gr1tsaenko/trainer_output

1{2  "architectures": [3    "LlamaForSequenceClassification"4  ],5  "attention_bias": false,6  "attention_dropout": 0.0,7  "bos_token_id": 1,8  "dtype": "bfloat16",9  "eos_token_id": 2,10  "head_dim": 64,11  "hidden_act": "silu",12  "hidden_size": 576,13  "id2label": {14    "0": "LABEL_0"15  },16  "initializer_range": 0.02,17  "intermediate_size": 1536,18  "label2id": {19    "LABEL_0": 020  },21  "max_position_embeddings": 2048,22  "mlp_bias": false,23  "model_type": "llama",24  "num_attention_heads": 9,25  "num_hidden_layers": 30,26  "num_key_value_heads": 3,27  "pad_token_id": 2,28  "pretraining_tp": 1,29  "rms_norm_eps": 1e-05,30  "rope_scaling": null,31  "rope_theta": 10000.0,32  "tie_word_embeddings": true,33  "transformers_version": "4.57.1",34  "use_cache": true,35  "vocab_size": 4915236}37