| { | |
| "best_metric": 1.0231027603149414, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.05109535670945903, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0010219071341891805, | |
| "grad_norm": 0.3243594169616699, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0429, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010219071341891805, | |
| "eval_loss": 1.0704985857009888, | |
| "eval_runtime": 2.066, | |
| "eval_samples_per_second": 24.202, | |
| "eval_steps_per_second": 6.292, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002043814268378361, | |
| "grad_norm": 0.29733091592788696, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0394, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003065721402567542, | |
| "grad_norm": 0.19692915678024292, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 0.9919, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004087628536756722, | |
| "grad_norm": 0.21052394807338715, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 0.9055, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005109535670945903, | |
| "grad_norm": 0.15215978026390076, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.0328, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006131442805135084, | |
| "grad_norm": 0.08381917327642441, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.9929, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007153349939324264, | |
| "grad_norm": 0.15713754296302795, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.0356, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.008175257073513444, | |
| "grad_norm": 0.22464041411876678, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.976, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.009197164207702625, | |
| "grad_norm": 0.3136068880558014, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.0783, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.010219071341891806, | |
| "grad_norm": 0.21236161887645721, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.1129, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.011240978476080986, | |
| "grad_norm": 0.20021530985832214, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.16, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.012262885610270167, | |
| "grad_norm": 0.7468432188034058, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.2003, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.013284792744459347, | |
| "grad_norm": 0.12293215095996857, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.9661, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.014306699878648528, | |
| "grad_norm": 0.116572305560112, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.0391, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.015328607012837708, | |
| "grad_norm": 0.11617517471313477, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.0031, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.016350514147026887, | |
| "grad_norm": 0.14100442826747894, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.9627, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01737242128121607, | |
| "grad_norm": 0.08317362517118454, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.9225, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01839432841540525, | |
| "grad_norm": 0.08434411883354187, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.9577, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01941623554959443, | |
| "grad_norm": 0.07794798910617828, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.9331, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.020438142683783612, | |
| "grad_norm": 0.08238212764263153, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.0072, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.021460049817972792, | |
| "grad_norm": 0.11638768017292023, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.9893, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02248195695216197, | |
| "grad_norm": 0.12546801567077637, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.0059, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.02350386408635115, | |
| "grad_norm": 0.1414293348789215, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.1269, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.024525771220540334, | |
| "grad_norm": 0.1969396024942398, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.1024, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.025547678354729514, | |
| "grad_norm": 0.2868086099624634, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.2921, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.025547678354729514, | |
| "eval_loss": 1.027244210243225, | |
| "eval_runtime": 0.9918, | |
| "eval_samples_per_second": 50.414, | |
| "eval_steps_per_second": 13.108, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.026569585488918693, | |
| "grad_norm": 0.10399110615253448, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.9921, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.027591492623107877, | |
| "grad_norm": 0.11868777126073837, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.953, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.028613399757297056, | |
| "grad_norm": 0.08569394052028656, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 1.0039, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.029635306891486236, | |
| "grad_norm": 0.08266085386276245, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.9993, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.030657214025675415, | |
| "grad_norm": 0.08436281234025955, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.9719, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0316791211598646, | |
| "grad_norm": 0.07534889131784439, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.9922, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.032701028294053774, | |
| "grad_norm": 0.0886206105351448, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.9549, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.03372293542824296, | |
| "grad_norm": 0.12971074879169464, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.0573, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.03474484256243214, | |
| "grad_norm": 0.10268256813287735, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.0629, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.03576674969662132, | |
| "grad_norm": 0.13337336480617523, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.0963, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0367886568308105, | |
| "grad_norm": 0.16662007570266724, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.0929, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.03781056396499968, | |
| "grad_norm": 0.1939576119184494, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.1368, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.03883247109918886, | |
| "grad_norm": 0.10542629659175873, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.9937, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.03985437823337804, | |
| "grad_norm": 0.07947812229394913, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.9395, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.040876285367567225, | |
| "grad_norm": 0.07600011676549911, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 1.0002, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0418981925017564, | |
| "grad_norm": 0.08075827360153198, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.0617, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.042920099635945584, | |
| "grad_norm": 0.08019677549600601, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.0343, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.04394200677013477, | |
| "grad_norm": 0.0765736997127533, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.9314, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.04496391390432394, | |
| "grad_norm": 0.083722323179245, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.0294, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.045985821038513126, | |
| "grad_norm": 0.08264289796352386, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.9393, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0470077281727023, | |
| "grad_norm": 0.09311388432979584, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.0048, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.048029635306891486, | |
| "grad_norm": 0.11415554583072662, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.0739, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.04905154244108067, | |
| "grad_norm": 0.1320764273405075, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 1.0266, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.050073449575269845, | |
| "grad_norm": 0.16924385726451874, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.1562, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.05109535670945903, | |
| "grad_norm": 0.23526246845722198, | |
| "learning_rate": 1e-05, | |
| "loss": 1.2363, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05109535670945903, | |
| "eval_loss": 1.0231027603149414, | |
| "eval_runtime": 0.9849, | |
| "eval_samples_per_second": 50.766, | |
| "eval_steps_per_second": 13.199, | |
| "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": 8.33416392081408e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |