| { | |
| "best_metric": 1.0756638050079346, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.1038251366120218, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02185792349726776, | |
| "grad_norm": 0.054219260811805725, | |
| "learning_rate": 1.16e-05, | |
| "loss": 1.0221, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02185792349726776, | |
| "eval_loss": 1.3064125776290894, | |
| "eval_runtime": 1.5023, | |
| "eval_samples_per_second": 409.374, | |
| "eval_steps_per_second": 13.313, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04371584699453552, | |
| "grad_norm": 0.07374625653028488, | |
| "learning_rate": 2.32e-05, | |
| "loss": 1.13, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06557377049180328, | |
| "grad_norm": 0.08744122087955475, | |
| "learning_rate": 3.48e-05, | |
| "loss": 1.2471, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.08743169398907104, | |
| "grad_norm": 0.1099563017487526, | |
| "learning_rate": 4.64e-05, | |
| "loss": 1.3512, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.1092896174863388, | |
| "grad_norm": 0.14091312885284424, | |
| "learning_rate": 5.8e-05, | |
| "loss": 1.382, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.13114754098360656, | |
| "grad_norm": 0.19244275987148285, | |
| "learning_rate": 6.96e-05, | |
| "loss": 1.524, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.15300546448087432, | |
| "grad_norm": 0.052936580032110214, | |
| "learning_rate": 8.12e-05, | |
| "loss": 1.0329, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.17486338797814208, | |
| "grad_norm": 0.06494678556919098, | |
| "learning_rate": 9.28e-05, | |
| "loss": 1.1503, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.19672131147540983, | |
| "grad_norm": 0.07551469653844833, | |
| "learning_rate": 0.0001044, | |
| "loss": 1.2085, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.2185792349726776, | |
| "grad_norm": 0.08664041757583618, | |
| "learning_rate": 0.000116, | |
| "loss": 1.2444, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.24043715846994534, | |
| "grad_norm": 0.10655322670936584, | |
| "learning_rate": 0.00011598225532067881, | |
| "loss": 1.3136, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.26229508196721313, | |
| "grad_norm": 0.14484980702400208, | |
| "learning_rate": 0.00011592903214042715, | |
| "loss": 1.3774, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.28415300546448086, | |
| "grad_norm": 0.049404121935367584, | |
| "learning_rate": 0.00011584036302573693, | |
| "loss": 0.9998, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.30601092896174864, | |
| "grad_norm": 0.05533352494239807, | |
| "learning_rate": 0.0001157163022319532, | |
| "loss": 1.077, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.32786885245901637, | |
| "grad_norm": 0.06618451327085495, | |
| "learning_rate": 0.00011555692567007598, | |
| "loss": 1.1209, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.34972677595628415, | |
| "grad_norm": 0.07199019938707352, | |
| "learning_rate": 0.00011536233086031157, | |
| "loss": 1.2181, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.37158469945355194, | |
| "grad_norm": 0.08229127526283264, | |
| "learning_rate": 0.00011513263687240126, | |
| "loss": 1.2544, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.39344262295081966, | |
| "grad_norm": 0.10118231177330017, | |
| "learning_rate": 0.00011486798425276428, | |
| "loss": 1.3167, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.41530054644808745, | |
| "grad_norm": 0.06382325291633606, | |
| "learning_rate": 0.00011456853493849944, | |
| "loss": 0.9757, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.4371584699453552, | |
| "grad_norm": 0.06287430226802826, | |
| "learning_rate": 0.0001142344721582983, | |
| "loss": 1.0141, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.45901639344262296, | |
| "grad_norm": 0.061046287417411804, | |
| "learning_rate": 0.00011386600032033012, | |
| "loss": 1.1142, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.4808743169398907, | |
| "grad_norm": 0.05975975841283798, | |
| "learning_rate": 0.0001134633448871674, | |
| "loss": 1.172, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.5027322404371585, | |
| "grad_norm": 0.06590148061513901, | |
| "learning_rate": 0.00011302675223782873, | |
| "loss": 1.1934, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.5245901639344263, | |
| "grad_norm": 0.07652608305215836, | |
| "learning_rate": 0.00011255648951702296, | |
| "loss": 1.2285, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.546448087431694, | |
| "grad_norm": 0.11880210041999817, | |
| "learning_rate": 0.0001120528444716872, | |
| "loss": 1.2294, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5683060109289617, | |
| "grad_norm": 0.04327382519841194, | |
| "learning_rate": 0.00011151612527491878, | |
| "loss": 0.9457, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.5901639344262295, | |
| "grad_norm": 0.05113707482814789, | |
| "learning_rate": 0.00011094666033740846, | |
| "loss": 1.0301, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.6120218579234973, | |
| "grad_norm": 0.04633456468582153, | |
| "learning_rate": 0.00011034479810649071, | |
| "loss": 1.1369, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.6338797814207651, | |
| "grad_norm": 0.052176687866449356, | |
| "learning_rate": 0.00010971090685293396, | |
| "loss": 1.1575, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.6557377049180327, | |
| "grad_norm": 0.05911482125520706, | |
| "learning_rate": 0.00010904537444560093, | |
| "loss": 1.1915, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.6775956284153005, | |
| "grad_norm": 0.08560285717248917, | |
| "learning_rate": 0.0001083486081141173, | |
| "loss": 1.1844, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.6994535519125683, | |
| "grad_norm": 0.0443929098546505, | |
| "learning_rate": 0.00010762103419969393, | |
| "loss": 0.9784, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.7213114754098361, | |
| "grad_norm": 0.04982827231287956, | |
| "learning_rate": 0.00010686309789425474, | |
| "loss": 1.0368, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.7431693989071039, | |
| "grad_norm": 0.04613876715302467, | |
| "learning_rate": 0.00010607526296803026, | |
| "loss": 1.0534, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.7650273224043715, | |
| "grad_norm": 0.04624936357140541, | |
| "learning_rate": 0.00010525801148578341, | |
| "loss": 1.1136, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.7868852459016393, | |
| "grad_norm": 0.050727903842926025, | |
| "learning_rate": 0.000104411843511841, | |
| "loss": 1.1563, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.8087431693989071, | |
| "grad_norm": 0.07218360155820847, | |
| "learning_rate": 0.00010353727680411158, | |
| "loss": 1.148, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.8306010928961749, | |
| "grad_norm": 0.04049117863178253, | |
| "learning_rate": 0.00010263484649727705, | |
| "loss": 0.9096, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.8524590163934426, | |
| "grad_norm": 0.0455789640545845, | |
| "learning_rate": 0.00010170510477535133, | |
| "loss": 1.0006, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.8743169398907104, | |
| "grad_norm": 0.039463143795728683, | |
| "learning_rate": 0.00010074862053380711, | |
| "loss": 1.0411, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8961748633879781, | |
| "grad_norm": 0.042614974081516266, | |
| "learning_rate": 9.976597903147682e-05, | |
| "loss": 1.1396, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.9180327868852459, | |
| "grad_norm": 0.04930881783366203, | |
| "learning_rate": 9.875778153244143e-05, | |
| "loss": 1.1744, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.9398907103825137, | |
| "grad_norm": 0.06974472105503082, | |
| "learning_rate": 9.772464493812549e-05, | |
| "loss": 1.15, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.9617486338797814, | |
| "grad_norm": 0.04092060774564743, | |
| "learning_rate": 9.66672014098242e-05, | |
| "loss": 0.9676, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.9836065573770492, | |
| "grad_norm": 0.0392816998064518, | |
| "learning_rate": 9.558609798189311e-05, | |
| "loss": 1.0893, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.0163934426229508, | |
| "grad_norm": 0.08897832781076431, | |
| "learning_rate": 9.448199616583707e-05, | |
| "loss": 1.8898, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.0382513661202186, | |
| "grad_norm": 0.03982605040073395, | |
| "learning_rate": 9.335557154554105e-05, | |
| "loss": 0.9943, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.0601092896174864, | |
| "grad_norm": 0.03858646750450134, | |
| "learning_rate": 9.220751336389013e-05, | |
| "loss": 1.0459, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.0819672131147542, | |
| "grad_norm": 0.040587618947029114, | |
| "learning_rate": 9.10385241010317e-05, | |
| "loss": 1.1494, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.1038251366120218, | |
| "grad_norm": 0.052482884377241135, | |
| "learning_rate": 8.984931904453821e-05, | |
| "loss": 1.1475, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.1038251366120218, | |
| "eval_loss": 1.0756638050079346, | |
| "eval_runtime": 1.9721, | |
| "eval_samples_per_second": 311.855, | |
| "eval_steps_per_second": 10.142, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 137, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 50, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.8231094746742784e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |