| { | |
| "best_metric": 6.8076324462890625, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.05312084993359894, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0010624169986719787, | |
| "grad_norm": 0.5697853565216064, | |
| "learning_rate": 5e-05, | |
| "loss": 6.9091, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010624169986719787, | |
| "eval_loss": 6.900913715362549, | |
| "eval_runtime": 0.1154, | |
| "eval_samples_per_second": 433.248, | |
| "eval_steps_per_second": 112.645, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0021248339973439574, | |
| "grad_norm": 0.5687248110771179, | |
| "learning_rate": 0.0001, | |
| "loss": 6.9113, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0031872509960159364, | |
| "grad_norm": 0.5834084153175354, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 6.9041, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004249667994687915, | |
| "grad_norm": 0.5844998955726624, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 6.9019, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005312084993359893, | |
| "grad_norm": 0.5626636743545532, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 6.8945, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006374501992031873, | |
| "grad_norm": 0.5599868893623352, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 6.8961, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007436918990703851, | |
| "grad_norm": 0.5682830214500427, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 6.8866, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00849933598937583, | |
| "grad_norm": 0.5642528533935547, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 6.8891, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.009561752988047808, | |
| "grad_norm": 0.5969242453575134, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 6.879, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.010624169986719787, | |
| "grad_norm": 0.557924211025238, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 6.8858, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.011686586985391767, | |
| "grad_norm": 0.5749415159225464, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 6.881, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.012749003984063745, | |
| "grad_norm": 0.5889608263969421, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 6.8736, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.013811420982735724, | |
| "grad_norm": 0.535503625869751, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 6.8755, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.014873837981407702, | |
| "grad_norm": 0.5333693027496338, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 6.8741, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01593625498007968, | |
| "grad_norm": 0.5248175263404846, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 6.8701, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01699867197875166, | |
| "grad_norm": 0.5040876865386963, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 6.8671, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.018061088977423638, | |
| "grad_norm": 0.5249006152153015, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 6.8697, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.019123505976095617, | |
| "grad_norm": 0.54627925157547, | |
| "learning_rate": 7.75e-05, | |
| "loss": 6.8586, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.020185922974767595, | |
| "grad_norm": 0.562960147857666, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 6.8528, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.021248339973439574, | |
| "grad_norm": 0.5442079901695251, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 6.8498, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.022310756972111555, | |
| "grad_norm": 0.5389817357063293, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 6.8482, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.023373173970783534, | |
| "grad_norm": 0.5449718832969666, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 6.8423, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.024435590969455512, | |
| "grad_norm": 0.5577437877655029, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 6.8415, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.02549800796812749, | |
| "grad_norm": 0.5578014254570007, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 6.8358, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02656042496679947, | |
| "grad_norm": 0.5776466727256775, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 6.8356, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02656042496679947, | |
| "eval_loss": 6.831989765167236, | |
| "eval_runtime": 0.1152, | |
| "eval_samples_per_second": 433.859, | |
| "eval_steps_per_second": 112.803, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.027622841965471448, | |
| "grad_norm": 0.48254695534706116, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 6.8441, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.028685258964143426, | |
| "grad_norm": 0.4874054193496704, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 6.8453, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.029747675962815405, | |
| "grad_norm": 0.4814146161079407, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 6.8455, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.030810092961487383, | |
| "grad_norm": 0.5245039463043213, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 6.8339, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.03187250996015936, | |
| "grad_norm": 0.4892662465572357, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 6.8387, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.032934926958831344, | |
| "grad_norm": 0.48735734820365906, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 6.8307, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.03399734395750332, | |
| "grad_norm": 0.5039017200469971, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 6.8271, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0350597609561753, | |
| "grad_norm": 0.511929452419281, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 6.8286, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.036122177954847276, | |
| "grad_norm": 0.45853519439697266, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 6.8392, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.03718459495351926, | |
| "grad_norm": 0.5033186078071594, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 6.8262, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03824701195219123, | |
| "grad_norm": 0.5333366394042969, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 6.8221, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.039309428950863215, | |
| "grad_norm": 0.5256316661834717, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 6.813, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.04037184594953519, | |
| "grad_norm": 0.49777570366859436, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 6.8198, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.04143426294820717, | |
| "grad_norm": 0.44153058528900146, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 6.8374, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.04249667994687915, | |
| "grad_norm": 0.4926466643810272, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 6.8275, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04355909694555113, | |
| "grad_norm": 0.470235139131546, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 6.8234, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.04462151394422311, | |
| "grad_norm": 0.47815701365470886, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 6.8224, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.045683930942895086, | |
| "grad_norm": 0.4792591333389282, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 6.82, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.04674634794156707, | |
| "grad_norm": 0.4888472855091095, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 6.8158, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.04780876494023904, | |
| "grad_norm": 0.49055448174476624, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 6.8205, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.048871181938911025, | |
| "grad_norm": 0.4726165235042572, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 6.826, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.049933598937583, | |
| "grad_norm": 0.4675711393356323, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 6.8278, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.05099601593625498, | |
| "grad_norm": 0.49473482370376587, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 6.8164, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.05205843293492696, | |
| "grad_norm": 0.49276942014694214, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 6.8157, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.05312084993359894, | |
| "grad_norm": 0.5099896192550659, | |
| "learning_rate": 1e-05, | |
| "loss": 6.8102, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05312084993359894, | |
| "eval_loss": 6.8076324462890625, | |
| "eval_runtime": 0.1099, | |
| "eval_samples_per_second": 454.851, | |
| "eval_steps_per_second": 118.261, | |
| "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": 5706848927744.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |