| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00353534907152895, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.767674535764475e-05, | |
| "eval_loss": 10.380178451538086, | |
| "eval_runtime": 67.8401, | |
| "eval_samples_per_second": 351.12, | |
| "eval_steps_per_second": 175.56, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00017676745357644752, | |
| "grad_norm": 0.03153292462229729, | |
| "learning_rate": 0.00019967573081342103, | |
| "loss": 10.3799, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00035353490715289503, | |
| "grad_norm": 0.025041894987225533, | |
| "learning_rate": 0.0001970941817426052, | |
| "loss": 10.3802, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0005303023607293425, | |
| "grad_norm": 0.019651275128126144, | |
| "learning_rate": 0.00019199794436588243, | |
| "loss": 10.379, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0007070698143057901, | |
| "grad_norm": 0.04715586081147194, | |
| "learning_rate": 0.0001845190085543795, | |
| "loss": 10.376, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0008838372678822375, | |
| "grad_norm": 0.04065093770623207, | |
| "learning_rate": 0.00017485107481711012, | |
| "loss": 10.3746, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0008838372678822375, | |
| "eval_loss": 10.375716209411621, | |
| "eval_runtime": 68.057, | |
| "eval_samples_per_second": 350.001, | |
| "eval_steps_per_second": 175.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.001060604721458685, | |
| "grad_norm": 0.06875745952129364, | |
| "learning_rate": 0.00016324453755953773, | |
| "loss": 10.3741, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0012373721750351325, | |
| "grad_norm": 0.08086761832237244, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 10.375, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0014141396286115801, | |
| "grad_norm": 0.06105079501867294, | |
| "learning_rate": 0.00013546048870425356, | |
| "loss": 10.3691, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.0015909070821880276, | |
| "grad_norm": 0.088962621986866, | |
| "learning_rate": 0.00012000256937760445, | |
| "loss": 10.3672, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.001767674535764475, | |
| "grad_norm": 0.1441858559846878, | |
| "learning_rate": 0.00010402659401094152, | |
| "loss": 10.3632, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.001767674535764475, | |
| "eval_loss": 10.361382484436035, | |
| "eval_runtime": 68.1568, | |
| "eval_samples_per_second": 349.488, | |
| "eval_steps_per_second": 174.744, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0019444419893409226, | |
| "grad_norm": 0.09688922762870789, | |
| "learning_rate": 8.79463319744677e-05, | |
| "loss": 10.3623, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.00212120944291737, | |
| "grad_norm": 0.10141890496015549, | |
| "learning_rate": 7.217825360835473e-05, | |
| "loss": 10.3596, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.0022979768964938177, | |
| "grad_norm": 0.11141142249107361, | |
| "learning_rate": 5.713074385969457e-05, | |
| "loss": 10.3546, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.002474744350070265, | |
| "grad_norm": 0.10640386492013931, | |
| "learning_rate": 4.3193525326884435e-05, | |
| "loss": 10.3534, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.0026515118036467126, | |
| "grad_norm": 0.06903336197137833, | |
| "learning_rate": 3.072756464904006e-05, | |
| "loss": 10.3528, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.0026515118036467126, | |
| "eval_loss": 10.354546546936035, | |
| "eval_runtime": 68.7013, | |
| "eval_samples_per_second": 346.718, | |
| "eval_steps_per_second": 173.359, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.0028282792572231603, | |
| "grad_norm": 0.09616001695394516, | |
| "learning_rate": 2.0055723659649904e-05, | |
| "loss": 10.3559, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.0030050467107996075, | |
| "grad_norm": 0.11327233165502548, | |
| "learning_rate": 1.1454397434679021e-05, | |
| "loss": 10.3541, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.003181814164376055, | |
| "grad_norm": 0.06384103745222092, | |
| "learning_rate": 5.146355805285452e-06, | |
| "loss": 10.3542, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.0033585816179525028, | |
| "grad_norm": 0.08369371294975281, | |
| "learning_rate": 1.2949737362087156e-06, | |
| "loss": 10.3538, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.00353534907152895, | |
| "grad_norm": 0.1022939532995224, | |
| "learning_rate": 0.0, | |
| "loss": 10.354, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.00353534907152895, | |
| "eval_loss": 10.35390567779541, | |
| "eval_runtime": 68.4752, | |
| "eval_samples_per_second": 347.863, | |
| "eval_steps_per_second": 173.932, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3937461534720.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |