| { | |
| "best_metric": 0.529956579208374, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.055509297807382736, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011101859561476548, | |
| "grad_norm": 0.4921242296695709, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9256, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011101859561476548, | |
| "eval_loss": 0.9522705674171448, | |
| "eval_runtime": 178.3901, | |
| "eval_samples_per_second": 34.015, | |
| "eval_steps_per_second": 4.255, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0022203719122953097, | |
| "grad_norm": 0.2934083938598633, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6724, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0033305578684429643, | |
| "grad_norm": 0.32208752632141113, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.7233, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004440743824590619, | |
| "grad_norm": 0.34766772389411926, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.7119, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005550929780738274, | |
| "grad_norm": 0.36742880940437317, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.707, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006661115736885929, | |
| "grad_norm": 0.29567769169807434, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.6385, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007771301693033583, | |
| "grad_norm": 0.2962777018547058, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.7052, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.008881487649181239, | |
| "grad_norm": 0.28138846158981323, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.6713, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.009991673605328892, | |
| "grad_norm": 0.2824740707874298, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.6871, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.011101859561476548, | |
| "grad_norm": 0.34380483627319336, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.6946, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.012212045517624202, | |
| "grad_norm": 0.40067368745803833, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.715, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.013322231473771857, | |
| "grad_norm": 0.559396505355835, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.727, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.014432417429919511, | |
| "grad_norm": 0.22662867605686188, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.7065, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.015542603386067166, | |
| "grad_norm": 0.32227155566215515, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.5143, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01665278934221482, | |
| "grad_norm": 0.33295008540153503, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.5898, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.017762975298362477, | |
| "grad_norm": 0.29953694343566895, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.6246, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01887316125451013, | |
| "grad_norm": 0.24738679826259613, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.5557, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.019983347210657785, | |
| "grad_norm": 0.18604424595832825, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.5413, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02109353316680544, | |
| "grad_norm": 0.17332150042057037, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.5959, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.022203719122953096, | |
| "grad_norm": 0.17128834128379822, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.5223, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02331390507910075, | |
| "grad_norm": 0.24035468697547913, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.5646, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.024424091035248403, | |
| "grad_norm": 0.24414175748825073, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.5448, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.025534276991396057, | |
| "grad_norm": 0.3137146830558777, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.5881, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.026644462947543714, | |
| "grad_norm": 0.42251282930374146, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.5738, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.027754648903691368, | |
| "grad_norm": 0.812769889831543, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.7988, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.027754648903691368, | |
| "eval_loss": 0.5438412427902222, | |
| "eval_runtime": 178.7277, | |
| "eval_samples_per_second": 33.951, | |
| "eval_steps_per_second": 4.247, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.028864834859839022, | |
| "grad_norm": 0.07176178693771362, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5415, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.02997502081598668, | |
| "grad_norm": 0.09330936521291733, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.4694, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.031085206772134333, | |
| "grad_norm": 0.11705254018306732, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.5261, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03219539272828199, | |
| "grad_norm": 0.14393024146556854, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.5224, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.03330557868442964, | |
| "grad_norm": 0.16890911757946014, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.5004, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.034415764640577294, | |
| "grad_norm": 0.18463030457496643, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.5209, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.035525950596724955, | |
| "grad_norm": 0.18170933425426483, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.5202, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.03663613655287261, | |
| "grad_norm": 0.2058199942111969, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.552, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.03774632250902026, | |
| "grad_norm": 0.22453095018863678, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.5353, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.038856508465167916, | |
| "grad_norm": 0.23246823251247406, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.5407, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03996669442131557, | |
| "grad_norm": 0.2702462673187256, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.5738, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.041076880377463224, | |
| "grad_norm": 0.3108701705932617, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.5638, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.04218706633361088, | |
| "grad_norm": 0.09153717011213303, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.6503, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.04329725228975854, | |
| "grad_norm": 0.0784434825181961, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.4435, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.04440743824590619, | |
| "grad_norm": 0.09292080998420715, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.4758, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.045517624202053845, | |
| "grad_norm": 0.10125042498111725, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.5042, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0466278101582015, | |
| "grad_norm": 0.10794025659561157, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.4932, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.04773799611434915, | |
| "grad_norm": 0.12097963690757751, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.503, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.04884818207049681, | |
| "grad_norm": 0.13460612297058105, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.5198, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.04995836802664446, | |
| "grad_norm": 0.14509516954421997, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.4998, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.051068553982792114, | |
| "grad_norm": 0.15421025454998016, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.4843, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.052178739938939775, | |
| "grad_norm": 0.21875213086605072, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.5312, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.05328892589508743, | |
| "grad_norm": 0.20200785994529724, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.5591, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.05439911185123508, | |
| "grad_norm": 0.24777300655841827, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.5594, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.055509297807382736, | |
| "grad_norm": 0.4017266631126404, | |
| "learning_rate": 0.0, | |
| "loss": 0.6427, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.055509297807382736, | |
| "eval_loss": 0.529956579208374, | |
| "eval_runtime": 177.8954, | |
| "eval_samples_per_second": 34.11, | |
| "eval_steps_per_second": 4.267, | |
| "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": 5.2738959989538816e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |