| { | |
| "best_metric": 2.1368014812469482, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.1516300227445034, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003032600454890068, | |
| "grad_norm": 0.5732214450836182, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 1.2366, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003032600454890068, | |
| "eval_loss": 2.233814001083374, | |
| "eval_runtime": 2.1263, | |
| "eval_samples_per_second": 23.515, | |
| "eval_steps_per_second": 3.292, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006065200909780136, | |
| "grad_norm": 0.5826615691184998, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 1.2069, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.009097801364670205, | |
| "grad_norm": 0.8060511946678162, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 1.4296, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.012130401819560273, | |
| "grad_norm": 0.7838976979255676, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 1.8031, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.015163002274450341, | |
| "grad_norm": 0.9152936935424805, | |
| "learning_rate": 0.00015, | |
| "loss": 2.8825, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01819560272934041, | |
| "grad_norm": 0.9083536863327026, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 2.8714, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02122820318423048, | |
| "grad_norm": 0.7592295408248901, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 2.6227, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.024260803639120546, | |
| "grad_norm": 0.8848680257797241, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 2.3879, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.027293404094010616, | |
| "grad_norm": 1.1162092685699463, | |
| "learning_rate": 0.00027, | |
| "loss": 1.9078, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.030326004548900682, | |
| "grad_norm": 1.1469495296478271, | |
| "learning_rate": 0.0003, | |
| "loss": 2.3304, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03335860500379075, | |
| "grad_norm": 1.7421014308929443, | |
| "learning_rate": 0.0002999794957488703, | |
| "loss": 2.6528, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03639120545868082, | |
| "grad_norm": 2.160493850708008, | |
| "learning_rate": 0.0002999179886011389, | |
| "loss": 1.7365, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.039423805913570885, | |
| "grad_norm": 1.6525168418884277, | |
| "learning_rate": 0.0002998154953722457, | |
| "loss": 1.3977, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04245640636846096, | |
| "grad_norm": 1.732264757156372, | |
| "learning_rate": 0.00029967204408281613, | |
| "loss": 0.9095, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.045489006823351025, | |
| "grad_norm": 1.9203606843948364, | |
| "learning_rate": 0.00029948767395100045, | |
| "loss": 0.8081, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04852160727824109, | |
| "grad_norm": 1.9768295288085938, | |
| "learning_rate": 0.0002992624353817517, | |
| "loss": 0.5633, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05155420773313116, | |
| "grad_norm": 1.7694615125656128, | |
| "learning_rate": 0.0002989963899530457, | |
| "loss": 0.8582, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.05458680818802123, | |
| "grad_norm": 5.227871417999268, | |
| "learning_rate": 0.00029868961039904624, | |
| "loss": 2.0478, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0576194086429113, | |
| "grad_norm": 5.613846302032471, | |
| "learning_rate": 0.00029834218059022024, | |
| "loss": 2.628, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.060652009097801364, | |
| "grad_norm": 3.1168196201324463, | |
| "learning_rate": 0.00029795419551040833, | |
| "loss": 2.2502, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06368460955269144, | |
| "grad_norm": 2.028256893157959, | |
| "learning_rate": 0.00029752576123085736, | |
| "loss": 1.9875, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0667172100075815, | |
| "grad_norm": 2.2501745223999023, | |
| "learning_rate": 0.0002970569948812214, | |
| "loss": 1.3561, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.06974981046247157, | |
| "grad_norm": 2.091094970703125, | |
| "learning_rate": 0.0002965480246175399, | |
| "loss": 1.4375, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.07278241091736164, | |
| "grad_norm": 1.8560627698898315, | |
| "learning_rate": 0.0002959989895872009, | |
| "loss": 0.8881, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0758150113722517, | |
| "grad_norm": 1.5652915239334106, | |
| "learning_rate": 0.0002954100398908995, | |
| "loss": 1.1072, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0758150113722517, | |
| "eval_loss": 1.6969295740127563, | |
| "eval_runtime": 1.6362, | |
| "eval_samples_per_second": 30.559, | |
| "eval_steps_per_second": 4.278, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07884761182714177, | |
| "grad_norm": 2.593773126602173, | |
| "learning_rate": 0.0002947813365416023, | |
| "loss": 2.3669, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.08188021228203184, | |
| "grad_norm": 3.031888961791992, | |
| "learning_rate": 0.0002941130514205272, | |
| "loss": 2.1705, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.08491281273692192, | |
| "grad_norm": 5.483036994934082, | |
| "learning_rate": 0.0002934053672301536, | |
| "loss": 2.0639, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.08794541319181198, | |
| "grad_norm": 2.578169584274292, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 2.2763, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.09097801364670205, | |
| "grad_norm": 2.708948850631714, | |
| "learning_rate": 0.00029187258625509513, | |
| "loss": 2.6701, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09401061410159212, | |
| "grad_norm": 2.3376152515411377, | |
| "learning_rate": 0.00029104790851742417, | |
| "loss": 2.552, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.09704321455648218, | |
| "grad_norm": 4.5717453956604, | |
| "learning_rate": 0.0002901846696899191, | |
| "loss": 2.5146, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.10007581501137225, | |
| "grad_norm": 3.326918601989746, | |
| "learning_rate": 0.00028928310577345606, | |
| "loss": 2.7361, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.10310841546626232, | |
| "grad_norm": 3.0180697441101074, | |
| "learning_rate": 0.0002883434632466077, | |
| "loss": 2.1276, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.10614101592115238, | |
| "grad_norm": 3.3345470428466797, | |
| "learning_rate": 0.00028736599899825856, | |
| "loss": 3.5262, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.10917361637604246, | |
| "grad_norm": 4.028136730194092, | |
| "learning_rate": 0.00028635098025737434, | |
| "loss": 1.3238, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.11220621683093253, | |
| "grad_norm": 2.7964673042297363, | |
| "learning_rate": 0.00028529868451994384, | |
| "loss": 1.9645, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.1152388172858226, | |
| "grad_norm": 2.7283153533935547, | |
| "learning_rate": 0.0002842093994731145, | |
| "loss": 1.6322, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.11827141774071266, | |
| "grad_norm": 3.139758586883545, | |
| "learning_rate": 0.00028308342291654174, | |
| "loss": 1.3747, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.12130401819560273, | |
| "grad_norm": 3.401658535003662, | |
| "learning_rate": 0.00028192106268097334, | |
| "loss": 1.0433, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1243366186504928, | |
| "grad_norm": 3.2721481323242188, | |
| "learning_rate": 0.00028072263654409154, | |
| "loss": 0.9206, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.12736921910538287, | |
| "grad_norm": 2.2043514251708984, | |
| "learning_rate": 0.0002794884721436361, | |
| "loss": 0.6399, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.13040181956027294, | |
| "grad_norm": 2.3156049251556396, | |
| "learning_rate": 0.00027821890688783083, | |
| "loss": 0.8682, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.133434420015163, | |
| "grad_norm": 4.419061660766602, | |
| "learning_rate": 0.0002769142878631403, | |
| "loss": 0.5265, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.13646702047005307, | |
| "grad_norm": 2.9401931762695312, | |
| "learning_rate": 0.00027557497173937923, | |
| "loss": 0.4974, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.13949962092494314, | |
| "grad_norm": 2.4342000484466553, | |
| "learning_rate": 0.000274201324672203, | |
| "loss": 0.4075, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.1425322213798332, | |
| "grad_norm": 1.5229568481445312, | |
| "learning_rate": 0.00027279372220300385, | |
| "loss": 0.2443, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.14556482183472327, | |
| "grad_norm": 0.7514405846595764, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 0.032, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.14859742228961334, | |
| "grad_norm": 3.046010732650757, | |
| "learning_rate": 0.00026987819953423867, | |
| "loss": 0.6208, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.1516300227445034, | |
| "grad_norm": 3.323383331298828, | |
| "learning_rate": 0.00026837107640945905, | |
| "loss": 0.4257, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1516300227445034, | |
| "eval_loss": 2.1368014812469482, | |
| "eval_runtime": 1.6375, | |
| "eval_samples_per_second": 30.534, | |
| "eval_steps_per_second": 4.275, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 1.0333462563127296e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |