| { | |
| "best_metric": 3.432676315307617, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.009146306607063235, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001829261321412647, | |
| "grad_norm": 1.9110344648361206, | |
| "learning_rate": 5e-05, | |
| "loss": 3.6323, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001829261321412647, | |
| "eval_loss": 6.4708404541015625, | |
| "eval_runtime": 2.6694, | |
| "eval_samples_per_second": 18.731, | |
| "eval_steps_per_second": 4.87, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003658522642825294, | |
| "grad_norm": 1.928886890411377, | |
| "learning_rate": 0.0001, | |
| "loss": 4.427, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0005487783964237942, | |
| "grad_norm": 1.885818362236023, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 4.7624, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0007317045285650588, | |
| "grad_norm": 2.122727155685425, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 4.9093, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0009146306607063236, | |
| "grad_norm": 2.3126866817474365, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 4.9697, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0010975567928475883, | |
| "grad_norm": 2.9748995304107666, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 5.0934, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001280482924988853, | |
| "grad_norm": 3.3190455436706543, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 5.0183, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0014634090571301176, | |
| "grad_norm": 3.633790969848633, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 4.873, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0016463351892713823, | |
| "grad_norm": 3.4954895973205566, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 4.6961, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0018292613214126471, | |
| "grad_norm": 3.1350529193878174, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 4.7941, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002012187453553912, | |
| "grad_norm": 3.9131839275360107, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 4.3245, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0021951135856951767, | |
| "grad_norm": 4.561995029449463, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 4.2026, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.002378039717836441, | |
| "grad_norm": 5.815301895141602, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 3.5911, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.002560965849977706, | |
| "grad_norm": 5.602147579193115, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 3.6752, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0027438919821189704, | |
| "grad_norm": 3.8843131065368652, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 3.6851, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0029268181142602353, | |
| "grad_norm": 3.2248361110687256, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 3.7318, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0031097442464015, | |
| "grad_norm": 2.665513277053833, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 3.7105, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0032926703785427646, | |
| "grad_norm": 2.0910823345184326, | |
| "learning_rate": 7.75e-05, | |
| "loss": 3.5708, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0034755965106840294, | |
| "grad_norm": 1.4845154285430908, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 3.6131, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0036585226428252943, | |
| "grad_norm": 1.4835506677627563, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 3.584, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0038414487749665587, | |
| "grad_norm": 1.5968637466430664, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 3.7142, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.004024374907107824, | |
| "grad_norm": 1.9748867750167847, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 3.7735, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0042073010392490885, | |
| "grad_norm": 2.7007381916046143, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 3.7163, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.004390227171390353, | |
| "grad_norm": 2.6866607666015625, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 3.5792, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004573153303531617, | |
| "grad_norm": 4.762912273406982, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 4.3612, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004573153303531617, | |
| "eval_loss": 3.5562896728515625, | |
| "eval_runtime": 2.0393, | |
| "eval_samples_per_second": 24.518, | |
| "eval_steps_per_second": 6.375, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004756079435672882, | |
| "grad_norm": 1.803903341293335, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 3.0202, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.004939005567814147, | |
| "grad_norm": 1.4035038948059082, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 3.1542, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.005121931699955412, | |
| "grad_norm": 1.3655030727386475, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 3.2782, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.005304857832096677, | |
| "grad_norm": 1.1467270851135254, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 3.396, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.005487783964237941, | |
| "grad_norm": 1.1027382612228394, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 3.4175, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005670710096379206, | |
| "grad_norm": 1.5248521566390991, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 3.4381, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0058536362285204705, | |
| "grad_norm": 1.9056307077407837, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 3.4771, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.006036562360661735, | |
| "grad_norm": 1.7207236289978027, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 3.5574, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.006219488492803, | |
| "grad_norm": 1.2745652198791504, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 3.6236, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.006402414624944265, | |
| "grad_norm": 1.5298084020614624, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 3.5052, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.006585340757085529, | |
| "grad_norm": 1.6400824785232544, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 3.5871, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.006768266889226794, | |
| "grad_norm": 2.165523052215576, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 3.7025, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.006951193021368059, | |
| "grad_norm": 1.51387619972229, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 3.0254, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.007134119153509324, | |
| "grad_norm": 1.3941786289215088, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 3.1322, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.007317045285650589, | |
| "grad_norm": 1.2476261854171753, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 3.1812, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.007499971417791853, | |
| "grad_norm": 1.377185344696045, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 3.4018, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0076828975499331174, | |
| "grad_norm": 1.416702389717102, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 3.2872, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.007865823682074382, | |
| "grad_norm": 1.2533056735992432, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 3.4308, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.008048749814215647, | |
| "grad_norm": 1.3103725910186768, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 3.4037, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.008231675946356912, | |
| "grad_norm": 1.1992508172988892, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 3.5168, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.008414602078498177, | |
| "grad_norm": 1.243343710899353, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 3.4219, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.008597528210639442, | |
| "grad_norm": 1.248721718788147, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 3.3442, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.008780454342780707, | |
| "grad_norm": 1.4735393524169922, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 3.6574, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.00896338047492197, | |
| "grad_norm": 1.8419065475463867, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 3.504, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.009146306607063235, | |
| "grad_norm": 3.8599138259887695, | |
| "learning_rate": 1e-05, | |
| "loss": 3.868, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.009146306607063235, | |
| "eval_loss": 3.432676315307617, | |
| "eval_runtime": 2.0429, | |
| "eval_samples_per_second": 24.475, | |
| "eval_steps_per_second": 6.363, | |
| "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": 5.968083617316864e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |