| { | |
| "best_global_step": 229, | |
| "best_metric": 0.22333618998527527, | |
| "best_model_checkpoint": "./lora_qwen7b_python_abdiff_v1/checkpoint-229", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 229, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.043835616438356165, | |
| "grad_norm": 0.210234135389328, | |
| "learning_rate": 3.913043478260869e-06, | |
| "loss": 0.6169, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08767123287671233, | |
| "grad_norm": 0.25168153643608093, | |
| "learning_rate": 8.260869565217392e-06, | |
| "loss": 0.6133, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.13150684931506848, | |
| "grad_norm": 0.19567625224590302, | |
| "learning_rate": 1.2608695652173912e-05, | |
| "loss": 0.5688, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.17534246575342466, | |
| "grad_norm": 0.30335545539855957, | |
| "learning_rate": 1.6956521739130433e-05, | |
| "loss": 0.5225, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2191780821917808, | |
| "grad_norm": 0.24670398235321045, | |
| "learning_rate": 2.1304347826086958e-05, | |
| "loss": 0.3971, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.26301369863013696, | |
| "grad_norm": 0.12593719363212585, | |
| "learning_rate": 2.565217391304348e-05, | |
| "loss": 0.2952, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.30684931506849317, | |
| "grad_norm": 0.11282460391521454, | |
| "learning_rate": 3e-05, | |
| "loss": 0.2592, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.3506849315068493, | |
| "grad_norm": 0.10163664072751999, | |
| "learning_rate": 2.9514563106796115e-05, | |
| "loss": 0.2402, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.39452054794520547, | |
| "grad_norm": 0.09871397167444229, | |
| "learning_rate": 2.9029126213592237e-05, | |
| "loss": 0.2251, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.4383561643835616, | |
| "grad_norm": 0.09532774984836578, | |
| "learning_rate": 2.854368932038835e-05, | |
| "loss": 0.2132, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.4821917808219178, | |
| "grad_norm": 0.08755984157323837, | |
| "learning_rate": 2.8058252427184466e-05, | |
| "loss": 0.2086, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.5260273972602739, | |
| "grad_norm": 0.09590521454811096, | |
| "learning_rate": 2.757281553398058e-05, | |
| "loss": 0.198, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.5698630136986301, | |
| "grad_norm": 0.09363297373056412, | |
| "learning_rate": 2.7087378640776702e-05, | |
| "loss": 0.1954, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.6136986301369863, | |
| "grad_norm": 0.09872984886169434, | |
| "learning_rate": 2.6601941747572816e-05, | |
| "loss": 0.1902, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.6575342465753424, | |
| "grad_norm": 0.12371695041656494, | |
| "learning_rate": 2.611650485436893e-05, | |
| "loss": 0.1892, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.7013698630136986, | |
| "grad_norm": 0.10814935714006424, | |
| "learning_rate": 2.563106796116505e-05, | |
| "loss": 0.1808, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.7452054794520548, | |
| "grad_norm": 0.12739220261573792, | |
| "learning_rate": 2.5145631067961167e-05, | |
| "loss": 0.1815, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.7890410958904109, | |
| "grad_norm": 0.1482655555009842, | |
| "learning_rate": 2.466019417475728e-05, | |
| "loss": 0.1652, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.8328767123287671, | |
| "grad_norm": 0.13323327898979187, | |
| "learning_rate": 2.41747572815534e-05, | |
| "loss": 0.1663, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.8767123287671232, | |
| "grad_norm": 0.1497439742088318, | |
| "learning_rate": 2.3689320388349514e-05, | |
| "loss": 0.1693, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.9205479452054794, | |
| "grad_norm": 0.16727504134178162, | |
| "learning_rate": 2.3203883495145632e-05, | |
| "loss": 0.1588, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.9643835616438357, | |
| "grad_norm": 0.159692645072937, | |
| "learning_rate": 2.2718446601941746e-05, | |
| "loss": 0.1489, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.22333618998527527, | |
| "eval_runtime": 65.6094, | |
| "eval_samples_per_second": 18.808, | |
| "eval_steps_per_second": 9.404, | |
| "step": 229 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 687, | |
| "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": 2.450291044029481e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |