| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.11478585264366167, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002295717052873233, | |
| "grad_norm": 0.012660520151257515, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9322, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002295717052873233, | |
| "eval_loss": 11.929409980773926, | |
| "eval_runtime": 0.1854, | |
| "eval_samples_per_second": 269.624, | |
| "eval_steps_per_second": 70.102, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004591434105746466, | |
| "grad_norm": 0.010631855577230453, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9317, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0068871511586197, | |
| "grad_norm": 0.012013992294669151, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 11.932, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009182868211492933, | |
| "grad_norm": 0.011967318132519722, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 11.9327, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.011478585264366167, | |
| "grad_norm": 0.011771964840590954, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 11.931, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0137743023172394, | |
| "grad_norm": 0.011810662224888802, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 11.9318, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.016070019370112633, | |
| "grad_norm": 0.012616390362381935, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 11.9327, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.018365736422985866, | |
| "grad_norm": 0.013262227177619934, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 11.9311, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.020661453475859102, | |
| "grad_norm": 0.013076732866466045, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 11.9317, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.022957170528732335, | |
| "grad_norm": 0.013569272123277187, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 11.9313, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.025252887581605567, | |
| "grad_norm": 0.013419965282082558, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 11.9313, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0275486046344788, | |
| "grad_norm": 0.01281964872032404, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 11.932, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.029844321687352033, | |
| "grad_norm": 0.016497211530804634, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 11.9315, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.032140038740225266, | |
| "grad_norm": 0.02070445939898491, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 11.9319, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0344357557930985, | |
| "grad_norm": 0.021560179069638252, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 11.932, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03673147284597173, | |
| "grad_norm": 0.022953500971198082, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 11.9309, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.03902718989884497, | |
| "grad_norm": 0.02006385661661625, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 11.9313, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.041322906951718204, | |
| "grad_norm": 0.022738860920071602, | |
| "learning_rate": 7.75e-05, | |
| "loss": 11.9308, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04361862400459143, | |
| "grad_norm": 0.02438095398247242, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 11.9308, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04591434105746467, | |
| "grad_norm": 0.01977449096739292, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 11.9317, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0482100581103379, | |
| "grad_norm": 0.022069524973630905, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 11.9311, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.050505775163211135, | |
| "grad_norm": 0.016071053221821785, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 11.9316, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.052801492216084364, | |
| "grad_norm": 0.01722380891442299, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 11.9301, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0550972092689576, | |
| "grad_norm": 0.01678800769150257, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 11.9308, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05739292632183084, | |
| "grad_norm": 0.014287649653851986, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 11.9307, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05739292632183084, | |
| "eval_loss": 11.928374290466309, | |
| "eval_runtime": 0.177, | |
| "eval_samples_per_second": 282.412, | |
| "eval_steps_per_second": 73.427, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.059688643374704066, | |
| "grad_norm": 0.03297346457839012, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 11.931, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0619843604275773, | |
| "grad_norm": 0.03240511566400528, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 11.9304, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06428007748045053, | |
| "grad_norm": 0.030236361548304558, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 11.9319, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.06657579453332377, | |
| "grad_norm": 0.02867850475013256, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 11.9315, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.068871511586197, | |
| "grad_norm": 0.033412039279937744, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 11.9306, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07116722863907024, | |
| "grad_norm": 0.031119193881750107, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 11.9311, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.07346294569194346, | |
| "grad_norm": 0.03084520809352398, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 11.9302, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0757586627448167, | |
| "grad_norm": 0.030229168012738228, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 11.9302, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.07805437979768994, | |
| "grad_norm": 0.027583809569478035, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 11.9302, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.08035009685056317, | |
| "grad_norm": 0.023065637797117233, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 11.9309, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08264581390343641, | |
| "grad_norm": 0.017537105828523636, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 11.9303, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.08494153095630963, | |
| "grad_norm": 0.01801358535885811, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 11.9312, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.08723724800918287, | |
| "grad_norm": 0.03332036733627319, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 11.9313, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0895329650620561, | |
| "grad_norm": 0.04296748340129852, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 11.9302, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.09182868211492934, | |
| "grad_norm": 0.03908509761095047, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 11.93, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09412439916780257, | |
| "grad_norm": 0.03531024605035782, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 11.9302, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0964201162206758, | |
| "grad_norm": 0.03801163285970688, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 11.9311, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.09871583327354903, | |
| "grad_norm": 0.036971934139728546, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 11.931, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.10101155032642227, | |
| "grad_norm": 0.033191367983818054, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 11.9305, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1033072673792955, | |
| "grad_norm": 0.03528426215052605, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 11.9296, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.10560298443216873, | |
| "grad_norm": 0.02626977674663067, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 11.9298, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.10789870148504196, | |
| "grad_norm": 0.026993898674845695, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 11.9309, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.1101944185379152, | |
| "grad_norm": 0.024933425709605217, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 11.9299, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.11249013559078844, | |
| "grad_norm": 0.018691590055823326, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 11.9317, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.11478585264366167, | |
| "grad_norm": 0.02374712936580181, | |
| "learning_rate": 1e-05, | |
| "loss": 11.9307, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11478585264366167, | |
| "eval_loss": 11.927669525146484, | |
| "eval_runtime": 0.1788, | |
| "eval_samples_per_second": 279.696, | |
| "eval_steps_per_second": 72.721, | |
| "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": 1043797377024.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |