| { | |
| "best_metric": 11.9102783203125, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-150", | |
| "epoch": 3.0, | |
| "eval_steps": 50, | |
| "global_step": 168, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.017857142857142856, | |
| "eval_loss": 11.9290132522583, | |
| "eval_runtime": 0.5421, | |
| "eval_samples_per_second": 175.25, | |
| "eval_steps_per_second": 44.274, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05357142857142857, | |
| "grad_norm": 0.019959961995482445, | |
| "learning_rate": 3e-05, | |
| "loss": 11.9303, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.10714285714285714, | |
| "grad_norm": 0.022794105112552643, | |
| "learning_rate": 6e-05, | |
| "loss": 11.9305, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.16071428571428573, | |
| "grad_norm": 0.0353395938873291, | |
| "learning_rate": 9e-05, | |
| "loss": 11.9295, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.21428571428571427, | |
| "grad_norm": 0.03792329132556915, | |
| "learning_rate": 9.996046986136509e-05, | |
| "loss": 11.93, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.26785714285714285, | |
| "grad_norm": 0.03241180628538132, | |
| "learning_rate": 9.975310752612137e-05, | |
| "loss": 11.9276, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.32142857142857145, | |
| "grad_norm": 0.05070869252085686, | |
| "learning_rate": 9.936876709681668e-05, | |
| "loss": 11.9291, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.375, | |
| "grad_norm": 0.05852275714278221, | |
| "learning_rate": 9.880881572095256e-05, | |
| "loss": 11.9291, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.42857142857142855, | |
| "grad_norm": 0.08124187588691711, | |
| "learning_rate": 9.807524521637102e-05, | |
| "loss": 11.9278, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.48214285714285715, | |
| "grad_norm": 0.05361940711736679, | |
| "learning_rate": 9.717066498610673e-05, | |
| "loss": 11.9256, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.5357142857142857, | |
| "grad_norm": 0.0750463530421257, | |
| "learning_rate": 9.609829273641034e-05, | |
| "loss": 11.9261, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5892857142857143, | |
| "grad_norm": 0.08543704450130463, | |
| "learning_rate": 9.486194303096062e-05, | |
| "loss": 11.9248, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.6428571428571429, | |
| "grad_norm": 0.09016852080821991, | |
| "learning_rate": 9.346601372197914e-05, | |
| "loss": 11.9243, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.6964285714285714, | |
| "grad_norm": 0.10736904293298721, | |
| "learning_rate": 9.191547030651383e-05, | |
| "loss": 11.9206, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.0793285071849823, | |
| "learning_rate": 9.021582826353824e-05, | |
| "loss": 11.9232, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.8035714285714286, | |
| "grad_norm": 0.05057210102677345, | |
| "learning_rate": 8.83731334346954e-05, | |
| "loss": 11.9215, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 0.05617088824510574, | |
| "learning_rate": 8.639394051847472e-05, | |
| "loss": 11.9211, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.8928571428571429, | |
| "eval_loss": 11.918818473815918, | |
| "eval_runtime": 0.5369, | |
| "eval_samples_per_second": 176.942, | |
| "eval_steps_per_second": 44.701, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.9107142857142857, | |
| "grad_norm": 0.06780627369880676, | |
| "learning_rate": 8.428528975432066e-05, | |
| "loss": 11.9193, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.9642857142857143, | |
| "grad_norm": 0.03634953871369362, | |
| "learning_rate": 8.2054681879611e-05, | |
| "loss": 11.9178, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.0178571428571428, | |
| "grad_norm": 0.04605906456708908, | |
| "learning_rate": 7.971005144858553e-05, | |
| "loss": 11.9182, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 1.0714285714285714, | |
| "grad_norm": 0.025876272469758987, | |
| "learning_rate": 7.725973860813338e-05, | |
| "loss": 11.9199, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.125, | |
| "grad_norm": 0.04855341464281082, | |
| "learning_rate": 7.471245943083615e-05, | |
| "loss": 11.9185, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 1.1785714285714286, | |
| "grad_norm": 0.03910359740257263, | |
| "learning_rate": 7.20772749107956e-05, | |
| "loss": 11.9184, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.2321428571428572, | |
| "grad_norm": 0.08992303162813187, | |
| "learning_rate": 6.936355873253206e-05, | |
| "loss": 11.9154, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 1.2857142857142856, | |
| "grad_norm": 0.04321262612938881, | |
| "learning_rate": 6.65809639276034e-05, | |
| "loss": 11.919, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.3392857142857144, | |
| "grad_norm": 0.049111876636743546, | |
| "learning_rate": 6.373938853755126e-05, | |
| "loss": 11.9185, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.3928571428571428, | |
| "grad_norm": 0.0660889744758606, | |
| "learning_rate": 6.08489404053159e-05, | |
| "loss": 11.9156, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.4464285714285714, | |
| "grad_norm": 0.0920424684882164, | |
| "learning_rate": 5.791990122036075e-05, | |
| "loss": 11.9151, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 0.04646582156419754, | |
| "learning_rate": 5.496268994540309e-05, | |
| "loss": 11.9162, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.5535714285714286, | |
| "grad_norm": 0.053827133029699326, | |
| "learning_rate": 5.19878257548463e-05, | |
| "loss": 11.9172, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 1.6071428571428572, | |
| "grad_norm": 0.04865885153412819, | |
| "learning_rate": 4.900589061674649e-05, | |
| "loss": 11.9165, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.6607142857142856, | |
| "grad_norm": 0.0875491127371788, | |
| "learning_rate": 4.602749165141428e-05, | |
| "loss": 11.9132, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 1.7142857142857144, | |
| "grad_norm": 0.04339161515235901, | |
| "learning_rate": 4.3063223400546594e-05, | |
| "loss": 11.9123, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.7678571428571428, | |
| "grad_norm": 0.04742836579680443, | |
| "learning_rate": 4.012363014110237e-05, | |
| "loss": 11.9154, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 1.7857142857142856, | |
| "eval_loss": 11.913043975830078, | |
| "eval_runtime": 0.5398, | |
| "eval_samples_per_second": 175.99, | |
| "eval_steps_per_second": 44.461, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.8214285714285714, | |
| "grad_norm": 0.04398871585726738, | |
| "learning_rate": 3.721916837797627e-05, | |
| "loss": 11.9137, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.875, | |
| "grad_norm": 0.05781185254454613, | |
| "learning_rate": 3.436016964888865e-05, | |
| "loss": 11.9125, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.9285714285714286, | |
| "grad_norm": 0.08808522671461105, | |
| "learning_rate": 3.1556803773799614e-05, | |
| "loss": 11.9077, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.9821428571428572, | |
| "grad_norm": 0.06021308898925781, | |
| "learning_rate": 2.8819042679573617e-05, | |
| "loss": 11.9141, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 2.0357142857142856, | |
| "grad_norm": 0.048566147685050964, | |
| "learning_rate": 2.6156624928574707e-05, | |
| "loss": 11.9136, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 2.0892857142857144, | |
| "grad_norm": 0.04223039001226425, | |
| "learning_rate": 2.3579021077369046e-05, | |
| "loss": 11.9142, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 2.142857142857143, | |
| "grad_norm": 0.04601627215743065, | |
| "learning_rate": 2.1095399988757574e-05, | |
| "loss": 11.9133, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.1964285714285716, | |
| "grad_norm": 0.05840318650007248, | |
| "learning_rate": 1.8714596216972007e-05, | |
| "loss": 11.9112, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "grad_norm": 0.035777896642684937, | |
| "learning_rate": 1.6445078582048155e-05, | |
| "loss": 11.9091, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 2.3035714285714284, | |
| "grad_norm": 0.037539299577474594, | |
| "learning_rate": 1.4294920045162513e-05, | |
| "loss": 11.9146, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 2.357142857142857, | |
| "grad_norm": 0.042784880846738815, | |
| "learning_rate": 1.2271768992088489e-05, | |
| "loss": 11.9117, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 2.4107142857142856, | |
| "grad_norm": 0.05495860055088997, | |
| "learning_rate": 1.038282202692129e-05, | |
| "loss": 11.9109, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 2.4642857142857144, | |
| "grad_norm": 0.07855169475078583, | |
| "learning_rate": 8.634798372847148e-06, | |
| "loss": 11.9069, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 2.517857142857143, | |
| "grad_norm": 0.03630689159035683, | |
| "learning_rate": 7.033915971016952e-06, | |
| "loss": 11.9139, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 2.571428571428571, | |
| "grad_norm": 0.048760075122117996, | |
| "learning_rate": 5.585869362543416e-06, | |
| "loss": 11.9124, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 2.625, | |
| "grad_norm": 0.04377627745270729, | |
| "learning_rate": 4.29580943229827e-06, | |
| "loss": 11.9118, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 2.678571428571429, | |
| "grad_norm": 0.05847623199224472, | |
| "learning_rate": 3.1683250865636114e-06, | |
| "loss": 11.9095, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.678571428571429, | |
| "eval_loss": 11.9102783203125, | |
| "eval_runtime": 0.5392, | |
| "eval_samples_per_second": 176.177, | |
| "eval_steps_per_second": 44.508, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.732142857142857, | |
| "grad_norm": 0.034065768122673035, | |
| "learning_rate": 2.2074269297119587e-06, | |
| "loss": 11.9088, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 2.7857142857142856, | |
| "grad_norm": 0.04465312138199806, | |
| "learning_rate": 1.4165329979794973e-06, | |
| "loss": 11.9133, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 2.8392857142857144, | |
| "grad_norm": 0.043062131851911545, | |
| "learning_rate": 7.984566010789674e-07, | |
| "loss": 11.9122, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 2.892857142857143, | |
| "grad_norm": 0.05254960432648659, | |
| "learning_rate": 3.553963149013295e-07, | |
| "loss": 11.9094, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 2.946428571428571, | |
| "grad_norm": 0.032099399715662, | |
| "learning_rate": 8.892816090335099e-08, | |
| "loss": 11.9082, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.09737348556518555, | |
| "learning_rate": 0.0, | |
| "loss": 11.908, | |
| "step": 168 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 168, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "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": 808543272960.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |