| { | |
| "best_metric": 0.7341717481613159, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.009366804046459348, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00018733608092918696, | |
| "grad_norm": 0.995975136756897, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7169, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00018733608092918696, | |
| "eval_loss": 1.0681145191192627, | |
| "eval_runtime": 386.6689, | |
| "eval_samples_per_second": 23.25, | |
| "eval_steps_per_second": 2.907, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003746721618583739, | |
| "grad_norm": 1.6124424934387207, | |
| "learning_rate": 4e-05, | |
| "loss": 0.7643, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0005620082427875609, | |
| "grad_norm": 0.8237774968147278, | |
| "learning_rate": 6e-05, | |
| "loss": 0.7519, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0007493443237167478, | |
| "grad_norm": 0.6065216064453125, | |
| "learning_rate": 8e-05, | |
| "loss": 0.7889, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0009366804046459348, | |
| "grad_norm": 0.5464012622833252, | |
| "learning_rate": 0.0001, | |
| "loss": 0.791, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0011240164855751218, | |
| "grad_norm": 0.5549437999725342, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.8423, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0013113525665043087, | |
| "grad_norm": 0.7405556440353394, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 0.7497, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0014986886474334957, | |
| "grad_norm": 0.6293168663978577, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.7415, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0016860247283626826, | |
| "grad_norm": 0.6109768748283386, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 0.7327, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0018733608092918695, | |
| "grad_norm": 0.43437162041664124, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.7141, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0020606968902210565, | |
| "grad_norm": 0.45942363142967224, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 0.7687, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0022480329711502436, | |
| "grad_norm": 0.5360703468322754, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.8617, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0024353690520794303, | |
| "grad_norm": 0.5143129229545593, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 0.6849, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0026227051330086175, | |
| "grad_norm": 0.5019359588623047, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.8373, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.002810041213937804, | |
| "grad_norm": 0.4394899904727936, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.7991, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0029973772948669914, | |
| "grad_norm": 0.4200367331504822, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 0.7756, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0031847133757961785, | |
| "grad_norm": 0.4958840310573578, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 0.8609, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0033720494567253652, | |
| "grad_norm": 0.46299058198928833, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 0.7695, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0035593855376545524, | |
| "grad_norm": 0.47689881920814514, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 0.8458, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.003746721618583739, | |
| "grad_norm": 0.5088708996772766, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.7982, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003934057699512926, | |
| "grad_norm": 0.4710184633731842, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 0.7445, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.004121393780442113, | |
| "grad_norm": 0.5304281115531921, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 0.7787, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0043087298613713005, | |
| "grad_norm": 0.43736979365348816, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.7815, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.004496065942300487, | |
| "grad_norm": 0.439891517162323, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 0.6483, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004683402023229674, | |
| "grad_norm": 0.5140251517295837, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 0.7267, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004683402023229674, | |
| "eval_loss": 0.7544652819633484, | |
| "eval_runtime": 388.632, | |
| "eval_samples_per_second": 23.132, | |
| "eval_steps_per_second": 2.892, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004870738104158861, | |
| "grad_norm": 0.5454508066177368, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 0.8716, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.005058074185088048, | |
| "grad_norm": 0.5985477566719055, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 0.8829, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.005245410266017235, | |
| "grad_norm": 0.47764837741851807, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 0.7194, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.005432746346946422, | |
| "grad_norm": 0.5462313294410706, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 0.7651, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.005620082427875608, | |
| "grad_norm": 0.617461085319519, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.8141, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005807418508804796, | |
| "grad_norm": 0.5380529165267944, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 0.7566, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.005994754589733983, | |
| "grad_norm": 0.6068387627601624, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.93, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.006182090670663169, | |
| "grad_norm": 0.6764094829559326, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 0.8094, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.006369426751592357, | |
| "grad_norm": 0.5809192657470703, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 0.8799, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.006556762832521544, | |
| "grad_norm": 0.5970680117607117, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.8053, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0067440989134507304, | |
| "grad_norm": 0.6570981740951538, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 0.7297, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.006931434994379917, | |
| "grad_norm": 0.6267858743667603, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 0.8391, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.007118771075309105, | |
| "grad_norm": 0.7596061825752258, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 0.7552, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0073061071562382915, | |
| "grad_norm": 0.6376911401748657, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 0.8012, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.007493443237167478, | |
| "grad_norm": 0.7316814064979553, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 0.8273, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.007680779318096666, | |
| "grad_norm": 0.7131224274635315, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.7949, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.007868115399025852, | |
| "grad_norm": 0.8190371990203857, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 0.8927, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.00805545147995504, | |
| "grad_norm": 0.7501890659332275, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 0.8301, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.008242787560884226, | |
| "grad_norm": 0.7030087113380432, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 0.6574, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.008430123641813413, | |
| "grad_norm": 1.0874273777008057, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 1.0137, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.008617459722742601, | |
| "grad_norm": 1.1512134075164795, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 0.8957, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.008804795803671788, | |
| "grad_norm": 0.7169827222824097, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 0.7942, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.008992131884600974, | |
| "grad_norm": 0.8034902215003967, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 0.6321, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.009179467965530161, | |
| "grad_norm": 0.9918283224105835, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 0.6772, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.009366804046459348, | |
| "grad_norm": 1.1916050910949707, | |
| "learning_rate": 0.0, | |
| "loss": 0.6989, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.009366804046459348, | |
| "eval_loss": 0.7341717481613159, | |
| "eval_runtime": 388.3384, | |
| "eval_samples_per_second": 23.15, | |
| "eval_steps_per_second": 2.894, | |
| "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": 5, | |
| "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": 4.261550859957043e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |