| { |
| "best_global_step": 300, |
| "best_metric": 0.25355157256126404, |
| "best_model_checkpoint": "/workspace/anchor/olmo-urban-web-s3407/train/checkpoint-300", |
| "epoch": 0.32064128256513025, |
| "eval_steps": 50, |
| "global_step": 300, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.005344021376085505, |
| "grad_norm": 1.4809995889663696, |
| "learning_rate": 1.7021276595744682e-05, |
| "loss": 1.0756, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.01068804275217101, |
| "grad_norm": 1.63643217086792, |
| "learning_rate": 3.829787234042553e-05, |
| "loss": 1.1123, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.01603206412825651, |
| "grad_norm": 1.0598446130752563, |
| "learning_rate": 5.9574468085106384e-05, |
| "loss": 0.9598, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.02137608550434202, |
| "grad_norm": 0.9156885147094727, |
| "learning_rate": 8.085106382978723e-05, |
| "loss": 0.7757, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.026720106880427523, |
| "grad_norm": 1.0118458271026611, |
| "learning_rate": 0.00010212765957446809, |
| "loss": 0.812, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.03206412825651302, |
| "grad_norm": 1.6732467412948608, |
| "learning_rate": 0.00012340425531914893, |
| "loss": 0.5924, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.03740814963259853, |
| "grad_norm": 1.381805419921875, |
| "learning_rate": 0.0001446808510638298, |
| "loss": 0.5532, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.04275217100868404, |
| "grad_norm": 1.6085081100463867, |
| "learning_rate": 0.00016595744680851065, |
| "loss": 0.6015, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.04809619238476954, |
| "grad_norm": 1.6940559148788452, |
| "learning_rate": 0.0001872340425531915, |
| "loss": 0.6312, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.053440213760855046, |
| "grad_norm": 1.14291512966156, |
| "learning_rate": 0.00019999750239122662, |
| "loss": 0.5936, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.053440213760855046, |
| "eval_loss": 0.35635676980018616, |
| "eval_runtime": 197.9074, |
| "eval_samples_per_second": 1.94, |
| "eval_steps_per_second": 0.97, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.058784235136940546, |
| "grad_norm": 1.2360730171203613, |
| "learning_rate": 0.0001999694057253083, |
| "loss": 0.5085, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.06412825651302605, |
| "grad_norm": 1.0623812675476074, |
| "learning_rate": 0.00019991009918336413, |
| "loss": 0.5838, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.06947227788911156, |
| "grad_norm": 0.8848221898078918, |
| "learning_rate": 0.00019981960128055687, |
| "loss": 0.6131, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.07481629926519706, |
| "grad_norm": 0.665597677230835, |
| "learning_rate": 0.0001996979402698136, |
| "loss": 0.7009, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.08016032064128256, |
| "grad_norm": 0.7245955467224121, |
| "learning_rate": 0.00019954515413300516, |
| "loss": 0.54, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.08550434201736808, |
| "grad_norm": 0.5969834327697754, |
| "learning_rate": 0.00019936129056908865, |
| "loss": 0.512, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.09084836339345358, |
| "grad_norm": 0.7601527571678162, |
| "learning_rate": 0.00019914640697921585, |
| "loss": 0.3896, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.09619238476953908, |
| "grad_norm": 0.6279251575469971, |
| "learning_rate": 0.00019890057044881306, |
| "loss": 0.4683, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.10153640614562458, |
| "grad_norm": 0.5151042938232422, |
| "learning_rate": 0.0001986238577266374, |
| "loss": 0.5528, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.10688042752171009, |
| "grad_norm": 0.6342965960502625, |
| "learning_rate": 0.00019831635520081625, |
| "loss": 0.3956, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.10688042752171009, |
| "eval_loss": 0.2861863374710083, |
| "eval_runtime": 120.3365, |
| "eval_samples_per_second": 3.191, |
| "eval_steps_per_second": 1.596, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.11222444889779559, |
| "grad_norm": 0.5351696014404297, |
| "learning_rate": 0.00019797815887187726, |
| "loss": 0.6591, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.11756847027388109, |
| "grad_norm": 0.6033509373664856, |
| "learning_rate": 0.00019760937432277786, |
| "loss": 0.6495, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.1229124916499666, |
| "grad_norm": 0.6111649870872498, |
| "learning_rate": 0.0001972101166859425, |
| "loss": 0.3099, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.1282565130260521, |
| "grad_norm": 0.5129374265670776, |
| "learning_rate": 0.0001967805106073192, |
| "loss": 0.4583, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.13360053440213762, |
| "grad_norm": 0.5804239511489868, |
| "learning_rate": 0.00019632069020746572, |
| "loss": 0.4746, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.13894455577822312, |
| "grad_norm": 0.539404034614563, |
| "learning_rate": 0.00019583079903967785, |
| "loss": 0.6141, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.14428857715430862, |
| "grad_norm": 0.5828493237495422, |
| "learning_rate": 0.000195310990045173, |
| "loss": 0.5721, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.14963259853039412, |
| "grad_norm": 0.4139210879802704, |
| "learning_rate": 0.0001947614255053428, |
| "loss": 0.5957, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.15497661990647962, |
| "grad_norm": 0.6727572679519653, |
| "learning_rate": 0.00019418227699108956, |
| "loss": 0.4985, |
| "step": 145 |
| }, |
| { |
| "epoch": 0.16032064128256512, |
| "grad_norm": 0.4434640109539032, |
| "learning_rate": 0.00019357372530926322, |
| "loss": 0.4117, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.16032064128256512, |
| "eval_loss": 0.2693035304546356, |
| "eval_runtime": 118.6291, |
| "eval_samples_per_second": 3.237, |
| "eval_steps_per_second": 1.618, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.16566466265865062, |
| "grad_norm": 0.38281476497650146, |
| "learning_rate": 0.00019293596044621416, |
| "loss": 0.437, |
| "step": 155 |
| }, |
| { |
| "epoch": 0.17100868403473615, |
| "grad_norm": 0.5160496830940247, |
| "learning_rate": 0.00019226918150848068, |
| "loss": 0.508, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.17635270541082165, |
| "grad_norm": 0.5432295203208923, |
| "learning_rate": 0.00019157359666062903, |
| "loss": 0.5346, |
| "step": 165 |
| }, |
| { |
| "epoch": 0.18169672678690715, |
| "grad_norm": 0.5758904218673706, |
| "learning_rate": 0.00019084942306026568, |
| "loss": 0.4258, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.18704074816299265, |
| "grad_norm": 0.7517985105514526, |
| "learning_rate": 0.0001900968867902419, |
| "loss": 0.539, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.19238476953907815, |
| "grad_norm": 0.4932438135147095, |
| "learning_rate": 0.00018931622278807212, |
| "loss": 0.4305, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.19772879091516365, |
| "grad_norm": 0.5545088648796082, |
| "learning_rate": 0.00018850767477258753, |
| "loss": 0.5264, |
| "step": 185 |
| }, |
| { |
| "epoch": 0.20307281229124916, |
| "grad_norm": 0.3543582856655121, |
| "learning_rate": 0.00018767149516784874, |
| "loss": 0.335, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.20841683366733466, |
| "grad_norm": 0.4083511233329773, |
| "learning_rate": 0.00018680794502434018, |
| "loss": 0.2961, |
| "step": 195 |
| }, |
| { |
| "epoch": 0.21376085504342018, |
| "grad_norm": 0.5639245510101318, |
| "learning_rate": 0.00018591729393747187, |
| "loss": 0.5175, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.21376085504342018, |
| "eval_loss": 0.2626599371433258, |
| "eval_runtime": 120.4944, |
| "eval_samples_per_second": 3.187, |
| "eval_steps_per_second": 1.593, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.21910487641950568, |
| "grad_norm": 0.5704315304756165, |
| "learning_rate": 0.0001849998199634131, |
| "loss": 0.5696, |
| "step": 205 |
| }, |
| { |
| "epoch": 0.22444889779559118, |
| "grad_norm": 0.42737486958503723, |
| "learning_rate": 0.00018405580953228493, |
| "loss": 0.4428, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.22979291917167669, |
| "grad_norm": 0.5710329413414001, |
| "learning_rate": 0.00018308555735873844, |
| "loss": 0.5583, |
| "step": 215 |
| }, |
| { |
| "epoch": 0.23513694054776219, |
| "grad_norm": 0.37969711422920227, |
| "learning_rate": 0.0001820893663499464, |
| "loss": 0.3781, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.24048096192384769, |
| "grad_norm": 0.5003648400306702, |
| "learning_rate": 0.00018106754751103735, |
| "loss": 0.429, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.2458249832999332, |
| "grad_norm": 0.5391137003898621, |
| "learning_rate": 0.00018002041984800174, |
| "loss": 0.3553, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.2511690046760187, |
| "grad_norm": 0.5544339418411255, |
| "learning_rate": 0.00017894831026809985, |
| "loss": 0.4363, |
| "step": 235 |
| }, |
| { |
| "epoch": 0.2565130260521042, |
| "grad_norm": 0.4919127821922302, |
| "learning_rate": 0.00017785155347780352, |
| "loss": 0.4771, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.2618570474281897, |
| "grad_norm": 0.35894012451171875, |
| "learning_rate": 0.00017673049187830252, |
| "loss": 0.3043, |
| "step": 245 |
| }, |
| { |
| "epoch": 0.26720106880427524, |
| "grad_norm": 0.6900591850280762, |
| "learning_rate": 0.00017558547545860868, |
| "loss": 0.5773, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.26720106880427524, |
| "eval_loss": 0.2562713325023651, |
| "eval_runtime": 100.5733, |
| "eval_samples_per_second": 3.818, |
| "eval_steps_per_second": 1.909, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.2725450901803607, |
| "grad_norm": 0.5279027223587036, |
| "learning_rate": 0.0001744168616862918, |
| "loss": 0.5462, |
| "step": 255 |
| }, |
| { |
| "epoch": 0.27788911155644624, |
| "grad_norm": 0.5291879177093506, |
| "learning_rate": 0.00017322501539587988, |
| "loss": 0.6081, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.2832331329325317, |
| "grad_norm": 0.5350746512413025, |
| "learning_rate": 0.00017201030867496005, |
| "loss": 0.5318, |
| "step": 265 |
| }, |
| { |
| "epoch": 0.28857715430861725, |
| "grad_norm": 0.5358083248138428, |
| "learning_rate": 0.00017077312074801498, |
| "loss": 0.4774, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.2939211756847027, |
| "grad_norm": 0.6184861660003662, |
| "learning_rate": 0.00016951383785803115, |
| "loss": 0.5627, |
| "step": 275 |
| }, |
| { |
| "epoch": 0.29926519706078825, |
| "grad_norm": 0.6525461077690125, |
| "learning_rate": 0.00016823285314591593, |
| "loss": 0.5387, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.3046092184368738, |
| "grad_norm": 0.5439752340316772, |
| "learning_rate": 0.00016693056652776126, |
| "loss": 0.5333, |
| "step": 285 |
| }, |
| { |
| "epoch": 0.30995323981295925, |
| "grad_norm": 0.5216503739356995, |
| "learning_rate": 0.00016560738456999232, |
| "loss": 0.262, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.3152972611890448, |
| "grad_norm": 0.5546067953109741, |
| "learning_rate": 0.00016426372036243945, |
| "loss": 0.4517, |
| "step": 295 |
| }, |
| { |
| "epoch": 0.32064128256513025, |
| "grad_norm": 0.5637602210044861, |
| "learning_rate": 0.00016289999338937427, |
| "loss": 0.4488, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.32064128256513025, |
| "eval_loss": 0.25355157256126404, |
| "eval_runtime": 102.3017, |
| "eval_samples_per_second": 3.754, |
| "eval_steps_per_second": 1.877, |
| "step": 300 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 936, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 2, |
| "early_stopping_threshold": 0.001 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 0 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 8.163962850308751e+17, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
