| { | |
| "best_metric": 11.050453186035156, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.19300361881785283, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0038600723763570566, | |
| "grad_norm": 4.272080898284912, | |
| "learning_rate": 5e-05, | |
| "loss": 11.0898, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0038600723763570566, | |
| "eval_loss": 11.0899019241333, | |
| "eval_runtime": 1.8216, | |
| "eval_samples_per_second": 957.975, | |
| "eval_steps_per_second": 120.227, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007720144752714113, | |
| "grad_norm": 4.217146873474121, | |
| "learning_rate": 0.0001, | |
| "loss": 11.0862, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01158021712907117, | |
| "grad_norm": 4.589000225067139, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 11.0849, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.015440289505428226, | |
| "grad_norm": 4.838542461395264, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 11.0859, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.019300361881785282, | |
| "grad_norm": 5.116698265075684, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 11.0849, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02316043425814234, | |
| "grad_norm": 4.157015323638916, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 11.0858, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.027020506634499397, | |
| "grad_norm": 4.388658046722412, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 11.0843, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.030880579010856453, | |
| "grad_norm": 4.618198871612549, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 11.0835, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03474065138721351, | |
| "grad_norm": 4.6166276931762695, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 11.0822, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.038600723763570564, | |
| "grad_norm": 4.856595993041992, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 11.074, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04246079613992763, | |
| "grad_norm": 4.96979284286499, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 11.0747, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04632086851628468, | |
| "grad_norm": 5.501377582550049, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 11.0702, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.05018094089264174, | |
| "grad_norm": 4.807370662689209, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 11.0664, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.054041013268998794, | |
| "grad_norm": 4.258703231811523, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 11.0712, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.05790108564535585, | |
| "grad_norm": 4.211122989654541, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 11.0717, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.061761158021712906, | |
| "grad_norm": 4.176085948944092, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 11.0681, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.06562123039806997, | |
| "grad_norm": 4.601294994354248, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 11.0634, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.06948130277442702, | |
| "grad_norm": 4.531471252441406, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 11.0651, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.07334137515078408, | |
| "grad_norm": 3.695352554321289, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 11.0707, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.07720144752714113, | |
| "grad_norm": 3.846127510070801, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 11.0624, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08106151990349819, | |
| "grad_norm": 3.707059621810913, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 11.0589, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.08492159227985525, | |
| "grad_norm": 4.043831825256348, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 11.058, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0887816646562123, | |
| "grad_norm": 4.06102180480957, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 11.0572, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.09264173703256937, | |
| "grad_norm": 4.315989971160889, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 11.053, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.09650180940892641, | |
| "grad_norm": 4.479373931884766, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 11.0506, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.09650180940892641, | |
| "eval_loss": 11.057889938354492, | |
| "eval_runtime": 1.8106, | |
| "eval_samples_per_second": 963.753, | |
| "eval_steps_per_second": 120.952, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.10036188178528348, | |
| "grad_norm": 3.5759146213531494, | |
| "learning_rate": 5e-05, | |
| "loss": 11.0631, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.10422195416164053, | |
| "grad_norm": 3.4713640213012695, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 11.0568, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.10808202653799759, | |
| "grad_norm": 3.517700672149658, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 11.0592, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.11194209891435464, | |
| "grad_norm": 3.803478479385376, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 11.0491, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.1158021712907117, | |
| "grad_norm": 3.692575216293335, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 11.0552, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11966224366706876, | |
| "grad_norm": 3.297511577606201, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 11.0584, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.12352231604342581, | |
| "grad_norm": 3.4056272506713867, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 11.055, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.12738238841978286, | |
| "grad_norm": 3.3810365200042725, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 11.0535, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.13124246079613994, | |
| "grad_norm": 3.5185937881469727, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 11.0526, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.13510253317249699, | |
| "grad_norm": 3.627316951751709, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 11.0508, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.13896260554885403, | |
| "grad_norm": 3.6404926776885986, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 11.0464, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.1428226779252111, | |
| "grad_norm": 3.660294532775879, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 11.04, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.14668275030156816, | |
| "grad_norm": 3.650830030441284, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 11.0468, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.1505428226779252, | |
| "grad_norm": 3.3983261585235596, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 11.0528, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.15440289505428226, | |
| "grad_norm": 3.4742696285247803, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 11.0479, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.15826296743063933, | |
| "grad_norm": 3.557180166244507, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 11.0481, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.16212303980699638, | |
| "grad_norm": 3.4408743381500244, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 11.0475, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.16598311218335343, | |
| "grad_norm": 3.4046168327331543, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 11.0487, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.1698431845597105, | |
| "grad_norm": 2.9810149669647217, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 11.0557, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.17370325693606756, | |
| "grad_norm": 3.1998450756073, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 11.0516, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1775633293124246, | |
| "grad_norm": 3.363704204559326, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 11.0471, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.18142340168878165, | |
| "grad_norm": 3.268141746520996, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 11.0491, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.18528347406513873, | |
| "grad_norm": 3.6082420349121094, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 11.0462, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.18914354644149578, | |
| "grad_norm": 3.4948015213012695, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 11.0508, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.19300361881785283, | |
| "grad_norm": 3.8561291694641113, | |
| "learning_rate": 0.0, | |
| "loss": 11.042, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.19300361881785283, | |
| "eval_loss": 11.050453186035156, | |
| "eval_runtime": 1.8118, | |
| "eval_samples_per_second": 963.139, | |
| "eval_steps_per_second": 120.875, | |
| "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": 4202692608000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |