amm297/tmp_trainer
014
1{2 "_name_or_path": "facebook/opt-350m",3 "_remove_final_layer_norm": false,4 "activation_dropout": 0.0,5 "activation_function": "relu",6 "architectures": [7 "OPTForCausalLM"8 ],9 "attention_dropout": 0.0,10 "bos_token_id": 2,11 "do_layer_norm_before": false,12 "dropout": 0.1,13 "enable_bias": true,14 "eos_token_id": 2,15 "ffn_dim": 4096,16 "hidden_size": 1024,17 "init_std": 0.02,18 "layer_norm_elementwise_affine": true,19 "layerdrop": 0.0,20 "max_position_embeddings": 2048,21 "model_type": "opt",22 "num_attention_heads": 16,23 "num_hidden_layers": 24,24 "pad_token_id": 1,25 "prefix": "</s>",26 "torch_dtype": "float32",27 "transformers_version": "4.31.0.dev0",28 "use_cache": true,29 "vocab_size": 50272,30 "word_embed_proj_dim": 51231}32 