| { | |
| "best_metric": 3.769723415374756, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 2.9197080291970803, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.058394160583941604, | |
| "grad_norm": 7.178121089935303, | |
| "learning_rate": 5e-05, | |
| "loss": 5.6547, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.058394160583941604, | |
| "eval_loss": 10.544025421142578, | |
| "eval_runtime": 4.2843, | |
| "eval_samples_per_second": 27.076, | |
| "eval_steps_per_second": 3.501, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11678832116788321, | |
| "grad_norm": 10.532174110412598, | |
| "learning_rate": 0.0001, | |
| "loss": 8.3479, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.17518248175182483, | |
| "grad_norm": 11.256950378417969, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 10.3404, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.23357664233576642, | |
| "grad_norm": 11.276129722595215, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 12.5499, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.291970802919708, | |
| "grad_norm": 6.291708946228027, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 5.0173, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.35036496350364965, | |
| "grad_norm": 7.52332878112793, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 5.1909, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.40875912408759124, | |
| "grad_norm": 11.636759757995605, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 5.2024, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.46715328467153283, | |
| "grad_norm": 14.254714012145996, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 5.1898, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5255474452554745, | |
| "grad_norm": 19.869718551635742, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 5.0212, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.583941605839416, | |
| "grad_norm": 28.700305938720703, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 5.0837, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6423357664233577, | |
| "grad_norm": 17.099992752075195, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 4.4892, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.7007299270072993, | |
| "grad_norm": 6.795928001403809, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 3.9635, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.7591240875912408, | |
| "grad_norm": 11.230073928833008, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 4.6467, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.8175182481751825, | |
| "grad_norm": 7.433228015899658, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.7848, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.8759124087591241, | |
| "grad_norm": 8.049349784851074, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 3.0702, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.9343065693430657, | |
| "grad_norm": 11.795612335205078, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 3.7323, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.9927007299270073, | |
| "grad_norm": 22.33142852783203, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 6.9964, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.051094890510949, | |
| "grad_norm": 12.504145622253418, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 4.5506, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.1094890510948905, | |
| "grad_norm": 4.087507247924805, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.3913, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.167883211678832, | |
| "grad_norm": 5.464754581451416, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.9846, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.2262773722627738, | |
| "grad_norm": 9.033888816833496, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 4.1974, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.2846715328467153, | |
| "grad_norm": 10.449952125549316, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 3.1968, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.343065693430657, | |
| "grad_norm": 4.285083293914795, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 2.4567, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.4014598540145986, | |
| "grad_norm": 3.442805528640747, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 2.79, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.4598540145985401, | |
| "grad_norm": 5.1094489097595215, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 3.548, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.4598540145985401, | |
| "eval_loss": 4.088964939117432, | |
| "eval_runtime": 4.2886, | |
| "eval_samples_per_second": 27.049, | |
| "eval_steps_per_second": 3.498, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.5182481751824817, | |
| "grad_norm": 8.438632011413574, | |
| "learning_rate": 5e-05, | |
| "loss": 2.9593, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.5766423357664232, | |
| "grad_norm": 4.3603973388671875, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 2.233, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.635036496350365, | |
| "grad_norm": 3.5132715702056885, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 2.6478, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.6934306569343067, | |
| "grad_norm": 5.387185573577881, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 3.4366, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.7518248175182483, | |
| "grad_norm": 10.731122970581055, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 3.3479, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.8102189781021898, | |
| "grad_norm": 4.213603973388672, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 2.4378, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.8686131386861313, | |
| "grad_norm": 3.420297861099243, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.438, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.9270072992700729, | |
| "grad_norm": 4.06689453125, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 3.0176, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.9854014598540146, | |
| "grad_norm": 13.928680419921875, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 4.8958, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.0437956204379564, | |
| "grad_norm": 13.590108871459961, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 4.3551, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.102189781021898, | |
| "grad_norm": 3.0986621379852295, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 2.0465, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.1605839416058394, | |
| "grad_norm": 3.8003571033477783, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 2.5161, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.218978102189781, | |
| "grad_norm": 5.729832172393799, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 3.7431, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.2773722627737225, | |
| "grad_norm": 8.212564468383789, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 2.6757, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.335766423357664, | |
| "grad_norm": 3.1556713581085205, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.9733, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.394160583941606, | |
| "grad_norm": 3.279280662536621, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 2.4297, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.4525547445255476, | |
| "grad_norm": 4.959506511688232, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 3.1727, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.510948905109489, | |
| "grad_norm": 10.50008773803711, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 2.6681, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.5693430656934306, | |
| "grad_norm": 3.126262903213501, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.1269, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.627737226277372, | |
| "grad_norm": 3.2277610301971436, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 2.2094, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.686131386861314, | |
| "grad_norm": 4.040760517120361, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 3.1212, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.7445255474452557, | |
| "grad_norm": 9.804378509521484, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 2.8362, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.802919708029197, | |
| "grad_norm": 4.868627548217773, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 2.4408, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.8613138686131387, | |
| "grad_norm": 2.8890411853790283, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 2.1388, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.9197080291970803, | |
| "grad_norm": 4.135127067565918, | |
| "learning_rate": 0.0, | |
| "loss": 2.9231, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.9197080291970803, | |
| "eval_loss": 3.769723415374756, | |
| "eval_runtime": 9.422, | |
| "eval_samples_per_second": 12.312, | |
| "eval_steps_per_second": 1.592, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 6.823228785819648e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |