| { | |
| "best_metric": 0.315158873796463, | |
| "best_model_checkpoint": "checkpoints/instrucode/low-shot-task-specific-500-ex/commonsense_qa/checkpoint-120", | |
| "epoch": 9.6, | |
| "eval_steps": 500, | |
| "global_step": 120, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 7.333333333333333e-05, | |
| "loss": 4.3959, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 2.007786750793457, | |
| "eval_runtime": 3.9225, | |
| "eval_samples_per_second": 25.494, | |
| "eval_steps_per_second": 3.314, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 1.4138, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.5842701196670532, | |
| "eval_runtime": 3.8952, | |
| "eval_samples_per_second": 25.673, | |
| "eval_steps_per_second": 3.337, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 6.000000000000001e-05, | |
| "loss": 0.5802, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "eval_loss": 0.48449742794036865, | |
| "eval_runtime": 3.9041, | |
| "eval_samples_per_second": 25.614, | |
| "eval_steps_per_second": 3.33, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 5.333333333333333e-05, | |
| "loss": 0.4476, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.666666666666667e-05, | |
| "loss": 0.3758, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.3487338721752167, | |
| "eval_runtime": 3.9136, | |
| "eval_samples_per_second": 25.552, | |
| "eval_steps_per_second": 3.322, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 4e-05, | |
| "loss": 0.3099, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "eval_loss": 0.3447181284427643, | |
| "eval_runtime": 3.9145, | |
| "eval_samples_per_second": 25.546, | |
| "eval_steps_per_second": 3.321, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.2785, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.3341815173625946, | |
| "eval_runtime": 3.9058, | |
| "eval_samples_per_second": 25.603, | |
| "eval_steps_per_second": 3.328, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 0.2473, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 6.96, | |
| "eval_loss": 0.32787469029426575, | |
| "eval_runtime": 3.9132, | |
| "eval_samples_per_second": 25.555, | |
| "eval_steps_per_second": 3.322, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2096, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.2026, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.36058053374290466, | |
| "eval_runtime": 3.9049, | |
| "eval_samples_per_second": 25.609, | |
| "eval_steps_per_second": 3.329, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.1703, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "eval_loss": 0.32292404770851135, | |
| "eval_runtime": 3.9053, | |
| "eval_samples_per_second": 25.606, | |
| "eval_steps_per_second": 3.329, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 0.0, | |
| "loss": 0.174, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "eval_loss": 0.315158873796463, | |
| "eval_runtime": 3.9182, | |
| "eval_samples_per_second": 25.522, | |
| "eval_steps_per_second": 3.318, | |
| "step": 120 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 120, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 1.884385099874304e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |