| { | |
| "best_metric": 0.7517201834862385, | |
| "best_model_checkpoint": "/mnt/cachenew/gutianle/llama2-scorer-non-existent/checkpoint-1800", | |
| "epoch": 0.9174311926605505, | |
| "eval_steps": 100, | |
| "global_step": 1800, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0001, | |
| "loss": 1.409, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_accuracy": 0.4294724770642202, | |
| "eval_f1-score": 0.41676886432858656, | |
| "eval_loss": 1.2865188121795654, | |
| "eval_precision": 0.5191394843763429, | |
| "eval_recall": 0.4294724770642202, | |
| "eval_runtime": 100.35, | |
| "eval_samples_per_second": 17.379, | |
| "eval_steps_per_second": 2.172, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0433, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_accuracy": 0.6439220183486238, | |
| "eval_f1-score": 0.6287928936906987, | |
| "eval_loss": 0.9169857501983643, | |
| "eval_precision": 0.6326166016462452, | |
| "eval_recall": 0.6439220183486238, | |
| "eval_runtime": 99.1386, | |
| "eval_samples_per_second": 17.592, | |
| "eval_steps_per_second": 2.199, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0001, | |
| "loss": 0.9457, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_accuracy": 0.573394495412844, | |
| "eval_f1-score": 0.5780536942349181, | |
| "eval_loss": 0.9270332455635071, | |
| "eval_precision": 0.6119488919407539, | |
| "eval_recall": 0.573394495412844, | |
| "eval_runtime": 99.5145, | |
| "eval_samples_per_second": 17.525, | |
| "eval_steps_per_second": 2.191, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8176, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_accuracy": 0.6702981651376146, | |
| "eval_f1-score": 0.6704055625650827, | |
| "eval_loss": 0.8484154343605042, | |
| "eval_precision": 0.6748752577010106, | |
| "eval_recall": 0.6702981651376146, | |
| "eval_runtime": 99.7876, | |
| "eval_samples_per_second": 17.477, | |
| "eval_steps_per_second": 2.185, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7769, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_accuracy": 0.6955275229357798, | |
| "eval_f1-score": 0.6937246764104357, | |
| "eval_loss": 0.8070082068443298, | |
| "eval_precision": 0.6933530425142568, | |
| "eval_recall": 0.6955275229357798, | |
| "eval_runtime": 99.3769, | |
| "eval_samples_per_second": 17.549, | |
| "eval_steps_per_second": 2.194, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7069, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_accuracy": 0.6961009174311926, | |
| "eval_f1-score": 0.6962474525389031, | |
| "eval_loss": 0.8322665095329285, | |
| "eval_precision": 0.7002298404175326, | |
| "eval_recall": 0.6961009174311926, | |
| "eval_runtime": 99.2464, | |
| "eval_samples_per_second": 17.572, | |
| "eval_steps_per_second": 2.197, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6742, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_accuracy": 0.7276376146788991, | |
| "eval_f1-score": 0.7163514624677091, | |
| "eval_loss": 0.7878208160400391, | |
| "eval_precision": 0.731064800275646, | |
| "eval_recall": 0.7276376146788991, | |
| "eval_runtime": 99.1023, | |
| "eval_samples_per_second": 17.598, | |
| "eval_steps_per_second": 2.2, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7139, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_accuracy": 0.694954128440367, | |
| "eval_f1-score": 0.7017678594633088, | |
| "eval_loss": 0.7812691926956177, | |
| "eval_precision": 0.7171557777434424, | |
| "eval_recall": 0.694954128440367, | |
| "eval_runtime": 99.2742, | |
| "eval_samples_per_second": 17.568, | |
| "eval_steps_per_second": 2.196, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7566, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_accuracy": 0.6909403669724771, | |
| "eval_f1-score": 0.6922199349668261, | |
| "eval_loss": 0.7475219368934631, | |
| "eval_precision": 0.7040747986976179, | |
| "eval_recall": 0.6909403669724771, | |
| "eval_runtime": 99.2593, | |
| "eval_samples_per_second": 17.57, | |
| "eval_steps_per_second": 2.196, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6692, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_accuracy": 0.6857798165137615, | |
| "eval_f1-score": 0.6973150689879362, | |
| "eval_loss": 0.7810325026512146, | |
| "eval_precision": 0.7120290886583457, | |
| "eval_recall": 0.6857798165137615, | |
| "eval_runtime": 99.239, | |
| "eval_samples_per_second": 17.574, | |
| "eval_steps_per_second": 2.197, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6733, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_accuracy": 0.7368119266055045, | |
| "eval_f1-score": 0.7271862000397501, | |
| "eval_loss": 0.7271122336387634, | |
| "eval_precision": 0.74773502586483, | |
| "eval_recall": 0.7368119266055045, | |
| "eval_runtime": 99.0466, | |
| "eval_samples_per_second": 17.608, | |
| "eval_steps_per_second": 2.201, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6356, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_accuracy": 0.7253440366972477, | |
| "eval_f1-score": 0.7249868939903279, | |
| "eval_loss": 0.7682604193687439, | |
| "eval_precision": 0.7249192202979644, | |
| "eval_recall": 0.7253440366972477, | |
| "eval_runtime": 99.36, | |
| "eval_samples_per_second": 17.552, | |
| "eval_steps_per_second": 2.194, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6112, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_accuracy": 0.7264908256880734, | |
| "eval_f1-score": 0.7199307263891085, | |
| "eval_loss": 0.8078410029411316, | |
| "eval_precision": 0.7206056594932215, | |
| "eval_recall": 0.7264908256880734, | |
| "eval_runtime": 99.258, | |
| "eval_samples_per_second": 17.57, | |
| "eval_steps_per_second": 2.196, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.0001, | |
| "loss": 0.646, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_accuracy": 0.7431192660550459, | |
| "eval_f1-score": 0.7350696097040301, | |
| "eval_loss": 0.7144489288330078, | |
| "eval_precision": 0.7421391963845961, | |
| "eval_recall": 0.7431192660550459, | |
| "eval_runtime": 99.3431, | |
| "eval_samples_per_second": 17.555, | |
| "eval_steps_per_second": 2.194, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6052, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_accuracy": 0.7471330275229358, | |
| "eval_f1-score": 0.7394703056430186, | |
| "eval_loss": 0.679287850856781, | |
| "eval_precision": 0.7525699542508473, | |
| "eval_recall": 0.7471330275229358, | |
| "eval_runtime": 99.4231, | |
| "eval_samples_per_second": 17.541, | |
| "eval_steps_per_second": 2.193, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6004, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_accuracy": 0.75, | |
| "eval_f1-score": 0.7503577703532133, | |
| "eval_loss": 0.7611460089683533, | |
| "eval_precision": 0.7582961750700967, | |
| "eval_recall": 0.75, | |
| "eval_runtime": 99.3947, | |
| "eval_samples_per_second": 17.546, | |
| "eval_steps_per_second": 2.193, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6041, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_accuracy": 0.7563073394495413, | |
| "eval_f1-score": 0.7497128952328905, | |
| "eval_loss": 0.7003496289253235, | |
| "eval_precision": 0.7580686951357652, | |
| "eval_recall": 0.7563073394495413, | |
| "eval_runtime": 99.3241, | |
| "eval_samples_per_second": 17.559, | |
| "eval_steps_per_second": 2.195, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5445, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_accuracy": 0.7517201834862385, | |
| "eval_f1-score": 0.7465676797118755, | |
| "eval_loss": 0.6659787893295288, | |
| "eval_precision": 0.7528237883767219, | |
| "eval_recall": 0.7517201834862385, | |
| "eval_runtime": 99.3316, | |
| "eval_samples_per_second": 17.557, | |
| "eval_steps_per_second": 2.195, | |
| "step": 1800 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 5886, | |
| "num_train_epochs": 3, | |
| "save_steps": 200, | |
| "total_flos": 2.868620669485056e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |