| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.001348632823475202, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.49544274491734e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1364.6943, | |
| "eval_samples_per_second": 6.864, | |
| "eval_steps_per_second": 3.432, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00013486328234752021, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000224772137245867, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1366.7798, | |
| "eval_samples_per_second": 6.853, | |
| "eval_steps_per_second": 3.427, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00026972656469504043, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0004045898470425606, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.000449544274491734, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1367.6027, | |
| "eval_samples_per_second": 6.849, | |
| "eval_steps_per_second": 3.425, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0005394531293900809, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.000674316411737601, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.000674316411737601, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1368.9612, | |
| "eval_samples_per_second": 6.842, | |
| "eval_steps_per_second": 3.422, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0008091796940851212, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.000899088548983468, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1531.396, | |
| "eval_samples_per_second": 6.117, | |
| "eval_steps_per_second": 3.059, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0009440429764326414, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0010789062587801617, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.001123860686229335, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2054.9787, | |
| "eval_samples_per_second": 4.558, | |
| "eval_steps_per_second": 2.279, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.001213769541127682, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.001348632823475202, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.001348632823475202, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1397.7655, | |
| "eval_samples_per_second": 6.701, | |
| "eval_steps_per_second": 3.351, | |
| "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": 2.159681118142464e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |