| { | |
| "best_metric": 0.6489943265914917, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.3021001615508885, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.025848142164781908, | |
| "grad_norm": 4.880069255828857, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5723, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.025848142164781908, | |
| "eval_loss": 4.013998508453369, | |
| "eval_runtime": 7.9669, | |
| "eval_samples_per_second": 32.761, | |
| "eval_steps_per_second": 4.142, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.051696284329563816, | |
| "grad_norm": 9.304342269897461, | |
| "learning_rate": 0.0001, | |
| "loss": 2.0352, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.07754442649434572, | |
| "grad_norm": 9.894126892089844, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.0236, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.10339256865912763, | |
| "grad_norm": 10.942134857177734, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.7414, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.12924071082390953, | |
| "grad_norm": 5.521557331085205, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.8353, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.15508885298869143, | |
| "grad_norm": 10.370209693908691, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.7426, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.18093699515347333, | |
| "grad_norm": 3.6883773803710938, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.6915, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.20678513731825526, | |
| "grad_norm": 3.1144471168518066, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.5608, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.23263327948303716, | |
| "grad_norm": 2.9336555004119873, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.5569, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.25848142164781907, | |
| "grad_norm": 5.899685382843018, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.2174, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.284329563812601, | |
| "grad_norm": 4.57917594909668, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.1618, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.31017770597738287, | |
| "grad_norm": 2.7850589752197266, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.8585, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.3360258481421648, | |
| "grad_norm": 3.2607767581939697, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.862, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.36187399030694667, | |
| "grad_norm": 4.28148078918457, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.8488, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3877221324717286, | |
| "grad_norm": 3.7991559505462646, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.814, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.4135702746365105, | |
| "grad_norm": 3.3533058166503906, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.5973, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.4394184168012924, | |
| "grad_norm": 2.7965564727783203, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.4449, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.46526655896607433, | |
| "grad_norm": 2.6489598751068115, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.5361, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.4911147011308562, | |
| "grad_norm": 3.193338394165039, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.602, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.5169628432956381, | |
| "grad_norm": 2.7645440101623535, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.1143, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5428109854604201, | |
| "grad_norm": 4.164054870605469, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.1591, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.568659127625202, | |
| "grad_norm": 3.5855021476745605, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.0142, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.5945072697899838, | |
| "grad_norm": 2.638758420944214, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.7719, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.6203554119547657, | |
| "grad_norm": 2.7778890132904053, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.5908, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.6462035541195477, | |
| "grad_norm": 1.9736764430999756, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.4878, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6462035541195477, | |
| "eval_loss": 0.6939923167228699, | |
| "eval_runtime": 7.9374, | |
| "eval_samples_per_second": 32.883, | |
| "eval_steps_per_second": 4.158, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6720516962843296, | |
| "grad_norm": 2.508800745010376, | |
| "learning_rate": 5e-05, | |
| "loss": 0.628, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.6978998384491115, | |
| "grad_norm": 2.8532986640930176, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.5209, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.7237479806138933, | |
| "grad_norm": 3.32419490814209, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.6523, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.7495961227786753, | |
| "grad_norm": 1.6802136898040771, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.0802, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.7754442649434572, | |
| "grad_norm": 1.3012361526489258, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.0615, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.8012924071082391, | |
| "grad_norm": 1.8923187255859375, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.7458, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.827140549273021, | |
| "grad_norm": 2.164623975753784, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.6567, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.8529886914378029, | |
| "grad_norm": 2.3818938732147217, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.6405, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.8788368336025848, | |
| "grad_norm": 2.1383883953094482, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.5945, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.9046849757673667, | |
| "grad_norm": 2.281585693359375, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.5481, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.9305331179321487, | |
| "grad_norm": 2.466137647628784, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.4819, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.9563812600969306, | |
| "grad_norm": 2.864682912826538, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.4667, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.9822294022617124, | |
| "grad_norm": 3.9639532566070557, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.6574, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.0177705977382876, | |
| "grad_norm": 2.692258596420288, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.5385, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.0436187399030694, | |
| "grad_norm": 1.938528060913086, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.7774, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.0694668820678515, | |
| "grad_norm": 2.162245988845825, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.5262, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.0953150242326333, | |
| "grad_norm": 1.9805015325546265, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.4586, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.121163166397415, | |
| "grad_norm": 2.3543405532836914, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.4878, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.1470113085621971, | |
| "grad_norm": 2.19230318069458, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.4103, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.172859450726979, | |
| "grad_norm": 2.6225059032440186, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.4584, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.198707592891761, | |
| "grad_norm": 2.018688678741455, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.297, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.2245557350565428, | |
| "grad_norm": 2.281841993331909, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.3342, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.2504038772213248, | |
| "grad_norm": 1.823398232460022, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.583, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.2762520193861067, | |
| "grad_norm": 2.1011440753936768, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.1869, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.3021001615508885, | |
| "grad_norm": 2.315281391143799, | |
| "learning_rate": 0.0, | |
| "loss": 0.7053, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.3021001615508885, | |
| "eval_loss": 0.6489943265914917, | |
| "eval_runtime": 7.9368, | |
| "eval_samples_per_second": 32.885, | |
| "eval_steps_per_second": 4.158, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 5.658024559509504e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |