| { | |
| "best_metric": 0.6852201819419861, | |
| "best_model_checkpoint": "add_BERT_no_pretrain_wnli/checkpoint-40", | |
| "epoch": 13.0, | |
| "global_step": 65, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.9200000000000004e-05, | |
| "loss": 0.9529, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5633802816901409, | |
| "eval_loss": 0.6859562397003174, | |
| "eval_runtime": 0.1385, | |
| "eval_samples_per_second": 512.641, | |
| "eval_steps_per_second": 7.22, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 3.8400000000000005e-05, | |
| "loss": 0.762, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.43661971830985913, | |
| "eval_loss": 0.8068376183509827, | |
| "eval_runtime": 0.1395, | |
| "eval_samples_per_second": 509.037, | |
| "eval_steps_per_second": 7.17, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 3.76e-05, | |
| "loss": 0.7199, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.43661971830985913, | |
| "eval_loss": 0.6986883878707886, | |
| "eval_runtime": 0.14, | |
| "eval_samples_per_second": 507.156, | |
| "eval_steps_per_second": 7.143, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 3.680000000000001e-05, | |
| "loss": 0.7092, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.5633802816901409, | |
| "eval_loss": 0.6958004236221313, | |
| "eval_runtime": 0.1388, | |
| "eval_samples_per_second": 511.607, | |
| "eval_steps_per_second": 7.206, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 3.6e-05, | |
| "loss": 0.7149, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.5633802816901409, | |
| "eval_loss": 0.6853562593460083, | |
| "eval_runtime": 0.1392, | |
| "eval_samples_per_second": 509.961, | |
| "eval_steps_per_second": 7.183, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 3.52e-05, | |
| "loss": 0.7069, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.43661971830985913, | |
| "eval_loss": 0.6955687403678894, | |
| "eval_runtime": 0.1393, | |
| "eval_samples_per_second": 509.691, | |
| "eval_steps_per_second": 7.179, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 3.44e-05, | |
| "loss": 0.7008, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.43661971830985913, | |
| "eval_loss": 0.6985586881637573, | |
| "eval_runtime": 0.1391, | |
| "eval_samples_per_second": 510.536, | |
| "eval_steps_per_second": 7.191, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 3.3600000000000004e-05, | |
| "loss": 0.7079, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.5633802816901409, | |
| "eval_loss": 0.6852201819419861, | |
| "eval_runtime": 0.139, | |
| "eval_samples_per_second": 510.861, | |
| "eval_steps_per_second": 7.195, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 3.28e-05, | |
| "loss": 0.7444, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.43661971830985913, | |
| "eval_loss": 0.7381781935691833, | |
| "eval_runtime": 0.1382, | |
| "eval_samples_per_second": 513.836, | |
| "eval_steps_per_second": 7.237, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 0.7147, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.5633802816901409, | |
| "eval_loss": 0.7008692026138306, | |
| "eval_runtime": 0.1384, | |
| "eval_samples_per_second": 512.872, | |
| "eval_steps_per_second": 7.224, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 3.1200000000000006e-05, | |
| "loss": 0.7318, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.43661971830985913, | |
| "eval_loss": 0.7316415309906006, | |
| "eval_runtime": 0.1391, | |
| "eval_samples_per_second": 510.379, | |
| "eval_steps_per_second": 7.188, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 3.0400000000000004e-05, | |
| "loss": 0.7212, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.5633802816901409, | |
| "eval_loss": 0.6857689023017883, | |
| "eval_runtime": 0.1384, | |
| "eval_samples_per_second": 512.863, | |
| "eval_steps_per_second": 7.223, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 2.96e-05, | |
| "loss": 0.7043, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.43661971830985913, | |
| "eval_loss": 0.7075231075286865, | |
| "eval_runtime": 0.1394, | |
| "eval_samples_per_second": 509.331, | |
| "eval_steps_per_second": 7.174, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "step": 65, | |
| "total_flos": 1179011824746496.0, | |
| "train_loss": 0.7377610133244441, | |
| "train_runtime": 98.1104, | |
| "train_samples_per_second": 323.615, | |
| "train_steps_per_second": 2.548 | |
| } | |
| ], | |
| "max_steps": 250, | |
| "num_train_epochs": 50, | |
| "total_flos": 1179011824746496.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |