| { | |
| "best_metric": 2.279601573944092, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.13173061090070806, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002634612218014161, | |
| "grad_norm": 3.7004904747009277, | |
| "learning_rate": 5e-05, | |
| "loss": 3.3357, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002634612218014161, | |
| "eval_loss": 3.7921037673950195, | |
| "eval_runtime": 83.8421, | |
| "eval_samples_per_second": 30.498, | |
| "eval_steps_per_second": 3.817, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005269224436028322, | |
| "grad_norm": 4.056653022766113, | |
| "learning_rate": 0.0001, | |
| "loss": 3.4321, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007903836654042483, | |
| "grad_norm": 3.613128423690796, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 3.2043, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010538448872056645, | |
| "grad_norm": 2.3369836807250977, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.7478, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.013173061090070805, | |
| "grad_norm": 2.1272072792053223, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.4311, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.015807673308084965, | |
| "grad_norm": 1.9916740655899048, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.4115, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01844228552609913, | |
| "grad_norm": 1.659110188484192, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.299, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02107689774411329, | |
| "grad_norm": 1.9141302108764648, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.4022, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02371150996212745, | |
| "grad_norm": 1.782318115234375, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.3077, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02634612218014161, | |
| "grad_norm": 1.637131690979004, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.2941, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02898073439815577, | |
| "grad_norm": 1.4875625371932983, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.2788, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03161534661616993, | |
| "grad_norm": 1.896338701248169, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.1422, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.034249958834184094, | |
| "grad_norm": 2.6705243587493896, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.6537, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03688457105219826, | |
| "grad_norm": 3.0532562732696533, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.5635, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.039519183270212414, | |
| "grad_norm": 1.8682883977890015, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.5155, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04215379548822658, | |
| "grad_norm": 1.363270878791809, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.4212, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.044788407706240735, | |
| "grad_norm": 1.2420154809951782, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 2.3214, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0474230199242549, | |
| "grad_norm": 1.5372400283813477, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.4063, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05005763214226906, | |
| "grad_norm": 1.3143343925476074, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.3189, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05269224436028322, | |
| "grad_norm": 1.522864580154419, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.3619, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05532685657829738, | |
| "grad_norm": 1.3693466186523438, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 2.3427, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05796146879631154, | |
| "grad_norm": 1.3375619649887085, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 2.1721, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0605960810143257, | |
| "grad_norm": 1.2832212448120117, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 2.2632, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.06323069323233986, | |
| "grad_norm": 1.3973746299743652, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 2.159, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06586530545035403, | |
| "grad_norm": 1.6126805543899536, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 2.0133, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06586530545035403, | |
| "eval_loss": 2.317429780960083, | |
| "eval_runtime": 84.2768, | |
| "eval_samples_per_second": 30.341, | |
| "eval_steps_per_second": 3.797, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06849991766836819, | |
| "grad_norm": 1.438060998916626, | |
| "learning_rate": 5e-05, | |
| "loss": 2.4561, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.07113452988638234, | |
| "grad_norm": 1.4393006563186646, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 2.4412, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07376914210439652, | |
| "grad_norm": 1.3842298984527588, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 2.4253, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.07640375432241067, | |
| "grad_norm": 1.2816487550735474, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 2.3898, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.07903836654042483, | |
| "grad_norm": 1.2254124879837036, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 2.3172, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08167297875843899, | |
| "grad_norm": 1.1389992237091064, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 2.2249, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.08430759097645316, | |
| "grad_norm": 1.2742527723312378, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.2767, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.08694220319446731, | |
| "grad_norm": 1.1469522714614868, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 2.341, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.08957681541248147, | |
| "grad_norm": 1.3233062028884888, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.3118, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.09221142763049564, | |
| "grad_norm": 1.3203026056289673, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 2.2315, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0948460398485098, | |
| "grad_norm": 1.3014671802520752, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 2.2017, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.09748065206652395, | |
| "grad_norm": 1.498002529144287, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 2.1095, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.10011526428453812, | |
| "grad_norm": 1.0392613410949707, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.4473, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.10274987650255228, | |
| "grad_norm": 0.9770948886871338, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 2.3847, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.10538448872056644, | |
| "grad_norm": 1.0258359909057617, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 2.4703, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10801910093858061, | |
| "grad_norm": 1.0511903762817383, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 2.399, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.11065371315659477, | |
| "grad_norm": 1.0126500129699707, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 2.3849, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.11328832537460892, | |
| "grad_norm": 1.061611294746399, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 2.3324, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.11592293759262308, | |
| "grad_norm": 1.1187413930892944, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.3951, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.11855754981063725, | |
| "grad_norm": 1.0918892621994019, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 2.1854, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1211921620286514, | |
| "grad_norm": 1.1284306049346924, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 2.2851, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.12382677424666556, | |
| "grad_norm": 1.0848690271377563, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 2.1642, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.12646138646467972, | |
| "grad_norm": 1.2179816961288452, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 2.2824, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1290959986826939, | |
| "grad_norm": 1.3205076456069946, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 2.1305, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.13173061090070806, | |
| "grad_norm": 1.5582979917526245, | |
| "learning_rate": 0.0, | |
| "loss": 2.0369, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13173061090070806, | |
| "eval_loss": 2.279601573944092, | |
| "eval_runtime": 84.3886, | |
| "eval_samples_per_second": 30.3, | |
| "eval_steps_per_second": 3.792, | |
| "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": 6.174479344467968e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |