| { | |
| "best_metric": 0.4297037422657013, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.3686440677966103, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02711864406779661, | |
| "grad_norm": 6.654329776763916, | |
| "learning_rate": 5e-05, | |
| "loss": 5.9176, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02711864406779661, | |
| "eval_loss": 7.1914238929748535, | |
| "eval_runtime": 3.0005, | |
| "eval_samples_per_second": 16.664, | |
| "eval_steps_per_second": 4.333, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05423728813559322, | |
| "grad_norm": 7.07365608215332, | |
| "learning_rate": 0.0001, | |
| "loss": 6.263, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.08135593220338982, | |
| "grad_norm": 6.792131423950195, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 6.2585, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.10847457627118644, | |
| "grad_norm": 6.233402729034424, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 4.6468, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.13559322033898305, | |
| "grad_norm": 7.542125701904297, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 3.8493, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.16271186440677965, | |
| "grad_norm": 7.424484729766846, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.7199, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.18983050847457628, | |
| "grad_norm": 8.212982177734375, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 2.0568, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.21694915254237288, | |
| "grad_norm": 7.07874059677124, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.4176, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.2440677966101695, | |
| "grad_norm": 6.48041296005249, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.0568, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.2711864406779661, | |
| "grad_norm": 7.512641429901123, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.7767, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2983050847457627, | |
| "grad_norm": 3.8094427585601807, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.6959, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.3254237288135593, | |
| "grad_norm": 2.816176652908325, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.5913, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.3525423728813559, | |
| "grad_norm": 3.8954684734344482, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.5801, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.37966101694915255, | |
| "grad_norm": 2.8891689777374268, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.574, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.4067796610169492, | |
| "grad_norm": 3.304783344268799, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.5433, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.43389830508474575, | |
| "grad_norm": 2.807281732559204, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.5548, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.4610169491525424, | |
| "grad_norm": 8.233451843261719, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.6403, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.488135593220339, | |
| "grad_norm": 8.032986640930176, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.6811, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.5152542372881356, | |
| "grad_norm": 2.5166850090026855, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.4471, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.5423728813559322, | |
| "grad_norm": 2.66556453704834, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.5133, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5694915254237288, | |
| "grad_norm": 3.332446813583374, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.5163, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.5966101694915255, | |
| "grad_norm": 2.7612719535827637, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.5193, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.6237288135593221, | |
| "grad_norm": 2.3616223335266113, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.5007, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.6508474576271186, | |
| "grad_norm": 2.6576013565063477, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.5167, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.6779661016949152, | |
| "grad_norm": 1.7816935777664185, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.5106, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6779661016949152, | |
| "eval_loss": 0.5217246413230896, | |
| "eval_runtime": 3.0304, | |
| "eval_samples_per_second": 16.5, | |
| "eval_steps_per_second": 4.29, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7050847457627119, | |
| "grad_norm": 2.0804121494293213, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.4793, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.7322033898305085, | |
| "grad_norm": 2.41282057762146, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.4887, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.7593220338983051, | |
| "grad_norm": 1.6098804473876953, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.4879, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.7864406779661017, | |
| "grad_norm": 1.7615506649017334, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.4757, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.8135593220338984, | |
| "grad_norm": 1.765375018119812, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.4545, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.8406779661016949, | |
| "grad_norm": 1.167455792427063, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.4685, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.8677966101694915, | |
| "grad_norm": 1.3772835731506348, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.458, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.8949152542372881, | |
| "grad_norm": 1.6152493953704834, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.4649, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.9220338983050848, | |
| "grad_norm": 1.2044497728347778, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.4376, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.9491525423728814, | |
| "grad_norm": 1.3679577112197876, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.4165, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.976271186440678, | |
| "grad_norm": 1.4477646350860596, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.4905, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.0161016949152541, | |
| "grad_norm": 3.4008398056030273, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.6072, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.0432203389830508, | |
| "grad_norm": 1.8189399242401123, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.3882, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.0703389830508474, | |
| "grad_norm": 0.9250749349594116, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.3339, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.097457627118644, | |
| "grad_norm": 1.2397493124008179, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.4049, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.1245762711864407, | |
| "grad_norm": 1.5129092931747437, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.3999, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.1516949152542373, | |
| "grad_norm": 1.52627432346344, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.3978, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.178813559322034, | |
| "grad_norm": 1.3015371561050415, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.378, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.2059322033898305, | |
| "grad_norm": 1.3487688302993774, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.4213, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.2330508474576272, | |
| "grad_norm": 1.26216721534729, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.3905, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.2601694915254238, | |
| "grad_norm": 1.045103669166565, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.3698, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.2872881355932204, | |
| "grad_norm": 1.2951055765151978, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.3458, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.314406779661017, | |
| "grad_norm": 1.3998348712921143, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.3566, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.3415254237288137, | |
| "grad_norm": 1.8256560564041138, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.3871, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.3686440677966103, | |
| "grad_norm": 1.4336544275283813, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3851, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.3686440677966103, | |
| "eval_loss": 0.4297037422657013, | |
| "eval_runtime": 3.0435, | |
| "eval_samples_per_second": 16.429, | |
| "eval_steps_per_second": 4.271, | |
| "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": 5.968083617316864e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |