| { | |
| "best_metric": 1.8114935159683228, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.5708169818052087, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.011416339636104174, | |
| "grad_norm": 7.898479461669922, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 3.839, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011416339636104174, | |
| "eval_loss": 4.370181083679199, | |
| "eval_runtime": 4.6814, | |
| "eval_samples_per_second": 10.681, | |
| "eval_steps_per_second": 1.495, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.022832679272208348, | |
| "grad_norm": 7.888498306274414, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 3.8169, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03424901890831252, | |
| "grad_norm": 8.71157455444336, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 3.9081, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.045665358544416695, | |
| "grad_norm": 7.415948867797852, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 3.4078, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.05708169818052087, | |
| "grad_norm": 4.761682033538818, | |
| "learning_rate": 0.00015, | |
| "loss": 2.8352, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06849803781662504, | |
| "grad_norm": 4.246852397918701, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 2.5466, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07991437745272922, | |
| "grad_norm": 3.3111937046051025, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 2.3276, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.09133071708883339, | |
| "grad_norm": 4.848330020904541, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 2.3207, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.10274705672493757, | |
| "grad_norm": 2.9185802936553955, | |
| "learning_rate": 0.00027, | |
| "loss": 2.2468, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.11416339636104174, | |
| "grad_norm": 2.7042579650878906, | |
| "learning_rate": 0.0003, | |
| "loss": 1.9733, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12557973599714592, | |
| "grad_norm": 3.202441692352295, | |
| "learning_rate": 0.0002999794957488703, | |
| "loss": 2.0887, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1369960756332501, | |
| "grad_norm": 2.5777502059936523, | |
| "learning_rate": 0.0002999179886011389, | |
| "loss": 1.6886, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.14841241526935425, | |
| "grad_norm": 3.485649347305298, | |
| "learning_rate": 0.0002998154953722457, | |
| "loss": 1.9007, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.15982875490545845, | |
| "grad_norm": 2.80680775642395, | |
| "learning_rate": 0.00029967204408281613, | |
| "loss": 1.9419, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.17124509454156261, | |
| "grad_norm": 2.477963924407959, | |
| "learning_rate": 0.00029948767395100045, | |
| "loss": 1.8113, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.18266143417766678, | |
| "grad_norm": 3.5928072929382324, | |
| "learning_rate": 0.0002992624353817517, | |
| "loss": 2.0529, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.19407777381377095, | |
| "grad_norm": 2.8333468437194824, | |
| "learning_rate": 0.0002989963899530457, | |
| "loss": 1.9951, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.20549411344987514, | |
| "grad_norm": 2.8093178272247314, | |
| "learning_rate": 0.00029868961039904624, | |
| "loss": 1.9505, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2169104530859793, | |
| "grad_norm": 3.1787095069885254, | |
| "learning_rate": 0.00029834218059022024, | |
| "loss": 1.9297, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.22832679272208348, | |
| "grad_norm": 2.9454715251922607, | |
| "learning_rate": 0.00029795419551040833, | |
| "loss": 1.9485, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.23974313235818764, | |
| "grad_norm": 3.2813782691955566, | |
| "learning_rate": 0.00029752576123085736, | |
| "loss": 2.0743, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.25115947199429184, | |
| "grad_norm": 2.510538101196289, | |
| "learning_rate": 0.0002970569948812214, | |
| "loss": 1.9988, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.262575811630396, | |
| "grad_norm": 2.534315586090088, | |
| "learning_rate": 0.0002965480246175399, | |
| "loss": 1.9098, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2739921512665002, | |
| "grad_norm": 2.1965324878692627, | |
| "learning_rate": 0.0002959989895872009, | |
| "loss": 1.7517, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.28540849090260434, | |
| "grad_norm": 2.1002790927886963, | |
| "learning_rate": 0.0002954100398908995, | |
| "loss": 1.6897, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.28540849090260434, | |
| "eval_loss": 1.9441114664077759, | |
| "eval_runtime": 4.7777, | |
| "eval_samples_per_second": 10.465, | |
| "eval_steps_per_second": 1.465, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2968248305387085, | |
| "grad_norm": 2.207418918609619, | |
| "learning_rate": 0.0002947813365416023, | |
| "loss": 1.95, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3082411701748127, | |
| "grad_norm": 2.6818461418151855, | |
| "learning_rate": 0.0002941130514205272, | |
| "loss": 1.9706, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3196575098109169, | |
| "grad_norm": 2.279365062713623, | |
| "learning_rate": 0.0002934053672301536, | |
| "loss": 1.6524, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.33107384944702106, | |
| "grad_norm": 2.2755017280578613, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 1.7105, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.34249018908312523, | |
| "grad_norm": 2.5415656566619873, | |
| "learning_rate": 0.00029187258625509513, | |
| "loss": 1.8029, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3539065287192294, | |
| "grad_norm": 2.6460940837860107, | |
| "learning_rate": 0.00029104790851742417, | |
| "loss": 1.8104, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.36532286835533356, | |
| "grad_norm": 2.3558075428009033, | |
| "learning_rate": 0.0002901846696899191, | |
| "loss": 1.8417, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.37673920799143773, | |
| "grad_norm": 2.1366970539093018, | |
| "learning_rate": 0.00028928310577345606, | |
| "loss": 1.7281, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.3881555476275419, | |
| "grad_norm": 2.147944450378418, | |
| "learning_rate": 0.0002883434632466077, | |
| "loss": 1.7001, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.3995718872636461, | |
| "grad_norm": 1.9789509773254395, | |
| "learning_rate": 0.00028736599899825856, | |
| "loss": 1.7427, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4109882268997503, | |
| "grad_norm": 2.110389471054077, | |
| "learning_rate": 0.00028635098025737434, | |
| "loss": 1.8732, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.42240456653585445, | |
| "grad_norm": 2.150489568710327, | |
| "learning_rate": 0.00028529868451994384, | |
| "loss": 1.6447, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.4338209061719586, | |
| "grad_norm": 2.31097674369812, | |
| "learning_rate": 0.0002842093994731145, | |
| "loss": 1.8932, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.4452372458080628, | |
| "grad_norm": 2.4540700912475586, | |
| "learning_rate": 0.00028308342291654174, | |
| "loss": 1.8748, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.45665358544416695, | |
| "grad_norm": 2.4295310974121094, | |
| "learning_rate": 0.00028192106268097334, | |
| "loss": 1.8415, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4680699250802711, | |
| "grad_norm": 3.067713737487793, | |
| "learning_rate": 0.00028072263654409154, | |
| "loss": 1.9419, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.4794862647163753, | |
| "grad_norm": 2.9190239906311035, | |
| "learning_rate": 0.0002794884721436361, | |
| "loss": 1.9494, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.4909026043524795, | |
| "grad_norm": 2.983987808227539, | |
| "learning_rate": 0.00027821890688783083, | |
| "loss": 1.8778, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5023189439885837, | |
| "grad_norm": 3.0087473392486572, | |
| "learning_rate": 0.0002769142878631403, | |
| "loss": 1.8793, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5137352836246878, | |
| "grad_norm": 1.934885859489441, | |
| "learning_rate": 0.00027557497173937923, | |
| "loss": 1.6278, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.525151623260792, | |
| "grad_norm": 1.9108154773712158, | |
| "learning_rate": 0.000274201324672203, | |
| "loss": 1.8105, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5365679628968962, | |
| "grad_norm": 2.1089630126953125, | |
| "learning_rate": 0.00027279372220300385, | |
| "loss": 1.675, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.5479843025330003, | |
| "grad_norm": 2.15185546875, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 1.8751, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.5594006421691046, | |
| "grad_norm": 2.311039686203003, | |
| "learning_rate": 0.00026987819953423867, | |
| "loss": 1.8339, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.5708169818052087, | |
| "grad_norm": 2.1658663749694824, | |
| "learning_rate": 0.00026837107640945905, | |
| "loss": 1.6501, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5708169818052087, | |
| "eval_loss": 1.8114935159683228, | |
| "eval_runtime": 4.7797, | |
| "eval_samples_per_second": 10.461, | |
| "eval_steps_per_second": 1.465, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "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": 8.14825259139072e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |