| { |
| "best_global_step": 300, |
| "best_metric": 0.2536058723926544, |
| "best_model_checkpoint": "/workspace/anchor/olmo-urban-web-s2/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": 1.4640703201293945, |
| "learning_rate": 1.7021276595744682e-05, |
| "loss": 1.0765, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.01068804275217101, |
| "grad_norm": 1.629133701324463, |
| "learning_rate": 3.829787234042553e-05, |
| "loss": 1.1151, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.01603206412825651, |
| "grad_norm": 1.0735725164413452, |
| "learning_rate": 5.9574468085106384e-05, |
| "loss": 0.9608, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.02137608550434202, |
| "grad_norm": 0.9052605032920837, |
| "learning_rate": 8.085106382978723e-05, |
| "loss": 0.7746, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.026720106880427523, |
| "grad_norm": 1.0044569969177246, |
| "learning_rate": 0.00010212765957446809, |
| "loss": 0.8126, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.03206412825651302, |
| "grad_norm": 1.6797224283218384, |
| "learning_rate": 0.00012340425531914893, |
| "loss": 0.5922, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.03740814963259853, |
| "grad_norm": 1.3676917552947998, |
| "learning_rate": 0.0001446808510638298, |
| "loss": 0.5543, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.04275217100868404, |
| "grad_norm": 1.5884857177734375, |
| "learning_rate": 0.00016595744680851065, |
| "loss": 0.6, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.04809619238476954, |
| "grad_norm": 1.681117057800293, |
| "learning_rate": 0.0001872340425531915, |
| "loss": 0.6283, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.053440213760855046, |
| "grad_norm": 1.1437196731567383, |
| "learning_rate": 0.00019999750239122662, |
| "loss": 0.5939, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.053440213760855046, |
| "eval_loss": 0.3563966751098633, |
| "eval_runtime": 167.4274, |
| "eval_samples_per_second": 2.294, |
| "eval_steps_per_second": 1.147, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.058784235136940546, |
| "grad_norm": 1.231215238571167, |
| "learning_rate": 0.0001999694057253083, |
| "loss": 0.5073, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.06412825651302605, |
| "grad_norm": 1.0620702505111694, |
| "learning_rate": 0.00019991009918336413, |
| "loss": 0.5825, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.06947227788911156, |
| "grad_norm": 0.9031045436859131, |
| "learning_rate": 0.00019981960128055687, |
| "loss": 0.6129, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.07481629926519706, |
| "grad_norm": 0.6679940819740295, |
| "learning_rate": 0.0001996979402698136, |
| "loss": 0.7001, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.08016032064128256, |
| "grad_norm": 0.7186521887779236, |
| "learning_rate": 0.00019954515413300516, |
| "loss": 0.5388, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.08550434201736808, |
| "grad_norm": 0.6060337424278259, |
| "learning_rate": 0.00019936129056908865, |
| "loss": 0.5136, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.09084836339345358, |
| "grad_norm": 0.7382415533065796, |
| "learning_rate": 0.00019914640697921585, |
| "loss": 0.3927, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.09619238476953908, |
| "grad_norm": 0.6298573017120361, |
| "learning_rate": 0.00019890057044881306, |
| "loss": 0.4683, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.10153640614562458, |
| "grad_norm": 0.536397397518158, |
| "learning_rate": 0.0001986238577266374, |
| "loss": 0.5533, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.10688042752171009, |
| "grad_norm": 0.6287534832954407, |
| "learning_rate": 0.00019831635520081625, |
| "loss": 0.3951, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.10688042752171009, |
| "eval_loss": 0.28746795654296875, |
| "eval_runtime": 63.1544, |
| "eval_samples_per_second": 6.08, |
| "eval_steps_per_second": 3.04, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.11222444889779559, |
| "grad_norm": 0.5217409729957581, |
| "learning_rate": 0.00019797815887187726, |
| "loss": 0.6573, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.11756847027388109, |
| "grad_norm": 0.5974845290184021, |
| "learning_rate": 0.00019760937432277786, |
| "loss": 0.6494, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.1229124916499666, |
| "grad_norm": 0.6097667813301086, |
| "learning_rate": 0.0001972101166859425, |
| "loss": 0.308, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.1282565130260521, |
| "grad_norm": 0.49901461601257324, |
| "learning_rate": 0.0001967805106073192, |
| "loss": 0.4571, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.13360053440213762, |
| "grad_norm": 0.5751474499702454, |
| "learning_rate": 0.00019632069020746572, |
| "loss": 0.4721, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.13894455577822312, |
| "grad_norm": 0.548405647277832, |
| "learning_rate": 0.00019583079903967785, |
| "loss": 0.6143, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.14428857715430862, |
| "grad_norm": 0.5808079242706299, |
| "learning_rate": 0.000195310990045173, |
| "loss": 0.5734, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.14963259853039412, |
| "grad_norm": 0.41290321946144104, |
| "learning_rate": 0.0001947614255053428, |
| "loss": 0.5947, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.15497661990647962, |
| "grad_norm": 0.8077467679977417, |
| "learning_rate": 0.00019418227699108956, |
| "loss": 0.4985, |
| "step": 145 |
| }, |
| { |
| "epoch": 0.16032064128256512, |
| "grad_norm": 0.4696853458881378, |
| "learning_rate": 0.00019357372530926322, |
| "loss": 0.4113, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.16032064128256512, |
| "eval_loss": 0.2695848047733307, |
| "eval_runtime": 63.6024, |
| "eval_samples_per_second": 6.038, |
| "eval_steps_per_second": 3.019, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.16566466265865062, |
| "grad_norm": 0.3784468173980713, |
| "learning_rate": 0.00019293596044621416, |
| "loss": 0.4385, |
| "step": 155 |
| }, |
| { |
| "epoch": 0.17100868403473615, |
| "grad_norm": 0.5272524356842041, |
| "learning_rate": 0.00019226918150848068, |
| "loss": 0.5087, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.17635270541082165, |
| "grad_norm": 0.5417175889015198, |
| "learning_rate": 0.00019157359666062903, |
| "loss": 0.5336, |
| "step": 165 |
| }, |
| { |
| "epoch": 0.18169672678690715, |
| "grad_norm": 0.5743632316589355, |
| "learning_rate": 0.00019084942306026568, |
| "loss": 0.4268, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.18704074816299265, |
| "grad_norm": 0.7294589877128601, |
| "learning_rate": 0.0001900968867902419, |
| "loss": 0.5432, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.19238476953907815, |
| "grad_norm": 0.4905416667461395, |
| "learning_rate": 0.00018931622278807212, |
| "loss": 0.4306, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.19772879091516365, |
| "grad_norm": 0.5544520616531372, |
| "learning_rate": 0.00018850767477258753, |
| "loss": 0.5264, |
| "step": 185 |
| }, |
| { |
| "epoch": 0.20307281229124916, |
| "grad_norm": 0.3537662625312805, |
| "learning_rate": 0.00018767149516784874, |
| "loss": 0.3355, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.20841683366733466, |
| "grad_norm": 0.4061245620250702, |
| "learning_rate": 0.00018680794502434018, |
| "loss": 0.2958, |
| "step": 195 |
| }, |
| { |
| "epoch": 0.21376085504342018, |
| "grad_norm": 0.5630972981452942, |
| "learning_rate": 0.00018591729393747187, |
| "loss": 0.5192, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.21376085504342018, |
| "eval_loss": 0.26297637820243835, |
| "eval_runtime": 63.2484, |
| "eval_samples_per_second": 6.071, |
| "eval_steps_per_second": 3.036, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.21910487641950568, |
| "grad_norm": 0.5688951015472412, |
| "learning_rate": 0.0001849998199634131, |
| "loss": 0.5684, |
| "step": 205 |
| }, |
| { |
| "epoch": 0.22444889779559118, |
| "grad_norm": 0.42737048864364624, |
| "learning_rate": 0.00018405580953228493, |
| "loss": 0.4469, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.22979291917167669, |
| "grad_norm": 0.5552764534950256, |
| "learning_rate": 0.00018308555735873844, |
| "loss": 0.5589, |
| "step": 215 |
| }, |
| { |
| "epoch": 0.23513694054776219, |
| "grad_norm": 0.37965238094329834, |
| "learning_rate": 0.0001820893663499464, |
| "loss": 0.3772, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.24048096192384769, |
| "grad_norm": 0.5016294121742249, |
| "learning_rate": 0.00018106754751103735, |
| "loss": 0.4254, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.2458249832999332, |
| "grad_norm": 0.539853036403656, |
| "learning_rate": 0.00018002041984800174, |
| "loss": 0.3553, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.2511690046760187, |
| "grad_norm": 0.5472220778465271, |
| "learning_rate": 0.00017894831026809985, |
| "loss": 0.433, |
| "step": 235 |
| }, |
| { |
| "epoch": 0.2565130260521042, |
| "grad_norm": 0.4908229410648346, |
| "learning_rate": 0.00017785155347780352, |
| "loss": 0.4766, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.2618570474281897, |
| "grad_norm": 0.37412312626838684, |
| "learning_rate": 0.00017673049187830252, |
| "loss": 0.3044, |
| "step": 245 |
| }, |
| { |
| "epoch": 0.26720106880427524, |
| "grad_norm": 0.6919337511062622, |
| "learning_rate": 0.00017558547545860868, |
| "loss": 0.5774, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.26720106880427524, |
| "eval_loss": 0.2562918961048126, |
| "eval_runtime": 63.5188, |
| "eval_samples_per_second": 6.045, |
| "eval_steps_per_second": 3.023, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.2725450901803607, |
| "grad_norm": 0.5289351940155029, |
| "learning_rate": 0.0001744168616862918, |
| "loss": 0.5464, |
| "step": 255 |
| }, |
| { |
| "epoch": 0.27788911155644624, |
| "grad_norm": 0.5302258729934692, |
| "learning_rate": 0.00017322501539587988, |
| "loss": 0.608, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.2832331329325317, |
| "grad_norm": 0.5346113443374634, |
| "learning_rate": 0.00017201030867496005, |
| "loss": 0.5323, |
| "step": 265 |
| }, |
| { |
| "epoch": 0.28857715430861725, |
| "grad_norm": 0.5241730809211731, |
| "learning_rate": 0.00017077312074801498, |
| "loss": 0.4764, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.2939211756847027, |
| "grad_norm": 0.6255365014076233, |
| "learning_rate": 0.00016951383785803115, |
| "loss": 0.5639, |
| "step": 275 |
| }, |
| { |
| "epoch": 0.29926519706078825, |
| "grad_norm": 0.6079185009002686, |
| "learning_rate": 0.00016823285314591593, |
| "loss": 0.5385, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.3046092184368738, |
| "grad_norm": 0.5327017307281494, |
| "learning_rate": 0.00016693056652776126, |
| "loss": 0.5337, |
| "step": 285 |
| }, |
| { |
| "epoch": 0.30995323981295925, |
| "grad_norm": 0.49495169520378113, |
| "learning_rate": 0.00016560738456999232, |
| "loss": 0.2606, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.3152972611890448, |
| "grad_norm": 0.554911196231842, |
| "learning_rate": 0.00016426372036243945, |
| "loss": 0.4513, |
| "step": 295 |
| }, |
| { |
| "epoch": 0.32064128256513025, |
| "grad_norm": 0.5562303066253662, |
| "learning_rate": 0.00016289999338937427, |
| "loss": 0.4496, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.32064128256513025, |
| "eval_loss": 0.2536058723926544, |
| "eval_runtime": 63.4153, |
| "eval_samples_per_second": 6.055, |
| "eval_steps_per_second": 3.028, |
| "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 |
| } |
|
|
