| { | |
| "best_metric": 2.0980021953582764, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.1512001512001512, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003024003024003024, | |
| "grad_norm": 0.08016479760408401, | |
| "learning_rate": 5e-05, | |
| "loss": 2.0956, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003024003024003024, | |
| "eval_loss": 2.1319236755371094, | |
| "eval_runtime": 106.5969, | |
| "eval_samples_per_second": 20.901, | |
| "eval_steps_per_second": 2.617, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006048006048006048, | |
| "grad_norm": 0.08361414074897766, | |
| "learning_rate": 0.0001, | |
| "loss": 2.1484, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.009072009072009071, | |
| "grad_norm": 0.07862434536218643, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.1698, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.012096012096012096, | |
| "grad_norm": 0.06358031928539276, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.1116, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01512001512001512, | |
| "grad_norm": 0.0700426697731018, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.0814, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.018144018144018143, | |
| "grad_norm": 0.07426423579454422, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.1462, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02116802116802117, | |
| "grad_norm": 0.06563010066747665, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.1135, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02419202419202419, | |
| "grad_norm": 0.06191810220479965, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.133, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.027216027216027217, | |
| "grad_norm": 0.05998856574296951, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.1765, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03024003024003024, | |
| "grad_norm": 0.06669733673334122, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.0953, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.033264033264033266, | |
| "grad_norm": 0.075091153383255, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.1187, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.036288036288036285, | |
| "grad_norm": 0.08541350811719894, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.1314, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03931203931203931, | |
| "grad_norm": 0.07246515899896622, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.0678, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04233604233604234, | |
| "grad_norm": 0.06962122023105621, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.0952, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04536004536004536, | |
| "grad_norm": 0.06301100552082062, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.1056, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04838404838404838, | |
| "grad_norm": 0.05902456119656563, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.1305, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05140805140805141, | |
| "grad_norm": 0.05771924927830696, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 2.1125, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.054432054432054434, | |
| "grad_norm": 0.05714090168476105, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.1277, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.057456057456057454, | |
| "grad_norm": 0.0576050840318203, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.0646, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06048006048006048, | |
| "grad_norm": 0.0556524321436882, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.1006, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0635040635040635, | |
| "grad_norm": 0.058506425470113754, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 2.1427, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.06652806652806653, | |
| "grad_norm": 0.064882293343544, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 2.1311, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.06955206955206955, | |
| "grad_norm": 0.0697692483663559, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 2.1386, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.07257607257607257, | |
| "grad_norm": 0.08023648709058762, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 2.0693, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0756000756000756, | |
| "grad_norm": 0.10361019521951675, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.995, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0756000756000756, | |
| "eval_loss": 2.1019418239593506, | |
| "eval_runtime": 106.5617, | |
| "eval_samples_per_second": 20.908, | |
| "eval_steps_per_second": 2.618, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07862407862407862, | |
| "grad_norm": 0.05332132428884506, | |
| "learning_rate": 5e-05, | |
| "loss": 2.0911, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.08164808164808164, | |
| "grad_norm": 0.05668758228421211, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 2.0646, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.08467208467208467, | |
| "grad_norm": 0.05856581777334213, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 2.0811, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0876960876960877, | |
| "grad_norm": 0.06092054769396782, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 2.1128, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.09072009072009073, | |
| "grad_norm": 0.061290230602025986, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 2.0705, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09374409374409375, | |
| "grad_norm": 0.05879451707005501, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 2.1229, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.09676809676809676, | |
| "grad_norm": 0.05842060595750809, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.148, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0997920997920998, | |
| "grad_norm": 0.05611104518175125, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 2.1368, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.10281610281610282, | |
| "grad_norm": 0.05795889347791672, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.2185, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.10584010584010584, | |
| "grad_norm": 0.06058291345834732, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 2.071, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.10886410886410887, | |
| "grad_norm": 0.07205378264188766, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 2.0645, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.11188811188811189, | |
| "grad_norm": 0.07796823978424072, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 2.0426, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.11491211491211491, | |
| "grad_norm": 0.0645485669374466, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.066, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.11793611793611794, | |
| "grad_norm": 0.05329917371273041, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 2.1214, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.12096012096012096, | |
| "grad_norm": 0.05362192541360855, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 2.0971, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.12398412398412398, | |
| "grad_norm": 0.05432514101266861, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 2.0811, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.127008127008127, | |
| "grad_norm": 0.05242035165429115, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 2.1001, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.13003213003213004, | |
| "grad_norm": 0.05346823111176491, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 2.0913, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.13305613305613306, | |
| "grad_norm": 0.05273548886179924, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.0959, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.13608013608013608, | |
| "grad_norm": 0.05268967151641846, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 2.0965, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1391041391041391, | |
| "grad_norm": 0.054601460695266724, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 2.1074, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.14212814212814212, | |
| "grad_norm": 0.05563381314277649, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 2.2237, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.14515214515214514, | |
| "grad_norm": 0.06596875190734863, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 2.1502, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1481761481761482, | |
| "grad_norm": 0.07697181403636932, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 2.0869, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.1512001512001512, | |
| "grad_norm": 0.10499610006809235, | |
| "learning_rate": 0.0, | |
| "loss": 2.0315, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1512001512001512, | |
| "eval_loss": 2.0980021953582764, | |
| "eval_runtime": 106.6124, | |
| "eval_samples_per_second": 20.898, | |
| "eval_steps_per_second": 2.617, | |
| "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": 1.821740327942226e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |