| { |
| "best_global_step": 200, |
| "best_metric": 0.3417225778102875, |
| "best_model_checkpoint": "/workspace/anchor/olmo-urban-s1/train/checkpoint-200", |
| "epoch": 0.21396095212623698, |
| "eval_steps": 50, |
| "global_step": 200, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.005349023803155924, |
| "grad_norm": 13.324837684631348, |
| "learning_rate": 1.7021276595744682e-05, |
| "loss": 7.0618, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.010698047606311848, |
| "grad_norm": 6.624647617340088, |
| "learning_rate": 3.829787234042553e-05, |
| "loss": 6.696, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.016047071409467772, |
| "grad_norm": 4.403502464294434, |
| "learning_rate": 5.9574468085106384e-05, |
| "loss": 5.7263, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.021396095212623697, |
| "grad_norm": 3.409543037414551, |
| "learning_rate": 8.085106382978723e-05, |
| "loss": 4.6143, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.026745119015779622, |
| "grad_norm": 2.948425531387329, |
| "learning_rate": 0.00010212765957446809, |
| "loss": 3.7153, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.032094142818935543, |
| "grad_norm": 1.9742685556411743, |
| "learning_rate": 0.00012340425531914893, |
| "loss": 3.3613, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.03744316662209147, |
| "grad_norm": 1.7550853490829468, |
| "learning_rate": 0.0001446808510638298, |
| "loss": 2.7215, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.042792190425247394, |
| "grad_norm": 2.1917495727539062, |
| "learning_rate": 0.00016595744680851065, |
| "loss": 2.1992, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.04814121422840332, |
| "grad_norm": 1.5336745977401733, |
| "learning_rate": 0.0001872340425531915, |
| "loss": 1.6695, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.053490238031559244, |
| "grad_norm": 1.1771143674850464, |
| "learning_rate": 0.00019999749676283775, |
| "loss": 1.2751, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.053490238031559244, |
| "eval_loss": 0.7962851524353027, |
| "eval_runtime": 227.0493, |
| "eval_samples_per_second": 1.691, |
| "eval_steps_per_second": 0.846, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.05883926183471516, |
| "grad_norm": 1.5906565189361572, |
| "learning_rate": 0.00019996933678400946, |
| "loss": 0.9749, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.06418828563787109, |
| "grad_norm": 1.3733729124069214, |
| "learning_rate": 0.00019990989662046818, |
| "loss": 0.8782, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.06953730944102701, |
| "grad_norm": 1.0649430751800537, |
| "learning_rate": 0.00019981919487090972, |
| "loss": 0.796, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.07488633324418294, |
| "grad_norm": 1.3244534730911255, |
| "learning_rate": 0.00019969725991571128, |
| "loss": 0.9512, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.08023535704733886, |
| "grad_norm": 1.153426170349121, |
| "learning_rate": 0.00019954412990805107, |
| "loss": 0.7218, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.08558438085049479, |
| "grad_norm": 0.7553210854530334, |
| "learning_rate": 0.0001993598527619703, |
| "loss": 0.9131, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.09093340465365071, |
| "grad_norm": 0.926650881767273, |
| "learning_rate": 0.00019914448613738106, |
| "loss": 0.6932, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.09628242845680664, |
| "grad_norm": 0.8621730208396912, |
| "learning_rate": 0.00019889809742202455, |
| "loss": 0.5124, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.10163145225996256, |
| "grad_norm": 0.7008249163627625, |
| "learning_rate": 0.0001986207637103857, |
| "loss": 0.8764, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.10698047606311849, |
| "grad_norm": 0.7580549716949463, |
| "learning_rate": 0.00019831257177957044, |
| "loss": 0.6443, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.10698047606311849, |
| "eval_loss": 0.4182993173599243, |
| "eval_runtime": 120.8184, |
| "eval_samples_per_second": 3.178, |
| "eval_steps_per_second": 1.589, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.1123294998662744, |
| "grad_norm": 0.5668728947639465, |
| "learning_rate": 0.00019797361806215332, |
| "loss": 0.6299, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.11767852366943032, |
| "grad_norm": 0.7871600985527039, |
| "learning_rate": 0.000197604008616004, |
| "loss": 0.5587, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.12302754747258625, |
| "grad_norm": 0.6859822273254395, |
| "learning_rate": 0.00019720385909110198, |
| "loss": 0.8384, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.12837657127574217, |
| "grad_norm": 0.7389317750930786, |
| "learning_rate": 0.0001967732946933499, |
| "loss": 0.5019, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.1337255950788981, |
| "grad_norm": 0.6546782851219177, |
| "learning_rate": 0.00019631245014539698, |
| "loss": 0.5265, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.13907461888205402, |
| "grad_norm": 0.6503968834877014, |
| "learning_rate": 0.0001958214696444846, |
| "loss": 0.7794, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.14442364268520994, |
| "grad_norm": 0.5992593169212341, |
| "learning_rate": 0.0001953005068173272, |
| "loss": 0.6717, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.14977266648836587, |
| "grad_norm": 0.6868244409561157, |
| "learning_rate": 0.00019474972467204297, |
| "loss": 0.7197, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.15512169029152179, |
| "grad_norm": 0.790126383304596, |
| "learning_rate": 0.00019416929554714888, |
| "loss": 0.6904, |
| "step": 145 |
| }, |
| { |
| "epoch": 0.16047071409467772, |
| "grad_norm": 0.862826943397522, |
| "learning_rate": 0.0001935594010576362, |
| "loss": 0.7539, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.16047071409467772, |
| "eval_loss": 0.3647921085357666, |
| "eval_runtime": 232.172, |
| "eval_samples_per_second": 1.654, |
| "eval_steps_per_second": 0.827, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.16581973789783364, |
| "grad_norm": 0.9797982573509216, |
| "learning_rate": 0.000192920232038144, |
| "loss": 0.8136, |
| "step": 155 |
| }, |
| { |
| "epoch": 0.17116876170098957, |
| "grad_norm": 0.7100125551223755, |
| "learning_rate": 0.0001922519884832469, |
| "loss": 0.628, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.17651778550414549, |
| "grad_norm": 0.5549789667129517, |
| "learning_rate": 0.00019155487948487748, |
| "loss": 0.5279, |
| "step": 165 |
| }, |
| { |
| "epoch": 0.18186680930730142, |
| "grad_norm": 0.6707829833030701, |
| "learning_rate": 0.0001908291231669019, |
| "loss": 0.5766, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.18721583311045734, |
| "grad_norm": 0.5204013586044312, |
| "learning_rate": 0.00019007494661686935, |
| "loss": 0.5413, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.19256485691361327, |
| "grad_norm": 0.6301614046096802, |
| "learning_rate": 0.00018929258581495685, |
| "loss": 0.5817, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.19791388071676919, |
| "grad_norm": 0.5853822827339172, |
| "learning_rate": 0.0001884822855601316, |
| "loss": 0.6344, |
| "step": 185 |
| }, |
| { |
| "epoch": 0.20326290451992512, |
| "grad_norm": 0.5293443202972412, |
| "learning_rate": 0.00018764429939355392, |
| "loss": 0.5642, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.20861192832308104, |
| "grad_norm": 0.55076003074646, |
| "learning_rate": 0.00018677888951924474, |
| "loss": 0.4617, |
| "step": 195 |
| }, |
| { |
| "epoch": 0.21396095212623698, |
| "grad_norm": 0.6361037492752075, |
| "learning_rate": 0.00018588632672204264, |
| "loss": 0.4439, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.21396095212623698, |
| "eval_loss": 0.3417225778102875, |
| "eval_runtime": 120.6829, |
| "eval_samples_per_second": 3.182, |
| "eval_steps_per_second": 1.591, |
| "step": 200 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 935, |
| "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": 5.583541081935053e+17, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
