| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.6257332811888933, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.012514665623777864, | |
| "grad_norm": 3.003929615020752, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7707, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012514665623777864, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.0475, | |
| "eval_samples_per_second": 24.42, | |
| "eval_steps_per_second": 6.349, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.025029331247555728, | |
| "grad_norm": 2.6678109169006348, | |
| "learning_rate": 0.0001, | |
| "loss": 2.3159, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03754399687133359, | |
| "grad_norm": 2.0421063899993896, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 2.5062, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.050058662495111456, | |
| "grad_norm": 1.8860653638839722, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.0819, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06257332811888933, | |
| "grad_norm": 2.093566656112671, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.1698, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07508799374266718, | |
| "grad_norm": 2.6375949382781982, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.1448, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.08760265936644505, | |
| "grad_norm": 2.7502684593200684, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 2.2762, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.10011732499022291, | |
| "grad_norm": 5.241250514984131, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 2.5179, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.11263199061400078, | |
| "grad_norm": 3.217245101928711, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 2.0864, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.12514665623777865, | |
| "grad_norm": 2.6275532245635986, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.8957, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.13766132186155652, | |
| "grad_norm": 4.345211505889893, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 2.3292, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.15017598748533437, | |
| "grad_norm": 2.715369462966919, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 2.1771, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.16269065310911224, | |
| "grad_norm": 1.941023826599121, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.3988, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1752053187328901, | |
| "grad_norm": 2.244020462036133, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.4134, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.18771998435666798, | |
| "grad_norm": 2.06498122215271, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.9165, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.20023464998044582, | |
| "grad_norm": 1.6291917562484741, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.523, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2127493156042237, | |
| "grad_norm": 1.4038172960281372, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.5351, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.22526398122800156, | |
| "grad_norm": 1.607500672340393, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.4412, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.23777864685177943, | |
| "grad_norm": 1.7136542797088623, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.6684, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2502933124755573, | |
| "grad_norm": 1.6591033935546875, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.6842, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.26280797809933515, | |
| "grad_norm": 2.4633328914642334, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.2249, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.27532264372311305, | |
| "grad_norm": 2.102135419845581, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.4803, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.2878373093468909, | |
| "grad_norm": 2.2035129070281982, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.4066, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.30035197497066873, | |
| "grad_norm": 2.510206937789917, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.4071, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.31286664059444663, | |
| "grad_norm": 3.517763376235962, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.8974, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.31286664059444663, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.0345, | |
| "eval_samples_per_second": 24.576, | |
| "eval_steps_per_second": 6.39, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3253813062182245, | |
| "grad_norm": 2.0011110305786133, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.991, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3378959718420024, | |
| "grad_norm": 2.0475192070007324, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 1.3608, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3504106374657802, | |
| "grad_norm": 1.8558727502822876, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 1.5395, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.36292530308955806, | |
| "grad_norm": 1.5381715297698975, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 1.183, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.37543996871333596, | |
| "grad_norm": 1.9737073183059692, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.2611, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3879546343371138, | |
| "grad_norm": 2.4097700119018555, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 1.0897, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.40046929996089164, | |
| "grad_norm": 1.9280041456222534, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.2415, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.41298396558466954, | |
| "grad_norm": 1.7732486724853516, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.3308, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.4254986312084474, | |
| "grad_norm": 1.8770219087600708, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.2773, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.4380132968322253, | |
| "grad_norm": 2.209496021270752, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.1981, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.45052796245600313, | |
| "grad_norm": 2.2610745429992676, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.0344, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.46304262807978097, | |
| "grad_norm": 2.2316040992736816, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.2909, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.47555729370355887, | |
| "grad_norm": 1.6294275522232056, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.9738, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.4880719593273367, | |
| "grad_norm": 1.528761625289917, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.8498, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5005866249511146, | |
| "grad_norm": 1.7920118570327759, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 1.5672, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5131012905748924, | |
| "grad_norm": 1.6099443435668945, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.1178, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5256159561986703, | |
| "grad_norm": 1.7412190437316895, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.1435, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5381306218224482, | |
| "grad_norm": 1.6830037832260132, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 1.075, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5506452874462261, | |
| "grad_norm": 1.8176605701446533, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.1402, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5631599530700039, | |
| "grad_norm": 1.6718379259109497, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 1.1893, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5756746186937818, | |
| "grad_norm": 1.240828037261963, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.6582, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5881892843175597, | |
| "grad_norm": 1.8477025032043457, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.9412, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6007039499413375, | |
| "grad_norm": 2.1296470165252686, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.9925, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6132186155651154, | |
| "grad_norm": 1.826198935508728, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.9655, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6257332811888933, | |
| "grad_norm": 2.643702745437622, | |
| "learning_rate": 1e-05, | |
| "loss": 1.618, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6257332811888933, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.0353, | |
| "eval_samples_per_second": 24.567, | |
| "eval_steps_per_second": 6.387, | |
| "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": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.589463780163584e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |