| { | |
| "best_metric": 0.6992263056092843, | |
| "best_model_checkpoint": "/train_synth_spider_sampled_all_01_run_01_train/checkpoint-392", | |
| "epoch": 6.997668673231497, | |
| "global_step": 392, | |
| "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": 3.5409, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5492, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_exact_match": 0.28336557059961315, | |
| "eval_exec": 0.3365570599613153, | |
| "eval_loss": 0.5485422015190125, | |
| "eval_runtime": 18949.0472, | |
| "eval_samples_per_second": 0.055, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1931, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_exact_match": 0.30947775628626695, | |
| "eval_exec": 0.5851063829787234, | |
| "eval_loss": 0.5121298432350159, | |
| "eval_runtime": 1802.6407, | |
| "eval_samples_per_second": 0.574, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1547, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_exact_match": 0.3404255319148936, | |
| "eval_exec": 0.6634429400386848, | |
| "eval_loss": 0.47683650255203247, | |
| "eval_runtime": 1827.0837, | |
| "eval_samples_per_second": 0.566, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1342, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_exact_match": 0.3529980657640232, | |
| "eval_exec": 0.6798839458413927, | |
| "eval_loss": 0.5107799768447876, | |
| "eval_runtime": 1921.6432, | |
| "eval_samples_per_second": 0.538, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1199, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_exact_match": 0.3152804642166344, | |
| "eval_exec": 0.6692456479690522, | |
| "eval_loss": 0.5156922936439514, | |
| "eval_runtime": 2316.9587, | |
| "eval_samples_per_second": 0.446, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1102, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_exact_match": 0.30754352030947774, | |
| "eval_exec": 0.6789168278529981, | |
| "eval_loss": 0.5207614898681641, | |
| "eval_runtime": 1852.842, | |
| "eval_samples_per_second": 0.558, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1024, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_exact_match": 0.3355899419729207, | |
| "eval_exec": 0.6992263056092843, | |
| "eval_loss": 0.502002477645874, | |
| "eval_runtime": 1897.7756, | |
| "eval_samples_per_second": 0.545, | |
| "step": 392 | |
| } | |
| ], | |
| "max_steps": 2800, | |
| "num_train_epochs": 50, | |
| "total_flos": 4.5786426052283474e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |