Meta-Okapi/trained_reward_fr_lr3e-5_10ksteps

1{2  "apply_residual_connection_post_layernorm": false,3  "architectures": [4    "BloomForSequenceClassification"5  ],6  "attention_dropout": 0.0,7  "attention_softmax_in_fp32": true,8  "bias_dropout_fusion": true,9  "bos_token_id": 1,10  "dtype": "bfloat16",11  "eos_token_id": 2,12  "hidden_dropout": 0.0,13  "hidden_size": 2048,14  "id2label": {15    "0": "LABEL_0"16  },17  "initializer_range": 0.02,18  "label2id": {19    "LABEL_0": 020  },21  "layer_norm_epsilon": 1e-05,22  "masked_softmax_fusion": true,23  "model_type": "bloom",24  "n_head": 16,25  "n_inner": null,26  "n_layer": 24,27  "offset_alibi": 100,28  "pad_token_id": 3,29  "pretraining_tp": 2,30  "seq_length": 4096,31  "skip_bias_add": true,32  "skip_bias_add_qkv": false,33  "slow_but_exact": false,34  "transformers_version": "4.56.0",35  "unk_token_id": 0,36  "use_cache": true,37  "vocab_size": 25088038}39