| { | |
| "best_metric": 0.5615120530128479, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.9900497512437811, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03980099502487562, | |
| "grad_norm": 0.13538791239261627, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7752, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03980099502487562, | |
| "eval_loss": 0.7566336393356323, | |
| "eval_runtime": 5.1026, | |
| "eval_samples_per_second": 33.316, | |
| "eval_steps_per_second": 4.312, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07960199004975124, | |
| "grad_norm": 0.13740819692611694, | |
| "learning_rate": 0.0001, | |
| "loss": 0.756, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11940298507462686, | |
| "grad_norm": 0.14167937636375427, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.7529, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.15920398009950248, | |
| "grad_norm": 0.1538102775812149, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.7392, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.19900497512437812, | |
| "grad_norm": 0.1964820772409439, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.7395, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.23880597014925373, | |
| "grad_norm": 0.12592492997646332, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.6386, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.27860696517412936, | |
| "grad_norm": 0.12350691109895706, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.6686, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.31840796019900497, | |
| "grad_norm": 0.14032255113124847, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.682, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3582089552238806, | |
| "grad_norm": 0.14228299260139465, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.6878, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.39800995024875624, | |
| "grad_norm": 0.10774895548820496, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.634, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.43781094527363185, | |
| "grad_norm": 0.10263238102197647, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.604, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.47761194029850745, | |
| "grad_norm": 0.10312753170728683, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.6044, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5174129353233831, | |
| "grad_norm": 0.07034023106098175, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.6199, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5572139303482587, | |
| "grad_norm": 0.07299194484949112, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.6362, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5970149253731343, | |
| "grad_norm": 0.07921850681304932, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.6404, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6368159203980099, | |
| "grad_norm": 0.07726301997900009, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.6213, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.6766169154228856, | |
| "grad_norm": 0.07813425362110138, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.5873, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.7164179104477612, | |
| "grad_norm": 0.10323521494865417, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.5738, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7562189054726368, | |
| "grad_norm": 0.07982894033193588, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.5988, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7960199004975125, | |
| "grad_norm": 0.06970314681529999, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.6514, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.835820895522388, | |
| "grad_norm": 0.07304966449737549, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.6176, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.8756218905472637, | |
| "grad_norm": 0.10210943222045898, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.5853, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.9154228855721394, | |
| "grad_norm": 0.08298351615667343, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.5827, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.9552238805970149, | |
| "grad_norm": 0.07600322365760803, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.573, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9950248756218906, | |
| "grad_norm": 0.08038770407438278, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.5355, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9950248756218906, | |
| "eval_loss": 0.5803007483482361, | |
| "eval_runtime": 5.094, | |
| "eval_samples_per_second": 33.373, | |
| "eval_steps_per_second": 4.319, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0348258706467661, | |
| "grad_norm": 0.2262948751449585, | |
| "learning_rate": 5e-05, | |
| "loss": 1.126, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.0746268656716418, | |
| "grad_norm": 0.1797284334897995, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.592, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.1144278606965174, | |
| "grad_norm": 0.11251581460237503, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.5877, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.154228855721393, | |
| "grad_norm": 0.1345890462398529, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.5576, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.1940298507462686, | |
| "grad_norm": 0.12311283499002457, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.555, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.2338308457711442, | |
| "grad_norm": 0.13137906789779663, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.5231, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.2736318407960199, | |
| "grad_norm": 0.11661550402641296, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.56, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.3134328358208955, | |
| "grad_norm": 0.12265345454216003, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.5983, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.3532338308457712, | |
| "grad_norm": 0.12625396251678467, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.5878, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.3930348258706466, | |
| "grad_norm": 0.11988857388496399, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.5562, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.4328358208955223, | |
| "grad_norm": 0.1285698562860489, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.5407, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.472636815920398, | |
| "grad_norm": 0.14078256487846375, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.5432, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.5124378109452736, | |
| "grad_norm": 0.12595324218273163, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.5203, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.5522388059701493, | |
| "grad_norm": 0.11833399534225464, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.5963, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.5920398009950247, | |
| "grad_norm": 0.12518984079360962, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.5595, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.6318407960199006, | |
| "grad_norm": 0.12780751287937164, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.5393, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.671641791044776, | |
| "grad_norm": 0.13122279942035675, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.5428, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.7114427860696517, | |
| "grad_norm": 0.1328832358121872, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.5523, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.7512437810945274, | |
| "grad_norm": 0.1302466094493866, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.4927, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.7910447761194028, | |
| "grad_norm": 0.1199650689959526, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.6295, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.8308457711442787, | |
| "grad_norm": 0.11739806085824966, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.5605, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.8706467661691542, | |
| "grad_norm": 0.12748704850673676, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.5549, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.9104477611940298, | |
| "grad_norm": 0.12685979902744293, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.5565, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.9502487562189055, | |
| "grad_norm": 0.1480509489774704, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.5537, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.9900497512437811, | |
| "grad_norm": 0.1484479457139969, | |
| "learning_rate": 0.0, | |
| "loss": 0.4925, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.9900497512437811, | |
| "eval_loss": 0.5615120530128479, | |
| "eval_runtime": 5.0865, | |
| "eval_samples_per_second": 33.422, | |
| "eval_steps_per_second": 4.325, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 25, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.259156315439104e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |