| { | |
| "best_metric": 10.357853889465332, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.11899449650453667, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002379889930090733, | |
| "grad_norm": 0.0426366962492466, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3782, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002379889930090733, | |
| "eval_loss": 10.375080108642578, | |
| "eval_runtime": 0.0848, | |
| "eval_samples_per_second": 589.444, | |
| "eval_steps_per_second": 153.255, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004759779860181466, | |
| "grad_norm": 0.05311519652605057, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3748, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0071396697902722, | |
| "grad_norm": 0.074241042137146, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 10.3696, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009519559720362933, | |
| "grad_norm": 0.07961831986904144, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 10.3689, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.011899449650453666, | |
| "grad_norm": 0.08965161442756653, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 10.3738, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0142793395805444, | |
| "grad_norm": 0.09700139611959457, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 10.3708, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.016659229510635132, | |
| "grad_norm": 0.10126373171806335, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 10.3701, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.019039119440725866, | |
| "grad_norm": 0.10692870616912842, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 10.3723, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0214190093708166, | |
| "grad_norm": 0.10815344750881195, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 10.3693, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.023798899300907332, | |
| "grad_norm": 0.10395736992359161, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 10.3701, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.026178789230998065, | |
| "grad_norm": 0.118967704474926, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 10.3687, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0285586791610888, | |
| "grad_norm": 0.12255120277404785, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 10.3699, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.030938569091179532, | |
| "grad_norm": 0.058280669152736664, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 10.3746, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.033318459021270265, | |
| "grad_norm": 0.04936497285962105, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 10.3754, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.035698348951361, | |
| "grad_norm": 0.07907063513994217, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 10.3692, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03807823888145173, | |
| "grad_norm": 0.0914483442902565, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 10.3659, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04045812881154247, | |
| "grad_norm": 0.1104273870587349, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 10.3646, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0428380187416332, | |
| "grad_norm": 0.116667240858078, | |
| "learning_rate": 7.75e-05, | |
| "loss": 10.365, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.045217908671723935, | |
| "grad_norm": 0.1322374939918518, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 10.3665, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.047597798601814664, | |
| "grad_norm": 0.13855485618114471, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 10.3659, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0499776885319054, | |
| "grad_norm": 0.12768369913101196, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 10.3616, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05235757846199613, | |
| "grad_norm": 0.1414341926574707, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 10.3626, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.05473746839208687, | |
| "grad_norm": 0.1361013501882553, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 10.3631, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0571173583221776, | |
| "grad_norm": 0.13812997937202454, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 10.3627, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.059497248252268334, | |
| "grad_norm": 0.13790108263492584, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 10.3618, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.059497248252268334, | |
| "eval_loss": 10.363873481750488, | |
| "eval_runtime": 0.0816, | |
| "eval_samples_per_second": 612.812, | |
| "eval_steps_per_second": 159.331, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.061877138182359064, | |
| "grad_norm": 0.06834245473146439, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 10.3747, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0642570281124498, | |
| "grad_norm": 0.07222069799900055, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 10.3685, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06663691804254053, | |
| "grad_norm": 0.10398434102535248, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 10.3603, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.06901680797263127, | |
| "grad_norm": 0.1319500207901001, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 10.3593, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.071396697902722, | |
| "grad_norm": 0.13767267763614655, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 10.3598, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07377658783281273, | |
| "grad_norm": 0.1553162932395935, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 10.3605, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.07615647776290346, | |
| "grad_norm": 0.16494451463222504, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 10.3616, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0785363676929942, | |
| "grad_norm": 0.17596690356731415, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 10.3608, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.08091625762308494, | |
| "grad_norm": 0.1648629605770111, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 10.3584, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.08329614755317566, | |
| "grad_norm": 0.16102421283721924, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 10.3577, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0856760374832664, | |
| "grad_norm": 0.15746867656707764, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 10.3566, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.08805592741335713, | |
| "grad_norm": 0.18058502674102783, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 10.3559, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.09043581734344787, | |
| "grad_norm": 0.08370359987020493, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 10.3671, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0928157072735386, | |
| "grad_norm": 0.06642691045999527, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 10.375, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.09519559720362933, | |
| "grad_norm": 0.10110778361558914, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 10.3617, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09757548713372007, | |
| "grad_norm": 0.12056875973939896, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 10.3613, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0999553770638108, | |
| "grad_norm": 0.14950105547904968, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 10.3561, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.10233526699390154, | |
| "grad_norm": 0.18000173568725586, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 10.3575, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.10471515692399226, | |
| "grad_norm": 0.18226058781147003, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 10.3569, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.107095046854083, | |
| "grad_norm": 0.1937638521194458, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 10.3542, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.10947493678417373, | |
| "grad_norm": 0.18526925146579742, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 10.3531, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.11185482671426447, | |
| "grad_norm": 0.2028881460428238, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 10.3568, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.1142347166443552, | |
| "grad_norm": 0.18155358731746674, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 10.3561, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.11661460657444593, | |
| "grad_norm": 0.17677204310894012, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 10.3552, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.11899449650453667, | |
| "grad_norm": 0.1765909194946289, | |
| "learning_rate": 1e-05, | |
| "loss": 10.3561, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11899449650453667, | |
| "eval_loss": 10.357853889465332, | |
| "eval_runtime": 0.0832, | |
| "eval_samples_per_second": 601.218, | |
| "eval_steps_per_second": 156.317, | |
| "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": 42768059596800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |