| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.6986899563318777, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.013973799126637555, | |
| "grad_norm": 0.11786681413650513, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3724, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013973799126637555, | |
| "eval_loss": 10.36445426940918, | |
| "eval_runtime": 0.1072, | |
| "eval_samples_per_second": 466.438, | |
| "eval_steps_per_second": 121.274, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02794759825327511, | |
| "grad_norm": 0.1330784261226654, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3681, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04192139737991266, | |
| "grad_norm": 0.13530316948890686, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 10.3664, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05589519650655022, | |
| "grad_norm": 0.15991181135177612, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 10.3676, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06986899563318777, | |
| "grad_norm": 0.16595715284347534, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 10.3639, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08384279475982533, | |
| "grad_norm": 0.16909931600093842, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 10.3653, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09781659388646288, | |
| "grad_norm": 0.18280765414237976, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 10.3602, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.11179039301310044, | |
| "grad_norm": 0.18596720695495605, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 10.3574, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.125764192139738, | |
| "grad_norm": 0.18361559510231018, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 10.3552, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.13973799126637554, | |
| "grad_norm": 0.2051653265953064, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 10.3528, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1537117903930131, | |
| "grad_norm": 0.22635610401630402, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 10.3513, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.16768558951965065, | |
| "grad_norm": 0.2839421331882477, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 10.346, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.18165938864628822, | |
| "grad_norm": 0.1253979653120041, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 10.3602, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.19563318777292577, | |
| "grad_norm": 0.12997491657733917, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 10.3649, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.2096069868995633, | |
| "grad_norm": 0.14003437757492065, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 10.3615, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.22358078602620088, | |
| "grad_norm": 0.1440284699201584, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 10.3572, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.23755458515283842, | |
| "grad_norm": 0.1578262448310852, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 10.3565, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.251528384279476, | |
| "grad_norm": 0.15315592288970947, | |
| "learning_rate": 7.75e-05, | |
| "loss": 10.3549, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.26550218340611353, | |
| "grad_norm": 0.1595955491065979, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 10.3558, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2794759825327511, | |
| "grad_norm": 0.15596911311149597, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 10.352, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2934497816593886, | |
| "grad_norm": 0.17770564556121826, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 10.3522, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.3074235807860262, | |
| "grad_norm": 0.1863674521446228, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 10.3471, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.32139737991266376, | |
| "grad_norm": 0.22435881197452545, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 10.3419, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3353711790393013, | |
| "grad_norm": 0.22188186645507812, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 10.3396, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.34934497816593885, | |
| "grad_norm": 0.3109688460826874, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 10.3271, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.34934497816593885, | |
| "eval_loss": 10.349708557128906, | |
| "eval_runtime": 0.0955, | |
| "eval_samples_per_second": 523.321, | |
| "eval_steps_per_second": 136.064, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.36331877729257644, | |
| "grad_norm": 0.13174213469028473, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 10.3622, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.377292576419214, | |
| "grad_norm": 0.13872195780277252, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 10.3582, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.39126637554585153, | |
| "grad_norm": 0.15271404385566711, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 10.3559, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.4052401746724891, | |
| "grad_norm": 0.1431555151939392, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 10.3543, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.4192139737991266, | |
| "grad_norm": 0.16119669377803802, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 10.3538, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4331877729257642, | |
| "grad_norm": 0.1416635364294052, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 10.3499, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.44716157205240176, | |
| "grad_norm": 0.1621275097131729, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 10.3458, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.4611353711790393, | |
| "grad_norm": 0.1729240119457245, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 10.3441, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.47510917030567684, | |
| "grad_norm": 0.1822398155927658, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 10.34, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.4890829694323144, | |
| "grad_norm": 0.1940406858921051, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 10.3377, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.503056768558952, | |
| "grad_norm": 0.213682621717453, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 10.3316, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5170305676855895, | |
| "grad_norm": 0.27538955211639404, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 10.3291, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5310043668122271, | |
| "grad_norm": 0.12671859562397003, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 10.3527, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5449781659388646, | |
| "grad_norm": 0.14045991003513336, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 10.3548, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5589519650655022, | |
| "grad_norm": 0.13294897973537445, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 10.3545, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5729257641921397, | |
| "grad_norm": 0.1276903599500656, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 10.35, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5868995633187772, | |
| "grad_norm": 0.13368958234786987, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 10.3532, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.6008733624454149, | |
| "grad_norm": 0.14260563254356384, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 10.348, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.6148471615720524, | |
| "grad_norm": 0.17048144340515137, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 10.3475, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.62882096069869, | |
| "grad_norm": 0.15034472942352295, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 10.3471, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6427947598253275, | |
| "grad_norm": 0.17590156197547913, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 10.3427, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6567685589519651, | |
| "grad_norm": 0.17019419372081757, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 10.3399, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6707423580786026, | |
| "grad_norm": 0.18595226109027863, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 10.3372, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6847161572052402, | |
| "grad_norm": 0.24787795543670654, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 10.3311, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6986899563318777, | |
| "grad_norm": 0.3069895803928375, | |
| "learning_rate": 1e-05, | |
| "loss": 10.3215, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6986899563318777, | |
| "eval_loss": 10.34473991394043, | |
| "eval_runtime": 0.1073, | |
| "eval_samples_per_second": 465.881, | |
| "eval_steps_per_second": 121.129, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 42768059596800.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |