| { | |
| "best_metric": 0.032030824571847916, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.721370604147881, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.014427412082957619, | |
| "grad_norm": 12.770562171936035, | |
| "learning_rate": 5e-05, | |
| "loss": 4.8158, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.014427412082957619, | |
| "eval_loss": 4.899957656860352, | |
| "eval_runtime": 32.9005, | |
| "eval_samples_per_second": 14.194, | |
| "eval_steps_per_second": 1.793, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.028854824165915238, | |
| "grad_norm": 12.038368225097656, | |
| "learning_rate": 0.0001, | |
| "loss": 4.3372, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04328223624887286, | |
| "grad_norm": 10.401562690734863, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 3.5381, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.057709648331830475, | |
| "grad_norm": 10.422679901123047, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.8847, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0721370604147881, | |
| "grad_norm": 7.631928443908691, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.9978, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08656447249774572, | |
| "grad_norm": 4.222036838531494, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.6336, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.10099188458070334, | |
| "grad_norm": 5.602912902832031, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.4358, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.11541929666366095, | |
| "grad_norm": 2.3386757373809814, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.3054, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.12984670874661858, | |
| "grad_norm": 3.5945801734924316, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.1667, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1442741208295762, | |
| "grad_norm": 2.0856850147247314, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.3064, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1587015329125338, | |
| "grad_norm": 1.8626433610916138, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.2161, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.17312894499549145, | |
| "grad_norm": 1.815616250038147, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.1882, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.18755635707844906, | |
| "grad_norm": 2.381495475769043, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.3416, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.20198376916140667, | |
| "grad_norm": 2.9028406143188477, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.3235, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.2164111812443643, | |
| "grad_norm": 1.7978252172470093, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.2324, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2308385933273219, | |
| "grad_norm": 1.1682114601135254, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.1501, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.24526600541027954, | |
| "grad_norm": 0.9924484491348267, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.1272, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.25969341749323716, | |
| "grad_norm": 1.2542763948440552, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.1947, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.27412082957619477, | |
| "grad_norm": 0.9769899249076843, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.1101, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2885482416591524, | |
| "grad_norm": 1.0046106576919556, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.1094, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.30297565374211, | |
| "grad_norm": 0.9217341542243958, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.0986, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.3174030658250676, | |
| "grad_norm": 1.1765563488006592, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.1346, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3318304779080252, | |
| "grad_norm": 1.1499828100204468, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.1222, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3462578899909829, | |
| "grad_norm": 1.1895837783813477, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.103, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3606853020739405, | |
| "grad_norm": 1.6911907196044922, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.1553, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3606853020739405, | |
| "eval_loss": 0.08920711278915405, | |
| "eval_runtime": 25.0663, | |
| "eval_samples_per_second": 18.631, | |
| "eval_steps_per_second": 2.354, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3751127141568981, | |
| "grad_norm": 1.3733659982681274, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1326, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.38954012623985573, | |
| "grad_norm": 1.0818101167678833, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.0961, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.40396753832281335, | |
| "grad_norm": 0.9106768369674683, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.09, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.41839495040577096, | |
| "grad_norm": 0.8540586233139038, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.0719, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.4328223624887286, | |
| "grad_norm": 0.49809011816978455, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0355, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4472497745716862, | |
| "grad_norm": 1.1465601921081543, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.1165, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.4616771866546438, | |
| "grad_norm": 1.0467514991760254, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0794, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.47610459873760147, | |
| "grad_norm": 0.6225173473358154, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.0427, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.4905320108205591, | |
| "grad_norm": 0.7643168568611145, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.053, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.5049594229035167, | |
| "grad_norm": 0.3798767626285553, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0249, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.5193868349864743, | |
| "grad_norm": 0.45972785353660583, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.0295, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5338142470694319, | |
| "grad_norm": 0.8855461478233337, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.0541, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5482416591523895, | |
| "grad_norm": 0.8349403738975525, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0784, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5626690712353472, | |
| "grad_norm": 1.1553421020507812, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.0662, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5770964833183048, | |
| "grad_norm": 0.6340785026550293, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.0282, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5915238954012624, | |
| "grad_norm": 0.7049694657325745, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0432, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.60595130748422, | |
| "grad_norm": 0.3650566339492798, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.0179, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.6203787195671776, | |
| "grad_norm": 0.7143826484680176, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.0569, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.6348061316501352, | |
| "grad_norm": 0.7505943179130554, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0829, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6492335437330928, | |
| "grad_norm": 0.2939123213291168, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.0217, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6636609558160504, | |
| "grad_norm": 0.6556983590126038, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.0513, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6780883678990082, | |
| "grad_norm": 0.6699650883674622, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0262, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6925157799819658, | |
| "grad_norm": 0.3060078024864197, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.0176, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.7069431920649234, | |
| "grad_norm": 0.27289947867393494, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.0141, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.721370604147881, | |
| "grad_norm": 0.819500207901001, | |
| "learning_rate": 0.0, | |
| "loss": 0.0505, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.721370604147881, | |
| "eval_loss": 0.032030824571847916, | |
| "eval_runtime": 25.0605, | |
| "eval_samples_per_second": 18.635, | |
| "eval_steps_per_second": 2.354, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "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": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.631381723512832e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |