| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 1563, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06397952655150352, | |
| "grad_norm": 2.6240322589874268, | |
| "learning_rate": 1.974664107485605e-05, | |
| "loss": 0.692889175415039, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.12795905310300704, | |
| "grad_norm": 1.6500952243804932, | |
| "learning_rate": 1.9490722968650032e-05, | |
| "loss": 0.6690621948242188, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.19193857965451055, | |
| "grad_norm": 5.539139747619629, | |
| "learning_rate": 1.923480486244402e-05, | |
| "loss": 0.6443107604980469, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.2559181062060141, | |
| "grad_norm": 9.561639785766602, | |
| "learning_rate": 1.8978886756238006e-05, | |
| "loss": 0.6174827194213868, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.3198976327575176, | |
| "grad_norm": 3.9405109882354736, | |
| "learning_rate": 1.8722968650031992e-05, | |
| "loss": 0.603485221862793, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.3838771593090211, | |
| "grad_norm": 5.654637336730957, | |
| "learning_rate": 1.846705054382598e-05, | |
| "loss": 0.5690624237060546, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.44785668586052463, | |
| "grad_norm": 6.288730144500732, | |
| "learning_rate": 1.8211132437619962e-05, | |
| "loss": 0.5585448455810547, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.5118362124120281, | |
| "grad_norm": 7.303677558898926, | |
| "learning_rate": 1.795521433141395e-05, | |
| "loss": 0.5453743362426757, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.5758157389635317, | |
| "grad_norm": 4.167948246002197, | |
| "learning_rate": 1.7699296225207935e-05, | |
| "loss": 0.5284878540039063, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.6397952655150352, | |
| "grad_norm": 6.335079669952393, | |
| "learning_rate": 1.744337811900192e-05, | |
| "loss": 0.497203369140625, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.7037747920665387, | |
| "grad_norm": 9.398835182189941, | |
| "learning_rate": 1.7187460012795908e-05, | |
| "loss": 0.4662479782104492, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.7677543186180422, | |
| "grad_norm": 17.086259841918945, | |
| "learning_rate": 1.693154190658989e-05, | |
| "loss": 0.4858377456665039, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.8317338451695457, | |
| "grad_norm": 11.53818416595459, | |
| "learning_rate": 1.6675623800383878e-05, | |
| "loss": 0.45729072570800783, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.8957133717210493, | |
| "grad_norm": 22.93279457092285, | |
| "learning_rate": 1.6419705694177864e-05, | |
| "loss": 0.45677249908447265, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.9596928982725528, | |
| "grad_norm": 15.763897895812988, | |
| "learning_rate": 1.616378758797185e-05, | |
| "loss": 0.4614885711669922, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.81124, | |
| "eval_f1": 0.8026596411993476, | |
| "eval_loss": 0.4272981286048889, | |
| "eval_precision": 0.8408832033645842, | |
| "eval_recall": 0.76776, | |
| "eval_runtime": 16.5749, | |
| "eval_samples_per_second": 1508.308, | |
| "eval_steps_per_second": 94.299, | |
| "step": 1563 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 7815, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 15881088000000.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |