| { | |
| "best_metric": 1.4071449041366577, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.4875076173065204, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009750152346130409, | |
| "grad_norm": 13.08584213256836, | |
| "learning_rate": 5e-05, | |
| "loss": 11.0885, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009750152346130409, | |
| "eval_loss": 10.92984390258789, | |
| "eval_runtime": 19.8062, | |
| "eval_samples_per_second": 34.888, | |
| "eval_steps_per_second": 4.393, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.019500304692260818, | |
| "grad_norm": 13.427562713623047, | |
| "learning_rate": 0.0001, | |
| "loss": 10.9445, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.029250457038391225, | |
| "grad_norm": 10.839264869689941, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 10.1519, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.039000609384521635, | |
| "grad_norm": 11.43056583404541, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 8.2367, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04875076173065204, | |
| "grad_norm": 12.200672149658203, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 6.0274, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05850091407678245, | |
| "grad_norm": 10.398240089416504, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 4.0896, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06825106642291286, | |
| "grad_norm": 11.074796676635742, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 3.0369, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07800121876904327, | |
| "grad_norm": 13.899006843566895, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.6031, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.08775137111517367, | |
| "grad_norm": 7.236443996429443, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.322, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.09750152346130408, | |
| "grad_norm": 9.208919525146484, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.1758, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10725167580743449, | |
| "grad_norm": 6.921333312988281, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.9933, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1170018281535649, | |
| "grad_norm": 4.525189399719238, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.7731, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1267519804996953, | |
| "grad_norm": 5.29202127456665, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.7128, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1365021328458257, | |
| "grad_norm": 1.2969841957092285, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.596, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.14625228519195613, | |
| "grad_norm": 2.6499223709106445, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.5564, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.15600243753808654, | |
| "grad_norm": 2.7539515495300293, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.4805, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.16575258988421693, | |
| "grad_norm": 1.3573620319366455, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.4873, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.17550274223034734, | |
| "grad_norm": 5.630860328674316, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.5256, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.18525289457647776, | |
| "grad_norm": 6.104781150817871, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.5169, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.19500304692260817, | |
| "grad_norm": 2.6459336280822754, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.4215, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.20475319926873858, | |
| "grad_norm": 7.261768341064453, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.5685, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.21450335161486897, | |
| "grad_norm": 7.078161716461182, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.5577, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.22425350396099938, | |
| "grad_norm": 6.434289932250977, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.5252, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2340036563071298, | |
| "grad_norm": 1.843693494796753, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.4233, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2437538086532602, | |
| "grad_norm": 3.2900617122650146, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.4623, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2437538086532602, | |
| "eval_loss": 1.4898197650909424, | |
| "eval_runtime": 19.8171, | |
| "eval_samples_per_second": 34.869, | |
| "eval_steps_per_second": 4.39, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2535039609993906, | |
| "grad_norm": 5.611640453338623, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4692, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.263254113345521, | |
| "grad_norm": 4.255390644073486, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.4596, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.2730042656916514, | |
| "grad_norm": 1.7595406770706177, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.4084, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.28275441803778184, | |
| "grad_norm": 4.331860542297363, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.4264, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.29250457038391225, | |
| "grad_norm": 5.486930847167969, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.4346, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.30225472273004267, | |
| "grad_norm": 4.307036399841309, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.4102, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.3120048750761731, | |
| "grad_norm": 2.45963454246521, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.4201, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.3217550274223035, | |
| "grad_norm": 2.097540855407715, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.3702, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.33150517976843386, | |
| "grad_norm": 2.6606364250183105, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.3941, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.34125533211456427, | |
| "grad_norm": 2.3306829929351807, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.3972, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3510054844606947, | |
| "grad_norm": 1.5131396055221558, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.3891, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.3607556368068251, | |
| "grad_norm": 0.22894760966300964, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.3895, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.3705057891529555, | |
| "grad_norm": 1.0239955186843872, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.3889, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.3802559414990859, | |
| "grad_norm": 1.6666826009750366, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.3956, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.39000609384521634, | |
| "grad_norm": 0.622130811214447, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.3491, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.39975624619134675, | |
| "grad_norm": 0.21952244639396667, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.3342, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.40950639853747717, | |
| "grad_norm": 0.7470478415489197, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.3829, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.4192565508836076, | |
| "grad_norm": 0.851636528968811, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.3954, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.42900670322973794, | |
| "grad_norm": 0.28048092126846313, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.3637, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.43875685557586835, | |
| "grad_norm": 0.6064202189445496, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.409, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.44850700792199877, | |
| "grad_norm": 0.278927206993103, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.3857, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.4582571602681292, | |
| "grad_norm": 0.37296435236930847, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.3855, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.4680073126142596, | |
| "grad_norm": 0.1863381415605545, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.3961, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.47775746496039, | |
| "grad_norm": 0.25494953989982605, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.394, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.4875076173065204, | |
| "grad_norm": 0.5845832824707031, | |
| "learning_rate": 0.0, | |
| "loss": 1.3817, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4875076173065204, | |
| "eval_loss": 1.4071449041366577, | |
| "eval_runtime": 19.8157, | |
| "eval_samples_per_second": 34.871, | |
| "eval_steps_per_second": 4.39, | |
| "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": 5.968083617316864e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |