| { | |
| "best_metric": 0.03734762966632843, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 2.6996699669966997, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.052805280528052806, | |
| "grad_norm": 241.61077880859375, | |
| "learning_rate": 5e-05, | |
| "loss": 61.3338, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.052805280528052806, | |
| "eval_loss": 3.5627546310424805, | |
| "eval_runtime": 4.3596, | |
| "eval_samples_per_second": 29.361, | |
| "eval_steps_per_second": 3.67, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.10561056105610561, | |
| "grad_norm": 313.4629821777344, | |
| "learning_rate": 0.0001, | |
| "loss": 55.4131, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.15841584158415842, | |
| "grad_norm": 185.32693481445312, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 35.7674, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.21122112211221122, | |
| "grad_norm": 110.76226806640625, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 20.0764, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.264026402640264, | |
| "grad_norm": 87.55223846435547, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 24.8683, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.31683168316831684, | |
| "grad_norm": 139.35531616210938, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 18.6656, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3696369636963696, | |
| "grad_norm": 132.13233947753906, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 14.8754, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.42244224422442245, | |
| "grad_norm": 63.427032470703125, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.6936, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.4752475247524752, | |
| "grad_norm": 70.66545104980469, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 9.8106, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.528052805280528, | |
| "grad_norm": 97.06773376464844, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 19.9034, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5808580858085809, | |
| "grad_norm": 69.93522644042969, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 10.8521, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.6336633663366337, | |
| "grad_norm": 57.24028396606445, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 10.1543, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.6864686468646864, | |
| "grad_norm": 57.92759323120117, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 7.9742, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.7392739273927392, | |
| "grad_norm": 64.80909729003906, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 9.9122, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.7920792079207921, | |
| "grad_norm": 62.86793518066406, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 8.432, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.8448844884488449, | |
| "grad_norm": 56.4834098815918, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 5.9763, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.8976897689768977, | |
| "grad_norm": 40.859291076660156, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 3.4547, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.9504950495049505, | |
| "grad_norm": 50.14191436767578, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.9626, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.033003300330033, | |
| "grad_norm": 71.62645721435547, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 5.432, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.0858085808580857, | |
| "grad_norm": 51.751678466796875, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.9714, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.1386138613861387, | |
| "grad_norm": 71.75513458251953, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 2.1652, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.1914191419141915, | |
| "grad_norm": 51.177284240722656, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.4909, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.2442244224422443, | |
| "grad_norm": 72.12232208251953, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.4707, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.297029702970297, | |
| "grad_norm": 81.59396362304688, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 2.5601, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.3498349834983498, | |
| "grad_norm": 44.115966796875, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.8231, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.3498349834983498, | |
| "eval_loss": 0.09059706330299377, | |
| "eval_runtime": 4.6098, | |
| "eval_samples_per_second": 27.767, | |
| "eval_steps_per_second": 3.471, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.4026402640264026, | |
| "grad_norm": 51.42778015136719, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5969, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.4554455445544554, | |
| "grad_norm": 41.340782165527344, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.6936, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.5082508250825084, | |
| "grad_norm": 62.70668411254883, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 2.3933, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.561056105610561, | |
| "grad_norm": 68.67789459228516, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.8647, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.613861386138614, | |
| "grad_norm": 48.94205856323242, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.5317, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.6666666666666665, | |
| "grad_norm": 18.71625518798828, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.1899, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.7194719471947195, | |
| "grad_norm": 47.35069274902344, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.7913, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.7722772277227723, | |
| "grad_norm": 40.61697006225586, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.6418, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.825082508250825, | |
| "grad_norm": 45.03499221801758, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.4943, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.8778877887788779, | |
| "grad_norm": 48.89573669433594, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.2491, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.9306930693069306, | |
| "grad_norm": 42.19164276123047, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.1735, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.0132013201320134, | |
| "grad_norm": 26.78213119506836, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.4541, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.066006600660066, | |
| "grad_norm": 43.349700927734375, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.2041, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.118811881188119, | |
| "grad_norm": 5.292726516723633, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.0695, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.1716171617161715, | |
| "grad_norm": 4.951777458190918, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.0261, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.2244224422442245, | |
| "grad_norm": 29.308528900146484, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0913, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.2772277227722775, | |
| "grad_norm": 20.512184143066406, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.3224, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.33003300330033, | |
| "grad_norm": 7.966917514801025, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.0802, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.382838283828383, | |
| "grad_norm": 3.8203468322753906, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0214, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.4356435643564356, | |
| "grad_norm": 3.0683605670928955, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.0138, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.4884488448844886, | |
| "grad_norm": 23.591899871826172, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.5393, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.541254125412541, | |
| "grad_norm": 18.360029220581055, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0586, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.594059405940594, | |
| "grad_norm": 14.321728706359863, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.0914, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.6468646864686467, | |
| "grad_norm": 16.951425552368164, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.1885, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.6996699669966997, | |
| "grad_norm": 31.718521118164062, | |
| "learning_rate": 0.0, | |
| "loss": 0.285, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.6996699669966997, | |
| "eval_loss": 0.03734762966632843, | |
| "eval_runtime": 4.8904, | |
| "eval_samples_per_second": 26.174, | |
| "eval_steps_per_second": 3.272, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 5.932088473514148e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |