| { | |
| "best_metric": 6.828060150146484, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.09704027171276079, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0019408054342552159, | |
| "grad_norm": 0.4789515733718872, | |
| "learning_rate": 2e-05, | |
| "loss": 6.9316, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0019408054342552159, | |
| "eval_loss": 6.919858932495117, | |
| "eval_runtime": 1.137, | |
| "eval_samples_per_second": 763.418, | |
| "eval_steps_per_second": 95.867, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0038816108685104317, | |
| "grad_norm": 0.45944270491600037, | |
| "learning_rate": 4e-05, | |
| "loss": 6.935, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005822416302765648, | |
| "grad_norm": 0.4508989453315735, | |
| "learning_rate": 6e-05, | |
| "loss": 6.9345, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0077632217370208634, | |
| "grad_norm": 0.47248098254203796, | |
| "learning_rate": 8e-05, | |
| "loss": 6.9324, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.009704027171276079, | |
| "grad_norm": 0.4529155492782593, | |
| "learning_rate": 0.0001, | |
| "loss": 6.9321, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.011644832605531296, | |
| "grad_norm": 0.4459758400917053, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 6.9296, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.013585638039786511, | |
| "grad_norm": 0.4499610364437103, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 6.9246, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.015526443474041727, | |
| "grad_norm": 0.46261221170425415, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 6.9182, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.017467248908296942, | |
| "grad_norm": 0.4620356559753418, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 6.9153, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.019408054342552158, | |
| "grad_norm": 0.4698457419872284, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 6.9106, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.021348859776807377, | |
| "grad_norm": 0.4636442959308624, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 6.9074, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.023289665211062592, | |
| "grad_norm": 0.4605291187763214, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 6.901, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.025230470645317808, | |
| "grad_norm": 0.4645829200744629, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 6.8961, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.027171276079573023, | |
| "grad_norm": 0.47509416937828064, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 6.8949, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.02911208151382824, | |
| "grad_norm": 0.4713204503059387, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 6.8898, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.031052886948083454, | |
| "grad_norm": 0.4826659858226776, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 6.8853, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.03299369238233867, | |
| "grad_norm": 0.4891706705093384, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 6.8812, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.034934497816593885, | |
| "grad_norm": 0.45633330941200256, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 6.8807, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.036875303250849104, | |
| "grad_norm": 0.45540496706962585, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 6.8775, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.038816108685104316, | |
| "grad_norm": 0.4875425696372986, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 6.8691, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.040756914119359534, | |
| "grad_norm": 0.45287904143333435, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 6.8747, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.04269771955361475, | |
| "grad_norm": 0.46057406067848206, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 6.8664, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.044638524987869965, | |
| "grad_norm": 0.44480112195014954, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 6.865, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.046579330422125184, | |
| "grad_norm": 0.4642225503921509, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 6.8566, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.048520135856380396, | |
| "grad_norm": 0.42264512181282043, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 6.8612, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.048520135856380396, | |
| "eval_loss": 6.847862243652344, | |
| "eval_runtime": 1.1078, | |
| "eval_samples_per_second": 783.548, | |
| "eval_steps_per_second": 98.395, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.050460941290635615, | |
| "grad_norm": 0.3825906813144684, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 6.8667, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.05240174672489083, | |
| "grad_norm": 0.39277198910713196, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 6.8628, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.054342552159146046, | |
| "grad_norm": 0.39206662774086, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 6.8594, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.056283357593401265, | |
| "grad_norm": 0.3919509947299957, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 6.8515, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.05822416302765648, | |
| "grad_norm": 0.40495046973228455, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 6.8458, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.060164968461911696, | |
| "grad_norm": 0.4313710331916809, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 6.8364, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.06210577389616691, | |
| "grad_norm": 0.46062034368515015, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 6.8315, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.06404657933042213, | |
| "grad_norm": 0.47267451882362366, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 6.8277, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.06598738476467735, | |
| "grad_norm": 1.8254433870315552, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 6.8264, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.06792819019893255, | |
| "grad_norm": 1.8017712831497192, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 6.8216, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.06986899563318777, | |
| "grad_norm": 1.805820107460022, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 6.8203, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.07180980106744299, | |
| "grad_norm": 1.792947769165039, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 6.8177, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.07375060650169821, | |
| "grad_norm": 1.7828471660614014, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 6.8137, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.07569141193595343, | |
| "grad_norm": 1.78638756275177, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 6.8141, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.07763221737020863, | |
| "grad_norm": 1.765810489654541, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 6.8104, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07957302280446385, | |
| "grad_norm": 1.7625008821487427, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 6.8077, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.08151382823871907, | |
| "grad_norm": 1.7558047771453857, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 6.8057, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.08345463367297429, | |
| "grad_norm": 1.758226990699768, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 6.8066, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0853954391072295, | |
| "grad_norm": 1.747825264930725, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 6.8011, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.08733624454148471, | |
| "grad_norm": 1.7420827150344849, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 6.8014, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.08927704997573993, | |
| "grad_norm": 1.7530667781829834, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 6.8033, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.09121785540999515, | |
| "grad_norm": 1.7421718835830688, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 6.8006, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.09315866084425037, | |
| "grad_norm": 1.7380465269088745, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 6.7997, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.09509946627850557, | |
| "grad_norm": 1.743160605430603, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 6.7994, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.09704027171276079, | |
| "grad_norm": 1.7376538515090942, | |
| "learning_rate": 0.0, | |
| "loss": 6.7979, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.09704027171276079, | |
| "eval_loss": 6.828060150146484, | |
| "eval_runtime": 1.1077, | |
| "eval_samples_per_second": 783.584, | |
| "eval_steps_per_second": 98.399, | |
| "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": 961128038400.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |