| { | |
| "best_metric": 3.2531516551971436, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.06830601092896176, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001366120218579235, | |
| "grad_norm": 0.44335052371025085, | |
| "learning_rate": 5e-05, | |
| "loss": 2.6892, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001366120218579235, | |
| "eval_loss": 5.153928279876709, | |
| "eval_runtime": 3.8216, | |
| "eval_samples_per_second": 13.083, | |
| "eval_steps_per_second": 3.402, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00273224043715847, | |
| "grad_norm": 0.7610616087913513, | |
| "learning_rate": 0.0001, | |
| "loss": 3.4109, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004098360655737705, | |
| "grad_norm": 0.8422530293464661, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 3.6229, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00546448087431694, | |
| "grad_norm": 1.0623952150344849, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 3.8425, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006830601092896175, | |
| "grad_norm": 1.3338203430175781, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 4.0178, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00819672131147541, | |
| "grad_norm": 1.3180989027023315, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 3.9725, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009562841530054645, | |
| "grad_norm": 1.4900894165039062, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 4.0658, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01092896174863388, | |
| "grad_norm": 1.6651378870010376, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 4.0658, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.012295081967213115, | |
| "grad_norm": 2.3617329597473145, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 4.1574, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01366120218579235, | |
| "grad_norm": 2.1438562870025635, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 4.0263, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.015027322404371584, | |
| "grad_norm": 2.567352056503296, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 4.3152, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.01639344262295082, | |
| "grad_norm": 3.2836036682128906, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 4.4783, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.017759562841530054, | |
| "grad_norm": 2.9316556453704834, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 2.6311, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01912568306010929, | |
| "grad_norm": 2.8917789459228516, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 2.9126, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.020491803278688523, | |
| "grad_norm": 2.161324977874756, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 3.212, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02185792349726776, | |
| "grad_norm": 1.3268905878067017, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 3.1585, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.023224043715846996, | |
| "grad_norm": 1.1409670114517212, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 3.1252, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.02459016393442623, | |
| "grad_norm": 1.4727307558059692, | |
| "learning_rate": 7.75e-05, | |
| "loss": 3.444, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.025956284153005466, | |
| "grad_norm": 1.4901679754257202, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 3.3458, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0273224043715847, | |
| "grad_norm": 1.6833194494247437, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 3.7137, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.028688524590163935, | |
| "grad_norm": 1.7084633111953735, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 3.7297, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.030054644808743168, | |
| "grad_norm": 1.8367313146591187, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 3.8357, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.031420765027322405, | |
| "grad_norm": 1.7240302562713623, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 3.9129, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03278688524590164, | |
| "grad_norm": 2.0994315147399902, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 3.9074, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03415300546448088, | |
| "grad_norm": 2.9252614974975586, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 4.198, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03415300546448088, | |
| "eval_loss": 3.398573398590088, | |
| "eval_runtime": 3.4647, | |
| "eval_samples_per_second": 14.431, | |
| "eval_steps_per_second": 3.752, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03551912568306011, | |
| "grad_norm": 1.455446720123291, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 2.3439, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.036885245901639344, | |
| "grad_norm": 2.329031467437744, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 2.9435, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03825136612021858, | |
| "grad_norm": 2.5059032440185547, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 2.9663, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03961748633879782, | |
| "grad_norm": 1.9605844020843506, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 3.1745, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.040983606557377046, | |
| "grad_norm": 1.597434163093567, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 3.3009, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04234972677595628, | |
| "grad_norm": 1.3100905418395996, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 3.3497, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.04371584699453552, | |
| "grad_norm": 1.4777722358703613, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 3.3907, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.045081967213114756, | |
| "grad_norm": 1.580230712890625, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 3.6009, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.04644808743169399, | |
| "grad_norm": 1.8173338174819946, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 3.4578, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.04781420765027322, | |
| "grad_norm": 2.1014060974121094, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 3.507, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04918032786885246, | |
| "grad_norm": 2.4913907051086426, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 3.7169, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.050546448087431695, | |
| "grad_norm": 2.769925594329834, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 4.0094, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.05191256830601093, | |
| "grad_norm": 0.6865216493606567, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 2.4872, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.05327868852459016, | |
| "grad_norm": 0.6267939805984497, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 2.6732, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0546448087431694, | |
| "grad_norm": 0.74587482213974, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 2.8649, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.056010928961748634, | |
| "grad_norm": 0.9323634505271912, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 3.1053, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.05737704918032787, | |
| "grad_norm": 0.9466826915740967, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 3.1002, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.05874316939890711, | |
| "grad_norm": 0.9597004652023315, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 3.0931, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.060109289617486336, | |
| "grad_norm": 1.058807134628296, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 3.2562, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.06147540983606557, | |
| "grad_norm": 1.2648183107376099, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 3.4148, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.06284153005464481, | |
| "grad_norm": 1.4772535562515259, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 3.44, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.06420765027322405, | |
| "grad_norm": 1.4803715944290161, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 3.658, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.06557377049180328, | |
| "grad_norm": 1.6075665950775146, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 3.5905, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.06693989071038252, | |
| "grad_norm": 1.932875156402588, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 3.6877, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.06830601092896176, | |
| "grad_norm": 3.3861000537872314, | |
| "learning_rate": 1e-05, | |
| "loss": 4.0972, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06830601092896176, | |
| "eval_loss": 3.2531516551971436, | |
| "eval_runtime": 3.4586, | |
| "eval_samples_per_second": 14.457, | |
| "eval_steps_per_second": 3.759, | |
| "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": 5.971813667564421e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |