| { | |
| "best_metric": 2.43630313873291, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.15634160641000586, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003126832128200117, | |
| "grad_norm": 3.185676097869873, | |
| "learning_rate": 5e-05, | |
| "loss": 2.8605, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003126832128200117, | |
| "eval_loss": 3.4071238040924072, | |
| "eval_runtime": 1.999, | |
| "eval_samples_per_second": 25.013, | |
| "eval_steps_per_second": 6.503, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006253664256400234, | |
| "grad_norm": 4.262716293334961, | |
| "learning_rate": 0.0001, | |
| "loss": 2.8928, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.009380496384600352, | |
| "grad_norm": 2.0842199325561523, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 2.8935, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.012507328512800469, | |
| "grad_norm": 1.7061878442764282, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.8417, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.015634160641000587, | |
| "grad_norm": 4.168418884277344, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.7099, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.018760992769200704, | |
| "grad_norm": 2.976910352706909, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.7049, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02188782489740082, | |
| "grad_norm": 1.781235933303833, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 2.7099, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.025014657025600937, | |
| "grad_norm": 1.7685775756835938, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 2.618, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.028141489153801054, | |
| "grad_norm": 1.6979849338531494, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 2.6275, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.031268321282001174, | |
| "grad_norm": 1.94242262840271, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 2.5901, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03439515341020129, | |
| "grad_norm": 2.7704176902770996, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 2.7957, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03752198553840141, | |
| "grad_norm": 2.373657464981079, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 2.7742, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04064881766660153, | |
| "grad_norm": 3.330683946609497, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 2.9312, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04377564979480164, | |
| "grad_norm": 2.2943036556243896, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 2.3264, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04690248192300176, | |
| "grad_norm": 1.1991941928863525, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 2.4025, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.050029314051201874, | |
| "grad_norm": 1.1084790229797363, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 2.324, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.053156146179401995, | |
| "grad_norm": 1.0802116394042969, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 2.3501, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.05628297830760211, | |
| "grad_norm": 1.2232404947280884, | |
| "learning_rate": 7.75e-05, | |
| "loss": 2.3179, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05940981043580223, | |
| "grad_norm": 1.2925686836242676, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 2.363, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06253664256400235, | |
| "grad_norm": 1.402012825012207, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 2.3214, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06566347469220246, | |
| "grad_norm": 1.4307760000228882, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 2.3474, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.06879030682040257, | |
| "grad_norm": 1.4304847717285156, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 2.4598, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0719171389486027, | |
| "grad_norm": 1.6131951808929443, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 2.5516, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.07504397107680282, | |
| "grad_norm": 1.541904091835022, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 2.5627, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.07817080320500293, | |
| "grad_norm": 2.422374725341797, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 2.8529, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07817080320500293, | |
| "eval_loss": 2.51509952545166, | |
| "eval_runtime": 2.0027, | |
| "eval_samples_per_second": 24.966, | |
| "eval_steps_per_second": 6.491, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08129763533320306, | |
| "grad_norm": 2.5973637104034424, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 2.3456, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.08442446746140317, | |
| "grad_norm": 2.757310390472412, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 2.3969, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.08755129958960328, | |
| "grad_norm": 3.2795515060424805, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 2.4594, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0906781317178034, | |
| "grad_norm": 2.4924538135528564, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 2.4313, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.09380496384600352, | |
| "grad_norm": 2.260542154312134, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 2.3361, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09693179597420364, | |
| "grad_norm": 1.74604332447052, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 2.2974, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.10005862810240375, | |
| "grad_norm": 1.271629810333252, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 2.2899, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.10318546023060388, | |
| "grad_norm": 1.225449562072754, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 2.3584, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.10631229235880399, | |
| "grad_norm": 1.117197036743164, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 2.3665, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.1094391244870041, | |
| "grad_norm": 1.334246039390564, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 2.4026, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.11256595661520422, | |
| "grad_norm": 1.4346826076507568, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 2.4023, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.11569278874340434, | |
| "grad_norm": 2.0627875328063965, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 2.7722, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.11881962087160446, | |
| "grad_norm": 0.9819260239601135, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 2.4724, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.12194645299980457, | |
| "grad_norm": 0.9288238286972046, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 2.2767, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1250732851280047, | |
| "grad_norm": 0.9036171436309814, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 2.2425, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1282001172562048, | |
| "grad_norm": 0.9765707850456238, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 2.2438, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.13132694938440492, | |
| "grad_norm": 0.8984200954437256, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 2.2662, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.13445378151260504, | |
| "grad_norm": 1.0145357847213745, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 2.3001, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.13758061364080515, | |
| "grad_norm": 1.061907172203064, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 2.2892, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.14070744576900526, | |
| "grad_norm": 1.0922386646270752, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 2.2792, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1438342778972054, | |
| "grad_norm": 1.1090540885925293, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 2.2617, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.14696111002540552, | |
| "grad_norm": 1.2806262969970703, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 2.3924, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.15008794215360563, | |
| "grad_norm": 1.502442479133606, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 2.4509, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.15321477428180574, | |
| "grad_norm": 1.635464072227478, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 2.5069, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.15634160641000586, | |
| "grad_norm": 2.803654432296753, | |
| "learning_rate": 1e-05, | |
| "loss": 2.9058, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.15634160641000586, | |
| "eval_loss": 2.43630313873291, | |
| "eval_runtime": 1.9888, | |
| "eval_samples_per_second": 25.14, | |
| "eval_steps_per_second": 6.536, | |
| "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": 1.059536353886208e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |