| { | |
| "best_metric": 0.9089703559875488, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.6717044500419815, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01343408900083963, | |
| "grad_norm": 0.8362644910812378, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1136, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01343408900083963, | |
| "eval_loss": 1.1835139989852905, | |
| "eval_runtime": 1.074, | |
| "eval_samples_per_second": 46.557, | |
| "eval_steps_per_second": 12.105, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02686817800167926, | |
| "grad_norm": 1.0008957386016846, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1574, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04030226700251889, | |
| "grad_norm": 0.8080355525016785, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 1.118, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05373635600335852, | |
| "grad_norm": 0.7615368366241455, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.0521, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06717044500419815, | |
| "grad_norm": 0.7490801811218262, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.0336, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08060453400503778, | |
| "grad_norm": 0.707514226436615, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.0098, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09403862300587741, | |
| "grad_norm": 0.6249326467514038, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.9947, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.10747271200671704, | |
| "grad_norm": 0.5083645582199097, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.9741, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.12090680100755667, | |
| "grad_norm": 0.4019154906272888, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.9344, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1343408900083963, | |
| "grad_norm": 0.3534398078918457, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.9608, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14777497900923595, | |
| "grad_norm": 0.36086758971214294, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.9205, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.16120906801007556, | |
| "grad_norm": 0.3750108480453491, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.9329, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1746431570109152, | |
| "grad_norm": 0.33276858925819397, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.9355, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.18807724601175482, | |
| "grad_norm": 0.3458476960659027, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.9559, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.20151133501259447, | |
| "grad_norm": 0.27732521295547485, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.9445, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.21494542401343408, | |
| "grad_norm": 0.24506236612796783, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.9247, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.22837951301427373, | |
| "grad_norm": 0.25953516364097595, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.9535, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.24181360201511334, | |
| "grad_norm": 0.2728007435798645, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.9509, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.25524769101595296, | |
| "grad_norm": 0.26726973056793213, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.9021, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2686817800167926, | |
| "grad_norm": 0.27751967310905457, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.9273, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.28211586901763225, | |
| "grad_norm": 0.2526088058948517, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.9206, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.2955499580184719, | |
| "grad_norm": 0.26598045229911804, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.9472, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3089840470193115, | |
| "grad_norm": 0.23789013922214508, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.9241, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3224181360201511, | |
| "grad_norm": 0.2451629936695099, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.9206, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.33585222502099077, | |
| "grad_norm": 0.2759345471858978, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.9514, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.33585222502099077, | |
| "eval_loss": 0.922303318977356, | |
| "eval_runtime": 0.5959, | |
| "eval_samples_per_second": 83.903, | |
| "eval_steps_per_second": 21.815, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3492863140218304, | |
| "grad_norm": 0.2772812247276306, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.9499, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.36272040302267, | |
| "grad_norm": 0.2742224931716919, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.9397, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.37615449202350965, | |
| "grad_norm": 0.249447762966156, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.915, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.3895885810243493, | |
| "grad_norm": 0.24550966918468475, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.9255, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.40302267002518893, | |
| "grad_norm": 0.22773662209510803, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.8901, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4164567590260285, | |
| "grad_norm": 0.22250418365001678, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.9029, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.42989084802686817, | |
| "grad_norm": 0.2120346873998642, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.9311, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.4433249370277078, | |
| "grad_norm": 0.22748982906341553, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.8937, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.45675902602854745, | |
| "grad_norm": 0.24521538615226746, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.8982, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.47019311502938704, | |
| "grad_norm": 0.2516072690486908, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.9221, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4836272040302267, | |
| "grad_norm": 0.23325960338115692, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.8955, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.49706129303106633, | |
| "grad_norm": 0.25947290658950806, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.8837, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5104953820319059, | |
| "grad_norm": 0.22557468712329865, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.9096, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5239294710327456, | |
| "grad_norm": 0.20343045890331268, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.9161, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5373635600335852, | |
| "grad_norm": 0.20457938313484192, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.9176, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5507976490344249, | |
| "grad_norm": 0.20346155762672424, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.9319, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5642317380352645, | |
| "grad_norm": 0.20841321349143982, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.8758, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5776658270361041, | |
| "grad_norm": 0.20341482758522034, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.8818, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5910999160369438, | |
| "grad_norm": 0.20321235060691833, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.9079, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6045340050377834, | |
| "grad_norm": 0.20054325461387634, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.894, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.617968094038623, | |
| "grad_norm": 0.21549059450626373, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.8953, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6314021830394626, | |
| "grad_norm": 0.2093229442834854, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.8795, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6448362720403022, | |
| "grad_norm": 0.21790167689323425, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.9229, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6582703610411419, | |
| "grad_norm": 0.22668731212615967, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.8744, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6717044500419815, | |
| "grad_norm": 0.2757410407066345, | |
| "learning_rate": 1e-05, | |
| "loss": 0.9385, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6717044500419815, | |
| "eval_loss": 0.9089703559875488, | |
| "eval_runtime": 0.5908, | |
| "eval_samples_per_second": 84.633, | |
| "eval_steps_per_second": 22.004, | |
| "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": 2.95300912644096e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |