| { | |
| "best_metric": 1.1884355545043945, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.02226737551145378, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00044534751022907564, | |
| "grad_norm": 47.07219696044922, | |
| "learning_rate": 5e-05, | |
| "loss": 5.2543, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00044534751022907564, | |
| "eval_loss": 6.243781089782715, | |
| "eval_runtime": 744.7627, | |
| "eval_samples_per_second": 20.313, | |
| "eval_steps_per_second": 2.539, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008906950204581513, | |
| "grad_norm": 45.64754867553711, | |
| "learning_rate": 0.0001, | |
| "loss": 5.2971, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001336042530687227, | |
| "grad_norm": 47.91440200805664, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 5.4586, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0017813900409163026, | |
| "grad_norm": 70.59400939941406, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 5.7296, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002226737551145378, | |
| "grad_norm": 76.9289779663086, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 4.7535, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002672085061374454, | |
| "grad_norm": 85.37005615234375, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 4.4255, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0031174325716035295, | |
| "grad_norm": 78.97339630126953, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 3.985, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.003562780081832605, | |
| "grad_norm": 72.35723876953125, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.5995, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00400812759206168, | |
| "grad_norm": 47.47407150268555, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 3.2972, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004453475102290756, | |
| "grad_norm": 50.4141731262207, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.7779, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0048988226125198315, | |
| "grad_norm": 49.30196762084961, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.5713, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.005344170122748908, | |
| "grad_norm": 48.11530303955078, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.6868, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0057895176329779835, | |
| "grad_norm": 44.87623596191406, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.4733, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.006234865143207059, | |
| "grad_norm": 37.1474494934082, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.1475, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.006680212653436135, | |
| "grad_norm": 39.766693115234375, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.8127, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00712556016366521, | |
| "grad_norm": 44.069801330566406, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.7889, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.007570907673894286, | |
| "grad_norm": 41.7119255065918, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.8528, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.00801625518412336, | |
| "grad_norm": 44.02607345581055, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.6579, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.008461602694352437, | |
| "grad_norm": 44.727508544921875, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.592, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.008906950204581512, | |
| "grad_norm": 30.102256774902344, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.3037, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.009352297714810588, | |
| "grad_norm": 35.799583435058594, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.3378, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.009797645225039663, | |
| "grad_norm": 38.51300811767578, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.5105, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01024299273526874, | |
| "grad_norm": 37.920658111572266, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.4866, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.010688340245497816, | |
| "grad_norm": 36.737457275390625, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.3023, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01113368775572689, | |
| "grad_norm": 34.89516830444336, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.4595, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01113368775572689, | |
| "eval_loss": 1.3559179306030273, | |
| "eval_runtime": 747.1899, | |
| "eval_samples_per_second": 20.247, | |
| "eval_steps_per_second": 2.531, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.011579035265955967, | |
| "grad_norm": 32.98725891113281, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5365, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.012024382776185042, | |
| "grad_norm": 32.930747985839844, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.4982, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.012469730286414118, | |
| "grad_norm": 28.717748641967773, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.1867, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.012915077796643193, | |
| "grad_norm": 30.79573631286621, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.2698, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.01336042530687227, | |
| "grad_norm": 27.480850219726562, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.1484, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.013805772817101344, | |
| "grad_norm": 30.580167770385742, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.1711, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.01425112032733042, | |
| "grad_norm": 29.669355392456055, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.0647, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.014696467837559495, | |
| "grad_norm": 27.924560546875, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.3464, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.015141815347788572, | |
| "grad_norm": 27.85472869873047, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.0039, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.015587162858017646, | |
| "grad_norm": 38.81391525268555, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.1041, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01603251036824672, | |
| "grad_norm": 31.527891159057617, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.177, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.016477857878475798, | |
| "grad_norm": 29.892866134643555, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.0821, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.016923205388704874, | |
| "grad_norm": 42.137596130371094, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.2294, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.01736855289893395, | |
| "grad_norm": 31.368568420410156, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.3406, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.017813900409163023, | |
| "grad_norm": 25.95120620727539, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.1407, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0182592479193921, | |
| "grad_norm": 28.08237648010254, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.168, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.018704595429621176, | |
| "grad_norm": 28.876585006713867, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.0792, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.019149942939850253, | |
| "grad_norm": 31.20652961730957, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.2324, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.019595290450079326, | |
| "grad_norm": 40.13499450683594, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.9863, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.020040637960308402, | |
| "grad_norm": 33.80912780761719, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.0541, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02048598547053748, | |
| "grad_norm": 34.41985321044922, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.3358, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.020931332980766555, | |
| "grad_norm": 26.706026077270508, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.0551, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.02137668049099563, | |
| "grad_norm": 33.23057174682617, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.1884, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.021822028001224705, | |
| "grad_norm": 31.000152587890625, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.1141, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.02226737551145378, | |
| "grad_norm": 34.39252853393555, | |
| "learning_rate": 0.0, | |
| "loss": 1.2389, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02226737551145378, | |
| "eval_loss": 1.1884355545043945, | |
| "eval_runtime": 748.0826, | |
| "eval_samples_per_second": 20.222, | |
| "eval_steps_per_second": 2.528, | |
| "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": 1.0952750720352256e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |