| { | |
| "best_metric": 0.9714913368225098, | |
| "best_model_checkpoint": "saves/qwen_7b/lora/sft/checkpoint-1126", | |
| "epoch": 2.9955555555555557, | |
| "eval_steps": 500, | |
| "global_step": 1686, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.17777777777777778, | |
| "grad_norm": 0.7376002073287964, | |
| "learning_rate": 2.958579881656805e-05, | |
| "loss": 1.36, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 0.946097731590271, | |
| "learning_rate": 4.9948499337185685e-05, | |
| "loss": 1.0892, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5333333333333333, | |
| "grad_norm": 0.8915076851844788, | |
| "learning_rate": 4.9085642733870516e-05, | |
| "loss": 1.0346, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 0.952915370464325, | |
| "learning_rate": 4.7193504727388485e-05, | |
| "loss": 1.0148, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 0.9156692028045654, | |
| "learning_rate": 4.435294437904082e-05, | |
| "loss": 1.0175, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.9917173981666565, | |
| "eval_runtime": 119.6686, | |
| "eval_samples_per_second": 4.178, | |
| "eval_steps_per_second": 4.178, | |
| "step": 563 | |
| }, | |
| { | |
| "epoch": 1.0657777777777777, | |
| "grad_norm": 0.9918724894523621, | |
| "learning_rate": 4.068535084889406e-05, | |
| "loss": 0.9865, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.2435555555555555, | |
| "grad_norm": 1.2041079998016357, | |
| "learning_rate": 3.634745592345962e-05, | |
| "loss": 0.955, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.4213333333333333, | |
| "grad_norm": 1.1156851053237915, | |
| "learning_rate": 3.1524636203435906e-05, | |
| "loss": 0.9512, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.5991111111111111, | |
| "grad_norm": 1.1498212814331055, | |
| "learning_rate": 2.642299117736456e-05, | |
| "loss": 0.9495, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.7768888888888887, | |
| "grad_norm": 1.1297115087509155, | |
| "learning_rate": 2.1260535718625273e-05, | |
| "loss": 0.949, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.9546666666666668, | |
| "grad_norm": 1.1540333032608032, | |
| "learning_rate": 1.625788338763118e-05, | |
| "loss": 0.9563, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.9714913368225098, | |
| "eval_runtime": 119.3272, | |
| "eval_samples_per_second": 4.19, | |
| "eval_steps_per_second": 4.19, | |
| "step": 1126 | |
| }, | |
| { | |
| "epoch": 2.1315555555555554, | |
| "grad_norm": 1.1917593479156494, | |
| "learning_rate": 1.1628818681133966e-05, | |
| "loss": 0.9097, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.3093333333333335, | |
| "grad_norm": 1.2136421203613281, | |
| "learning_rate": 7.571161116308206e-06, | |
| "loss": 0.8999, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.487111111111111, | |
| "grad_norm": 1.2269536256790161, | |
| "learning_rate": 4.258311565949436e-06, | |
| "loss": 0.8997, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.664888888888889, | |
| "grad_norm": 1.2763224840164185, | |
| "learning_rate": 1.8318421056443574e-06, | |
| "loss": 0.9011, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.8426666666666667, | |
| "grad_norm": 1.2190372943878174, | |
| "learning_rate": 3.954460400907217e-07, | |
| "loss": 0.9017, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.9955555555555557, | |
| "eval_loss": 0.9726876020431519, | |
| "eval_runtime": 119.2495, | |
| "eval_samples_per_second": 4.193, | |
| "eval_steps_per_second": 4.193, | |
| "step": 1686 | |
| }, | |
| { | |
| "epoch": 2.9955555555555557, | |
| "step": 1686, | |
| "total_flos": 5.872683475324109e+17, | |
| "train_loss": 0.9816320471350691, | |
| "train_runtime": 11250.2702, | |
| "train_samples_per_second": 1.2, | |
| "train_steps_per_second": 0.15 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 1686, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.872683475324109e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |