| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.5252100840336135, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.026260504201680673, | |
| "grad_norm": 2.606417417526245, | |
| "learning_rate": 0.0038949579831932773, | |
| "loss": 1.2269, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.052521008403361345, | |
| "grad_norm": 2.463599920272827, | |
| "learning_rate": 0.0037899159663865546, | |
| "loss": 1.1055, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07878151260504201, | |
| "grad_norm": 3.1962060928344727, | |
| "learning_rate": 0.003684873949579832, | |
| "loss": 1.0706, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.10504201680672269, | |
| "grad_norm": 3.148374557495117, | |
| "learning_rate": 0.0035798319327731095, | |
| "loss": 1.1056, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.13130252100840337, | |
| "grad_norm": 2.5041284561157227, | |
| "learning_rate": 0.0034747899159663868, | |
| "loss": 1.0834, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.15756302521008403, | |
| "grad_norm": 2.5208585262298584, | |
| "learning_rate": 0.003369747899159664, | |
| "loss": 1.1076, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.18382352941176472, | |
| "grad_norm": 2.758544445037842, | |
| "learning_rate": 0.0032647058823529413, | |
| "loss": 1.0285, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.21008403361344538, | |
| "grad_norm": 3.854949951171875, | |
| "learning_rate": 0.0031596638655462185, | |
| "loss": 1.0204, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.23634453781512604, | |
| "grad_norm": 3.600606918334961, | |
| "learning_rate": 0.0030546218487394958, | |
| "loss": 1.0311, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.26260504201680673, | |
| "grad_norm": 3.2583634853363037, | |
| "learning_rate": 0.0029495798319327735, | |
| "loss": 0.9868, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.28886554621848737, | |
| "grad_norm": 3.2210769653320312, | |
| "learning_rate": 0.0028445378151260507, | |
| "loss": 1.0129, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.31512605042016806, | |
| "grad_norm": 3.139937162399292, | |
| "learning_rate": 0.002739495798319328, | |
| "loss": 1.0096, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.34138655462184875, | |
| "grad_norm": 2.95237398147583, | |
| "learning_rate": 0.002634453781512605, | |
| "loss": 0.9322, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.36764705882352944, | |
| "grad_norm": 3.39207124710083, | |
| "learning_rate": 0.0025294117647058825, | |
| "loss": 0.939, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.3939075630252101, | |
| "grad_norm": 3.5582635402679443, | |
| "learning_rate": 0.0024243697478991597, | |
| "loss": 1.0108, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.42016806722689076, | |
| "grad_norm": 3.2852275371551514, | |
| "learning_rate": 0.0023193277310924374, | |
| "loss": 0.884, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.44642857142857145, | |
| "grad_norm": 3.8662281036376953, | |
| "learning_rate": 0.0022142857142857146, | |
| "loss": 0.8889, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.4726890756302521, | |
| "grad_norm": 3.1788485050201416, | |
| "learning_rate": 0.002109243697478992, | |
| "loss": 0.8649, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.4989495798319328, | |
| "grad_norm": 3.658193588256836, | |
| "learning_rate": 0.002004201680672269, | |
| "loss": 0.821, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.5252100840336135, | |
| "grad_norm": 3.557441234588623, | |
| "learning_rate": 0.0018991596638655462, | |
| "loss": 0.8908, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 1904, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 200, | |
| "total_flos": 0.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |