| { | |
| "best_metric": 1.580679178237915, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.9060022650056625, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01812004530011325, | |
| "grad_norm": 3.4313976764678955, | |
| "learning_rate": 5e-05, | |
| "loss": 2.8413, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01812004530011325, | |
| "eval_loss": 3.0799570083618164, | |
| "eval_runtime": 5.5107, | |
| "eval_samples_per_second": 67.505, | |
| "eval_steps_per_second": 8.529, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0362400906002265, | |
| "grad_norm": 3.271883726119995, | |
| "learning_rate": 0.0001, | |
| "loss": 2.8953, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.05436013590033975, | |
| "grad_norm": 3.337348699569702, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.85, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.072480181200453, | |
| "grad_norm": 2.874163866043091, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.5231, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.09060022650056625, | |
| "grad_norm": 2.444824457168579, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.4577, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1087202718006795, | |
| "grad_norm": 2.7738895416259766, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.2367, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.12684031710079274, | |
| "grad_norm": 2.341843605041504, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.2075, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.144960362400906, | |
| "grad_norm": 2.175292491912842, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.0947, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.16308040770101925, | |
| "grad_norm": 1.9448224306106567, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.9842, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1812004530011325, | |
| "grad_norm": 2.1992733478546143, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.8758, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.19932049830124576, | |
| "grad_norm": 2.2357699871063232, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.8661, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.217440543601359, | |
| "grad_norm": 2.4109785556793213, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.8779, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.23556058890147225, | |
| "grad_norm": 2.885878324508667, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.9331, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.2536806342015855, | |
| "grad_norm": 2.8825745582580566, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.9207, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.2718006795016987, | |
| "grad_norm": 1.4513825178146362, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.7996, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.289920724801812, | |
| "grad_norm": 1.592366099357605, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.7757, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.30804077010192527, | |
| "grad_norm": 1.6597822904586792, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.7923, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.3261608154020385, | |
| "grad_norm": 1.6842970848083496, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.8184, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.34428086070215175, | |
| "grad_norm": 1.4194010496139526, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.7352, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.362400906002265, | |
| "grad_norm": 1.407707691192627, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.6919, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.38052095130237823, | |
| "grad_norm": 1.2742618322372437, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.7242, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.3986409966024915, | |
| "grad_norm": 1.22260320186615, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.681, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.41676104190260477, | |
| "grad_norm": 1.375704050064087, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.5154, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.434881087202718, | |
| "grad_norm": 1.7079826593399048, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.6821, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.45300113250283125, | |
| "grad_norm": 2.1471540927886963, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.6327, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.45300113250283125, | |
| "eval_loss": 1.6661137342453003, | |
| "eval_runtime": 5.4731, | |
| "eval_samples_per_second": 67.969, | |
| "eval_steps_per_second": 8.587, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4711211778029445, | |
| "grad_norm": 2.759873628616333, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7678, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.48924122310305773, | |
| "grad_norm": 2.2776923179626465, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.6622, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.507361268403171, | |
| "grad_norm": 1.715643048286438, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.6111, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.5254813137032842, | |
| "grad_norm": 1.1728720664978027, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.7084, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.5436013590033975, | |
| "grad_norm": 1.093131422996521, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.5723, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5617214043035108, | |
| "grad_norm": 1.1297237873077393, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.6665, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.579841449603624, | |
| "grad_norm": 1.1554903984069824, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.6255, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.5979614949037373, | |
| "grad_norm": 1.2691186666488647, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.626, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.6160815402038505, | |
| "grad_norm": 1.2710535526275635, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.575, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.6342015855039638, | |
| "grad_norm": 1.1556159257888794, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.5889, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.652321630804077, | |
| "grad_norm": 1.3670322895050049, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.5913, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.6704416761041903, | |
| "grad_norm": 1.659157395362854, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.4877, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.6885617214043035, | |
| "grad_norm": 1.1815394163131714, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.6078, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.7066817667044167, | |
| "grad_norm": 0.9515262842178345, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.6307, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.72480181200453, | |
| "grad_norm": 1.057732105255127, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.6513, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7429218573046432, | |
| "grad_norm": 1.056545615196228, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.5733, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.7610419026047565, | |
| "grad_norm": 0.9949175119400024, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.5788, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.7791619479048698, | |
| "grad_norm": 1.1183514595031738, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.6422, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.797281993204983, | |
| "grad_norm": 0.9963149428367615, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.5984, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.8154020385050963, | |
| "grad_norm": 0.9642331600189209, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.551, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.8335220838052095, | |
| "grad_norm": 1.0647437572479248, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.5695, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.8516421291053228, | |
| "grad_norm": 1.0514017343521118, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.5329, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.869762174405436, | |
| "grad_norm": 1.249781608581543, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.6063, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.8878822197055493, | |
| "grad_norm": 1.281449317932129, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.53, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.9060022650056625, | |
| "grad_norm": 2.3760650157928467, | |
| "learning_rate": 0.0, | |
| "loss": 1.6412, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.9060022650056625, | |
| "eval_loss": 1.580679178237915, | |
| "eval_runtime": 2.5354, | |
| "eval_samples_per_second": 146.722, | |
| "eval_steps_per_second": 18.537, | |
| "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": 2.95300912644096e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |