| { | |
| "best_metric": 1.396116852760315, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.5841584158415842, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.031683168316831684, | |
| "grad_norm": 123.59939575195312, | |
| "learning_rate": 5e-05, | |
| "loss": 4.0351, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.031683168316831684, | |
| "eval_loss": 4.633000373840332, | |
| "eval_runtime": 19.8883, | |
| "eval_samples_per_second": 21.42, | |
| "eval_steps_per_second": 1.358, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06336633663366337, | |
| "grad_norm": 140.6913299560547, | |
| "learning_rate": 0.0001, | |
| "loss": 4.3784, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.09504950495049505, | |
| "grad_norm": 132.14886474609375, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 4.063, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.12673267326732673, | |
| "grad_norm": 72.3555908203125, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.9489, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.15841584158415842, | |
| "grad_norm": 53.992122650146484, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.3328, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1900990099009901, | |
| "grad_norm": 39.890628814697266, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.0503, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.22178217821782178, | |
| "grad_norm": 20.836332321166992, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.7499, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.25346534653465347, | |
| "grad_norm": 10.976515769958496, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.7231, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.2851485148514851, | |
| "grad_norm": 19.44645118713379, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.7058, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.31683168316831684, | |
| "grad_norm": 10.474262237548828, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.5838, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3485148514851485, | |
| "grad_norm": 6.232975006103516, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.3863, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.3801980198019802, | |
| "grad_norm": 6.1638288497924805, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.3966, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.41188118811881186, | |
| "grad_norm": 6.118275165557861, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.3583, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.44356435643564357, | |
| "grad_norm": 7.997486591339111, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.398, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.4752475247524752, | |
| "grad_norm": 9.315695762634277, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.4856, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5069306930693069, | |
| "grad_norm": 13.862922668457031, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.6599, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.5386138613861386, | |
| "grad_norm": 15.675683975219727, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.6805, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.5702970297029702, | |
| "grad_norm": 8.870408058166504, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.3952, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.601980198019802, | |
| "grad_norm": 6.7011189460754395, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.3927, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.6336633663366337, | |
| "grad_norm": 5.8261213302612305, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.3644, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6653465346534654, | |
| "grad_norm": 4.526528835296631, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.3722, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.697029702970297, | |
| "grad_norm": 6.313098907470703, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.406, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.7287128712871287, | |
| "grad_norm": 9.860219955444336, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.5312, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.7603960396039604, | |
| "grad_norm": 9.333724975585938, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.5527, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.7920792079207921, | |
| "grad_norm": 6.874697685241699, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.5393, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7920792079207921, | |
| "eval_loss": 1.4412074089050293, | |
| "eval_runtime": 19.9527, | |
| "eval_samples_per_second": 21.35, | |
| "eval_steps_per_second": 1.353, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8237623762376237, | |
| "grad_norm": 5.965777397155762, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3469, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.8554455445544554, | |
| "grad_norm": 4.295379161834717, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.319, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.8871287128712871, | |
| "grad_norm": 4.880377292633057, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.2994, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.9188118811881189, | |
| "grad_norm": 4.994838237762451, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.3067, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.9504950495049505, | |
| "grad_norm": 5.390483379364014, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.3938, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.9821782178217822, | |
| "grad_norm": 9.734456062316895, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.4057, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.0138613861386139, | |
| "grad_norm": 6.865916728973389, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.4327, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.0455445544554456, | |
| "grad_norm": 8.426886558532715, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.528, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.0772277227722773, | |
| "grad_norm": 6.466370105743408, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.3748, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.108910891089109, | |
| "grad_norm": 6.0085601806640625, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.2561, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.1405940594059407, | |
| "grad_norm": 5.070044040679932, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.2524, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.1722772277227722, | |
| "grad_norm": 5.348262310028076, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.297, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.203960396039604, | |
| "grad_norm": 6.561531066894531, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.3092, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.2356435643564356, | |
| "grad_norm": 8.211418151855469, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.3696, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.2673267326732673, | |
| "grad_norm": 7.698812961578369, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.47, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.299009900990099, | |
| "grad_norm": 7.947728157043457, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.4385, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.3306930693069308, | |
| "grad_norm": 6.462954044342041, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.2735, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.3623762376237623, | |
| "grad_norm": 5.012844562530518, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.2215, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.394059405940594, | |
| "grad_norm": 5.397099494934082, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.3073, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.4257425742574257, | |
| "grad_norm": 5.290295124053955, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.2953, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.4574257425742574, | |
| "grad_norm": 6.2458319664001465, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.2694, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.489108910891089, | |
| "grad_norm": 10.212119102478027, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.4039, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.5207920792079208, | |
| "grad_norm": 10.062838554382324, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.5661, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.5524752475247525, | |
| "grad_norm": 6.744816780090332, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.4388, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.5841584158415842, | |
| "grad_norm": 6.674411296844482, | |
| "learning_rate": 0.0, | |
| "loss": 1.2739, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.5841584158415842, | |
| "eval_loss": 1.396116852760315, | |
| "eval_runtime": 19.9429, | |
| "eval_samples_per_second": 21.361, | |
| "eval_steps_per_second": 1.354, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 2.1905501440704512e+18, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |