| { | |
| "best_metric": 0.22196684777736664, | |
| "best_model_checkpoint": "sci_cite2/checkpoint-16134", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 16134, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.845047725300608e-06, | |
| "loss": 0.4454, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.690095450601216e-06, | |
| "loss": 0.3583, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.535143175901823e-06, | |
| "loss": 0.3288, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 9.38019090120243e-06, | |
| "loss": 0.3102, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 9.225238626503039e-06, | |
| "loss": 0.3006, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 9.070286351803646e-06, | |
| "loss": 0.2881, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 8.915334077104253e-06, | |
| "loss": 0.2824, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 8.76038180240486e-06, | |
| "loss": 0.2765, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 8.605429527705468e-06, | |
| "loss": 0.2682, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 8.450477253006075e-06, | |
| "loss": 0.2638, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 8.295524978306682e-06, | |
| "loss": 0.259, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 8.14057270360729e-06, | |
| "loss": 0.257, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 7.985620428907898e-06, | |
| "loss": 0.2526, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 7.830668154208505e-06, | |
| "loss": 0.248, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 7.675715879509111e-06, | |
| "loss": 0.2485, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 7.520763604809719e-06, | |
| "loss": 0.2418, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 8067, | |
| "train_accuracy": 0.8732977099630939, | |
| "train_f1": 0.8722354031725915, | |
| "train_loss": 0.213734969496727, | |
| "train_precision": 0.8861924332063127, | |
| "train_recall": 0.8732977099630939, | |
| "train_runtime": 2526.3719, | |
| "train_samples_per_second": 306.526, | |
| "train_steps_per_second": 3.193 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8648553719008264, | |
| "eval_f1": 0.863761374500173, | |
| "eval_loss": 0.2356892228126526, | |
| "eval_precision": 0.8767616410024536, | |
| "eval_recall": 0.8648553719008264, | |
| "eval_runtime": 633.1197, | |
| "eval_samples_per_second": 305.787, | |
| "eval_steps_per_second": 3.186, | |
| "step": 8067 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 7.365811330110326e-06, | |
| "loss": 0.222, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 7.210859055410934e-06, | |
| "loss": 0.2236, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 7.055906780711541e-06, | |
| "loss": 0.2179, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 6.900954506012149e-06, | |
| "loss": 0.2204, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 6.746002231312756e-06, | |
| "loss": 0.2182, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 6.591049956613363e-06, | |
| "loss": 0.2172, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 6.436097681913971e-06, | |
| "loss": 0.2094, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 6.281145407214578e-06, | |
| "loss": 0.2139, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 6.126193132515186e-06, | |
| "loss": 0.2105, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 5.9712408578157935e-06, | |
| "loss": 0.211, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 5.8162885831164004e-06, | |
| "loss": 0.2137, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 5.661336308417008e-06, | |
| "loss": 0.2132, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 5.506384033717615e-06, | |
| "loss": 0.2108, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 5.351431759018223e-06, | |
| "loss": 0.21, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 5.196479484318831e-06, | |
| "loss": 0.2109, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 5.041527209619438e-06, | |
| "loss": 0.2094, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 16134, | |
| "train_accuracy": 0.8852553854736195, | |
| "train_f1": 0.8841428775695753, | |
| "train_loss": 0.18161344528198242, | |
| "train_precision": 0.9007014174019812, | |
| "train_recall": 0.8852553854736195, | |
| "train_runtime": 2519.4245, | |
| "train_samples_per_second": 307.371, | |
| "train_steps_per_second": 3.202 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8720867768595041, | |
| "eval_f1": 0.8708637537852376, | |
| "eval_loss": 0.22196684777736664, | |
| "eval_precision": 0.8865148727683396, | |
| "eval_recall": 0.8720867768595041, | |
| "eval_runtime": 636.0409, | |
| "eval_samples_per_second": 304.383, | |
| "eval_steps_per_second": 3.171, | |
| "step": 16134 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 32268, | |
| "num_train_epochs": 4, | |
| "save_steps": 500, | |
| "total_flos": 4.0750535009734656e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |