| { | |
| "best_metric": 0.8767569661140442, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.04155088685174124, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008310177370348249, | |
| "grad_norm": 1.5722951889038086, | |
| "learning_rate": 5e-05, | |
| "loss": 1.9916, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008310177370348249, | |
| "eval_loss": 2.3691599369049072, | |
| "eval_runtime": 1.8044, | |
| "eval_samples_per_second": 27.71, | |
| "eval_steps_per_second": 7.205, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016620354740696497, | |
| "grad_norm": 1.4873651266098022, | |
| "learning_rate": 0.0001, | |
| "loss": 1.8681, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0024930532111044745, | |
| "grad_norm": 1.3406665325164795, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 1.8218, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0033240709481392994, | |
| "grad_norm": 0.8420897126197815, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.6587, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004155088685174124, | |
| "grad_norm": 0.9133013486862183, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.5451, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004986106422208949, | |
| "grad_norm": 0.9935890436172485, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.4639, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0058171241592437735, | |
| "grad_norm": 0.7139455676078796, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.4083, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006648141896278599, | |
| "grad_norm": 0.5123319029808044, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.3572, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.007479159633313423, | |
| "grad_norm": 0.4208027720451355, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.3165, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.008310177370348249, | |
| "grad_norm": 0.49735113978385925, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.2558, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009141195107383072, | |
| "grad_norm": 0.522138237953186, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.2403, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.009972212844417898, | |
| "grad_norm": 0.5232024788856506, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.1446, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.010803230581452723, | |
| "grad_norm": 0.7474119663238525, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.3153, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.011634248318487547, | |
| "grad_norm": 0.5357264280319214, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.3944, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.012465266055522372, | |
| "grad_norm": 0.433485209941864, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.3849, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.013296283792557198, | |
| "grad_norm": 0.3791271150112152, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.3529, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.014127301529592021, | |
| "grad_norm": 0.3937087655067444, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.3603, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.014958319266626847, | |
| "grad_norm": 0.4040830433368683, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.2942, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.015789337003661672, | |
| "grad_norm": 0.3635517358779907, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.2594, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.016620354740696498, | |
| "grad_norm": 0.34205764532089233, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.2722, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.017451372477731323, | |
| "grad_norm": 0.3680824041366577, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.2576, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.018282390214766145, | |
| "grad_norm": 0.38117313385009766, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.1952, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01911340795180097, | |
| "grad_norm": 0.354202002286911, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.1572, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.019944425688835796, | |
| "grad_norm": 0.4271661639213562, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.1535, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02077544342587062, | |
| "grad_norm": 0.5694829821586609, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.9831, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02077544342587062, | |
| "eval_loss": 0.905754566192627, | |
| "eval_runtime": 1.8047, | |
| "eval_samples_per_second": 27.705, | |
| "eval_steps_per_second": 7.203, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.021606461162905446, | |
| "grad_norm": 0.4972676932811737, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.3552, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.022437478899940272, | |
| "grad_norm": 0.43715959787368774, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 1.3542, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.023268496636975094, | |
| "grad_norm": 0.3699018955230713, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 1.3111, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.02409951437400992, | |
| "grad_norm": 0.3309498131275177, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 1.2836, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.024930532111044745, | |
| "grad_norm": 0.3133479654788971, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.2586, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02576154984807957, | |
| "grad_norm": 0.31654348969459534, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 1.2002, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.026592567585114395, | |
| "grad_norm": 0.3819998800754547, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.2523, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.02742358532214922, | |
| "grad_norm": 0.36355435848236084, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.2093, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.028254603059184043, | |
| "grad_norm": 0.35316434502601624, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.1676, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.029085620796218868, | |
| "grad_norm": 0.33619120717048645, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.1965, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.029916638533253694, | |
| "grad_norm": 0.3945019841194153, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.1519, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.03074765627028852, | |
| "grad_norm": 0.43868768215179443, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.0291, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.031578674007323344, | |
| "grad_norm": 0.45660218596458435, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.2871, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.03240969174435817, | |
| "grad_norm": 0.3676553964614868, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 1.3529, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.033240709481392995, | |
| "grad_norm": 0.33921658992767334, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 1.2429, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03407172721842782, | |
| "grad_norm": 0.3425234258174896, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.2934, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.034902744955462646, | |
| "grad_norm": 0.3707738220691681, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.2652, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.03573376269249747, | |
| "grad_norm": 0.32860931754112244, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 1.2167, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.03656478042953229, | |
| "grad_norm": 0.30463269352912903, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.2074, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.037395798166567115, | |
| "grad_norm": 0.39124321937561035, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 1.2168, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03822681590360194, | |
| "grad_norm": 0.34144067764282227, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.1737, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.039057833640636766, | |
| "grad_norm": 0.37623947858810425, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.1541, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.03988885137767159, | |
| "grad_norm": 0.35394471883773804, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 1.1364, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.04071986911470642, | |
| "grad_norm": 0.4109288156032562, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.0774, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.04155088685174124, | |
| "grad_norm": 0.5452594757080078, | |
| "learning_rate": 1e-05, | |
| "loss": 0.9995, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04155088685174124, | |
| "eval_loss": 0.8767569661140442, | |
| "eval_runtime": 1.8138, | |
| "eval_samples_per_second": 27.566, | |
| "eval_steps_per_second": 7.167, | |
| "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": 6.21519958580396e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |