| { | |
| "best_metric": 0.7021276595744681, | |
| "best_model_checkpoint": "/train_synth_spider_sampled_all_01_run_00_train/checkpoint-336", | |
| "epoch": 5.997668673231497, | |
| "global_step": 336, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0001, | |
| "loss": 3.5417, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5468, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_exact_match": 0.281431334622824, | |
| "eval_exec": 0.4951644100580271, | |
| "eval_loss": 0.5159241557121277, | |
| "eval_runtime": 1406.1616, | |
| "eval_samples_per_second": 0.735, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1933, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_exact_match": 0.3317214700193424, | |
| "eval_exec": 0.6363636363636364, | |
| "eval_loss": 0.518136203289032, | |
| "eval_runtime": 2302.9263, | |
| "eval_samples_per_second": 0.449, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1528, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_exact_match": 0.3181818181818182, | |
| "eval_exec": 0.6344294003868471, | |
| "eval_loss": 0.4836026132106781, | |
| "eval_runtime": 1889.4185, | |
| "eval_samples_per_second": 0.547, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1327, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_exact_match": 0.3607350096711799, | |
| "eval_exec": 0.6847195357833655, | |
| "eval_loss": 0.498320996761322, | |
| "eval_runtime": 1664.6976, | |
| "eval_samples_per_second": 0.621, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0001, | |
| "loss": 0.12, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_exact_match": 0.31431334622823986, | |
| "eval_exec": 0.6731141199226306, | |
| "eval_loss": 0.5015786290168762, | |
| "eval_runtime": 2255.9177, | |
| "eval_samples_per_second": 0.458, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1106, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_exact_match": 0.32495164410058025, | |
| "eval_exec": 0.7021276595744681, | |
| "eval_loss": 0.5117971301078796, | |
| "eval_runtime": 1729.5329, | |
| "eval_samples_per_second": 0.598, | |
| "step": 336 | |
| } | |
| ], | |
| "max_steps": 2800, | |
| "num_train_epochs": 50, | |
| "total_flos": 3.9251496697240044e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |