| { | |
| "best_metric": 4.0636701583862305, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.129680661371373, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00259361322742746, | |
| "grad_norm": 1.6538571119308472, | |
| "learning_rate": 5e-05, | |
| "loss": 4.7632, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00259361322742746, | |
| "eval_loss": 6.2558770179748535, | |
| "eval_runtime": 1.8092, | |
| "eval_samples_per_second": 27.637, | |
| "eval_steps_per_second": 7.186, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00518722645485492, | |
| "grad_norm": 1.891584038734436, | |
| "learning_rate": 0.0001, | |
| "loss": 5.0511, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007780839682282379, | |
| "grad_norm": 1.8761420249938965, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 5.1433, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01037445290970984, | |
| "grad_norm": 1.7208211421966553, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 5.174, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0129680661371373, | |
| "grad_norm": 1.9773727655410767, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 5.1621, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.015561679364564759, | |
| "grad_norm": 2.2091774940490723, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 5.2007, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01815529259199222, | |
| "grad_norm": 2.763857841491699, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 4.9401, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02074890581941968, | |
| "grad_norm": 2.8243825435638428, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 4.9278, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02334251904684714, | |
| "grad_norm": 2.69087290763855, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 4.7506, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0259361322742746, | |
| "grad_norm": 2.3833048343658447, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 4.6704, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.028529745501702057, | |
| "grad_norm": 2.517953395843506, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 4.5205, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.031123358729129517, | |
| "grad_norm": 3.408473491668701, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 4.2597, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03371697195655698, | |
| "grad_norm": 4.755646705627441, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 4.8062, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03631058518398444, | |
| "grad_norm": 5.37370491027832, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 5.0298, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0389041984114119, | |
| "grad_norm": 4.0354461669921875, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 4.6675, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04149781163883936, | |
| "grad_norm": 3.4104719161987305, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 4.4444, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04409142486626682, | |
| "grad_norm": 2.6559720039367676, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 4.4518, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04668503809369428, | |
| "grad_norm": 1.7017279863357544, | |
| "learning_rate": 7.75e-05, | |
| "loss": 4.3672, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04927865132112174, | |
| "grad_norm": 1.2864271402359009, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 4.2291, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0518722645485492, | |
| "grad_norm": 1.4418666362762451, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 4.4045, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05446587777597666, | |
| "grad_norm": 2.0589725971221924, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 4.3825, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.057059491003404114, | |
| "grad_norm": 2.6695613861083984, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 4.4697, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.059653104230831575, | |
| "grad_norm": 3.5077600479125977, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 4.4973, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.062246717458259035, | |
| "grad_norm": 3.4810781478881836, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 4.3632, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0648403306856865, | |
| "grad_norm": 6.267790794372559, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 4.3646, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0648403306856865, | |
| "eval_loss": 4.229829788208008, | |
| "eval_runtime": 1.1553, | |
| "eval_samples_per_second": 43.278, | |
| "eval_steps_per_second": 11.252, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06743394391311396, | |
| "grad_norm": 1.1068377494812012, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 4.0776, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.07002755714054142, | |
| "grad_norm": 1.0573188066482544, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 4.0905, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07262117036796888, | |
| "grad_norm": 1.0603560209274292, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 4.1695, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.07521478359539634, | |
| "grad_norm": 1.1383318901062012, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 4.2141, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0778083968228238, | |
| "grad_norm": 1.0839500427246094, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 4.2506, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08040201005025126, | |
| "grad_norm": 0.967460036277771, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 4.1442, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.08299562327767872, | |
| "grad_norm": 0.9629656672477722, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 4.0578, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.08558923650510618, | |
| "grad_norm": 1.2750022411346436, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 4.2702, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.08818284973253364, | |
| "grad_norm": 1.3888616561889648, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 4.2641, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0907764629599611, | |
| "grad_norm": 1.6543223857879639, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 4.3656, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.09337007618738856, | |
| "grad_norm": 1.957236409187317, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 4.3184, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.09596368941481602, | |
| "grad_norm": 2.900848627090454, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 4.1326, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.09855730264224348, | |
| "grad_norm": 1.2549171447753906, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 3.9195, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.10115091586967094, | |
| "grad_norm": 0.8486330509185791, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 4.0072, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1037445290970984, | |
| "grad_norm": 0.8748946189880371, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 4.1093, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10633814232452586, | |
| "grad_norm": 0.8913637399673462, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 3.9297, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.10893175555195332, | |
| "grad_norm": 0.9824759364128113, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 3.9566, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.11152536877938077, | |
| "grad_norm": 0.8479898571968079, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 4.084, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.11411898200680823, | |
| "grad_norm": 0.8927655816078186, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 4.0899, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.11671259523423569, | |
| "grad_norm": 0.931806743144989, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 4.1325, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.11930620846166315, | |
| "grad_norm": 1.0513771772384644, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 4.1224, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.12189982168909061, | |
| "grad_norm": 1.2372894287109375, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 4.293, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.12449343491651807, | |
| "grad_norm": 1.6081628799438477, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 4.1659, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.12708704814394553, | |
| "grad_norm": 2.187530040740967, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 4.1753, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.129680661371373, | |
| "grad_norm": 4.7116546630859375, | |
| "learning_rate": 1e-05, | |
| "loss": 3.9957, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.129680661371373, | |
| "eval_loss": 4.0636701583862305, | |
| "eval_runtime": 1.1579, | |
| "eval_samples_per_second": 43.181, | |
| "eval_steps_per_second": 11.227, | |
| "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": 2.229252309123072e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |