| { | |
| "best_metric": 1.4836927652359009, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.1182197496522948, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.022253129346314324, | |
| "grad_norm": 0.3120327889919281, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6035, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.022253129346314324, | |
| "eval_loss": 1.542589545249939, | |
| "eval_runtime": 9.287, | |
| "eval_samples_per_second": 5.384, | |
| "eval_steps_per_second": 1.4, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04450625869262865, | |
| "grad_norm": 0.37038734555244446, | |
| "learning_rate": 0.0001, | |
| "loss": 1.6081, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06675938803894298, | |
| "grad_norm": 0.37281283736228943, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 1.5752, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0890125173852573, | |
| "grad_norm": 0.3437151312828064, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.6186, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.11126564673157163, | |
| "grad_norm": 0.3911067545413971, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.6111, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.13351877607788595, | |
| "grad_norm": 0.4079926908016205, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.6172, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.15577190542420027, | |
| "grad_norm": 0.3889995813369751, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.5655, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.1780250347705146, | |
| "grad_norm": 0.4306317865848541, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.5386, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.20027816411682892, | |
| "grad_norm": 0.5149466395378113, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.5265, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.22253129346314326, | |
| "grad_norm": 0.4121442437171936, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.4133, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.24478442280945759, | |
| "grad_norm": 0.46690434217453003, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.4478, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.2670375521557719, | |
| "grad_norm": 0.3639894425868988, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.5897, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.28929068150208626, | |
| "grad_norm": 0.368277370929718, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.6057, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.31154381084840055, | |
| "grad_norm": 0.3164932131767273, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.6024, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3337969401947149, | |
| "grad_norm": 0.35643574595451355, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.589, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3560500695410292, | |
| "grad_norm": 0.3688993453979492, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.5525, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.37830319888734354, | |
| "grad_norm": 0.4437098801136017, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.5871, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.40055632823365783, | |
| "grad_norm": 0.42263108491897583, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.5396, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.4228094575799722, | |
| "grad_norm": 0.4129128158092499, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.5581, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.44506258692628653, | |
| "grad_norm": 0.4998800754547119, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.5161, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.4673157162726008, | |
| "grad_norm": 0.40443554520606995, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.4355, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.48956884561891517, | |
| "grad_norm": 0.48541754484176636, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.467, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.5118219749652295, | |
| "grad_norm": 0.4150247275829315, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.5855, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.5340751043115438, | |
| "grad_norm": 0.383695513010025, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.649, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5563282336578581, | |
| "grad_norm": 0.34226423501968384, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.5947, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5563282336578581, | |
| "eval_loss": 1.4937388896942139, | |
| "eval_runtime": 9.3685, | |
| "eval_samples_per_second": 5.337, | |
| "eval_steps_per_second": 1.388, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5785813630041725, | |
| "grad_norm": 0.3235774636268616, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.5641, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.6008344923504868, | |
| "grad_norm": 0.36498793959617615, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 1.5675, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.6230876216968011, | |
| "grad_norm": 0.3361755311489105, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 1.5869, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.6453407510431154, | |
| "grad_norm": 0.38626089692115784, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 1.5792, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.6675938803894298, | |
| "grad_norm": 0.41537216305732727, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.5387, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.6898470097357441, | |
| "grad_norm": 0.5004784464836121, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 1.5281, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.7121001390820584, | |
| "grad_norm": 0.4615420699119568, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.4667, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.7343532684283728, | |
| "grad_norm": 0.41852062940597534, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.4371, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.7566063977746871, | |
| "grad_norm": 0.2556873857975006, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.6198, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.7788595271210014, | |
| "grad_norm": 0.27681005001068115, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.589, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.8011126564673157, | |
| "grad_norm": 0.28919461369514465, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.5619, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.8233657858136301, | |
| "grad_norm": 0.3032487630844116, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.5334, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.8456189151599444, | |
| "grad_norm": 0.32653772830963135, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.555, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.8678720445062587, | |
| "grad_norm": 0.5661789774894714, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 1.5973, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.8901251738525731, | |
| "grad_norm": 0.38925230503082275, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 1.5983, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.9123783031988874, | |
| "grad_norm": 0.4309825003147125, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.4893, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.9346314325452016, | |
| "grad_norm": 0.44985729455947876, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.5213, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.9568845618915159, | |
| "grad_norm": 0.5200555920600891, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 1.4216, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.9791376912378303, | |
| "grad_norm": 0.3593793213367462, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.4851, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.0069541029207232, | |
| "grad_norm": 0.4502297639846802, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 2.2216, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.0292072322670376, | |
| "grad_norm": 0.2939792275428772, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.4284, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.0514603616133518, | |
| "grad_norm": 0.2818860411643982, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.4967, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.0737134909596662, | |
| "grad_norm": 0.32414528727531433, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 1.4624, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.0959666203059806, | |
| "grad_norm": 0.355913370847702, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.4607, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.1182197496522948, | |
| "grad_norm": 0.3229123055934906, | |
| "learning_rate": 1e-05, | |
| "loss": 1.5119, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.1182197496522948, | |
| "eval_loss": 1.4836927652359009, | |
| "eval_runtime": 9.3523, | |
| "eval_samples_per_second": 5.346, | |
| "eval_steps_per_second": 1.39, | |
| "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": 1.1690990744528486e+18, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |