| { | |
| "best_metric": 6.804957389831543, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.015535187199005748, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00031070374398011494, | |
| "grad_norm": 0.8794885277748108, | |
| "learning_rate": 5e-05, | |
| "loss": 6.9512, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00031070374398011494, | |
| "eval_loss": 6.953421115875244, | |
| "eval_runtime": 0.5806, | |
| "eval_samples_per_second": 86.115, | |
| "eval_steps_per_second": 22.39, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006214074879602299, | |
| "grad_norm": 0.8848797678947449, | |
| "learning_rate": 0.0001, | |
| "loss": 6.9527, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0009321112319403449, | |
| "grad_norm": 0.9171912670135498, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 6.9531, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0012428149759204598, | |
| "grad_norm": 0.9026643633842468, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 6.9434, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0015535187199005747, | |
| "grad_norm": 0.8722476363182068, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 6.9413, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0018642224638806897, | |
| "grad_norm": 0.8943967819213867, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 6.9355, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0021749262078608047, | |
| "grad_norm": 0.91636061668396, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 6.925, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0024856299518409195, | |
| "grad_norm": 0.8784703612327576, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 6.9253, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0027963336958210347, | |
| "grad_norm": 0.9190695285797119, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 6.9221, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0031070374398011495, | |
| "grad_norm": 0.9101545214653015, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 6.9123, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0034177411837812647, | |
| "grad_norm": 0.9356749653816223, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 6.9131, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0037284449277613795, | |
| "grad_norm": 0.9299861788749695, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 6.9067, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.004039148671741494, | |
| "grad_norm": 0.9103074669837952, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 6.9068, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0043498524157216095, | |
| "grad_norm": 0.9127833247184753, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 6.8984, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.004660556159701725, | |
| "grad_norm": 0.944182813167572, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 6.8922, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004971259903681839, | |
| "grad_norm": 0.9511967897415161, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 6.8884, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.005281963647661954, | |
| "grad_norm": 0.9112333059310913, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 6.8823, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.005592667391642069, | |
| "grad_norm": 0.9329969882965088, | |
| "learning_rate": 7.75e-05, | |
| "loss": 6.8777, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.005903371135622185, | |
| "grad_norm": 0.933712899684906, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 6.8732, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.006214074879602299, | |
| "grad_norm": 0.9171957969665527, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 6.8695, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006524778623582414, | |
| "grad_norm": 0.9286287426948547, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 6.8655, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.006835482367562529, | |
| "grad_norm": 0.9478336572647095, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 6.8623, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.007146186111542644, | |
| "grad_norm": 0.9306831955909729, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 6.8576, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.007456889855522759, | |
| "grad_norm": 0.9243201017379761, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 6.8575, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.007767593599502874, | |
| "grad_norm": 0.933986485004425, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 6.8562, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.007767593599502874, | |
| "eval_loss": 6.847867012023926, | |
| "eval_runtime": 0.0854, | |
| "eval_samples_per_second": 585.63, | |
| "eval_steps_per_second": 152.264, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.008078297343482988, | |
| "grad_norm": 0.9630571603775024, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 6.8474, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.008389001087463105, | |
| "grad_norm": 0.9458622932434082, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 6.8424, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.008699704831443219, | |
| "grad_norm": 0.9316064119338989, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 6.8424, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.009010408575423333, | |
| "grad_norm": 0.9313185214996338, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 6.8408, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.00932111231940345, | |
| "grad_norm": 0.9337138533592224, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 6.8354, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.009631816063383564, | |
| "grad_norm": 0.9357588291168213, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 6.8374, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.009942519807363678, | |
| "grad_norm": 0.9744881391525269, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 6.8308, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.010253223551343794, | |
| "grad_norm": 0.9172983765602112, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 6.832, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.010563927295323908, | |
| "grad_norm": 0.9618328213691711, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 6.8243, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.010874631039304023, | |
| "grad_norm": 0.953589141368866, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 6.821, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.011185334783284139, | |
| "grad_norm": 0.9559220671653748, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 6.8221, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.011496038527264253, | |
| "grad_norm": 0.9633547067642212, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 6.8274, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.01180674227124437, | |
| "grad_norm": 0.9454740285873413, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 6.8239, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.012117446015224484, | |
| "grad_norm": 0.9660118818283081, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 6.815, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.012428149759204598, | |
| "grad_norm": 1.0026577711105347, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 6.8159, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.012738853503184714, | |
| "grad_norm": 0.9559350609779358, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 6.8132, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.013049557247164828, | |
| "grad_norm": 0.9687345623970032, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 6.8148, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.013360260991144943, | |
| "grad_norm": 0.9497601985931396, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 6.8111, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.013670964735125059, | |
| "grad_norm": 0.9612035155296326, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 6.8119, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.013981668479105173, | |
| "grad_norm": 0.9472883939743042, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 6.8096, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.014292372223085287, | |
| "grad_norm": 0.940109133720398, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 6.8134, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.014603075967065404, | |
| "grad_norm": 0.9567110538482666, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 6.8083, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.014913779711045518, | |
| "grad_norm": 0.9558574557304382, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 6.808, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.015224483455025632, | |
| "grad_norm": 0.9513011574745178, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 6.8101, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.015535187199005748, | |
| "grad_norm": 0.9502997994422913, | |
| "learning_rate": 1e-05, | |
| "loss": 6.8095, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.015535187199005748, | |
| "eval_loss": 6.804957389831543, | |
| "eval_runtime": 0.0973, | |
| "eval_samples_per_second": 513.611, | |
| "eval_steps_per_second": 133.539, | |
| "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": 5705957376000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |