LamaDiab/NewMiniLM-V25Data-256BATCH-SemanticEngine

1{2  "best_global_step": null,3  "best_metric": null,4  "best_model_checkpoint": null,5  "epoch": 1.0,6  "eval_steps": 1000,7  "global_step": 1966,8  "is_hyper_param_search": false,9  "is_local_process_zero": true,10  "is_world_process_zero": true,11  "log_history": [12    {13      "epoch": 0.000508646998982706,14      "grad_norm": 4.802672863006592,15      "learning_rate": 0.0,16      "loss": 3.5148,17      "step": 118    },19    {20      "epoch": 0.508646998982706,21      "grad_norm": 4.325772285461426,22      "learning_rate": 2.994574432010851e-05,23      "loss": 2.3332,24      "step": 100025    },26    {27      "epoch": 0.508646998982706,28      "eval_cosine_accuracy": 0.9514144659042358,29      "eval_loss": 0.4182649254798889,30      "eval_runtime": 40.3586,31      "eval_samples_per_second": 235.613,32      "eval_steps_per_second": 0.942,33      "step": 100034    }35  ],36  "logging_steps": 1000,37  "max_steps": 9830,38  "num_input_tokens_seen": 0,39  "num_train_epochs": 5,40  "save_steps": 500,41  "stateful_callbacks": {42    "TrainerControl": {43      "args": {44        "should_epoch_stop": false,45        "should_evaluate": false,46        "should_log": false,47        "should_save": true,48        "should_training_stop": false49      },50      "attributes": {}51    }52  },53  "total_flos": 0.0,54  "train_batch_size": 256,55  "trial_name": null,56  "trial_params": null57}58