| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.4317323259579061, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0021586616297895305, | |
| "eval_loss": 1.2982888221740723, | |
| "eval_runtime": 10.4026, | |
| "eval_samples_per_second": 18.745, | |
| "eval_steps_per_second": 9.421, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.021586616297895305, | |
| "grad_norm": 1.0675714015960693, | |
| "learning_rate": 0.00019967573081342103, | |
| "loss": 1.3815, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04317323259579061, | |
| "grad_norm": 1.0740491151809692, | |
| "learning_rate": 0.0001970941817426052, | |
| "loss": 0.7551, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06475984889368591, | |
| "grad_norm": 1.1137008666992188, | |
| "learning_rate": 0.00019199794436588243, | |
| "loss": 0.7594, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08634646519158122, | |
| "grad_norm": 1.2131980657577515, | |
| "learning_rate": 0.0001845190085543795, | |
| "loss": 0.6061, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10793308148947653, | |
| "grad_norm": 0.9385984539985657, | |
| "learning_rate": 0.00017485107481711012, | |
| "loss": 0.7562, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.10793308148947653, | |
| "eval_loss": 0.6811017394065857, | |
| "eval_runtime": 9.2826, | |
| "eval_samples_per_second": 21.007, | |
| "eval_steps_per_second": 10.557, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12951969778737182, | |
| "grad_norm": 0.8435693979263306, | |
| "learning_rate": 0.00016324453755953773, | |
| "loss": 0.7173, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.15110631408526715, | |
| "grad_norm": 0.8595899939537048, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.6499, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.17269293038316244, | |
| "grad_norm": 0.7316609025001526, | |
| "learning_rate": 0.00013546048870425356, | |
| "loss": 0.6147, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.19427954668105774, | |
| "grad_norm": 0.845934271812439, | |
| "learning_rate": 0.00012000256937760445, | |
| "loss": 0.6582, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.21586616297895306, | |
| "grad_norm": 0.7001475691795349, | |
| "learning_rate": 0.00010402659401094152, | |
| "loss": 0.6764, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.21586616297895306, | |
| "eval_loss": 0.633052408695221, | |
| "eval_runtime": 9.2699, | |
| "eval_samples_per_second": 21.036, | |
| "eval_steps_per_second": 10.572, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.23745277927684835, | |
| "grad_norm": 0.856549084186554, | |
| "learning_rate": 8.79463319744677e-05, | |
| "loss": 0.6925, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.25903939557474365, | |
| "grad_norm": 0.6513226628303528, | |
| "learning_rate": 7.217825360835473e-05, | |
| "loss": 0.536, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.28062601187263897, | |
| "grad_norm": 0.8596200942993164, | |
| "learning_rate": 5.713074385969457e-05, | |
| "loss": 0.686, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.3022126281705343, | |
| "grad_norm": 0.7842469215393066, | |
| "learning_rate": 4.3193525326884435e-05, | |
| "loss": 0.6524, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.32379924446842956, | |
| "grad_norm": 0.6701909899711609, | |
| "learning_rate": 3.072756464904006e-05, | |
| "loss": 0.7561, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.32379924446842956, | |
| "eval_loss": 0.6158544421195984, | |
| "eval_runtime": 9.2669, | |
| "eval_samples_per_second": 21.043, | |
| "eval_steps_per_second": 10.575, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3453858607663249, | |
| "grad_norm": 0.7736531496047974, | |
| "learning_rate": 2.0055723659649904e-05, | |
| "loss": 0.5596, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.3669724770642202, | |
| "grad_norm": 0.8683272004127502, | |
| "learning_rate": 1.1454397434679021e-05, | |
| "loss": 0.6751, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.38855909336211547, | |
| "grad_norm": 0.7860276699066162, | |
| "learning_rate": 5.146355805285452e-06, | |
| "loss": 0.5672, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.4101457096600108, | |
| "grad_norm": 0.7141091823577881, | |
| "learning_rate": 1.2949737362087156e-06, | |
| "loss": 0.6592, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.4317323259579061, | |
| "grad_norm": 0.5997033715248108, | |
| "learning_rate": 0.0, | |
| "loss": 0.5211, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4317323259579061, | |
| "eval_loss": 0.6122936606407166, | |
| "eval_runtime": 9.2708, | |
| "eval_samples_per_second": 21.034, | |
| "eval_steps_per_second": 10.571, | |
| "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": 6.3324083453952e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |