| { | |
| "best_metric": 0.7489719390869141, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.016435204207412277, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00032870408414824553, | |
| "grad_norm": 6.7998504638671875, | |
| "learning_rate": 5e-05, | |
| "loss": 7.4841, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00032870408414824553, | |
| "eval_loss": 7.972625732421875, | |
| "eval_runtime": 2155.344, | |
| "eval_samples_per_second": 9.509, | |
| "eval_steps_per_second": 1.189, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006574081682964911, | |
| "grad_norm": 7.001423358917236, | |
| "learning_rate": 0.0001, | |
| "loss": 7.3824, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0009861122524447367, | |
| "grad_norm": 7.489500045776367, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 7.3376, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0013148163365929821, | |
| "grad_norm": 8.27587890625, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 4.7217, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0016435204207412278, | |
| "grad_norm": 6.817953109741211, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.3513, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0019722245048894734, | |
| "grad_norm": 3.7894959449768066, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.3255, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0023009285890377186, | |
| "grad_norm": 1.6379387378692627, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.94, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0026296326731859642, | |
| "grad_norm": 3.812008857727051, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.118, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00295833675733421, | |
| "grad_norm": 5.046061992645264, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.0113, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0032870408414824555, | |
| "grad_norm": 1.9192111492156982, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.8087, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003615744925630701, | |
| "grad_norm": 2.565617322921753, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.776, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.003944449009778947, | |
| "grad_norm": 2.1589443683624268, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.7718, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.004273153093927192, | |
| "grad_norm": 1.7386910915374756, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.7525, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.004601857178075437, | |
| "grad_norm": 0.905386745929718, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.7191, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.004930561262223683, | |
| "grad_norm": 1.1218856573104858, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.7873, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0052592653463719285, | |
| "grad_norm": 1.1609421968460083, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.7631, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.005587969430520174, | |
| "grad_norm": 0.9598643779754639, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.7264, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.00591667351466842, | |
| "grad_norm": 1.402292251586914, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.7519, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.006245377598816665, | |
| "grad_norm": 0.7951710224151611, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.6636, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.006574081682964911, | |
| "grad_norm": 1.159343957901001, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.7116, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006902785767113157, | |
| "grad_norm": 1.6361199617385864, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.7876, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.007231489851261402, | |
| "grad_norm": 1.2136658430099487, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.7738, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.007560193935409647, | |
| "grad_norm": 1.2736364603042603, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.8209, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.007888898019557894, | |
| "grad_norm": 1.6376301050186157, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.8366, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.008217602103706138, | |
| "grad_norm": 2.051626205444336, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.694, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.008217602103706138, | |
| "eval_loss": 0.7877915501594543, | |
| "eval_runtime": 1814.1467, | |
| "eval_samples_per_second": 11.297, | |
| "eval_steps_per_second": 1.412, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.008546306187854385, | |
| "grad_norm": 1.6266748905181885, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7129, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.00887501027200263, | |
| "grad_norm": 1.2160279750823975, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.7406, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.009203714356150874, | |
| "grad_norm": 1.0015685558319092, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.7597, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.009532418440299121, | |
| "grad_norm": 0.55552738904953, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.737, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.009861122524447366, | |
| "grad_norm": 0.5415008664131165, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.7192, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.010189826608595612, | |
| "grad_norm": 1.0667164325714111, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.738, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.010518530692743857, | |
| "grad_norm": 1.0163336992263794, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.7654, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.010847234776892103, | |
| "grad_norm": 0.5743635296821594, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.7435, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.011175938861040348, | |
| "grad_norm": 0.6187846660614014, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.7465, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.011504642945188595, | |
| "grad_norm": 0.5016359686851501, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.7376, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01183334702933684, | |
| "grad_norm": 0.46876969933509827, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.7177, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.012162051113485084, | |
| "grad_norm": 0.546317458152771, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.6776, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.01249075519763333, | |
| "grad_norm": 0.6002888083457947, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.6374, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.012819459281781576, | |
| "grad_norm": 0.9599287509918213, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.6531, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.013148163365929822, | |
| "grad_norm": 0.32457417249679565, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.7018, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.013476867450078067, | |
| "grad_norm": 0.39083102345466614, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.7042, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.013805571534226313, | |
| "grad_norm": 0.38013777136802673, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.7211, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.014134275618374558, | |
| "grad_norm": 0.7130141258239746, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.7401, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.014462979702522805, | |
| "grad_norm": 0.433555006980896, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.6968, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.01479168378667105, | |
| "grad_norm": 0.5339280366897583, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.6373, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.015120387870819294, | |
| "grad_norm": 0.5228230357170105, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.7326, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.01544909195496754, | |
| "grad_norm": 0.8945353031158447, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.7346, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.015777796039115787, | |
| "grad_norm": 0.7894071340560913, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.7375, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.01610650012326403, | |
| "grad_norm": 0.5900431275367737, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.6634, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.016435204207412277, | |
| "grad_norm": 0.824525773525238, | |
| "learning_rate": 0.0, | |
| "loss": 0.6322, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.016435204207412277, | |
| "eval_loss": 0.7489719390869141, | |
| "eval_runtime": 981.6847, | |
| "eval_samples_per_second": 20.877, | |
| "eval_steps_per_second": 2.61, | |
| "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": 1.0228361536208896e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |