| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.006121728210964172, | |
| "eval_steps": 5, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00015696739002472236, | |
| "eval_loss": NaN, | |
| "eval_runtime": 95.1302, | |
| "eval_samples_per_second": 28.203, | |
| "eval_steps_per_second": 14.107, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004709021700741671, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0007848369501236119, | |
| "eval_loss": NaN, | |
| "eval_runtime": 94.1059, | |
| "eval_samples_per_second": 28.51, | |
| "eval_steps_per_second": 14.261, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0009418043401483342, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.714285714285714e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0014127065102225013, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.571428571428571e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0015696739002472237, | |
| "eval_loss": NaN, | |
| "eval_runtime": 94.1239, | |
| "eval_samples_per_second": 28.505, | |
| "eval_steps_per_second": 14.258, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0018836086802966683, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011428571428571428, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0023545108503708356, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014285714285714287, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0023545108503708356, | |
| "eval_loss": NaN, | |
| "eval_runtime": 94.1191, | |
| "eval_samples_per_second": 28.506, | |
| "eval_steps_per_second": 14.259, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0028254130204450026, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017142857142857143, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0031393478004944474, | |
| "eval_loss": NaN, | |
| "eval_runtime": 94.0127, | |
| "eval_samples_per_second": 28.539, | |
| "eval_steps_per_second": 14.275, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0032963151905191696, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0037672173605933367, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.003924184750618059, | |
| "eval_loss": NaN, | |
| "eval_runtime": 94.2067, | |
| "eval_samples_per_second": 28.48, | |
| "eval_steps_per_second": 14.245, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004238119530667504, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.004709021700741671, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004709021700741671, | |
| "eval_loss": NaN, | |
| "eval_runtime": 94.1205, | |
| "eval_samples_per_second": 28.506, | |
| "eval_steps_per_second": 14.258, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005179923870815838, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.005493858650865283, | |
| "eval_loss": NaN, | |
| "eval_runtime": 94.1646, | |
| "eval_samples_per_second": 28.493, | |
| "eval_steps_per_second": 14.252, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.005650826040890005, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.006121728210964172, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 39 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 39, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 21, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2726836196868096.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |