| { | |
| "best_metric": 3.48060941696167, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.8676789587852495, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01735357917570499, | |
| "grad_norm": 0.4170111119747162, | |
| "learning_rate": 5e-05, | |
| "loss": 3.4937, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01735357917570499, | |
| "eval_loss": 4.655571460723877, | |
| "eval_runtime": 7.0046, | |
| "eval_samples_per_second": 55.535, | |
| "eval_steps_per_second": 6.995, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03470715835140998, | |
| "grad_norm": 0.6830735206604004, | |
| "learning_rate": 0.0001, | |
| "loss": 3.7561, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.052060737527114966, | |
| "grad_norm": 0.8404021263122559, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 3.8155, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06941431670281996, | |
| "grad_norm": 1.0794098377227783, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.9448, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.08676789587852494, | |
| "grad_norm": 1.107664942741394, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.9424, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.10412147505422993, | |
| "grad_norm": 0.918507993221283, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 3.866, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.12147505422993492, | |
| "grad_norm": 1.0156458616256714, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 3.9169, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.13882863340563992, | |
| "grad_norm": 0.9362125992774963, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.8416, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1561822125813449, | |
| "grad_norm": 1.0593806505203247, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 3.8265, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1735357917570499, | |
| "grad_norm": 1.35044527053833, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 3.8124, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.19088937093275488, | |
| "grad_norm": 1.6010715961456299, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 3.8055, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.20824295010845986, | |
| "grad_norm": 2.412663698196411, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 3.9354, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.22559652928416485, | |
| "grad_norm": 2.1417734622955322, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 3.3487, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.24295010845986983, | |
| "grad_norm": 2.07533597946167, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.6248, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.2603036876355748, | |
| "grad_norm": 1.414640188217163, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 3.5541, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.27765726681127983, | |
| "grad_norm": 0.8634867072105408, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 3.5574, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2950108459869848, | |
| "grad_norm": 0.7481741905212402, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 3.6066, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.3123644251626898, | |
| "grad_norm": 0.8131154775619507, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 3.6356, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3297180043383948, | |
| "grad_norm": 0.9127227067947388, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 3.6669, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.3470715835140998, | |
| "grad_norm": 1.0353364944458008, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 3.523, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3644251626898048, | |
| "grad_norm": 1.0504580736160278, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 3.6235, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.38177874186550975, | |
| "grad_norm": 1.1734845638275146, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 3.6677, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.39913232104121477, | |
| "grad_norm": 1.5449906587600708, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 3.7673, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.4164859002169197, | |
| "grad_norm": 1.9320975542068481, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 3.7706, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.43383947939262474, | |
| "grad_norm": 3.898677349090576, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 3.8721, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.43383947939262474, | |
| "eval_loss": 3.5544095039367676, | |
| "eval_runtime": 7.0046, | |
| "eval_samples_per_second": 55.535, | |
| "eval_steps_per_second": 6.995, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4511930585683297, | |
| "grad_norm": 0.786327064037323, | |
| "learning_rate": 5e-05, | |
| "loss": 3.2751, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.4685466377440347, | |
| "grad_norm": 1.0305312871932983, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 3.4125, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.48590021691973967, | |
| "grad_norm": 1.1478524208068848, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 3.5463, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.5032537960954447, | |
| "grad_norm": 1.2337690591812134, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 3.5402, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.5206073752711496, | |
| "grad_norm": 1.154429316520691, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 3.5452, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5379609544468547, | |
| "grad_norm": 0.9768087863922119, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 3.5021, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.5553145336225597, | |
| "grad_norm": 0.9559707641601562, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 3.5008, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.5726681127982647, | |
| "grad_norm": 0.9601343870162964, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 3.5435, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.5900216919739696, | |
| "grad_norm": 1.1038984060287476, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 3.5946, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.6073752711496746, | |
| "grad_norm": 1.253346562385559, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 3.5455, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.6247288503253796, | |
| "grad_norm": 1.8003921508789062, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 3.7233, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.6420824295010846, | |
| "grad_norm": 2.6431398391723633, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 3.5173, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.6594360086767896, | |
| "grad_norm": 0.43522414565086365, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 3.2058, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.6767895878524945, | |
| "grad_norm": 0.4335356652736664, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 3.3444, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.6941431670281996, | |
| "grad_norm": 0.45088207721710205, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 3.3811, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7114967462039046, | |
| "grad_norm": 0.5164139866828918, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 3.3587, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.7288503253796096, | |
| "grad_norm": 0.5385364294052124, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 3.4513, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.7462039045553145, | |
| "grad_norm": 0.6080254316329956, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 3.4158, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.7635574837310195, | |
| "grad_norm": 0.711311936378479, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 3.4986, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.7809110629067245, | |
| "grad_norm": 0.8071969747543335, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 3.45, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.7982646420824295, | |
| "grad_norm": 1.0393857955932617, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 3.4904, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.8156182212581344, | |
| "grad_norm": 1.210397720336914, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 3.5673, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.8329718004338394, | |
| "grad_norm": 1.5411838293075562, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 3.4864, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.8503253796095445, | |
| "grad_norm": 2.104750394821167, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 3.6277, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.8676789587852495, | |
| "grad_norm": 3.844982385635376, | |
| "learning_rate": 0.0, | |
| "loss": 3.8283, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8676789587852495, | |
| "eval_loss": 3.48060941696167, | |
| "eval_runtime": 6.9978, | |
| "eval_samples_per_second": 55.589, | |
| "eval_steps_per_second": 7.002, | |
| "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": 2.254995537788928e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |