| { | |
| "best_metric": 2.2425832748413086, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.6517311608961304, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.013034623217922607, | |
| "grad_norm": 0.6276217103004456, | |
| "learning_rate": 7.5e-05, | |
| "loss": 2.9674, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013034623217922607, | |
| "eval_loss": 3.5546200275421143, | |
| "eval_runtime": 0.2814, | |
| "eval_samples_per_second": 177.672, | |
| "eval_steps_per_second": 46.195, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.026069246435845215, | |
| "grad_norm": 0.6501481533050537, | |
| "learning_rate": 0.00015, | |
| "loss": 3.2018, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.039103869653767824, | |
| "grad_norm": 0.5839198231697083, | |
| "learning_rate": 0.000225, | |
| "loss": 3.3157, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05213849287169043, | |
| "grad_norm": 0.5366824865341187, | |
| "learning_rate": 0.0003, | |
| "loss": 3.3337, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06517311608961303, | |
| "grad_norm": 0.4950920641422272, | |
| "learning_rate": 0.0002999703922691041, | |
| "loss": 3.3257, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07820773930753565, | |
| "grad_norm": 0.4459711015224457, | |
| "learning_rate": 0.00029988158206334587, | |
| "loss": 3.2473, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09124236252545825, | |
| "grad_norm": 0.5029334425926208, | |
| "learning_rate": 0.00029973360833781664, | |
| "loss": 3.251, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.10427698574338086, | |
| "grad_norm": 0.5529475808143616, | |
| "learning_rate": 0.0002995265359986831, | |
| "loss": 3.212, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.11731160896130347, | |
| "grad_norm": 0.6158551573753357, | |
| "learning_rate": 0.00029926045587471686, | |
| "loss": 3.1893, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.13034623217922606, | |
| "grad_norm": 0.6573907136917114, | |
| "learning_rate": 0.0002989354846774545, | |
| "loss": 3.1782, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14338085539714868, | |
| "grad_norm": 0.6919009685516357, | |
| "learning_rate": 0.0002985517649500034, | |
| "loss": 3.0629, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1564154786150713, | |
| "grad_norm": 0.7953146696090698, | |
| "learning_rate": 0.00029810946500451814, | |
| "loss": 3.132, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1694501018329939, | |
| "grad_norm": 0.9705007672309875, | |
| "learning_rate": 0.00029760877884837294, | |
| "loss": 2.7258, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1824847250509165, | |
| "grad_norm": 0.9804863333702087, | |
| "learning_rate": 0.0002970499260990637, | |
| "loss": 2.7512, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.1955193482688391, | |
| "grad_norm": 0.6821589469909668, | |
| "learning_rate": 0.0002964331518878766, | |
| "loss": 2.6437, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.20855397148676172, | |
| "grad_norm": 0.4936249554157257, | |
| "learning_rate": 0.0002957587267523652, | |
| "loss": 2.6137, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2215885947046843, | |
| "grad_norm": 0.5652141571044922, | |
| "learning_rate": 0.00029502694651768383, | |
| "loss": 2.6432, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.23462321792260693, | |
| "grad_norm": 0.6153628826141357, | |
| "learning_rate": 0.000294238132166829, | |
| "loss": 2.6485, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.24765784114052952, | |
| "grad_norm": 0.4337889552116394, | |
| "learning_rate": 0.0002933926296998457, | |
| "loss": 2.5919, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2606924643584521, | |
| "grad_norm": 0.5410802364349365, | |
| "learning_rate": 0.0002924908099820599, | |
| "loss": 2.6103, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.27372708757637476, | |
| "grad_norm": 0.5030240416526794, | |
| "learning_rate": 0.00029153306858140533, | |
| "loss": 2.6104, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.28676171079429735, | |
| "grad_norm": 0.38985803723335266, | |
| "learning_rate": 0.00029051982559491393, | |
| "loss": 2.5794, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.29979633401221994, | |
| "grad_norm": 0.5979215502738953, | |
| "learning_rate": 0.00028945152546444754, | |
| "loss": 2.6287, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3128309572301426, | |
| "grad_norm": 0.5737847089767456, | |
| "learning_rate": 0.0002883286367817511, | |
| "loss": 2.6541, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3258655804480652, | |
| "grad_norm": 0.572758138179779, | |
| "learning_rate": 0.00028715165208291265, | |
| "loss": 2.6881, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3258655804480652, | |
| "eval_loss": 2.5153815746307373, | |
| "eval_runtime": 0.2797, | |
| "eval_samples_per_second": 178.771, | |
| "eval_steps_per_second": 46.481, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3389002036659878, | |
| "grad_norm": 1.4206351041793823, | |
| "learning_rate": 0.0002859210876323207, | |
| "loss": 2.4658, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.35193482688391037, | |
| "grad_norm": 1.5302618741989136, | |
| "learning_rate": 0.00028463748319621396, | |
| "loss": 2.5304, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.364969450101833, | |
| "grad_norm": 0.9723348021507263, | |
| "learning_rate": 0.00028330140180592156, | |
| "loss": 2.4213, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.3780040733197556, | |
| "grad_norm": 0.4521373212337494, | |
| "learning_rate": 0.0002819134295108992, | |
| "loss": 2.4048, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.3910386965376782, | |
| "grad_norm": 0.6521058678627014, | |
| "learning_rate": 0.00028047417512166837, | |
| "loss": 2.4019, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4040733197556008, | |
| "grad_norm": 0.7668533325195312, | |
| "learning_rate": 0.00027898426994277204, | |
| "loss": 2.4534, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.41710794297352344, | |
| "grad_norm": 0.791877269744873, | |
| "learning_rate": 0.0002774443674958634, | |
| "loss": 2.4232, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.43014256619144603, | |
| "grad_norm": 0.814365565776825, | |
| "learning_rate": 0.00027585514323305, | |
| "loss": 2.4323, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.4431771894093686, | |
| "grad_norm": 0.6510496735572815, | |
| "learning_rate": 0.00027421729424061787, | |
| "loss": 2.3904, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.45621181262729127, | |
| "grad_norm": 0.42264309525489807, | |
| "learning_rate": 0.00027253153893326646, | |
| "loss": 2.4016, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.46924643584521386, | |
| "grad_norm": 0.5813013911247253, | |
| "learning_rate": 0.0002707986167389884, | |
| "loss": 2.4511, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.48228105906313645, | |
| "grad_norm": 0.8300145864486694, | |
| "learning_rate": 0.0002690192877747315, | |
| "loss": 2.4128, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.49531568228105904, | |
| "grad_norm": 0.7689920663833618, | |
| "learning_rate": 0.0002671943325129871, | |
| "loss": 2.3281, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5083503054989816, | |
| "grad_norm": 1.024122953414917, | |
| "learning_rate": 0.0002653245514394482, | |
| "loss": 2.3381, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5213849287169042, | |
| "grad_norm": 0.6759045720100403, | |
| "learning_rate": 0.0002634107647018905, | |
| "loss": 2.3008, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5344195519348269, | |
| "grad_norm": 0.3922083377838135, | |
| "learning_rate": 0.0002614538117504284, | |
| "loss": 2.2719, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5474541751527495, | |
| "grad_norm": 0.5142776966094971, | |
| "learning_rate": 0.0002594545509693043, | |
| "loss": 2.276, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5604887983706721, | |
| "grad_norm": 0.6373997926712036, | |
| "learning_rate": 0.00025741385930037295, | |
| "loss": 2.2602, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5735234215885947, | |
| "grad_norm": 0.6760398149490356, | |
| "learning_rate": 0.00025533263185844587, | |
| "loss": 2.3169, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5865580448065173, | |
| "grad_norm": 0.7617467045783997, | |
| "learning_rate": 0.00025321178153866423, | |
| "loss": 2.2778, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5995926680244399, | |
| "grad_norm": 0.7649106979370117, | |
| "learning_rate": 0.00025105223861607306, | |
| "loss": 2.2692, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6126272912423625, | |
| "grad_norm": 0.6090757250785828, | |
| "learning_rate": 0.0002488549503375719, | |
| "loss": 2.2845, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6256619144602852, | |
| "grad_norm": 0.45042526721954346, | |
| "learning_rate": 0.0002466208805064206, | |
| "loss": 2.2431, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6386965376782078, | |
| "grad_norm": 0.46896523237228394, | |
| "learning_rate": 0.00024435100905948387, | |
| "loss": 2.2985, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6517311608961304, | |
| "grad_norm": 0.5649595260620117, | |
| "learning_rate": 0.00024204633163739828, | |
| "loss": 2.4211, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6517311608961304, | |
| "eval_loss": 2.2425832748413086, | |
| "eval_runtime": 0.2798, | |
| "eval_samples_per_second": 178.69, | |
| "eval_steps_per_second": 46.46, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 154, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 50, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.22140137734144e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |