| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.6734006734006734, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003367003367003367, | |
| "eval_loss": 0.4757673144340515, | |
| "eval_runtime": 6.3098, | |
| "eval_samples_per_second": 19.81, | |
| "eval_steps_per_second": 9.984, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03367003367003367, | |
| "grad_norm": 0.0321938619017601, | |
| "learning_rate": 0.00019967573081342103, | |
| "loss": 0.2081, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06734006734006734, | |
| "grad_norm": 0.0025896921288222075, | |
| "learning_rate": 0.0001970941817426052, | |
| "loss": 0.0003, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.10101010101010101, | |
| "grad_norm": 0.000806357420515269, | |
| "learning_rate": 0.00019199794436588243, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.13468013468013468, | |
| "grad_norm": 0.0002514805528335273, | |
| "learning_rate": 0.0001845190085543795, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.16835016835016836, | |
| "grad_norm": 0.00018703643581829965, | |
| "learning_rate": 0.00017485107481711012, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.16835016835016836, | |
| "eval_loss": 5.421519290393917e-06, | |
| "eval_runtime": 5.0523, | |
| "eval_samples_per_second": 24.741, | |
| "eval_steps_per_second": 12.47, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.20202020202020202, | |
| "grad_norm": 0.00014419539365917444, | |
| "learning_rate": 0.00016324453755953773, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2356902356902357, | |
| "grad_norm": 0.00012529775267466903, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.26936026936026936, | |
| "grad_norm": 0.00010909074626397341, | |
| "learning_rate": 0.00013546048870425356, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.30303030303030304, | |
| "grad_norm": 8.513720240443945e-05, | |
| "learning_rate": 0.00012000256937760445, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.3367003367003367, | |
| "grad_norm": 8.307689131470397e-05, | |
| "learning_rate": 0.00010402659401094152, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3367003367003367, | |
| "eval_loss": 2.8263091280678054e-06, | |
| "eval_runtime": 5.0543, | |
| "eval_samples_per_second": 24.731, | |
| "eval_steps_per_second": 12.465, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.37037037037037035, | |
| "grad_norm": 7.26988073438406e-05, | |
| "learning_rate": 8.79463319744677e-05, | |
| "loss": 0.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.40404040404040403, | |
| "grad_norm": 7.398388697765768e-05, | |
| "learning_rate": 7.217825360835473e-05, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.4377104377104377, | |
| "grad_norm": 6.602691428270191e-05, | |
| "learning_rate": 5.713074385969457e-05, | |
| "loss": 0.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.4713804713804714, | |
| "grad_norm": 6.265695265028626e-05, | |
| "learning_rate": 4.3193525326884435e-05, | |
| "loss": 0.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.5050505050505051, | |
| "grad_norm": 6.212826701812446e-05, | |
| "learning_rate": 3.072756464904006e-05, | |
| "loss": 0.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.5050505050505051, | |
| "eval_loss": 2.2449421521741897e-06, | |
| "eval_runtime": 5.0442, | |
| "eval_samples_per_second": 24.781, | |
| "eval_steps_per_second": 12.49, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.5387205387205387, | |
| "grad_norm": 6.019990178174339e-05, | |
| "learning_rate": 2.0055723659649904e-05, | |
| "loss": 0.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.5723905723905723, | |
| "grad_norm": 6.026657501934096e-05, | |
| "learning_rate": 1.1454397434679021e-05, | |
| "loss": 0.0, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.6060606060606061, | |
| "grad_norm": 5.954002699581906e-05, | |
| "learning_rate": 5.146355805285452e-06, | |
| "loss": 0.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.6397306397306397, | |
| "grad_norm": 5.726645395043306e-05, | |
| "learning_rate": 1.2949737362087156e-06, | |
| "loss": 0.0, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.6734006734006734, | |
| "grad_norm": 6.246352131711319e-05, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.6734006734006734, | |
| "eval_loss": 2.194750777562149e-06, | |
| "eval_runtime": 5.0618, | |
| "eval_samples_per_second": 24.695, | |
| "eval_steps_per_second": 12.446, | |
| "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": 4.2243654156288e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |