| { | |
| "best_metric": 0.07823102176189423, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.9400705052878966, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01880141010575793, | |
| "grad_norm": 0.7600845098495483, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1707, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01880141010575793, | |
| "eval_loss": 0.4366946518421173, | |
| "eval_runtime": 5.0457, | |
| "eval_samples_per_second": 9.909, | |
| "eval_steps_per_second": 2.576, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03760282021151586, | |
| "grad_norm": 1.3569352626800537, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2471, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0564042303172738, | |
| "grad_norm": 0.5642196536064148, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 0.2538, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.07520564042303172, | |
| "grad_norm": 0.5840835571289062, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 0.2145, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.09400705052878966, | |
| "grad_norm": 0.46224477887153625, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 0.1904, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1128084606345476, | |
| "grad_norm": 0.4062245488166809, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.1852, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.13160987074030553, | |
| "grad_norm": 0.3530953526496887, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.1477, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.15041128084606345, | |
| "grad_norm": 0.2826444208621979, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.1289, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1692126909518214, | |
| "grad_norm": 0.377310574054718, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.144, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.18801410105757932, | |
| "grad_norm": 0.3118053078651428, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.1509, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.20681551116333724, | |
| "grad_norm": 0.3501030504703522, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.1615, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.2256169212690952, | |
| "grad_norm": 1.3040632009506226, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.1281, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2444183313748531, | |
| "grad_norm": 0.16963200271129608, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.068, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.26321974148061106, | |
| "grad_norm": 0.21708229184150696, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.0867, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.282021151586369, | |
| "grad_norm": 0.134294793009758, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.0941, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3008225616921269, | |
| "grad_norm": 0.12663644552230835, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.0955, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.3196239717978848, | |
| "grad_norm": 0.1226968914270401, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.0999, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.3384253819036428, | |
| "grad_norm": 0.11707764118909836, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.103, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3572267920094007, | |
| "grad_norm": 0.12075494229793549, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.1034, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.37602820211515864, | |
| "grad_norm": 0.11400816589593887, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.1066, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.39482961222091656, | |
| "grad_norm": 0.13738061487674713, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.1075, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.4136310223266745, | |
| "grad_norm": 0.15788087248802185, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.1107, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.43243243243243246, | |
| "grad_norm": 0.1624337136745453, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.118, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.4512338425381904, | |
| "grad_norm": 0.18111398816108704, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.1158, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.4700352526439483, | |
| "grad_norm": 0.2933941185474396, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.0768, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4700352526439483, | |
| "eval_loss": 0.0913226529955864, | |
| "eval_runtime": 5.314, | |
| "eval_samples_per_second": 9.409, | |
| "eval_steps_per_second": 2.446, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4888366627497062, | |
| "grad_norm": 0.07355140149593353, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0664, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.5076380728554641, | |
| "grad_norm": 0.09695981442928314, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.0782, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.5264394829612221, | |
| "grad_norm": 0.10992906242609024, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.0901, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.54524089306698, | |
| "grad_norm": 0.12939049303531647, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.0932, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.564042303172738, | |
| "grad_norm": 0.13968101143836975, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.0948, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5828437132784959, | |
| "grad_norm": 0.13001416623592377, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.0851, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.6016451233842538, | |
| "grad_norm": 0.12713101506233215, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.0955, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.6204465334900118, | |
| "grad_norm": 0.12246720492839813, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.0975, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.6392479435957696, | |
| "grad_norm": 0.14322993159294128, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.1107, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.6580493537015276, | |
| "grad_norm": 0.13620127737522125, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.0914, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.6768507638072856, | |
| "grad_norm": 0.15739606320858002, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.1033, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.6956521739130435, | |
| "grad_norm": 0.1808631420135498, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.0984, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.7144535840188014, | |
| "grad_norm": 0.04972299933433533, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.0567, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.7332549941245593, | |
| "grad_norm": 0.05645684152841568, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.0602, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.7520564042303173, | |
| "grad_norm": 0.06678657978773117, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.0685, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7708578143360753, | |
| "grad_norm": 0.08744647353887558, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.0779, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.7896592244418331, | |
| "grad_norm": 0.10616064816713333, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.0799, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.8084606345475911, | |
| "grad_norm": 0.11365273594856262, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.0825, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.827262044653349, | |
| "grad_norm": 0.09806361794471741, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.0878, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.8460634547591069, | |
| "grad_norm": 0.11302643269300461, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.0881, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.8648648648648649, | |
| "grad_norm": 0.10468102991580963, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.0962, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.8836662749706228, | |
| "grad_norm": 0.11554855108261108, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.0893, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.9024676850763808, | |
| "grad_norm": 0.10484100878238678, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.0817, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.9212690951821386, | |
| "grad_norm": 0.14057570695877075, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.094, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.9400705052878966, | |
| "grad_norm": 0.2136404663324356, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0722, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.9400705052878966, | |
| "eval_loss": 0.07823102176189423, | |
| "eval_runtime": 5.3305, | |
| "eval_samples_per_second": 9.38, | |
| "eval_steps_per_second": 2.439, | |
| "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": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.196549313091338e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |