| { | |
| "best_global_step": 58, | |
| "best_metric": 0.08409731090068817, | |
| "best_model_checkpoint": "finetune/sqlcoder-finetuned\\checkpoint-58", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 58, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.35398230088495575, | |
| "grad_norm": 1.021061897277832, | |
| "learning_rate": 0.00019882804237803488, | |
| "loss": 0.21164827346801757, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.7079646017699115, | |
| "grad_norm": 0.6921543478965759, | |
| "learning_rate": 0.00018595696069872013, | |
| "loss": 0.06274759769439697, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.09725816547870636, | |
| "eval_runtime": 6.4034, | |
| "eval_samples_per_second": 3.904, | |
| "eval_steps_per_second": 2.03, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.0353982300884956, | |
| "grad_norm": 0.7166405320167542, | |
| "learning_rate": 0.0001606225410966638, | |
| "loss": 0.05296058654785156, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.3893805309734513, | |
| "grad_norm": 0.9153704643249512, | |
| "learning_rate": 0.0001264981502196662, | |
| "loss": 0.034215536713600156, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.7433628318584071, | |
| "grad_norm": 0.3629709482192993, | |
| "learning_rate": 8.853165746015997e-05, | |
| "loss": 0.029726356267929077, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.08409731090068817, | |
| "eval_runtime": 6.3711, | |
| "eval_samples_per_second": 3.924, | |
| "eval_steps_per_second": 2.04, | |
| "step": 58 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 87, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6008684516278272.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |