| { | |
| "best_metric": 2.906017303466797, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.6498781478472786, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.012997562956945572, | |
| "grad_norm": 2.1815783977508545, | |
| "learning_rate": 5e-05, | |
| "loss": 4.2735, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012997562956945572, | |
| "eval_loss": 4.643681526184082, | |
| "eval_runtime": 4.5171, | |
| "eval_samples_per_second": 114.898, | |
| "eval_steps_per_second": 14.39, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.025995125913891144, | |
| "grad_norm": 2.4761829376220703, | |
| "learning_rate": 0.0001, | |
| "loss": 4.3582, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03899268887083672, | |
| "grad_norm": 2.5254948139190674, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 4.4128, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05199025182778229, | |
| "grad_norm": 2.0806477069854736, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 4.1466, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06498781478472786, | |
| "grad_norm": 1.82292902469635, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.8892, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07798537774167344, | |
| "grad_norm": 1.9830964803695679, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 3.8104, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09098294069861901, | |
| "grad_norm": 1.7637877464294434, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 3.6088, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.10398050365556458, | |
| "grad_norm": 1.730930209159851, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.4998, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.11697806661251016, | |
| "grad_norm": 1.2427796125411987, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 3.4402, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.12997562956945571, | |
| "grad_norm": 1.4184691905975342, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 3.3537, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1429731925264013, | |
| "grad_norm": 1.116524577140808, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 3.361, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.15597075548334688, | |
| "grad_norm": 1.3125693798065186, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 3.3196, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.16896831844029245, | |
| "grad_norm": 1.5652897357940674, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 3.3531, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.18196588139723802, | |
| "grad_norm": 1.2380902767181396, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.3461, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.19496344435418358, | |
| "grad_norm": 0.9211981892585754, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 3.2463, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.20796100731112915, | |
| "grad_norm": 1.0457210540771484, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 3.2257, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.22095857026807472, | |
| "grad_norm": 1.1892938613891602, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 3.1579, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.23395613322502032, | |
| "grad_norm": 1.3801074028015137, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 3.1586, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2469536961819659, | |
| "grad_norm": 1.560684323310852, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 3.1782, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.25995125913891143, | |
| "grad_norm": 1.7278943061828613, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 3.0888, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.272948822095857, | |
| "grad_norm": 1.8793681859970093, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 3.0725, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.2859463850528026, | |
| "grad_norm": 1.8100998401641846, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 3.1031, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.29894394800974816, | |
| "grad_norm": 1.5798654556274414, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 2.9822, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.31194151096669376, | |
| "grad_norm": 1.183044195175171, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 3.0436, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3249390739236393, | |
| "grad_norm": 0.942845344543457, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 2.9858, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3249390739236393, | |
| "eval_loss": 3.04049015045166, | |
| "eval_runtime": 4.5118, | |
| "eval_samples_per_second": 115.032, | |
| "eval_steps_per_second": 14.407, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3379366368805849, | |
| "grad_norm": 1.285607933998108, | |
| "learning_rate": 5e-05, | |
| "loss": 3.074, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.35093419983753044, | |
| "grad_norm": 1.0849254131317139, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 3.0416, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.36393176279447603, | |
| "grad_norm": 0.8848364353179932, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 3.0016, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.37692932575142163, | |
| "grad_norm": 0.8195856213569641, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 2.9401, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.38992688870836717, | |
| "grad_norm": 0.7989217042922974, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 2.9424, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.40292445166531277, | |
| "grad_norm": 1.0459684133529663, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 3.0352, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.4159220146222583, | |
| "grad_norm": 0.9750694036483765, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.9754, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.4289195775792039, | |
| "grad_norm": 0.9632560014724731, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 2.9216, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.44191714053614944, | |
| "grad_norm": 0.8961259722709656, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.9141, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.45491470349309504, | |
| "grad_norm": 0.8920239210128784, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 2.9091, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.46791226645004064, | |
| "grad_norm": 0.9372305870056152, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 2.9598, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.4809098294069862, | |
| "grad_norm": 0.9390608072280884, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 2.8996, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.4939073923639318, | |
| "grad_norm": 0.8650014996528625, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.9825, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5069049553208773, | |
| "grad_norm": 1.0225095748901367, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 3.0036, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5199025182778229, | |
| "grad_norm": 0.9922052621841431, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 2.9469, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5329000812347685, | |
| "grad_norm": 0.9688642621040344, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 2.9164, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.545897644191714, | |
| "grad_norm": 0.8949860334396362, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 2.9194, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5588952071486596, | |
| "grad_norm": 0.768169641494751, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 2.9348, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5718927701056052, | |
| "grad_norm": 0.8468419313430786, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.9256, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5848903330625508, | |
| "grad_norm": 0.7886675000190735, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 2.8906, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5978878960194963, | |
| "grad_norm": 0.8044082522392273, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 2.8235, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6108854589764419, | |
| "grad_norm": 0.7295715808868408, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 2.8605, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6238830219333875, | |
| "grad_norm": 0.7860828638076782, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 2.9205, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6368805848903331, | |
| "grad_norm": 0.7991708517074585, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 2.8495, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6498781478472786, | |
| "grad_norm": 0.9875921607017517, | |
| "learning_rate": 0.0, | |
| "loss": 2.891, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6498781478472786, | |
| "eval_loss": 2.906017303466797, | |
| "eval_runtime": 4.5116, | |
| "eval_samples_per_second": 115.037, | |
| "eval_steps_per_second": 14.407, | |
| "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": 7.83042868150272e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |