| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.19895548371051977, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003979109674210396, | |
| "grad_norm": 2.9791555404663086, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6096, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003979109674210396, | |
| "eval_loss": NaN, | |
| "eval_runtime": 48.2331, | |
| "eval_samples_per_second": 35.1, | |
| "eval_steps_per_second": 4.395, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007958219348420791, | |
| "grad_norm": 3.1181411743164062, | |
| "learning_rate": 0.0001, | |
| "loss": 1.6967, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.011937329022631187, | |
| "grad_norm": 2.6549630165100098, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.5392, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.015916438696841582, | |
| "grad_norm": 1.4652327299118042, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.2583, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.019895548371051976, | |
| "grad_norm": 1.368378758430481, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.2953, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.023874658045262374, | |
| "grad_norm": 2.6306588649749756, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.3455, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.027853767719472768, | |
| "grad_norm": 2.6213881969451904, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.4012, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.031832877393683165, | |
| "grad_norm": 2.0289101600646973, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.3413, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.035811987067893555, | |
| "grad_norm": 1.663008451461792, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.2587, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03979109674210395, | |
| "grad_norm": 1.5361347198486328, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.2325, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04377020641631435, | |
| "grad_norm": 1.3923861980438232, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.125, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04774931609052475, | |
| "grad_norm": 1.616533637046814, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.0613, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.05172842576473514, | |
| "grad_norm": 2.5865578651428223, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.3307, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.055707535438945535, | |
| "grad_norm": 2.565897226333618, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.3238, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.05968664511315593, | |
| "grad_norm": 2.217618227005005, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.2669, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.06366575478736633, | |
| "grad_norm": 1.8191733360290527, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.2399, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.06764486446157672, | |
| "grad_norm": 1.3909547328948975, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.1286, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.07162397413578711, | |
| "grad_norm": 0.9595183730125427, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.1888, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.07560308380999751, | |
| "grad_norm": 1.9232794046401978, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.2461, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0795821934842079, | |
| "grad_norm": 2.469712972640991, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.2748, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08356130315841831, | |
| "grad_norm": 2.726212501525879, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.213, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0875404128326287, | |
| "grad_norm": 2.625605344772339, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.1716, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.09151952250683909, | |
| "grad_norm": 2.5767502784729004, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.226, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0954986321810495, | |
| "grad_norm": 2.509836196899414, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.1883, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.09947774185525989, | |
| "grad_norm": 2.764094352722168, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.1184, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.09947774185525989, | |
| "eval_loss": NaN, | |
| "eval_runtime": 48.2239, | |
| "eval_samples_per_second": 35.107, | |
| "eval_steps_per_second": 4.396, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.10345685152947028, | |
| "grad_norm": 0.6516526937484741, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0348, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.10743596120368068, | |
| "grad_norm": 0.789240837097168, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.0676, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.11141507087789107, | |
| "grad_norm": 0.8339486718177795, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.1012, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.11539418055210146, | |
| "grad_norm": 0.896287739276886, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.1229, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.11937329022631187, | |
| "grad_norm": 0.9912587404251099, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.1645, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.12335239990052226, | |
| "grad_norm": 0.889596164226532, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.0521, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.12733150957473266, | |
| "grad_norm": 0.9579912424087524, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.1043, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.13131061924894305, | |
| "grad_norm": 1.0357494354248047, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.0756, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.13528972892315344, | |
| "grad_norm": 1.0748677253723145, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.058, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.13926883859736383, | |
| "grad_norm": 1.1622072458267212, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.963, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.14324794827157422, | |
| "grad_norm": 1.2325820922851562, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.0536, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.14722705794578464, | |
| "grad_norm": 1.3320115804672241, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.0085, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.15120616761999503, | |
| "grad_norm": 0.662959635257721, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.9924, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.15518527729420542, | |
| "grad_norm": 0.5767291188240051, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.0112, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1591643869684158, | |
| "grad_norm": 0.6378970742225647, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.0152, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1631434966426262, | |
| "grad_norm": 0.671429455280304, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.0604, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.16712260631683662, | |
| "grad_norm": 0.7947982549667358, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.1157, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.171101715991047, | |
| "grad_norm": 0.8399484753608704, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.2089, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.1750808256652574, | |
| "grad_norm": 0.9737657904624939, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.1138, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1790599353394678, | |
| "grad_norm": 0.9923420548439026, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.1005, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.18303904501367818, | |
| "grad_norm": 1.116300106048584, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.0755, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.18701815468788857, | |
| "grad_norm": 1.0894296169281006, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.0124, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.190997264362099, | |
| "grad_norm": 1.2329972982406616, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.0821, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.19497637403630938, | |
| "grad_norm": 1.27621591091156, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.023, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.19895548371051977, | |
| "grad_norm": 1.7285157442092896, | |
| "learning_rate": 0.0, | |
| "loss": 1.0262, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.19895548371051977, | |
| "eval_loss": NaN, | |
| "eval_runtime": 48.3094, | |
| "eval_samples_per_second": 35.045, | |
| "eval_steps_per_second": 4.388, | |
| "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": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.589463780163584e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |