| { | |
| "best_metric": 0.046489227563142776, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.7272727272727273, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.014545454545454545, | |
| "grad_norm": 11.122056007385254, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4167, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.014545454545454545, | |
| "eval_loss": 0.18857043981552124, | |
| "eval_runtime": 19.4782, | |
| "eval_samples_per_second": 23.821, | |
| "eval_steps_per_second": 2.978, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02909090909090909, | |
| "grad_norm": 13.08956527709961, | |
| "learning_rate": 0.0001, | |
| "loss": 1.7712, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04363636363636364, | |
| "grad_norm": 5.339229106903076, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.3119, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05818181818181818, | |
| "grad_norm": 4.250042915344238, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.2045, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.07272727272727272, | |
| "grad_norm": 3.770613670349121, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.1808, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08727272727272728, | |
| "grad_norm": 3.206460475921631, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.2892, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.10181818181818182, | |
| "grad_norm": 2.934950113296509, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.1655, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.11636363636363636, | |
| "grad_norm": 2.8372652530670166, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.9887, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.13090909090909092, | |
| "grad_norm": 2.5660459995269775, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.9768, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.14545454545454545, | |
| "grad_norm": 3.0583393573760986, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.181, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 2.9071054458618164, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.1382, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.17454545454545456, | |
| "grad_norm": 3.245757579803467, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.2227, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1890909090909091, | |
| "grad_norm": 2.9858620166778564, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.1112, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.20363636363636364, | |
| "grad_norm": 1.5873949527740479, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.5932, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.21818181818181817, | |
| "grad_norm": 1.6085785627365112, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.667, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.23272727272727273, | |
| "grad_norm": 1.4847350120544434, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.6418, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.24727272727272728, | |
| "grad_norm": 2.0964653491973877, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.7563, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.26181818181818184, | |
| "grad_norm": 2.545894145965576, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.9086, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.27636363636363637, | |
| "grad_norm": 1.9859825372695923, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.8807, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2909090909090909, | |
| "grad_norm": 1.907730221748352, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.8434, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3054545454545455, | |
| "grad_norm": 1.9781832695007324, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.9239, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 2.078003406524658, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.0007, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.33454545454545453, | |
| "grad_norm": 1.9957249164581299, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.93, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3490909090909091, | |
| "grad_norm": 2.3853352069854736, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.1238, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.36363636363636365, | |
| "grad_norm": 5.109256267547607, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.1849, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.36363636363636365, | |
| "eval_loss": 0.049961287528276443, | |
| "eval_runtime": 19.8678, | |
| "eval_samples_per_second": 23.354, | |
| "eval_steps_per_second": 2.919, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3781818181818182, | |
| "grad_norm": 1.5513335466384888, | |
| "learning_rate": 5e-05, | |
| "loss": 0.418, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3927272727272727, | |
| "grad_norm": 1.1485812664031982, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.523, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.4072727272727273, | |
| "grad_norm": 1.2391613721847534, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.5771, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.4218181818181818, | |
| "grad_norm": 1.317054033279419, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.6581, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.43636363636363634, | |
| "grad_norm": 1.6672873497009277, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.7339, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4509090909090909, | |
| "grad_norm": 1.7663410902023315, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.8093, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.46545454545454545, | |
| "grad_norm": 1.8384978771209717, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.8133, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 1.6507760286331177, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.8096, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.49454545454545457, | |
| "grad_norm": 1.973745584487915, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.9453, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.509090909090909, | |
| "grad_norm": 2.1544129848480225, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.9739, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.5236363636363637, | |
| "grad_norm": 2.3645403385162354, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.0393, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5381818181818182, | |
| "grad_norm": 2.7798073291778564, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.2032, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5527272727272727, | |
| "grad_norm": 2.2902143001556396, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.8116, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5672727272727273, | |
| "grad_norm": 1.0294620990753174, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.4392, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5818181818181818, | |
| "grad_norm": 1.2548834085464478, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.5312, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5963636363636363, | |
| "grad_norm": 1.2893308401107788, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.5329, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.610909090909091, | |
| "grad_norm": 1.4130041599273682, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.6743, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.6254545454545455, | |
| "grad_norm": 1.6451098918914795, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.8124, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 1.6494089365005493, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.8184, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6545454545454545, | |
| "grad_norm": 1.5135403871536255, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.6655, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6690909090909091, | |
| "grad_norm": 1.7748284339904785, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.9069, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6836363636363636, | |
| "grad_norm": 1.7287698984146118, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.879, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6981818181818182, | |
| "grad_norm": 1.8177392482757568, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.9566, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.7127272727272728, | |
| "grad_norm": 2.316375732421875, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.0862, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": 3.1790921688079834, | |
| "learning_rate": 0.0, | |
| "loss": 1.3497, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "eval_loss": 0.046489227563142776, | |
| "eval_runtime": 19.4744, | |
| "eval_samples_per_second": 23.826, | |
| "eval_steps_per_second": 2.978, | |
| "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": 8.994485807947448e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |