282, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.5524, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.015407207684344833, | |
| "grad_norm": 0.11174383759498596, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.588, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.015792387876453453, | |
| "grad_norm": 0.11161665618419647, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.605, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.016177568068562072, | |
| "grad_norm": 0.12438953667879105, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.6402, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.016562748260670695, | |
| "grad_norm": 0.13606998324394226, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.6113, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.016947928452779315, | |
| "grad_norm": 0.14335651695728302, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.6423, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.017333108644887938, | |
| "grad_norm": 0.1410508006811142, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.6304, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.017718288836996558, | |
| "grad_norm": 0.15272414684295654, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.6464, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.018103469029105177, | |
| "grad_norm": 0.17061223089694977, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.7002, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0184886492212138, | |
| "grad_norm": 0.18988090753555298, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.6744, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.01887382941332242, | |
| "grad_norm": 0.1816452443599701, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.6374, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.01925900960543104, | |
| "grad_norm": 0.23609229922294617, | |
| "learning_rate": 0.0, | |
| "loss": 0.6045, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01925900960543104, | |
| "eval_loss": 0.6269358396530151, | |
| "eval_runtime": 220.0212, | |
| "eval_samples_per_second": 79.492, | |
| "eval_steps_per_second": 9.94, | |
| "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": 1.101255600588718e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |