| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.40361911809222695, | |
| "eval_steps": 500, | |
| "global_step": 3000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.9997567688496474e-05, | |
| "loss": 2.9132, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.9990172715142793e-05, | |
| "loss": 0.0721, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.997781629993153e-05, | |
| "loss": 0.0757, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.9960500896052476e-05, | |
| "loss": 0.0599, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.9938477167054135e-05, | |
| "loss": 0.0353, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.9911304569050045e-05, | |
| "loss": 0.0256, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.987918618733232e-05, | |
| "loss": 0.0173, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.98421283985469e-05, | |
| "loss": 0.0276, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.9800138559988466e-05, | |
| "loss": 0.0225, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.97532250081397e-05, | |
| "loss": 0.026, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.970139705701628e-05, | |
| "loss": 0.0271, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.9644664996317616e-05, | |
| "loss": 0.0231, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.958304008938407e-05, | |
| "loss": 0.0196, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.951653457096072e-05, | |
| "loss": 0.0124, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.944516164476834e-05, | |
| "loss": 0.0159, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.9368935480882034e-05, | |
| "loss": 0.0144, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.9287871212917866e-05, | |
| "loss": 0.0182, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.9201984935028426e-05, | |
| "loss": 0.018, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.911129369870746e-05, | |
| "loss": 0.0156, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.90158155094046e-05, | |
| "loss": 0.0146, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.8915569322950615e-05, | |
| "loss": 0.0196, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 4.8810575041794e-05, | |
| "loss": 0.02, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.8700853511049656e-05, | |
| "loss": 0.0143, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.858642651436035e-05, | |
| "loss": 0.0111, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.846731676957191e-05, | |
| "loss": 0.0179, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.834354792422293e-05, | |
| "loss": 0.0133, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.821514455084985e-05, | |
| "loss": 0.0112, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.8082132142108465e-05, | |
| "loss": 0.0131, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 4.794453710571272e-05, | |
| "loss": 0.0134, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.780238675919182e-05, | |
| "loss": 0.0084, | |
| "step": 3000 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 22296, | |
| "num_train_epochs": 3, | |
| "save_steps": 3000, | |
| "total_flos": 1.213342101638185e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |