| { | |
| "best_metric": 11.054489135742188, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.08156606851549755, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0032626427406199023, | |
| "grad_norm": 0.8411857485771179, | |
| "learning_rate": 2e-05, | |
| "loss": 44.3182, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0032626427406199023, | |
| "eval_loss": 11.076725006103516, | |
| "eval_runtime": 0.7805, | |
| "eval_samples_per_second": 166.55, | |
| "eval_steps_per_second": 83.275, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0065252854812398045, | |
| "grad_norm": 0.9571336507797241, | |
| "learning_rate": 4e-05, | |
| "loss": 44.2994, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.009787928221859706, | |
| "grad_norm": 0.9268866181373596, | |
| "learning_rate": 6e-05, | |
| "loss": 44.2888, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.013050570962479609, | |
| "grad_norm": 0.8766740560531616, | |
| "learning_rate": 8e-05, | |
| "loss": 44.3059, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01631321370309951, | |
| "grad_norm": 0.8909149169921875, | |
| "learning_rate": 0.0001, | |
| "loss": 44.2964, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01631321370309951, | |
| "eval_loss": 11.075915336608887, | |
| "eval_runtime": 0.7908, | |
| "eval_samples_per_second": 164.387, | |
| "eval_steps_per_second": 82.194, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01957585644371941, | |
| "grad_norm": 0.886552095413208, | |
| "learning_rate": 0.00012, | |
| "loss": 44.2916, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.022838499184339316, | |
| "grad_norm": 0.9055843353271484, | |
| "learning_rate": 0.00014, | |
| "loss": 44.298, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.026101141924959218, | |
| "grad_norm": 0.9514639377593994, | |
| "learning_rate": 0.00016, | |
| "loss": 44.2994, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02936378466557912, | |
| "grad_norm": 0.969403862953186, | |
| "learning_rate": 0.00018, | |
| "loss": 44.279, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03262642740619902, | |
| "grad_norm": 0.8920151591300964, | |
| "learning_rate": 0.0002, | |
| "loss": 44.32, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03262642740619902, | |
| "eval_loss": 11.071589469909668, | |
| "eval_runtime": 0.7901, | |
| "eval_samples_per_second": 164.528, | |
| "eval_steps_per_second": 82.264, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03588907014681892, | |
| "grad_norm": 0.9465475082397461, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 44.2657, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03915171288743882, | |
| "grad_norm": 0.8892057538032532, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 44.2746, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04241435562805873, | |
| "grad_norm": 0.8875570893287659, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 44.2504, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04567699836867863, | |
| "grad_norm": 0.9216701984405518, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 44.2465, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.048939641109298535, | |
| "grad_norm": 0.8484591841697693, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 44.2617, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.048939641109298535, | |
| "eval_loss": 11.059526443481445, | |
| "eval_runtime": 0.7845, | |
| "eval_samples_per_second": 165.72, | |
| "eval_steps_per_second": 82.86, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.052202283849918436, | |
| "grad_norm": 0.9152474999427795, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 44.241, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05546492659053834, | |
| "grad_norm": 0.9288038611412048, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 44.2124, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.05872756933115824, | |
| "grad_norm": 0.9213078618049622, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 44.2012, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.06199021207177814, | |
| "grad_norm": 0.9989335536956787, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 44.2164, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06525285481239804, | |
| "grad_norm": 0.830315887928009, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 44.2418, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06525285481239804, | |
| "eval_loss": 11.055357933044434, | |
| "eval_runtime": 0.7665, | |
| "eval_samples_per_second": 169.595, | |
| "eval_steps_per_second": 84.797, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06851549755301795, | |
| "grad_norm": 0.9324968457221985, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 44.2029, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.07177814029363784, | |
| "grad_norm": 0.8638316988945007, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 44.2285, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.07504078303425775, | |
| "grad_norm": 0.9382745027542114, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 44.2117, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.07830342577487764, | |
| "grad_norm": 0.9010906219482422, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 44.2243, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.08156606851549755, | |
| "grad_norm": 0.9032869935035706, | |
| "learning_rate": 0.0, | |
| "loss": 44.2161, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08156606851549755, | |
| "eval_loss": 11.054489135742188, | |
| "eval_runtime": 0.7803, | |
| "eval_samples_per_second": 166.6, | |
| "eval_steps_per_second": 83.3, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "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": 20919091200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |