| { | |
| "best_metric": 1.020423412322998, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.10544352181362858, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0021088704362725716, | |
| "grad_norm": 1.0445363521575928, | |
| "learning_rate": 5e-05, | |
| "loss": 2.0005, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0021088704362725716, | |
| "eval_loss": 2.172279119491577, | |
| "eval_runtime": 91.0927, | |
| "eval_samples_per_second": 35.074, | |
| "eval_steps_per_second": 4.391, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004217740872545143, | |
| "grad_norm": 1.0849013328552246, | |
| "learning_rate": 0.0001, | |
| "loss": 2.0592, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006326611308817715, | |
| "grad_norm": 1.02006995677948, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.047, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.008435481745090286, | |
| "grad_norm": 0.9143255949020386, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.8777, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.010544352181362857, | |
| "grad_norm": 0.7838174104690552, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.7968, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01265322261763543, | |
| "grad_norm": 0.9264847040176392, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.7519, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.014762093053908, | |
| "grad_norm": 0.7748655676841736, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.6999, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.016870963490180572, | |
| "grad_norm": 0.752051055431366, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.6492, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.018979833926453145, | |
| "grad_norm": 0.6525676846504211, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.5985, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.021088704362725714, | |
| "grad_norm": 0.6811321377754211, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.5414, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.023197574798998286, | |
| "grad_norm": 0.6379256248474121, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.4974, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.02530644523527086, | |
| "grad_norm": 0.6451159715652466, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.4877, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02741531567154343, | |
| "grad_norm": 0.5045467615127563, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.3994, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.029524186107816, | |
| "grad_norm": 0.4902452528476715, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.4029, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03163305654408857, | |
| "grad_norm": 0.4506430923938751, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.3466, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.033741926980361145, | |
| "grad_norm": 0.44114139676094055, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.3213, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.03585079741663372, | |
| "grad_norm": 0.444820761680603, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.3173, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.03795966785290629, | |
| "grad_norm": 0.47539570927619934, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.2578, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.040068538289178855, | |
| "grad_norm": 0.42036089301109314, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.2263, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04217740872545143, | |
| "grad_norm": 0.48343217372894287, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.2371, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.044286279161724, | |
| "grad_norm": 0.46945393085479736, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.2132, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.04639514959799657, | |
| "grad_norm": 0.4912544786930084, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.1808, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.048504020034269145, | |
| "grad_norm": 0.5027343034744263, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.1536, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.05061289047054172, | |
| "grad_norm": 0.4939061999320984, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.1453, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05272176090681429, | |
| "grad_norm": 0.5463296175003052, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.1425, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05272176090681429, | |
| "eval_loss": 1.1423113346099854, | |
| "eval_runtime": 91.1944, | |
| "eval_samples_per_second": 35.035, | |
| "eval_steps_per_second": 4.386, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05483063134308686, | |
| "grad_norm": 0.4752199649810791, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1945, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.05693950177935943, | |
| "grad_norm": 0.4596542418003082, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.169, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.059048372215632, | |
| "grad_norm": 0.4172233045101166, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.1607, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.06115724265190457, | |
| "grad_norm": 0.4047132432460785, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.0959, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.06326611308817714, | |
| "grad_norm": 0.4105985164642334, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.1074, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06537498352444972, | |
| "grad_norm": 0.4306783378124237, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.0803, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.06748385396072229, | |
| "grad_norm": 0.5062503814697266, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.0811, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.06959272439699486, | |
| "grad_norm": 0.4912147521972656, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.0655, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.07170159483326743, | |
| "grad_norm": 0.508456289768219, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.0712, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.07381046526954001, | |
| "grad_norm": 0.4889466464519501, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.023, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.07591933570581258, | |
| "grad_norm": 0.5558086633682251, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.0458, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.07802820614208515, | |
| "grad_norm": 0.5452104806900024, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.0569, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.08013707657835771, | |
| "grad_norm": 0.4432591497898102, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.0839, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.08224594701463028, | |
| "grad_norm": 0.46508991718292236, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.0994, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.08435481745090286, | |
| "grad_norm": 0.4606338143348694, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.0723, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08646368788717543, | |
| "grad_norm": 0.49141889810562134, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.0715, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.088572558323448, | |
| "grad_norm": 0.4679344594478607, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.0741, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.09068142875972057, | |
| "grad_norm": 0.46846526861190796, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.0464, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.09279029919599315, | |
| "grad_norm": 0.4298027455806732, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.0106, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.09489916963226572, | |
| "grad_norm": 0.4400997757911682, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.0253, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.09700804006853829, | |
| "grad_norm": 0.48933765292167664, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.0295, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.09911691050481086, | |
| "grad_norm": 0.4610632359981537, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.0044, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.10122578094108343, | |
| "grad_norm": 0.482964426279068, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.9927, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.10333465137735601, | |
| "grad_norm": 0.5675437450408936, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.9708, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.10544352181362858, | |
| "grad_norm": 0.6064045429229736, | |
| "learning_rate": 0.0, | |
| "loss": 1.0077, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.10544352181362858, | |
| "eval_loss": 1.020423412322998, | |
| "eval_runtime": 91.108, | |
| "eval_samples_per_second": 35.068, | |
| "eval_steps_per_second": 4.39, | |
| "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": 5.305284264198144e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |