| { | |
| "best_metric": 3.5564169883728027, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 2.2727272727272725, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.045454545454545456, | |
| "grad_norm": 1.5379183292388916, | |
| "learning_rate": 5e-05, | |
| "loss": 3.7031, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.045454545454545456, | |
| "eval_loss": 4.0469136238098145, | |
| "eval_runtime": 5.7444, | |
| "eval_samples_per_second": 8.704, | |
| "eval_steps_per_second": 2.263, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.09090909090909091, | |
| "grad_norm": 1.5742955207824707, | |
| "learning_rate": 0.0001, | |
| "loss": 3.7189, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.13636363636363635, | |
| "grad_norm": 1.4300661087036133, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 3.7855, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.18181818181818182, | |
| "grad_norm": 0.657507598400116, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 3.8196, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.22727272727272727, | |
| "grad_norm": 1.8193498849868774, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 3.8961, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2727272727272727, | |
| "grad_norm": 2.063701868057251, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 3.637, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3181818181818182, | |
| "grad_norm": 1.1502482891082764, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 3.4455, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.36363636363636365, | |
| "grad_norm": 0.3972413241863251, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 3.4163, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.4090909090909091, | |
| "grad_norm": 0.4920276999473572, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 3.5949, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.45454545454545453, | |
| "grad_norm": 0.7862594723701477, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 3.656, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.6688703298568726, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 3.4889, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.5454545454545454, | |
| "grad_norm": 0.5711549520492554, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 3.3872, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5909090909090909, | |
| "grad_norm": 0.4735369086265564, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 3.4266, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.6363636363636364, | |
| "grad_norm": 0.42151445150375366, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 3.4877, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.6818181818181818, | |
| "grad_norm": 0.5356363654136658, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 3.5777, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": 0.6514257788658142, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 3.3887, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.7727272727272727, | |
| "grad_norm": 0.7753776907920837, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 3.4032, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.8181818181818182, | |
| "grad_norm": 0.680530309677124, | |
| "learning_rate": 7.75e-05, | |
| "loss": 3.4173, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.8636363636363636, | |
| "grad_norm": 0.49786874651908875, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 3.4205, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.9090909090909091, | |
| "grad_norm": 0.4995076060295105, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 3.5338, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.9545454545454546, | |
| "grad_norm": 0.6462302207946777, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 3.6464, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.32485461235046387, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 3.358, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.0454545454545454, | |
| "grad_norm": 0.31137824058532715, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 3.3269, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.0909090909090908, | |
| "grad_norm": 0.3454802632331848, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 3.3085, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.1363636363636362, | |
| "grad_norm": 0.3748566806316376, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 3.3711, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.1363636363636362, | |
| "eval_loss": 3.6008565425872803, | |
| "eval_runtime": 4.8752, | |
| "eval_samples_per_second": 10.256, | |
| "eval_steps_per_second": 2.667, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.1818181818181819, | |
| "grad_norm": 0.4389213025569916, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 3.4342, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.2272727272727273, | |
| "grad_norm": 0.506675124168396, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 3.5071, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.2727272727272727, | |
| "grad_norm": 0.33202725648880005, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 3.2895, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.3181818181818181, | |
| "grad_norm": 0.41267460584640503, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 3.2902, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.3636363636363638, | |
| "grad_norm": 0.3891868591308594, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 3.2911, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.4090909090909092, | |
| "grad_norm": 0.40933117270469666, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 3.4391, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.4545454545454546, | |
| "grad_norm": 0.4993307888507843, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 3.4417, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 0.355300635099411, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 3.3338, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.5454545454545454, | |
| "grad_norm": 0.3318493366241455, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 3.2812, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.5909090909090908, | |
| "grad_norm": 0.3499109148979187, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 3.2823, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.6363636363636362, | |
| "grad_norm": 0.3723719120025635, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 3.3055, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.6818181818181817, | |
| "grad_norm": 0.46838635206222534, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 3.4007, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.7272727272727273, | |
| "grad_norm": 0.3957988917827606, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 3.3339, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.7727272727272727, | |
| "grad_norm": 0.2677713632583618, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 3.2229, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.8181818181818183, | |
| "grad_norm": 0.30480334162712097, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 3.2728, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.8636363636363638, | |
| "grad_norm": 0.3701198995113373, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 3.3106, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.9090909090909092, | |
| "grad_norm": 0.4461487829685211, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 3.4646, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.9545454545454546, | |
| "grad_norm": 0.61518394947052, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 3.5355, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.3342447578907013, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 3.1614, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.0454545454545454, | |
| "grad_norm": 0.25999006628990173, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 3.229, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.090909090909091, | |
| "grad_norm": 0.3094271719455719, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 3.2783, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.1363636363636362, | |
| "grad_norm": 0.3765052855014801, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 3.1472, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.1818181818181817, | |
| "grad_norm": 0.4353832006454468, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 3.3006, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.227272727272727, | |
| "grad_norm": 0.509846031665802, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 3.3415, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.2727272727272725, | |
| "grad_norm": 0.2852264940738678, | |
| "learning_rate": 1e-05, | |
| "loss": 3.2566, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.2727272727272725, | |
| "eval_loss": 3.5564169883728027, | |
| "eval_runtime": 4.8889, | |
| "eval_samples_per_second": 10.227, | |
| "eval_steps_per_second": 2.659, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 6.94535732978516e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |