| { | |
| "best_metric": 1.0833128690719604, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-300", | |
| "epoch": 1.0015037593984963, | |
| "eval_steps": 50, | |
| "global_step": 333, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0030075187969924814, | |
| "eval_loss": 3.3393285274505615, | |
| "eval_runtime": 8.5355, | |
| "eval_samples_per_second": 16.402, | |
| "eval_steps_per_second": 4.101, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03007518796992481, | |
| "grad_norm": 6.7154974937438965, | |
| "learning_rate": 4.36e-05, | |
| "loss": 2.5046, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06015037593984962, | |
| "grad_norm": 6.054194927215576, | |
| "learning_rate": 8.72e-05, | |
| "loss": 1.9883, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09022556390977443, | |
| "grad_norm": 6.002712249755859, | |
| "learning_rate": 0.0001308, | |
| "loss": 1.7224, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.12030075187969924, | |
| "grad_norm": 7.4394683837890625, | |
| "learning_rate": 0.0001744, | |
| "loss": 1.9159, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.15037593984962405, | |
| "grad_norm": 17.918411254882812, | |
| "learning_rate": 0.000218, | |
| "loss": 1.7938, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.15037593984962405, | |
| "eval_loss": 1.9600940942764282, | |
| "eval_runtime": 8.5526, | |
| "eval_samples_per_second": 16.369, | |
| "eval_steps_per_second": 4.092, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.18045112781954886, | |
| "grad_norm": 4.931917667388916, | |
| "learning_rate": 0.00021732906980769228, | |
| "loss": 1.7875, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "grad_norm": 5.513779640197754, | |
| "learning_rate": 0.00021532453881467652, | |
| "loss": 1.415, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.24060150375939848, | |
| "grad_norm": 8.94431209564209, | |
| "learning_rate": 0.0002120110840918633, | |
| "loss": 1.4613, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.2706766917293233, | |
| "grad_norm": 7.7282328605651855, | |
| "learning_rate": 0.00020742949640648896, | |
| "loss": 1.6876, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.3007518796992481, | |
| "grad_norm": 9.372624397277832, | |
| "learning_rate": 0.00020163617806143107, | |
| "loss": 1.7947, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3007518796992481, | |
| "eval_loss": 2.0332393646240234, | |
| "eval_runtime": 8.5853, | |
| "eval_samples_per_second": 16.307, | |
| "eval_steps_per_second": 4.077, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3308270676691729, | |
| "grad_norm": 5.71964168548584, | |
| "learning_rate": 0.00019470244854643905, | |
| "loss": 1.7275, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.3609022556390977, | |
| "grad_norm": 5.346231460571289, | |
| "learning_rate": 0.0001867136665491626, | |
| "loss": 1.1856, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.39097744360902253, | |
| "grad_norm": 4.990022659301758, | |
| "learning_rate": 0.0001777681791345876, | |
| "loss": 1.1762, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 8.322728157043457, | |
| "learning_rate": 0.0001679761110291609, | |
| "loss": 1.6037, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.45112781954887216, | |
| "grad_norm": 17.498231887817383, | |
| "learning_rate": 0.0001574580089142965, | |
| "loss": 1.6452, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.45112781954887216, | |
| "eval_loss": 1.6451599597930908, | |
| "eval_runtime": 8.5559, | |
| "eval_samples_per_second": 16.363, | |
| "eval_steps_per_second": 4.091, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.48120300751879697, | |
| "grad_norm": 6.32410192489624, | |
| "learning_rate": 0.00014634335741888678, | |
| "loss": 1.5461, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.5112781954887218, | |
| "grad_norm": 3.9985594749450684, | |
| "learning_rate": 0.00013476898507990882, | |
| "loss": 1.1999, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.5413533834586466, | |
| "grad_norm": 5.48227071762085, | |
| "learning_rate": 0.00012287737989477975, | |
| "loss": 1.088, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 6.1915602684021, | |
| "learning_rate": 0.0001108149352020996, | |
| "loss": 1.3135, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.6015037593984962, | |
| "grad_norm": 8.36176586151123, | |
| "learning_rate": 9.873014748512275e-05, | |
| "loss": 1.4151, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.6015037593984962, | |
| "eval_loss": 1.3894352912902832, | |
| "eval_runtime": 8.5422, | |
| "eval_samples_per_second": 16.389, | |
| "eval_steps_per_second": 4.097, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.631578947368421, | |
| "grad_norm": 4.468929767608643, | |
| "learning_rate": 8.67717882841602e-05, | |
| "loss": 1.3629, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.6616541353383458, | |
| "grad_norm": 3.4488108158111572, | |
| "learning_rate": 7.5087072722852e-05, | |
| "loss": 0.9869, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.6917293233082706, | |
| "grad_norm": 4.566482067108154, | |
| "learning_rate": 6.381984719493421e-05, | |
| "loss": 1.0658, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.7218045112781954, | |
| "grad_norm": 7.519209861755371, | |
| "learning_rate": 5.310881852224566e-05, | |
| "loss": 1.4016, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.7518796992481203, | |
| "grad_norm": 12.673545837402344, | |
| "learning_rate": 4.308584638418418e-05, | |
| "loss": 1.4742, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.7518796992481203, | |
| "eval_loss": 1.1646312475204468, | |
| "eval_runtime": 8.5427, | |
| "eval_samples_per_second": 16.388, | |
| "eval_steps_per_second": 4.097, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.7819548872180451, | |
| "grad_norm": 3.2009496688842773, | |
| "learning_rate": 3.387432003990723e-05, | |
| "loss": 1.1397, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.8120300751879699, | |
| "grad_norm": 3.1080739498138428, | |
| "learning_rate": 2.5587639326875722e-05, | |
| "loss": 0.9926, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": 3.862886428833008, | |
| "learning_rate": 1.832781863562875e-05, | |
| "loss": 0.9932, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.8721804511278195, | |
| "grad_norm": 6.269960403442383, | |
| "learning_rate": 1.2184231046762632e-05, | |
| "loss": 1.2017, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.9022556390977443, | |
| "grad_norm": 9.295906066894531, | |
| "learning_rate": 7.232508090597738e-06, | |
| "loss": 1.3103, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.9022556390977443, | |
| "eval_loss": 1.0833128690719604, | |
| "eval_runtime": 8.5494, | |
| "eval_samples_per_second": 16.375, | |
| "eval_steps_per_second": 4.094, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.9323308270676691, | |
| "grad_norm": 3.119682550430298, | |
| "learning_rate": 3.5336086742025136e-06, | |
| "loss": 1.0088, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.9624060150375939, | |
| "grad_norm": 4.465202331542969, | |
| "learning_rate": 1.1330686378846785e-06, | |
| "loss": 0.9312, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.9924812030075187, | |
| "grad_norm": 7.782965183258057, | |
| "learning_rate": 6.044017959302761e-08, | |
| "loss": 1.1944, | |
| "step": 330 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 333, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "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": 6.279187771529626e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |