| { | |
| "best_metric": 1.0894900560379028, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.7912957467853611, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01582591493570722, | |
| "grad_norm": 16.39025115966797, | |
| "learning_rate": 5e-05, | |
| "loss": 1.2949, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01582591493570722, | |
| "eval_loss": 1.7229818105697632, | |
| "eval_runtime": 18.3646, | |
| "eval_samples_per_second": 23.197, | |
| "eval_steps_per_second": 2.94, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03165182987141444, | |
| "grad_norm": 21.861265182495117, | |
| "learning_rate": 0.0001, | |
| "loss": 1.4627, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04747774480712166, | |
| "grad_norm": 30.59173011779785, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.4737, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06330365974282888, | |
| "grad_norm": 19.03850555419922, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.4267, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0791295746785361, | |
| "grad_norm": 30.177947998046875, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.3638, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.09495548961424333, | |
| "grad_norm": 39.83805847167969, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.2977, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.11078140454995054, | |
| "grad_norm": 24.79155731201172, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.3324, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.12660731948565776, | |
| "grad_norm": 19.215362548828125, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.3577, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.142433234421365, | |
| "grad_norm": 15.088253021240234, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.263, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1582591493570722, | |
| "grad_norm": 15.523794174194336, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.3786, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.17408506429277942, | |
| "grad_norm": 15.526394844055176, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.2603, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.18991097922848665, | |
| "grad_norm": 29.357566833496094, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.3106, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.20573689416419386, | |
| "grad_norm": 28.918760299682617, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.203, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.2215628090999011, | |
| "grad_norm": 10.056431770324707, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.04, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.23738872403560832, | |
| "grad_norm": 10.02784252166748, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.0348, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2532146389713155, | |
| "grad_norm": 9.614541053771973, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.0446, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.26904055390702275, | |
| "grad_norm": 10.44601058959961, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.0899, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.28486646884273, | |
| "grad_norm": 10.773473739624023, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.0927, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3006923837784372, | |
| "grad_norm": 12.849751472473145, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.1194, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.3165182987141444, | |
| "grad_norm": 12.74648666381836, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.0976, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3323442136498516, | |
| "grad_norm": 13.762334823608398, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.1435, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.34817012858555885, | |
| "grad_norm": 11.167744636535645, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.0819, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3639960435212661, | |
| "grad_norm": 11.4578218460083, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.1206, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3798219584569733, | |
| "grad_norm": 19.657743453979492, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.1229, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.39564787339268054, | |
| "grad_norm": 19.466861724853516, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.1919, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.39564787339268054, | |
| "eval_loss": 1.122847557067871, | |
| "eval_runtime": 18.3421, | |
| "eval_samples_per_second": 23.225, | |
| "eval_steps_per_second": 2.944, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4114737883283877, | |
| "grad_norm": 9.869994163513184, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0232, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.42729970326409494, | |
| "grad_norm": 9.686948776245117, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.0263, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.4431256181998022, | |
| "grad_norm": 10.00652027130127, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.002, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.4589515331355094, | |
| "grad_norm": 9.696783065795898, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.0132, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.47477744807121663, | |
| "grad_norm": 11.705400466918945, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.092, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.49060336300692386, | |
| "grad_norm": 10.257039070129395, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.0313, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.506429277942631, | |
| "grad_norm": 10.613300323486328, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.0224, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.5222551928783383, | |
| "grad_norm": 11.017250061035156, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.0769, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.5380811078140455, | |
| "grad_norm": 16.603017807006836, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.0977, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.5539070227497527, | |
| "grad_norm": 13.133756637573242, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.1007, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.56973293768546, | |
| "grad_norm": 15.047310829162598, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.1513, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5855588526211671, | |
| "grad_norm": 17.72347640991211, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.1953, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.6013847675568744, | |
| "grad_norm": 12.774372100830078, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.0298, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.6172106824925816, | |
| "grad_norm": 8.430004119873047, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.9786, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.6330365974282888, | |
| "grad_norm": 8.151567459106445, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.9518, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6488625123639961, | |
| "grad_norm": 10.981574058532715, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.0174, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.6646884272997032, | |
| "grad_norm": 10.649538040161133, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.0235, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.6805143422354105, | |
| "grad_norm": 10.363326072692871, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.0967, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.6963402571711177, | |
| "grad_norm": 11.041847229003906, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.0079, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.712166172106825, | |
| "grad_norm": 10.589798927307129, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.0251, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.7279920870425322, | |
| "grad_norm": 12.95122241973877, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.0545, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.7438180019782393, | |
| "grad_norm": 19.719316482543945, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.0717, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.7596439169139466, | |
| "grad_norm": 13.02059555053711, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.0867, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.7754698318496538, | |
| "grad_norm": 14.491941452026367, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.0927, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.7912957467853611, | |
| "grad_norm": 20.872737884521484, | |
| "learning_rate": 0.0, | |
| "loss": 1.1306, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7912957467853611, | |
| "eval_loss": 1.0894900560379028, | |
| "eval_runtime": 18.3462, | |
| "eval_samples_per_second": 23.22, | |
| "eval_steps_per_second": 2.943, | |
| "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": 9.193961612640256e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |