| { | |
| "best_metric": 0.20686934888362885, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.02689618074233459, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005379236148466917, | |
| "grad_norm": 5.665757179260254, | |
| "learning_rate": 4e-05, | |
| "loss": 14.1149, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005379236148466917, | |
| "eval_loss": 14.399935722351074, | |
| "eval_runtime": 480.3434, | |
| "eval_samples_per_second": 1.63, | |
| "eval_steps_per_second": 0.816, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010758472296933835, | |
| "grad_norm": 6.0138421058654785, | |
| "learning_rate": 8e-05, | |
| "loss": 14.3315, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0016137708445400753, | |
| "grad_norm": 5.68032169342041, | |
| "learning_rate": 0.00012, | |
| "loss": 14.4942, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002151694459386767, | |
| "grad_norm": 7.876317977905273, | |
| "learning_rate": 0.00016, | |
| "loss": 14.411, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0026896180742334587, | |
| "grad_norm": 8.77420425415039, | |
| "learning_rate": 0.0002, | |
| "loss": 14.3799, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0032275416890801506, | |
| "grad_norm": 8.047574996948242, | |
| "learning_rate": 0.00019994532573409262, | |
| "loss": 11.1861, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0037654653039268424, | |
| "grad_norm": 8.94501781463623, | |
| "learning_rate": 0.00019978136272187747, | |
| "loss": 9.831, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004303388918773534, | |
| "grad_norm": 9.489190101623535, | |
| "learning_rate": 0.00019950829025450114, | |
| "loss": 7.9405, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004841312533620226, | |
| "grad_norm": 13.784337997436523, | |
| "learning_rate": 0.00019912640693269752, | |
| "loss": 6.1143, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0053792361484669175, | |
| "grad_norm": 9.499981880187988, | |
| "learning_rate": 0.00019863613034027224, | |
| "loss": 4.2967, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005917159763313609, | |
| "grad_norm": 9.118963241577148, | |
| "learning_rate": 0.00019803799658748094, | |
| "loss": 2.7132, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.006455083378160301, | |
| "grad_norm": 9.794291496276855, | |
| "learning_rate": 0.0001973326597248006, | |
| "loss": 1.1106, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.006993006993006993, | |
| "grad_norm": 5.810440540313721, | |
| "learning_rate": 0.00019652089102773488, | |
| "loss": 1.0159, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.007530930607853685, | |
| "grad_norm": 3.0343141555786133, | |
| "learning_rate": 0.00019560357815343577, | |
| "loss": 0.3357, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.008068854222700376, | |
| "grad_norm": 4.984272480010986, | |
| "learning_rate": 0.00019458172417006347, | |
| "loss": 0.3256, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.008606777837547068, | |
| "grad_norm": 8.477812767028809, | |
| "learning_rate": 0.0001934564464599461, | |
| "loss": 0.4395, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00914470145239376, | |
| "grad_norm": 7.445779323577881, | |
| "learning_rate": 0.00019222897549773848, | |
| "loss": 0.5309, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.009682625067240451, | |
| "grad_norm": 5.090211391448975, | |
| "learning_rate": 0.00019090065350491626, | |
| "loss": 0.2973, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.010220548682087143, | |
| "grad_norm": 7.343393802642822, | |
| "learning_rate": 0.00018947293298207635, | |
| "loss": 0.4837, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.010758472296933835, | |
| "grad_norm": 2.520585536956787, | |
| "learning_rate": 0.0001879473751206489, | |
| "loss": 0.1629, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.011296395911780527, | |
| "grad_norm": 3.9465153217315674, | |
| "learning_rate": 0.00018632564809575742, | |
| "loss": 0.1549, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.011834319526627219, | |
| "grad_norm": 3.0971474647521973, | |
| "learning_rate": 0.00018460952524209355, | |
| "loss": 0.2236, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01237224314147391, | |
| "grad_norm": 6.442452430725098, | |
| "learning_rate": 0.00018280088311480201, | |
| "loss": 0.3162, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.012910166756320602, | |
| "grad_norm": 4.07744026184082, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.1577, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.013448090371167294, | |
| "grad_norm": 1.9578357934951782, | |
| "learning_rate": 0.00017891405093963938, | |
| "loss": 0.1762, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.013448090371167294, | |
| "eval_loss": 0.20686934888362885, | |
| "eval_runtime": 482.315, | |
| "eval_samples_per_second": 1.623, | |
| "eval_steps_per_second": 0.813, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.013986013986013986, | |
| "grad_norm": 1.5185937881469727, | |
| "learning_rate": 0.00017684011108568592, | |
| "loss": 0.2361, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.014523937600860678, | |
| "grad_norm": 0.9820839762687683, | |
| "learning_rate": 0.0001746821476984154, | |
| "loss": 0.1982, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.01506186121570737, | |
| "grad_norm": 5.153009414672852, | |
| "learning_rate": 0.00017244252047910892, | |
| "loss": 0.2591, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.015599784830554062, | |
| "grad_norm": 1.0352336168289185, | |
| "learning_rate": 0.00017012367842724887, | |
| "loss": 0.14, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.01613770844540075, | |
| "grad_norm": 2.7931392192840576, | |
| "learning_rate": 0.00016772815716257412, | |
| "loss": 0.3103, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.016675632060247445, | |
| "grad_norm": 3.7326819896698, | |
| "learning_rate": 0.00016525857615241687, | |
| "loss": 0.2908, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.017213555675094135, | |
| "grad_norm": 1.1818197965621948, | |
| "learning_rate": 0.0001627176358473537, | |
| "loss": 0.1197, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.01775147928994083, | |
| "grad_norm": 3.522305727005005, | |
| "learning_rate": 0.00016010811472830252, | |
| "loss": 0.2051, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.01828940290478752, | |
| "grad_norm": 1.0128105878829956, | |
| "learning_rate": 0.00015743286626829437, | |
| "loss": 0.1311, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.018827326519634213, | |
| "grad_norm": 4.8102593421936035, | |
| "learning_rate": 0.00015469481581224272, | |
| "loss": 0.3403, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.019365250134480903, | |
| "grad_norm": 13.774560928344727, | |
| "learning_rate": 0.00015189695737812152, | |
| "loss": 0.9765, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.019903173749327596, | |
| "grad_norm": 5.964848518371582, | |
| "learning_rate": 0.00014904235038305083, | |
| "loss": 0.4839, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.020441097364174286, | |
| "grad_norm": 10.879966735839844, | |
| "learning_rate": 0.0001461341162978688, | |
| "loss": 0.685, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.02097902097902098, | |
| "grad_norm": 6.293717384338379, | |
| "learning_rate": 0.00014317543523384928, | |
| "loss": 0.3725, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.02151694459386767, | |
| "grad_norm": 0.753055214881897, | |
| "learning_rate": 0.00014016954246529696, | |
| "loss": 0.1652, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.022054868208714364, | |
| "grad_norm": 1.0214154720306396, | |
| "learning_rate": 0.00013711972489182208, | |
| "loss": 0.1115, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.022592791823561054, | |
| "grad_norm": 3.1957497596740723, | |
| "learning_rate": 0.00013402931744416433, | |
| "loss": 0.173, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.023130715438407747, | |
| "grad_norm": 0.9727430939674377, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.211, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.023668639053254437, | |
| "grad_norm": 4.678534030914307, | |
| "learning_rate": 0.00012774029087618446, | |
| "loss": 0.3037, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.02420656266810113, | |
| "grad_norm": 3.1848816871643066, | |
| "learning_rate": 0.00012454854871407994, | |
| "loss": 0.2527, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02474448628294782, | |
| "grad_norm": 2.432804584503174, | |
| "learning_rate": 0.0001213299630743747, | |
| "loss": 0.1629, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.025282409897794515, | |
| "grad_norm": 1.7503596544265747, | |
| "learning_rate": 0.000118088053433211, | |
| "loss": 0.1667, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.025820333512641205, | |
| "grad_norm": 3.7610039710998535, | |
| "learning_rate": 0.0001148263647711842, | |
| "loss": 0.2712, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.026358257127487898, | |
| "grad_norm": 1.4483740329742432, | |
| "learning_rate": 0.00011154846369695863, | |
| "loss": 0.1399, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.02689618074233459, | |
| "grad_norm": 2.2921817302703857, | |
| "learning_rate": 0.00010825793454723325, | |
| "loss": 0.091, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02689618074233459, | |
| "eval_loss": 0.21423955261707306, | |
| "eval_runtime": 482.3607, | |
| "eval_samples_per_second": 1.623, | |
| "eval_steps_per_second": 0.813, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.382181645582336e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |