| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.002277385561375541, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.591285204585137e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 419.603, | |
| "eval_samples_per_second": 13.22, | |
| "eval_steps_per_second": 6.611, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002277385561375541, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0003795642602292568, | |
| "eval_loss": NaN, | |
| "eval_runtime": 420.3349, | |
| "eval_samples_per_second": 13.197, | |
| "eval_steps_per_second": 6.599, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0004554771122751082, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0006832156684126623, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0007591285204585136, | |
| "eval_loss": NaN, | |
| "eval_runtime": 420.4888, | |
| "eval_samples_per_second": 13.192, | |
| "eval_steps_per_second": 6.597, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0009109542245502164, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0011386927806877705, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0011386927806877705, | |
| "eval_loss": NaN, | |
| "eval_runtime": 420.5451, | |
| "eval_samples_per_second": 13.19, | |
| "eval_steps_per_second": 6.596, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0013664313368253246, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0015182570409170272, | |
| "eval_loss": NaN, | |
| "eval_runtime": 707.8603, | |
| "eval_samples_per_second": 7.836, | |
| "eval_steps_per_second": 3.919, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0015941698929628787, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0018219084491004327, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.001897821301146284, | |
| "eval_loss": NaN, | |
| "eval_runtime": 903.2947, | |
| "eval_samples_per_second": 6.141, | |
| "eval_steps_per_second": 3.071, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0020496470052379866, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.002277385561375541, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.002277385561375541, | |
| "eval_loss": NaN, | |
| "eval_runtime": 903.4191, | |
| "eval_samples_per_second": 6.14, | |
| "eval_steps_per_second": 3.071, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.054694248022016e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |