| { | |
| "best_metric": 0.4201970100402832, | |
| "best_model_checkpoint": "/workspace/plateer_classifier_v0.1_result/checkpoint-15000", | |
| "epoch": 0.08784117144986245, | |
| "eval_steps": 5000, | |
| "global_step": 15000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0014640195241643742, | |
| "grad_norm": 50.05304718017578, | |
| "learning_rate": 4.880000000000001e-06, | |
| "loss": 4.3958, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.0029280390483287485, | |
| "grad_norm": 48.363304138183594, | |
| "learning_rate": 9.88e-06, | |
| "loss": 1.6496, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.004392058572493123, | |
| "grad_norm": 54.546974182128906, | |
| "learning_rate": 1.488e-05, | |
| "loss": 0.8787, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.005856078096657497, | |
| "grad_norm": 50.317874908447266, | |
| "learning_rate": 1.9880000000000003e-05, | |
| "loss": 0.7721, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.007320097620821872, | |
| "grad_norm": 62.48823928833008, | |
| "learning_rate": 2.488e-05, | |
| "loss": 0.7047, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.008784117144986246, | |
| "grad_norm": 44.35001754760742, | |
| "learning_rate": 2.9880000000000002e-05, | |
| "loss": 0.6749, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.01024813666915062, | |
| "grad_norm": 36.486793518066406, | |
| "learning_rate": 3.4880000000000005e-05, | |
| "loss": 0.6409, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.011712156193314994, | |
| "grad_norm": 47.03588104248047, | |
| "learning_rate": 3.988e-05, | |
| "loss": 0.6406, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.013176175717479368, | |
| "grad_norm": 31.227832794189453, | |
| "learning_rate": 4.488e-05, | |
| "loss": 0.6149, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.014640195241643743, | |
| "grad_norm": 39.8408317565918, | |
| "learning_rate": 4.9880000000000004e-05, | |
| "loss": 0.5956, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.016104214765808117, | |
| "grad_norm": 41.118736267089844, | |
| "learning_rate": 5.4879999999999996e-05, | |
| "loss": 0.5905, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 0.017568234289972492, | |
| "grad_norm": 29.624338150024414, | |
| "learning_rate": 5.988e-05, | |
| "loss": 0.5608, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.019032253814136865, | |
| "grad_norm": 22.993818283081055, | |
| "learning_rate": 6.488e-05, | |
| "loss": 0.5614, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 0.02049627333830124, | |
| "grad_norm": 19.964269638061523, | |
| "learning_rate": 6.988e-05, | |
| "loss": 0.5569, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.021960292862465612, | |
| "grad_norm": 36.538047790527344, | |
| "learning_rate": 7.488e-05, | |
| "loss": 0.5316, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 0.023424312386629988, | |
| "grad_norm": 37.63505935668945, | |
| "learning_rate": 7.988e-05, | |
| "loss": 0.5364, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.024888331910794363, | |
| "grad_norm": 25.934967041015625, | |
| "learning_rate": 8.486000000000001e-05, | |
| "loss": 0.5234, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 0.026352351434958735, | |
| "grad_norm": 24.810028076171875, | |
| "learning_rate": 8.986e-05, | |
| "loss": 0.5155, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.02781637095912311, | |
| "grad_norm": 32.76811981201172, | |
| "learning_rate": 9.484e-05, | |
| "loss": 0.5022, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 0.029280390483287486, | |
| "grad_norm": 27.094772338867188, | |
| "learning_rate": 9.984e-05, | |
| "loss": 0.5023, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.029280390483287486, | |
| "eval_accuracy": 0.8572352668691132, | |
| "eval_loss": 0.5044249296188354, | |
| "eval_runtime": 11541.1431, | |
| "eval_samples_per_second": 210.432, | |
| "eval_steps_per_second": 6.576, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.03074441000745186, | |
| "grad_norm": 24.74563217163086, | |
| "learning_rate": 0.00010484, | |
| "loss": 0.5073, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 0.032208429531616234, | |
| "grad_norm": 17.229019165039062, | |
| "learning_rate": 0.00010984, | |
| "loss": 0.4932, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.03367244905578061, | |
| "grad_norm": 23.318979263305664, | |
| "learning_rate": 0.00011484000000000002, | |
| "loss": 0.504, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 0.035136468579944985, | |
| "grad_norm": 22.271846771240234, | |
| "learning_rate": 0.00011983999999999999, | |
| "loss": 0.4817, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.036600488104109354, | |
| "grad_norm": 24.304887771606445, | |
| "learning_rate": 0.00012484, | |
| "loss": 0.4966, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 0.03806450762827373, | |
| "grad_norm": 23.76158905029297, | |
| "learning_rate": 0.00012984000000000002, | |
| "loss": 0.4899, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.039528527152438105, | |
| "grad_norm": 20.765274047851562, | |
| "learning_rate": 0.00013484, | |
| "loss": 0.4773, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 0.04099254667660248, | |
| "grad_norm": 12.793950080871582, | |
| "learning_rate": 0.00013982000000000003, | |
| "loss": 0.4781, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.042456566200766856, | |
| "grad_norm": 14.128210067749023, | |
| "learning_rate": 0.00014482, | |
| "loss": 0.4687, | |
| "step": 7250 | |
| }, | |
| { | |
| "epoch": 0.043920585724931224, | |
| "grad_norm": 22.348928451538086, | |
| "learning_rate": 0.00014982, | |
| "loss": 0.4722, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.0453846052490956, | |
| "grad_norm": 17.29800796508789, | |
| "learning_rate": 0.00015480000000000002, | |
| "loss": 0.4692, | |
| "step": 7750 | |
| }, | |
| { | |
| "epoch": 0.046848624773259975, | |
| "grad_norm": 11.0147066116333, | |
| "learning_rate": 0.0001598, | |
| "loss": 0.4689, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.04831264429742435, | |
| "grad_norm": 11.713265419006348, | |
| "learning_rate": 0.0001648, | |
| "loss": 0.4788, | |
| "step": 8250 | |
| }, | |
| { | |
| "epoch": 0.049776663821588726, | |
| "grad_norm": 12.367693901062012, | |
| "learning_rate": 0.0001698, | |
| "loss": 0.4697, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.0512406833457531, | |
| "grad_norm": 8.11889934539795, | |
| "learning_rate": 0.00017480000000000002, | |
| "loss": 0.4696, | |
| "step": 8750 | |
| }, | |
| { | |
| "epoch": 0.05270470286991747, | |
| "grad_norm": 12.321019172668457, | |
| "learning_rate": 0.0001798, | |
| "loss": 0.461, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.054168722394081846, | |
| "grad_norm": 15.612183570861816, | |
| "learning_rate": 0.00018480000000000002, | |
| "loss": 0.4646, | |
| "step": 9250 | |
| }, | |
| { | |
| "epoch": 0.05563274191824622, | |
| "grad_norm": 10.72978687286377, | |
| "learning_rate": 0.0001898, | |
| "loss": 0.4673, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.0570967614424106, | |
| "grad_norm": 8.815441131591797, | |
| "learning_rate": 0.0001948, | |
| "loss": 0.4472, | |
| "step": 9750 | |
| }, | |
| { | |
| "epoch": 0.05856078096657497, | |
| "grad_norm": 8.681705474853516, | |
| "learning_rate": 0.0001998, | |
| "loss": 0.4629, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.05856078096657497, | |
| "eval_accuracy": 0.8688706572649133, | |
| "eval_loss": 0.457188218832016, | |
| "eval_runtime": 11537.8227, | |
| "eval_samples_per_second": 210.492, | |
| "eval_steps_per_second": 6.578, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.06002480049073934, | |
| "grad_norm": 13.643828392028809, | |
| "learning_rate": 0.0001997014219778306, | |
| "loss": 0.456, | |
| "step": 10250 | |
| }, | |
| { | |
| "epoch": 0.06148882001490372, | |
| "grad_norm": 13.211404800415039, | |
| "learning_rate": 0.00019939040320473745, | |
| "loss": 0.4666, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.06295283953906809, | |
| "grad_norm": 11.1001615524292, | |
| "learning_rate": 0.00019907938443164432, | |
| "loss": 0.4495, | |
| "step": 10750 | |
| }, | |
| { | |
| "epoch": 0.06441685906323247, | |
| "grad_norm": 8.222249984741211, | |
| "learning_rate": 0.00019876836565855117, | |
| "loss": 0.4483, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.06588087858739684, | |
| "grad_norm": 13.589752197265625, | |
| "learning_rate": 0.0001984585909605504, | |
| "loss": 0.4438, | |
| "step": 11250 | |
| }, | |
| { | |
| "epoch": 0.06734489811156122, | |
| "grad_norm": 9.988068580627441, | |
| "learning_rate": 0.00019814757218745724, | |
| "loss": 0.447, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.0688089176357256, | |
| "grad_norm": 8.311960220336914, | |
| "learning_rate": 0.0001978365534143641, | |
| "loss": 0.4476, | |
| "step": 11750 | |
| }, | |
| { | |
| "epoch": 0.07027293715988997, | |
| "grad_norm": 8.099685668945312, | |
| "learning_rate": 0.00019752553464127094, | |
| "loss": 0.4477, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.07173695668405435, | |
| "grad_norm": 8.23130989074707, | |
| "learning_rate": 0.00019721451586817782, | |
| "loss": 0.4385, | |
| "step": 12250 | |
| }, | |
| { | |
| "epoch": 0.07320097620821871, | |
| "grad_norm": 10.875362396240234, | |
| "learning_rate": 0.00019690349709508467, | |
| "loss": 0.4345, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.07466499573238308, | |
| "grad_norm": 9.479572296142578, | |
| "learning_rate": 0.00019659247832199152, | |
| "loss": 0.4345, | |
| "step": 12750 | |
| }, | |
| { | |
| "epoch": 0.07612901525654746, | |
| "grad_norm": 11.883151054382324, | |
| "learning_rate": 0.0001962814595488984, | |
| "loss": 0.4241, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.07759303478071183, | |
| "grad_norm": 8.15208911895752, | |
| "learning_rate": 0.00019597044077580524, | |
| "loss": 0.4335, | |
| "step": 13250 | |
| }, | |
| { | |
| "epoch": 0.07905705430487621, | |
| "grad_norm": 9.323240280151367, | |
| "learning_rate": 0.0001956594220027121, | |
| "loss": 0.4396, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.08052107382904058, | |
| "grad_norm": 7.250824928283691, | |
| "learning_rate": 0.00019534840322961897, | |
| "loss": 0.4376, | |
| "step": 13750 | |
| }, | |
| { | |
| "epoch": 0.08198509335320496, | |
| "grad_norm": 12.220071792602539, | |
| "learning_rate": 0.0001950373844565258, | |
| "loss": 0.4323, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.08344911287736934, | |
| "grad_norm": 8.460916519165039, | |
| "learning_rate": 0.00019472636568343266, | |
| "loss": 0.4271, | |
| "step": 14250 | |
| }, | |
| { | |
| "epoch": 0.08491313240153371, | |
| "grad_norm": 6.110500812530518, | |
| "learning_rate": 0.0001944153469103395, | |
| "loss": 0.4253, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.08637715192569809, | |
| "grad_norm": 10.618386268615723, | |
| "learning_rate": 0.00019410432813724636, | |
| "loss": 0.427, | |
| "step": 14750 | |
| }, | |
| { | |
| "epoch": 0.08784117144986245, | |
| "grad_norm": 9.827556610107422, | |
| "learning_rate": 0.00019379330936415324, | |
| "loss": 0.4254, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.08784117144986245, | |
| "eval_accuracy": 0.877075711565186, | |
| "eval_loss": 0.4201970100402832, | |
| "eval_runtime": 11537.2443, | |
| "eval_samples_per_second": 210.503, | |
| "eval_steps_per_second": 6.578, | |
| "step": 15000 | |
| } | |
| ], | |
| "logging_steps": 250, | |
| "max_steps": 170762, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.8871669372931277e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |