| { | |
| "best_metric": 0.19170191884040833, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.21869874248223073, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004373974849644614, | |
| "grad_norm": 62.18521499633789, | |
| "learning_rate": 5e-05, | |
| "loss": 3.3747, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004373974849644614, | |
| "eval_loss": 3.6648952960968018, | |
| "eval_runtime": 114.0555, | |
| "eval_samples_per_second": 13.511, | |
| "eval_steps_per_second": 1.692, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008747949699289229, | |
| "grad_norm": 58.74281311035156, | |
| "learning_rate": 0.0001, | |
| "loss": 3.3611, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.013121924548933843, | |
| "grad_norm": 63.88774871826172, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 3.3568, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.017495899398578457, | |
| "grad_norm": 59.088706970214844, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.9885, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02186987424822307, | |
| "grad_norm": 49.485382080078125, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.2863, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.026243849097867686, | |
| "grad_norm": 35.785892486572266, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.8439, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0306178239475123, | |
| "grad_norm": 26.03848648071289, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.4486, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.034991798797156914, | |
| "grad_norm": 32.40800857543945, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.269, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03936577364680153, | |
| "grad_norm": 25.049684524536133, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.0448, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04373974849644614, | |
| "grad_norm": 21.390932083129883, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.9504, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04811372334609076, | |
| "grad_norm": 23.003036499023438, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.7769, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.05248769819573537, | |
| "grad_norm": 22.121341705322266, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.7093, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.056861673045379986, | |
| "grad_norm": 19.499107360839844, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.6384, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0612356478950246, | |
| "grad_norm": 17.174579620361328, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.5013, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.06560962274466922, | |
| "grad_norm": 21.63330078125, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.4385, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.06998359759431383, | |
| "grad_norm": 18.821762084960938, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.4091, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.07435757244395845, | |
| "grad_norm": 10.64421272277832, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.3555, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.07873154729360306, | |
| "grad_norm": 16.884422302246094, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.3377, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.08310552214324768, | |
| "grad_norm": 12.990285873413086, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.3202, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.08747949699289229, | |
| "grad_norm": 10.035831451416016, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.3148, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09185347184253691, | |
| "grad_norm": 8.899517059326172, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.2702, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.09622744669218151, | |
| "grad_norm": 10.785591125488281, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.2838, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.10060142154182614, | |
| "grad_norm": 10.352352142333984, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.2643, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.10497539639147074, | |
| "grad_norm": 9.038077354431152, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.2573, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.10934937124111536, | |
| "grad_norm": 10.318586349487305, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.2537, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.10934937124111536, | |
| "eval_loss": 0.23825594782829285, | |
| "eval_runtime": 114.0593, | |
| "eval_samples_per_second": 13.511, | |
| "eval_steps_per_second": 1.692, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11372334609075997, | |
| "grad_norm": 11.166613578796387, | |
| "learning_rate": 5e-05, | |
| "loss": 0.178, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.1180973209404046, | |
| "grad_norm": 10.714858055114746, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.2399, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1224712957900492, | |
| "grad_norm": 11.066264152526855, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.2025, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.1268452706396938, | |
| "grad_norm": 12.516129493713379, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.2187, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.13121924548933844, | |
| "grad_norm": 9.812530517578125, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.1807, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.13559322033898305, | |
| "grad_norm": 9.20337963104248, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.1832, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.13996719518862766, | |
| "grad_norm": 9.085219383239746, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.191, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1443411700382723, | |
| "grad_norm": 13.772695541381836, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.244, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1487151448879169, | |
| "grad_norm": 12.057571411132812, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.2197, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.1530891197375615, | |
| "grad_norm": 12.592830657958984, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.2383, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.15746309458720611, | |
| "grad_norm": 16.97599983215332, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.2584, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.16183706943685075, | |
| "grad_norm": 11.718450546264648, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.238, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.16621104428649536, | |
| "grad_norm": 11.560559272766113, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.21, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.17058501913613996, | |
| "grad_norm": 8.881017684936523, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.1504, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.17495899398578457, | |
| "grad_norm": 10.893447875976562, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.167, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1793329688354292, | |
| "grad_norm": 14.648825645446777, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.2115, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.18370694368507381, | |
| "grad_norm": 10.353060722351074, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.2011, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.18808091853471842, | |
| "grad_norm": 11.638842582702637, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.2043, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.19245489338436303, | |
| "grad_norm": 7.406494140625, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.1753, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.19682886823400766, | |
| "grad_norm": 7.78684663772583, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.1552, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.20120284308365227, | |
| "grad_norm": 7.1053595542907715, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.2005, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.20557681793329688, | |
| "grad_norm": 9.848479270935059, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.2091, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.2099507927829415, | |
| "grad_norm": 10.150044441223145, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.1856, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.21432476763258612, | |
| "grad_norm": 8.909294128417969, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.2062, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.21869874248223073, | |
| "grad_norm": 9.131242752075195, | |
| "learning_rate": 0.0, | |
| "loss": 0.2145, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.21869874248223073, | |
| "eval_loss": 0.19170191884040833, | |
| "eval_runtime": 114.0536, | |
| "eval_samples_per_second": 13.511, | |
| "eval_steps_per_second": 1.692, | |
| "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": 2.968064857808568e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |