Upload 28 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+pi_list/tokenizer.json filter=lfs diff=lfs merge=lfs -text

pi_cls/config.json

@@ -0,0 +1,33 @@
+{
+  "architectures": [
+    "MyModel"
+  ],
+  "hidden_size": 4096,
+  "dias_emb_dim": 64,
+  "dias_embed_table_path": "./data/saved_embedding/diag_embed_micron.pkl",
+  "dias_mlp_dim": 512,
+  "drug_emb_dim": 300,
+  "drug_embed_table_path": "./data/saved_embedding/med_embed_molebert.pkl",
+  "drug_mlp_dim": 1024,
+  "llm_emb_dim": 4096,
+  "llm_name": "Llama3-Aloe-8B-Alpha",
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "lora_r": 8,
+  "lora_target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "pat_emb_dim": 512,
+  "pat_embed_table_path": "./data/saved_embedding/pat_embed_raremed.pkl",
+  "pat_mlp_dim": 1024,
+  "pro_emb_dim": 64,
+  "pro_embed_table_path": "./data/saved_embedding/pro_embed_micron.pkl",
+  "pro_mlp_dim": 512,
+  "torch_dtype": "float16",
+  "transformers_version": "4.45.2",
+  "use_dias_embed": true,
+  "use_drug_embed": true,
+  "use_pat_embed": true,
+  "use_pro_embed": true
+}

pi_cls/generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.45.2"
+}

pi_cls/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6f2c9183dd00f295453ac4d285ec230b8cd722c482b182e69a36b0398915e81
+size 4980572264

pi_cls/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5af55ceb6c7b245de2573aed76cda056b895471ea026aa89e527ce375c02ff57
+size 4887483120

pi_cls/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfbecdfa9cdd8906a6c83d2fcb64f3a1e5f9d47a806a514fb044ff4e57980c08
+size 4920610568

pi_cls/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e3d5ca8a8809b7172ad98d8dbb39da0783191aabc2db447c4375ec5f190f25e
+size 1339611344

pi_cls/model.safetensors.index.json

@@ -0,0 +1,442 @@
+{
+  "metadata": {
+    "total_size": 16128217088
+  },
+  "weight_map": {
+    "dias_projector.0.bias": "model-00004-of-00004.safetensors",
+    "dias_projector.0.weight": "model-00004-of-00004.safetensors",
+    "dias_projector.2.bias": "model-00004-of-00004.safetensors",
+    "dias_projector.2.weight": "model-00004-of-00004.safetensors",
+    "drug_projector.0.bias": "model-00004-of-00004.safetensors",
+    "drug_projector.0.weight": "model-00004-of-00004.safetensors",
+    "drug_projector.2.bias": "model-00004-of-00004.safetensors",
+    "drug_projector.2.weight": "model-00004-of-00004.safetensors",
+    "llm.base_model.model.lm_head.weight": "model-00004-of-00004.safetensors",
+    "llm.base_model.model.model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.0.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.0.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.0.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.0.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.0.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.0.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.1.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.1.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.1.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.1.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.1.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.1.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.10.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.10.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.10.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.10.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.10.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.10.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.11.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.11.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.11.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.11.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.11.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.11.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.12.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.12.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.12.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.12.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.12.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.12.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.13.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.13.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.13.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.13.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.13.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.13.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.14.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.14.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.14.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.14.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.14.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.14.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.15.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.15.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.15.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.15.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.15.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.15.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.16.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.16.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.16.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.16.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.16.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.16.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.17.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.17.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.17.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.17.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.17.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.17.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.18.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.18.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.18.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.18.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.18.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.18.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.19.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.19.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.19.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.19.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.19.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.19.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.2.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.2.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.2.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.2.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.2.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.2.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.20.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.20.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.20.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.20.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.20.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.20.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.21.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.21.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.21.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.21.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.21.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.21.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.22.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.22.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.22.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.22.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.22.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.22.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.23.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.23.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.23.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.23.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.23.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.23.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.24.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.24.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.24.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.24.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.24.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.24.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.25.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.25.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.25.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.25.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.25.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.25.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.26.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.26.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.26.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.26.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.26.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.26.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.27.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.27.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.27.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.27.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.27.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.27.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.28.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.28.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.28.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.28.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.28.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.28.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.29.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.29.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.29.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.29.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.29.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.29.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.3.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.3.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.3.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.3.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.3.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.3.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.30.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.30.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.30.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.30.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.30.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.30.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "llm.base_model.model.model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "llm.base_model.model.model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "llm.base_model.model.model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "llm.base_model.model.model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.31.self_attn.q_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.31.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.31.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.31.self_attn.v_proj.base_layer.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.31.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.31.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00004.safetensors",
+    "llm.base_model.model.model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.4.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.4.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.4.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.4.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.4.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.4.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.5.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.5.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.5.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.5.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.5.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.5.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.6.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.6.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.6.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.6.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.6.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.6.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.7.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.7.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.7.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.7.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.7.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.7.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.8.self_attn.q_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.8.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.8.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.8.self_attn.v_proj.base_layer.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.8.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.8.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00004.safetensors",
+    "llm.base_model.model.model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.9.self_attn.q_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.9.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.9.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.9.self_attn.v_proj.base_layer.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.9.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.layers.9.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00004.safetensors",
+    "llm.base_model.model.model.norm.weight": "model-00004-of-00004.safetensors",
+    "pat_projector.0.bias": "model-00004-of-00004.safetensors",
+    "pat_projector.0.weight": "model-00004-of-00004.safetensors",
+    "pat_projector.2.bias": "model-00004-of-00004.safetensors",
+    "pat_projector.2.weight": "model-00004-of-00004.safetensors",
+    "pro_projector.0.bias": "model-00004-of-00004.safetensors",
+    "pro_projector.0.weight": "model-00004-of-00004.safetensors",
+    "pro_projector.2.bias": "model-00004-of-00004.safetensors",
+    "pro_projector.2.weight": "model-00004-of-00004.safetensors"
+  }
+}

pi_cls/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03cfad5aefb03ce696e07efff1c3abce8f2a69ede2b1dd0e47314a4b66dcb4d8
+size 135378693

pi_cls/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b059e979e3d13eccfb38e0267e9a0bfc2bcaa9fe63fac582fba703a499a51f49
+size 19639

pi_cls/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a08dfb6c557f1ef1912f58e6b9f555c096b93b6c1e982c062192777b88d4e8a3
+size 19639

pi_cls/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f0b0f916de96a494bb97abf5f337320d3aee074f5fd21f436d61084f8d42ad2
+size 19639

pi_cls/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:363620e126a6b661c7d88b02912cc0c67c6554177394118b0e604529a6104c2e
+size 19639

pi_cls/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b129cdb0d9171323d2b0a27065540b3ae535349689e136805872d119d33cbb8
+size 19639

pi_cls/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b78854dce18cf759be4588b5d3fed668f6bf069fde25f00fa99e127adaaca482
+size 19639

pi_cls/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a43bf638600b0bc916fd0839113e86def3556714f4c0d4b4244410169dc0e419
+size 627

pi_cls/trainer_state.json

@@ -0,0 +1,1918 @@
+{
+  "best_metric": 0.4764,
+  "best_model_checkpoint": "./output/0222_aloe_use_embed/checkpoint-11392",
+  "epoch": 1.0036835966671422,
+  "eval_steps": 128,
+  "global_step": 11392,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 8.810424830294436e-05,
+      "grad_norm": 1.5417201519012451,
+      "learning_rate": 5e-05,
+      "loss": 0.2594,
+      "step": 1
+    },
+    {
+      "epoch": 0.011277343782776878,
+      "grad_norm": 0.23772290349006653,
+      "learning_rate": 0.00013975424859373687,
+      "loss": 0.1162,
+      "step": 128
+    },
+    {
+      "epoch": 0.011277343782776878,
+      "eval_f1": 0.4683,
+      "eval_jaccard": 0.32,
+      "eval_loss": 0.09878014773130417,
+      "eval_num_drugs": 12.72,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.6935,
+      "eval_recall": 0.3805,
+      "eval_runtime": 202.7898,
+      "eval_samples_per_second": 74.461,
+      "eval_steps_per_second": 1.553,
+      "step": 128
+    },
+    {
+      "epoch": 0.022554687565553757,
+      "grad_norm": 0.2692396640777588,
+      "learning_rate": 9.882117688026184e-05,
+      "loss": 0.1007,
+      "step": 256
+    },
+    {
+      "epoch": 0.022554687565553757,
+      "eval_f1": 0.5251,
+      "eval_jaccard": 0.3711,
+      "eval_loss": 0.09602733701467514,
+      "eval_num_drugs": 15.36,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.6844,
+      "eval_recall": 0.4448,
+      "eval_runtime": 195.8787,
+      "eval_samples_per_second": 77.089,
+      "eval_steps_per_second": 1.608,
+      "step": 256
+    },
+    {
+      "epoch": 0.033832031348330634,
+      "grad_norm": 0.3894853889942169,
+      "learning_rate": 8.068715304598785e-05,
+      "loss": 0.094,
+      "step": 384
+    },
+    {
+      "epoch": 0.033832031348330634,
+      "eval_f1": 0.4424,
+      "eval_jaccard": 0.298,
+      "eval_loss": 0.10007771104574203,
+      "eval_num_drugs": 10.42,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7377,
+      "eval_recall": 0.3307,
+      "eval_runtime": 195.8037,
+      "eval_samples_per_second": 77.118,
+      "eval_steps_per_second": 1.609,
+      "step": 384
+    },
+    {
+      "epoch": 0.045109375131107514,
+      "grad_norm": 0.3436169922351837,
+      "learning_rate": 6.987712429686843e-05,
+      "loss": 0.0957,
+      "step": 512
+    },
+    {
+      "epoch": 0.045109375131107514,
+      "eval_f1": 0.5042,
+      "eval_jaccard": 0.3496,
+      "eval_loss": 0.09312926977872849,
+      "eval_num_drugs": 12.82,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7312,
+      "eval_recall": 0.4012,
+      "eval_runtime": 195.8163,
+      "eval_samples_per_second": 77.113,
+      "eval_steps_per_second": 1.609,
+      "step": 512
+    },
+    {
+      "epoch": 0.05638671891388439,
+      "grad_norm": 0.3193528950214386,
+      "learning_rate": 6.25e-05,
+      "loss": 0.0936,
+      "step": 640
+    },
+    {
+      "epoch": 0.05638671891388439,
+      "eval_f1": 0.5265,
+      "eval_jaccard": 0.3719,
+      "eval_loss": 0.09239081293344498,
+      "eval_num_drugs": 15.05,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.6917,
+      "eval_recall": 0.4447,
+      "eval_runtime": 195.8519,
+      "eval_samples_per_second": 77.099,
+      "eval_steps_per_second": 1.608,
+      "step": 640
+    },
+    {
+      "epoch": 0.06766406269666127,
+      "grad_norm": 0.4577213227748871,
+      "learning_rate": 5.705443307345481e-05,
+      "loss": 0.0912,
+      "step": 768
+    },
+    {
+      "epoch": 0.06766406269666127,
+      "eval_f1": 0.4896,
+      "eval_jaccard": 0.3425,
+      "eval_loss": 0.09166081994771957,
+      "eval_num_drugs": 12.97,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7252,
+      "eval_recall": 0.3887,
+      "eval_runtime": 195.9265,
+      "eval_samples_per_second": 77.07,
+      "eval_steps_per_second": 1.608,
+      "step": 768
+    },
+    {
+      "epoch": 0.07894140647943815,
+      "grad_norm": 0.2731820344924927,
+      "learning_rate": 5.2822140920532286e-05,
+      "loss": 0.0877,
+      "step": 896
+    },
+    {
+      "epoch": 0.07894140647943815,
+      "eval_f1": 0.5059,
+      "eval_jaccard": 0.3548,
+      "eval_loss": 0.09068360179662704,
+      "eval_num_drugs": 13.69,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7167,
+      "eval_recall": 0.4115,
+      "eval_runtime": 195.7999,
+      "eval_samples_per_second": 77.12,
+      "eval_steps_per_second": 1.609,
+      "step": 896
+    },
+    {
+      "epoch": 0.09021875026221503,
+      "grad_norm": 0.2719137668609619,
+      "learning_rate": 4.941058844013092e-05,
+      "loss": 0.0863,
+      "step": 1024
+    },
+    {
+      "epoch": 0.09021875026221503,
+      "eval_f1": 0.5368,
+      "eval_jaccard": 0.3819,
+      "eval_loss": 0.08904419839382172,
+      "eval_num_drugs": 15.78,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.6916,
+      "eval_recall": 0.4575,
+      "eval_runtime": 195.7912,
+      "eval_samples_per_second": 77.123,
+      "eval_steps_per_second": 1.609,
+      "step": 1024
+    },
+    {
+      "epoch": 0.10149609404499191,
+      "grad_norm": 0.32245615124702454,
+      "learning_rate": 4.658474953124562e-05,
+      "loss": 0.0852,
+      "step": 1152
+    },
+    {
+      "epoch": 0.10149609404499191,
+      "eval_f1": 0.4884,
+      "eval_jaccard": 0.3382,
+      "eval_loss": 0.09045682102441788,
+      "eval_num_drugs": 12.3,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7387,
+      "eval_recall": 0.3797,
+      "eval_runtime": 195.7828,
+      "eval_samples_per_second": 77.126,
+      "eval_steps_per_second": 1.609,
+      "step": 1152
+    },
+    {
+      "epoch": 0.11277343782776877,
+      "grad_norm": 0.45535603165626526,
+      "learning_rate": 4.419417382415922e-05,
+      "loss": 0.0879,
+      "step": 1280
+    },
+    {
+      "epoch": 0.11277343782776877,
+      "eval_f1": 0.5573,
+      "eval_jaccard": 0.4005,
+      "eval_loss": 0.0893692597746849,
+      "eval_num_drugs": 17.23,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.6755,
+      "eval_recall": 0.4937,
+      "eval_runtime": 195.6687,
+      "eval_samples_per_second": 77.171,
+      "eval_steps_per_second": 1.61,
+      "step": 1280
+    },
+    {
+      "epoch": 0.12405078161054565,
+      "grad_norm": 0.2283882200717926,
+      "learning_rate": 4.213749140395263e-05,
+      "loss": 0.088,
+      "step": 1408
+    },
+    {
+      "epoch": 0.12405078161054565,
+      "eval_f1": 0.5172,
+      "eval_jaccard": 0.3636,
+      "eval_loss": 0.08751444518566132,
+      "eval_num_drugs": 13.51,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7351,
+      "eval_recall": 0.4155,
+      "eval_runtime": 195.8082,
+      "eval_samples_per_second": 77.116,
+      "eval_steps_per_second": 1.609,
+      "step": 1408
+    },
+    {
+      "epoch": 0.13532812539332253,
+      "grad_norm": 0.29352277517318726,
+      "learning_rate": 4.0343576522993926e-05,
+      "loss": 0.0854,
+      "step": 1536
+    },
+    {
+      "epoch": 0.13532812539332253,
+      "eval_f1": 0.5465,
+      "eval_jaccard": 0.3926,
+      "eval_loss": 0.08854938298463821,
+      "eval_num_drugs": 15.62,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7063,
+      "eval_recall": 0.4631,
+      "eval_runtime": 195.7835,
+      "eval_samples_per_second": 77.126,
+      "eval_steps_per_second": 1.609,
+      "step": 1536
+    },
+    {
+      "epoch": 0.14660546917609943,
+      "grad_norm": 0.2647421360015869,
+      "learning_rate": 3.876085455912764e-05,
+      "loss": 0.0865,
+      "step": 1664
+    },
+    {
+      "epoch": 0.14660546917609943,
+      "eval_f1": 0.5254,
+      "eval_jaccard": 0.3705,
+      "eval_loss": 0.08727589249610901,
+      "eval_num_drugs": 14.2,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7208,
+      "eval_recall": 0.4289,
+      "eval_runtime": 195.7692,
+      "eval_samples_per_second": 77.132,
+      "eval_steps_per_second": 1.609,
+      "step": 1664
+    },
+    {
+      "epoch": 0.1578828129588763,
+      "grad_norm": 0.38300177454948425,
+      "learning_rate": 3.7350894041699797e-05,
+      "loss": 0.0863,
+      "step": 1792
+    },
+    {
+      "epoch": 0.1578828129588763,
+      "eval_f1": 0.545,
+      "eval_jaccard": 0.3906,
+      "eval_loss": 0.08650780469179153,
+      "eval_num_drugs": 15.84,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7013,
+      "eval_recall": 0.4628,
+      "eval_runtime": 195.6292,
+      "eval_samples_per_second": 77.187,
+      "eval_steps_per_second": 1.61,
+      "step": 1792
+    },
+    {
+      "epoch": 0.16916015674165316,
+      "grad_norm": 0.2728304862976074,
+      "learning_rate": 3.608439182435162e-05,
+      "loss": 0.0835,
+      "step": 1920
+    },
+    {
+      "epoch": 0.16916015674165316,
+      "eval_f1": 0.5221,
+      "eval_jaccard": 0.3695,
+      "eval_loss": 0.08654700964689255,
+      "eval_num_drugs": 13.26,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7471,
+      "eval_recall": 0.4178,
+      "eval_runtime": 195.6648,
+      "eval_samples_per_second": 77.173,
+      "eval_steps_per_second": 1.61,
+      "step": 1920
+    },
+    {
+      "epoch": 0.18043750052443006,
+      "grad_norm": 0.4084767997264862,
+      "learning_rate": 3.493856214843422e-05,
+      "loss": 0.083,
+      "step": 2048
+    },
+    {
+      "epoch": 0.18043750052443006,
+      "eval_f1": 0.568,
+      "eval_jaccard": 0.4119,
+      "eval_loss": 0.08511340618133545,
+      "eval_num_drugs": 16.65,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7107,
+      "eval_recall": 0.4901,
+      "eval_runtime": 195.8359,
+      "eval_samples_per_second": 77.105,
+      "eval_steps_per_second": 1.608,
+      "step": 2048
+    },
+    {
+      "epoch": 0.19171484430720692,
+      "grad_norm": 0.2854626476764679,
+      "learning_rate": 3.3895384034165023e-05,
+      "loss": 0.0825,
+      "step": 2176
+    },
+    {
+      "epoch": 0.19171484430720692,
+      "eval_f1": 0.5436,
+      "eval_jaccard": 0.3895,
+      "eval_loss": 0.08521977812051773,
+      "eval_num_drugs": 14.88,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7283,
+      "eval_recall": 0.4479,
+      "eval_runtime": 195.8491,
+      "eval_samples_per_second": 77.1,
+      "eval_steps_per_second": 1.608,
+      "step": 2176
+    },
+    {
+      "epoch": 0.20299218808998382,
+      "grad_norm": 0.3946376442909241,
+      "learning_rate": 3.294039229342062e-05,
+      "loss": 0.0824,
+      "step": 2304
+    },
+    {
+      "epoch": 0.20299218808998382,
+      "eval_f1": 0.5565,
+      "eval_jaccard": 0.4015,
+      "eval_loss": 0.08449013531208038,
+      "eval_num_drugs": 15.63,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7266,
+      "eval_recall": 0.4685,
+      "eval_runtime": 195.8046,
+      "eval_samples_per_second": 77.118,
+      "eval_steps_per_second": 1.609,
+      "step": 2304
+    },
+    {
+      "epoch": 0.21426953187276068,
+      "grad_norm": 0.39819344878196716,
+      "learning_rate": 3.206182350266107e-05,
+      "loss": 0.0838,
+      "step": 2432
+    },
+    {
+      "epoch": 0.21426953187276068,
+      "eval_f1": 0.5598,
+      "eval_jaccard": 0.4052,
+      "eval_loss": 0.08480122685432434,
+      "eval_num_drugs": 15.99,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7263,
+      "eval_recall": 0.4759,
+      "eval_runtime": 195.8068,
+      "eval_samples_per_second": 77.117,
+      "eval_steps_per_second": 1.609,
+      "step": 2432
+    },
+    {
+      "epoch": 0.22554687565553755,
+      "grad_norm": 0.40644770860671997,
+      "learning_rate": 3.125e-05,
+      "loss": 0.0808,
+      "step": 2560
+    },
+    {
+      "epoch": 0.22554687565553755,
+      "eval_f1": 0.5659,
+      "eval_jaccard": 0.4108,
+      "eval_loss": 0.08397021144628525,
+      "eval_num_drugs": 15.96,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.719,
+      "eval_recall": 0.486,
+      "eval_runtime": 195.678,
+      "eval_samples_per_second": 77.168,
+      "eval_steps_per_second": 1.61,
+      "step": 2560
+    },
+    {
+      "epoch": 0.23682421943831444,
+      "grad_norm": 0.3157194256782532,
+      "learning_rate": 3.049687727964166e-05,
+      "loss": 0.0818,
+      "step": 2688
+    },
+    {
+      "epoch": 0.23682421943831444,
+      "eval_f1": 0.5651,
+      "eval_jaccard": 0.41,
+      "eval_loss": 0.08456852287054062,
+      "eval_num_drugs": 16.17,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7168,
+      "eval_recall": 0.4853,
+      "eval_runtime": 195.5756,
+      "eval_samples_per_second": 77.208,
+      "eval_steps_per_second": 1.611,
+      "step": 2688
+    },
+    {
+      "epoch": 0.2481015632210913,
+      "grad_norm": 0.39622461795806885,
+      "learning_rate": 2.979570591392476e-05,
+      "loss": 0.0833,
+      "step": 2816
+    },
+    {
+      "epoch": 0.2481015632210913,
+      "eval_f1": 0.5621,
+      "eval_jaccard": 0.4064,
+      "eval_loss": 0.08314160257577896,
+      "eval_num_drugs": 15.53,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7432,
+      "eval_recall": 0.4715,
+      "eval_runtime": 195.5562,
+      "eval_samples_per_second": 77.216,
+      "eval_steps_per_second": 1.611,
+      "step": 2816
+    },
+    {
+      "epoch": 0.2593789070038682,
+      "grad_norm": 0.3746698200702667,
+      "learning_rate": 2.9140775257509805e-05,
+      "loss": 0.0819,
+      "step": 2944
+    },
+    {
+      "epoch": 0.2593789070038682,
+      "eval_f1": 0.5496,
+      "eval_jaccard": 0.3959,
+      "eval_loss": 0.08432751148939133,
+      "eval_num_drugs": 15.12,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7236,
+      "eval_recall": 0.4611,
+      "eval_runtime": 195.7114,
+      "eval_samples_per_second": 77.154,
+      "eval_steps_per_second": 1.61,
+      "step": 2944
+    },
+    {
+      "epoch": 0.27065625078664507,
+      "grad_norm": 0.3464062809944153,
+      "learning_rate": 2.8527216536727405e-05,
+      "loss": 0.0815,
+      "step": 3072
+    },
+    {
+      "epoch": 0.27065625078664507,
+      "eval_f1": 0.5655,
+      "eval_jaccard": 0.4104,
+      "eval_loss": 0.08330993354320526,
+      "eval_num_drugs": 16.18,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7149,
+      "eval_recall": 0.4862,
+      "eval_runtime": 195.7753,
+      "eval_samples_per_second": 77.129,
+      "eval_steps_per_second": 1.609,
+      "step": 3072
+    },
+    {
+      "epoch": 0.28193359456942196,
+      "grad_norm": 0.4193006455898285,
+      "learning_rate": 2.7950849718747372e-05,
+      "loss": 0.0838,
+      "step": 3200
+    },
+    {
+      "epoch": 0.28193359456942196,
+      "eval_f1": 0.5968,
+      "eval_jaccard": 0.4411,
+      "eval_loss": 0.0835125669836998,
+      "eval_num_drugs": 18.88,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.6926,
+      "eval_recall": 0.5435,
+      "eval_runtime": 195.749,
+      "eval_samples_per_second": 77.14,
+      "eval_steps_per_second": 1.609,
+      "step": 3200
+    },
+    {
+      "epoch": 0.29321093835219886,
+      "grad_norm": 0.3613840639591217,
+      "learning_rate": 2.7408063103344662e-05,
+      "loss": 0.0794,
+      "step": 3328
+    },
+    {
+      "epoch": 0.29321093835219886,
+      "eval_f1": 0.5667,
+      "eval_jaccard": 0.411,
+      "eval_loss": 0.08442004770040512,
+      "eval_num_drugs": 15.87,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7218,
+      "eval_recall": 0.4827,
+      "eval_runtime": 195.8795,
+      "eval_samples_per_second": 77.088,
+      "eval_steps_per_second": 1.608,
+      "step": 3328
+    },
+    {
+      "epoch": 0.3044882821349757,
+      "grad_norm": 0.4692389965057373,
+      "learning_rate": 2.689571768199595e-05,
+      "loss": 0.0836,
+      "step": 3456
+    },
+    {
+      "epoch": 0.3044882821349757,
+      "eval_f1": 0.5652,
+      "eval_jaccard": 0.4105,
+      "eval_loss": 0.082563117146492,
+      "eval_num_drugs": 16.22,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7177,
+      "eval_recall": 0.4819,
+      "eval_runtime": 195.7858,
+      "eval_samples_per_second": 77.125,
+      "eval_steps_per_second": 1.609,
+      "step": 3456
+    },
+    {
+      "epoch": 0.3157656259177526,
+      "grad_norm": 0.4498782753944397,
+      "learning_rate": 2.6411070460266143e-05,
+      "loss": 0.0829,
+      "step": 3584
+    },
+    {
+      "epoch": 0.3157656259177526,
+      "eval_f1": 0.5562,
+      "eval_jaccard": 0.4007,
+      "eval_loss": 0.08358080685138702,
+      "eval_num_drugs": 15.45,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7373,
+      "eval_recall": 0.4682,
+      "eval_runtime": 195.7125,
+      "eval_samples_per_second": 77.154,
+      "eval_steps_per_second": 1.61,
+      "step": 3584
+    },
+    {
+      "epoch": 0.3270429697005295,
+      "grad_norm": 0.3039364516735077,
+      "learning_rate": 2.595171245429374e-05,
+      "loss": 0.0807,
+      "step": 3712
+    },
+    {
+      "epoch": 0.3270429697005295,
+      "eval_f1": 0.5737,
+      "eval_jaccard": 0.4194,
+      "eval_loss": 0.08231409639120102,
+      "eval_num_drugs": 16.28,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7229,
+      "eval_recall": 0.4939,
+      "eval_runtime": 195.8345,
+      "eval_samples_per_second": 77.106,
+      "eval_steps_per_second": 1.609,
+      "step": 3712
+    },
+    {
+      "epoch": 0.3383203134833063,
+      "grad_norm": 0.35619407892227173,
+      "learning_rate": 2.5515518153991443e-05,
+      "loss": 0.081,
+      "step": 3840
+    },
+    {
+      "epoch": 0.3383203134833063,
+      "eval_f1": 0.552,
+      "eval_jaccard": 0.3985,
+      "eval_loss": 0.08209805935621262,
+      "eval_num_drugs": 14.51,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7461,
+      "eval_recall": 0.4559,
+      "eval_runtime": 195.7934,
+      "eval_samples_per_second": 77.122,
+      "eval_steps_per_second": 1.609,
+      "step": 3840
+    },
+    {
+      "epoch": 0.3495976572660832,
+      "grad_norm": 0.3351137936115265,
+      "learning_rate": 2.5100604028203093e-05,
+      "loss": 0.0812,
+      "step": 3968
+    },
+    {
+      "epoch": 0.3495976572660832,
+      "eval_f1": 0.5629,
+      "eval_jaccard": 0.4087,
+      "eval_loss": 0.08269884437322617,
+      "eval_num_drugs": 15.55,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7386,
+      "eval_recall": 0.4789,
+      "eval_runtime": 195.8309,
+      "eval_samples_per_second": 77.107,
+      "eval_steps_per_second": 1.609,
+      "step": 3968
+    },
+    {
+      "epoch": 0.3608750010488601,
+      "grad_norm": 0.39990243315696716,
+      "learning_rate": 2.470529422006546e-05,
+      "loss": 0.0812,
+      "step": 4096
+    },
+    {
+      "epoch": 0.3608750010488601,
+      "eval_f1": 0.5841,
+      "eval_jaccard": 0.4288,
+      "eval_loss": 0.08231902867555618,
+      "eval_num_drugs": 17.38,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7097,
+      "eval_recall": 0.5165,
+      "eval_runtime": 195.693,
+      "eval_samples_per_second": 77.162,
+      "eval_steps_per_second": 1.61,
+      "step": 4096
+    },
+    {
+      "epoch": 0.37215234483163695,
+      "grad_norm": 0.2565082013607025,
+      "learning_rate": 2.4328092005047595e-05,
+      "loss": 0.0783,
+      "step": 4224
+    },
+    {
+      "epoch": 0.37215234483163695,
+      "eval_f1": 0.5713,
+      "eval_jaccard": 0.4162,
+      "eval_loss": 0.08199464529752731,
+      "eval_num_drugs": 15.69,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7376,
+      "eval_recall": 0.4837,
+      "eval_runtime": 195.7555,
+      "eval_samples_per_second": 77.137,
+      "eval_steps_per_second": 1.609,
+      "step": 4224
+    },
+    {
+      "epoch": 0.38342968861441384,
+      "grad_norm": 0.4857080280780792,
+      "learning_rate": 2.3967655901480325e-05,
+      "loss": 0.0819,
+      "step": 4352
+    },
+    {
+      "epoch": 0.38342968861441384,
+      "eval_f1": 0.5795,
+      "eval_jaccard": 0.4247,
+      "eval_loss": 0.08161693811416626,
+      "eval_num_drugs": 15.81,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7537,
+      "eval_recall": 0.4909,
+      "eval_runtime": 195.7017,
+      "eval_samples_per_second": 77.158,
+      "eval_steps_per_second": 1.61,
+      "step": 4352
+    },
+    {
+      "epoch": 0.39470703239719074,
+      "grad_norm": 0.39347517490386963,
+      "learning_rate": 2.36227795630767e-05,
+      "loss": 0.0811,
+      "step": 4480
+    },
+    {
+      "epoch": 0.39470703239719074,
+      "eval_f1": 0.5847,
+      "eval_jaccard": 0.4309,
+      "eval_loss": 0.08170764893293381,
+      "eval_num_drugs": 16.48,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.735,
+      "eval_recall": 0.5028,
+      "eval_runtime": 195.7188,
+      "eval_samples_per_second": 77.151,
+      "eval_steps_per_second": 1.609,
+      "step": 4480
+    },
+    {
+      "epoch": 0.40598437617996763,
+      "grad_norm": 0.35565024614334106,
+      "learning_rate": 2.329237476562281e-05,
+      "loss": 0.08,
+      "step": 4608
+    },
+    {
+      "epoch": 0.40598437617996763,
+      "eval_f1": 0.58,
+      "eval_jaccard": 0.4256,
+      "eval_loss": 0.08203385025262833,
+      "eval_num_drugs": 16.35,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.742,
+      "eval_recall": 0.496,
+      "eval_runtime": 195.752,
+      "eval_samples_per_second": 77.138,
+      "eval_steps_per_second": 1.609,
+      "step": 4608
+    },
+    {
+      "epoch": 0.41726171996274447,
+      "grad_norm": 0.5460488200187683,
+      "learning_rate": 2.2975456940431496e-05,
+      "loss": 0.0777,
+      "step": 4736
+    },
+    {
+      "epoch": 0.41726171996274447,
+      "eval_f1": 0.5931,
+      "eval_jaccard": 0.4399,
+      "eval_loss": 0.08272645622491837,
+      "eval_num_drugs": 18.04,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.707,
+      "eval_recall": 0.5312,
+      "eval_runtime": 195.8093,
+      "eval_samples_per_second": 77.116,
+      "eval_steps_per_second": 1.609,
+      "step": 4736
+    },
+    {
+      "epoch": 0.42853906374552136,
+      "grad_norm": 0.4078308343887329,
+      "learning_rate": 2.2671132815937868e-05,
+      "loss": 0.08,
+      "step": 4864
+    },
+    {
+      "epoch": 0.42853906374552136,
+      "eval_f1": 0.5897,
+      "eval_jaccard": 0.4358,
+      "eval_loss": 0.08148450404405594,
+      "eval_num_drugs": 17.21,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7187,
+      "eval_recall": 0.5193,
+      "eval_runtime": 195.7601,
+      "eval_samples_per_second": 77.135,
+      "eval_steps_per_second": 1.609,
+      "step": 4864
+    },
+    {
+      "epoch": 0.43981640752829826,
+      "grad_norm": 0.3553188443183899,
+      "learning_rate": 2.2378589813732277e-05,
+      "loss": 0.0796,
+      "step": 4992
+    },
+    {
+      "epoch": 0.43981640752829826,
+      "eval_f1": 0.5861,
+      "eval_jaccard": 0.4309,
+      "eval_loss": 0.08156691491603851,
+      "eval_num_drugs": 16.24,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7484,
+      "eval_recall": 0.5024,
+      "eval_runtime": 195.8126,
+      "eval_samples_per_second": 77.115,
+      "eval_steps_per_second": 1.609,
+      "step": 4992
+    },
+    {
+      "epoch": 0.4510937513110751,
+      "grad_norm": 0.5286290645599365,
+      "learning_rate": 2.209708691207961e-05,
+      "loss": 0.0761,
+      "step": 5120
+    },
+    {
+      "epoch": 0.4510937513110751,
+      "eval_f1": 0.5758,
+      "eval_jaccard": 0.4222,
+      "eval_loss": 0.08142111450433731,
+      "eval_num_drugs": 15.89,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7446,
+      "eval_recall": 0.4902,
+      "eval_runtime": 195.7899,
+      "eval_samples_per_second": 77.123,
+      "eval_steps_per_second": 1.609,
+      "step": 5120
+    },
+    {
+      "epoch": 0.462371095093852,
+      "grad_norm": 0.4667411148548126,
+      "learning_rate": 2.1825946742799322e-05,
+      "loss": 0.0793,
+      "step": 5248
+    },
+    {
+      "epoch": 0.462371095093852,
+      "eval_f1": 0.5643,
+      "eval_jaccard": 0.4115,
+      "eval_loss": 0.08155496418476105,
+      "eval_num_drugs": 15.04,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7545,
+      "eval_recall": 0.4697,
+      "eval_runtime": 195.8346,
+      "eval_samples_per_second": 77.106,
+      "eval_steps_per_second": 1.608,
+      "step": 5248
+    },
+    {
+      "epoch": 0.4736484388766289,
+      "grad_norm": 0.4620329737663269,
+      "learning_rate": 2.1564548729448567e-05,
+      "loss": 0.0781,
+      "step": 5376
+    },
+    {
+      "epoch": 0.4736484388766289,
+      "eval_f1": 0.5788,
+      "eval_jaccard": 0.4237,
+      "eval_loss": 0.0817071869969368,
+      "eval_num_drugs": 16.09,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7328,
+      "eval_recall": 0.4961,
+      "eval_runtime": 195.7767,
+      "eval_samples_per_second": 77.129,
+      "eval_steps_per_second": 1.609,
+      "step": 5376
+    },
+    {
+      "epoch": 0.4849257826594058,
+      "grad_norm": 0.49800699949264526,
+      "learning_rate": 2.1312323108452298e-05,
+      "loss": 0.0778,
+      "step": 5504
+    },
+    {
+      "epoch": 0.4849257826594058,
+      "eval_f1": 0.5722,
+      "eval_jaccard": 0.4186,
+      "eval_loss": 0.08115211129188538,
+      "eval_num_drugs": 15.22,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7511,
+      "eval_recall": 0.4801,
+      "eval_runtime": 195.7716,
+      "eval_samples_per_second": 77.131,
+      "eval_steps_per_second": 1.609,
+      "step": 5504
+    },
+    {
+      "epoch": 0.4962031264421826,
+      "grad_norm": 0.30248183012008667,
+      "learning_rate": 2.1068745701976316e-05,
+      "loss": 0.079,
+      "step": 5632
+    },
+    {
+      "epoch": 0.4962031264421826,
+      "eval_f1": 0.5992,
+      "eval_jaccard": 0.4457,
+      "eval_loss": 0.08108273893594742,
+      "eval_num_drugs": 18.39,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7071,
+      "eval_recall": 0.5419,
+      "eval_runtime": 195.7529,
+      "eval_samples_per_second": 77.138,
+      "eval_steps_per_second": 1.609,
+      "step": 5632
+    },
+    {
+      "epoch": 0.5074804702249596,
+      "grad_norm": 0.37452149391174316,
+      "learning_rate": 2.0833333333333333e-05,
+      "loss": 0.0794,
+      "step": 5760
+    },
+    {
+      "epoch": 0.5074804702249596,
+      "eval_f1": 0.5915,
+      "eval_jaccard": 0.4389,
+      "eval_loss": 0.08032320439815521,
+      "eval_num_drugs": 16.98,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7322,
+      "eval_recall": 0.5169,
+      "eval_runtime": 195.7304,
+      "eval_samples_per_second": 77.147,
+      "eval_steps_per_second": 1.609,
+      "step": 5760
+    },
+    {
+      "epoch": 0.5187578140077364,
+      "grad_norm": 0.36206522583961487,
+      "learning_rate": 2.0605639793618346e-05,
+      "loss": 0.0764,
+      "step": 5888
+    },
+    {
+      "epoch": 0.5187578140077364,
+      "eval_f1": 0.5795,
+      "eval_jaccard": 0.426,
+      "eval_loss": 0.08015798032283783,
+      "eval_num_drugs": 16.07,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7413,
+      "eval_recall": 0.4968,
+      "eval_runtime": 195.7838,
+      "eval_samples_per_second": 77.126,
+      "eval_steps_per_second": 1.609,
+      "step": 5888
+    },
+    {
+      "epoch": 0.5300351577905132,
+      "grad_norm": 0.3741084933280945,
+      "learning_rate": 2.0385252282920068e-05,
+      "loss": 0.0802,
+      "step": 6016
+    },
+    {
+      "epoch": 0.5300351577905132,
+      "eval_f1": 0.5757,
+      "eval_jaccard": 0.4234,
+      "eval_loss": 0.08052277565002441,
+      "eval_num_drugs": 16.09,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7429,
+      "eval_recall": 0.489,
+      "eval_runtime": 195.7474,
+      "eval_samples_per_second": 77.14,
+      "eval_steps_per_second": 1.609,
+      "step": 6016
+    },
+    {
+      "epoch": 0.5413125015732901,
+      "grad_norm": 0.5264722108840942,
+      "learning_rate": 2.0171788261496963e-05,
+      "loss": 0.0771,
+      "step": 6144
+    },
+    {
+      "epoch": 0.5413125015732901,
+      "eval_f1": 0.5815,
+      "eval_jaccard": 0.4278,
+      "eval_loss": 0.08064176887273788,
+      "eval_num_drugs": 16.36,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7298,
+      "eval_recall": 0.5018,
+      "eval_runtime": 195.6883,
+      "eval_samples_per_second": 77.164,
+      "eval_steps_per_second": 1.61,
+      "step": 6144
+    },
+    {
+      "epoch": 0.552589845356067,
+      "grad_norm": 0.3785838782787323,
+      "learning_rate": 1.9964892656248124e-05,
+      "loss": 0.0772,
+      "step": 6272
+    },
+    {
+      "epoch": 0.552589845356067,
+      "eval_f1": 0.6013,
+      "eval_jaccard": 0.4469,
+      "eval_loss": 0.08050908893346786,
+      "eval_num_drugs": 17.68,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7373,
+      "eval_recall": 0.5306,
+      "eval_runtime": 195.7035,
+      "eval_samples_per_second": 77.158,
+      "eval_steps_per_second": 1.61,
+      "step": 6272
+    },
+    {
+      "epoch": 0.5638671891388439,
+      "grad_norm": 0.5334848761558533,
+      "learning_rate": 1.976423537605237e-05,
+      "loss": 0.0771,
+      "step": 6400
+    },
+    {
+      "epoch": 0.5638671891388439,
+      "eval_f1": 0.6003,
+      "eval_jaccard": 0.4468,
+      "eval_loss": 0.0803057849407196,
+      "eval_num_drugs": 17.82,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7298,
+      "eval_recall": 0.5334,
+      "eval_runtime": 195.7554,
+      "eval_samples_per_second": 77.137,
+      "eval_steps_per_second": 1.609,
+      "step": 6400
+    },
+    {
+      "epoch": 0.5751445329216208,
+      "grad_norm": 0.41966477036476135,
+      "learning_rate": 1.9569509096410924e-05,
+      "loss": 0.0802,
+      "step": 6528
+    },
+    {
+      "epoch": 0.5751445329216208,
+      "eval_f1": 0.5905,
+      "eval_jaccard": 0.437,
+      "eval_loss": 0.07989891618490219,
+      "eval_num_drugs": 17.17,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7345,
+      "eval_recall": 0.5173,
+      "eval_runtime": 195.6488,
+      "eval_samples_per_second": 77.179,
+      "eval_steps_per_second": 1.61,
+      "step": 6528
+    },
+    {
+      "epoch": 0.5864218767043977,
+      "grad_norm": 0.3353288471698761,
+      "learning_rate": 1.938042727956382e-05,
+      "loss": 0.0769,
+      "step": 6656
+    },
+    {
+      "epoch": 0.5864218767043977,
+      "eval_f1": 0.5883,
+      "eval_jaccard": 0.435,
+      "eval_loss": 0.08099842071533203,
+      "eval_num_drugs": 17.08,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7275,
+      "eval_recall": 0.5168,
+      "eval_runtime": 195.7812,
+      "eval_samples_per_second": 77.127,
+      "eval_steps_per_second": 1.609,
+      "step": 6656
+    },
+    {
+      "epoch": 0.5976992204871745,
+      "grad_norm": 0.3863771855831146,
+      "learning_rate": 1.9196722401060975e-05,
+      "loss": 0.0733,
+      "step": 6784
+    },
+    {
+      "epoch": 0.5976992204871745,
+      "eval_f1": 0.5824,
+      "eval_jaccard": 0.4299,
+      "eval_loss": 0.0798565074801445,
+      "eval_num_drugs": 17.14,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7309,
+      "eval_recall": 0.508,
+      "eval_runtime": 195.6748,
+      "eval_samples_per_second": 77.169,
+      "eval_steps_per_second": 1.61,
+      "step": 6784
+    },
+    {
+      "epoch": 0.6089765642699514,
+      "grad_norm": 0.4759310185909271,
+      "learning_rate": 1.9018144357818264e-05,
+      "loss": 0.0761,
+      "step": 6912
+    },
+    {
+      "epoch": 0.6089765642699514,
+      "eval_f1": 0.5843,
+      "eval_jaccard": 0.429,
+      "eval_loss": 0.0810072124004364,
+      "eval_num_drugs": 16.99,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7282,
+      "eval_recall": 0.5099,
+      "eval_runtime": 195.7644,
+      "eval_samples_per_second": 77.134,
+      "eval_steps_per_second": 1.609,
+      "step": 6912
+    },
+    {
+      "epoch": 0.6202539080527283,
+      "grad_norm": 0.38791966438293457,
+      "learning_rate": 1.8844459036110228e-05,
+      "loss": 0.075,
+      "step": 7040
+    },
+    {
+      "epoch": 0.6202539080527283,
+      "eval_f1": 0.5871,
+      "eval_jaccard": 0.432,
+      "eval_loss": 0.08122321218252182,
+      "eval_num_drugs": 17.21,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7211,
+      "eval_recall": 0.5175,
+      "eval_runtime": 195.7441,
+      "eval_samples_per_second": 77.142,
+      "eval_steps_per_second": 1.609,
+      "step": 7040
+    },
+    {
+      "epoch": 0.6315312518355052,
+      "grad_norm": 0.3954806923866272,
+      "learning_rate": 1.8675447020849898e-05,
+      "loss": 0.0791,
+      "step": 7168
+    },
+    {
+      "epoch": 0.6315312518355052,
+      "eval_f1": 0.5851,
+      "eval_jaccard": 0.43,
+      "eval_loss": 0.08063361793756485,
+      "eval_num_drugs": 16.62,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7364,
+      "eval_recall": 0.5086,
+      "eval_runtime": 195.715,
+      "eval_samples_per_second": 77.153,
+      "eval_steps_per_second": 1.609,
+      "step": 7168
+    },
+    {
+      "epoch": 0.6428085956182821,
+      "grad_norm": 0.3953387141227722,
+      "learning_rate": 1.8510902429971635e-05,
+      "loss": 0.0764,
+      "step": 7296
+    },
+    {
+      "epoch": 0.6428085956182821,
+      "eval_f1": 0.5976,
+      "eval_jaccard": 0.4439,
+      "eval_loss": 0.07970798760652542,
+      "eval_num_drugs": 18.1,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.725,
+      "eval_recall": 0.5305,
+      "eval_runtime": 195.7387,
+      "eval_samples_per_second": 77.144,
+      "eval_steps_per_second": 1.609,
+      "step": 7296
+    },
+    {
+      "epoch": 0.654085939401059,
+      "grad_norm": 0.3327171802520752,
+      "learning_rate": 1.8350631859834483e-05,
+      "loss": 0.0766,
+      "step": 7424
+    },
+    {
+      "epoch": 0.654085939401059,
+      "eval_f1": 0.5858,
+      "eval_jaccard": 0.432,
+      "eval_loss": 0.07969953864812851,
+      "eval_num_drugs": 16.76,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7351,
+      "eval_recall": 0.51,
+      "eval_runtime": 195.7287,
+      "eval_samples_per_second": 77.148,
+      "eval_steps_per_second": 1.609,
+      "step": 7424
+    },
+    {
+      "epoch": 0.6653632831838358,
+      "grad_norm": 0.4677251875400543,
+      "learning_rate": 1.8194453429361938e-05,
+      "loss": 0.0754,
+      "step": 7552
+    },
+    {
+      "epoch": 0.6653632831838358,
+      "eval_f1": 0.5712,
+      "eval_jaccard": 0.4195,
+      "eval_loss": 0.07947417348623276,
+      "eval_num_drugs": 15.5,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7558,
+      "eval_recall": 0.4822,
+      "eval_runtime": 195.6955,
+      "eval_samples_per_second": 77.161,
+      "eval_steps_per_second": 1.61,
+      "step": 7552
+    },
+    {
+      "epoch": 0.6766406269666126,
+      "grad_norm": 0.37151941657066345,
+      "learning_rate": 1.804219591217581e-05,
+      "loss": 0.0749,
+      "step": 7680
+    },
+    {
+      "epoch": 0.6766406269666126,
+      "eval_f1": 0.592,
+      "eval_jaccard": 0.4391,
+      "eval_loss": 0.08006121218204498,
+      "eval_num_drugs": 17.16,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.732,
+      "eval_recall": 0.5205,
+      "eval_runtime": 195.7464,
+      "eval_samples_per_second": 77.141,
+      "eval_steps_per_second": 1.609,
+      "step": 7680
+    },
+    {
+      "epoch": 0.6879179707493895,
+      "grad_norm": 0.3027561902999878,
+      "learning_rate": 1.789369794730838e-05,
+      "loss": 0.0776,
+      "step": 7808
+    },
+    {
+      "epoch": 0.6879179707493895,
+      "eval_f1": 0.5895,
+      "eval_jaccard": 0.4354,
+      "eval_loss": 0.07969165593385696,
+      "eval_num_drugs": 16.87,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7403,
+      "eval_recall": 0.5135,
+      "eval_runtime": 195.7582,
+      "eval_samples_per_second": 77.136,
+      "eval_steps_per_second": 1.609,
+      "step": 7808
+    },
+    {
+      "epoch": 0.6991953145321664,
+      "grad_norm": 0.39215460419654846,
+      "learning_rate": 1.7748807320220776e-05,
+      "loss": 0.0758,
+      "step": 7936
+    },
+    {
+      "epoch": 0.6991953145321664,
+      "eval_f1": 0.5807,
+      "eval_jaccard": 0.4275,
+      "eval_loss": 0.0798029750585556,
+      "eval_num_drugs": 16.66,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7346,
+      "eval_recall": 0.5039,
+      "eval_runtime": 195.7034,
+      "eval_samples_per_second": 77.158,
+      "eval_steps_per_second": 1.61,
+      "step": 7936
+    },
+    {
+      "epoch": 0.7104726583149433,
+      "grad_norm": 0.5017596483230591,
+      "learning_rate": 1.7607380306844094e-05,
+      "loss": 0.0754,
+      "step": 8064
+    },
+    {
+      "epoch": 0.7104726583149433,
+      "eval_f1": 0.5691,
+      "eval_jaccard": 0.4161,
+      "eval_loss": 0.0809771940112114,
+      "eval_num_drugs": 15.02,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7626,
+      "eval_recall": 0.4748,
+      "eval_runtime": 195.6836,
+      "eval_samples_per_second": 77.165,
+      "eval_steps_per_second": 1.61,
+      "step": 8064
+    },
+    {
+      "epoch": 0.7217500020977202,
+      "grad_norm": 0.4508849084377289,
+      "learning_rate": 1.746928107421711e-05,
+      "loss": 0.076,
+      "step": 8192
+    },
+    {
+      "epoch": 0.7217500020977202,
+      "eval_f1": 0.6147,
+      "eval_jaccard": 0.4622,
+      "eval_loss": 0.07949170470237732,
+      "eval_num_drugs": 19.8,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7027,
+      "eval_recall": 0.5719,
+      "eval_runtime": 195.6298,
+      "eval_samples_per_second": 77.187,
+      "eval_steps_per_second": 1.61,
+      "step": 8192
+    },
+    {
+      "epoch": 0.7330273458804971,
+      "grad_norm": 0.4924061596393585,
+      "learning_rate": 1.7334381132038412e-05,
+      "loss": 0.076,
+      "step": 8320
+    },
+    {
+      "epoch": 0.7330273458804971,
+      "eval_f1": 0.5685,
+      "eval_jaccard": 0.4151,
+      "eval_loss": 0.08067003637552261,
+      "eval_num_drugs": 15.11,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.757,
+      "eval_recall": 0.4747,
+      "eval_runtime": 195.6644,
+      "eval_samples_per_second": 77.173,
+      "eval_steps_per_second": 1.61,
+      "step": 8320
+    },
+    {
+      "epoch": 0.7443046896632739,
+      "grad_norm": 0.33014485239982605,
+      "learning_rate": 1.7202558830099385e-05,
+      "loss": 0.0762,
+      "step": 8448
+    },
+    {
+      "epoch": 0.7443046896632739,
+      "eval_f1": 0.6012,
+      "eval_jaccard": 0.4481,
+      "eval_loss": 0.07921886444091797,
+      "eval_num_drugs": 17.79,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7356,
+      "eval_recall": 0.5309,
+      "eval_runtime": 195.6071,
+      "eval_samples_per_second": 77.196,
+      "eval_steps_per_second": 1.61,
+      "step": 8448
+    },
+    {
+      "epoch": 0.7555820334460508,
+      "grad_norm": 0.3135475814342499,
+      "learning_rate": 1.7073698897129783e-05,
+      "loss": 0.0747,
+      "step": 8576
+    },
+    {
+      "epoch": 0.7555820334460508,
+      "eval_f1": 0.6014,
+      "eval_jaccard": 0.4481,
+      "eval_loss": 0.07929855585098267,
+      "eval_num_drugs": 17.05,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7456,
+      "eval_recall": 0.5259,
+      "eval_runtime": 195.6688,
+      "eval_samples_per_second": 77.171,
+      "eval_steps_per_second": 1.61,
+      "step": 8576
+    },
+    {
+      "epoch": 0.7668593772288277,
+      "grad_norm": 0.39268001914024353,
+      "learning_rate": 1.6947692017082512e-05,
+      "loss": 0.0771,
+      "step": 8704
+    },
+    {
+      "epoch": 0.7668593772288277,
+      "eval_f1": 0.5991,
+      "eval_jaccard": 0.4457,
+      "eval_loss": 0.07905127853155136,
+      "eval_num_drugs": 16.72,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7487,
+      "eval_recall": 0.52,
+      "eval_runtime": 195.6858,
+      "eval_samples_per_second": 77.165,
+      "eval_steps_per_second": 1.61,
+      "step": 8704
+    },
+    {
+      "epoch": 0.7781367210116046,
+      "grad_norm": 0.36871498823165894,
+      "learning_rate": 1.682443443931767e-05,
+      "loss": 0.0775,
+      "step": 8832
+    },
+    {
+      "epoch": 0.7781367210116046,
+      "eval_f1": 0.6053,
+      "eval_jaccard": 0.4506,
+      "eval_loss": 0.07942435890436172,
+      "eval_num_drugs": 18.07,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7266,
+      "eval_recall": 0.5417,
+      "eval_runtime": 195.6902,
+      "eval_samples_per_second": 77.163,
+      "eval_steps_per_second": 1.61,
+      "step": 8832
+    },
+    {
+      "epoch": 0.7894140647943815,
+      "grad_norm": 0.32927706837654114,
+      "learning_rate": 1.6703827619526526e-05,
+      "loss": 0.0757,
+      "step": 8960
+    },
+    {
+      "epoch": 0.7894140647943815,
+      "eval_f1": 0.6014,
+      "eval_jaccard": 0.4477,
+      "eval_loss": 0.07913407683372498,
+      "eval_num_drugs": 17.73,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7289,
+      "eval_recall": 0.5319,
+      "eval_runtime": 195.6382,
+      "eval_samples_per_second": 77.183,
+      "eval_steps_per_second": 1.61,
+      "step": 8960
+    },
+    {
+      "epoch": 0.8006914085771584,
+      "grad_norm": 0.35670703649520874,
+      "learning_rate": 1.65857778885711e-05,
+      "loss": 0.0791,
+      "step": 9088
+    },
+    {
+      "epoch": 0.8006914085771584,
+      "eval_f1": 0.6013,
+      "eval_jaccard": 0.4474,
+      "eval_loss": 0.07878393679857254,
+      "eval_num_drugs": 16.97,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7501,
+      "eval_recall": 0.5219,
+      "eval_runtime": 195.6368,
+      "eval_samples_per_second": 77.184,
+      "eval_steps_per_second": 1.61,
+      "step": 9088
+    },
+    {
+      "epoch": 0.8119687523599353,
+      "grad_norm": 0.467021107673645,
+      "learning_rate": 1.647019614671031e-05,
+      "loss": 0.075,
+      "step": 9216
+    },
+    {
+      "epoch": 0.8119687523599353,
+      "eval_f1": 0.5871,
+      "eval_jaccard": 0.4341,
+      "eval_loss": 0.07932396233081818,
+      "eval_num_drugs": 16.34,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7538,
+      "eval_recall": 0.5027,
+      "eval_runtime": 195.563,
+      "eval_samples_per_second": 77.213,
+      "eval_steps_per_second": 1.611,
+      "step": 9216
+    },
+    {
+      "epoch": 0.823246096142712,
+      "grad_norm": 0.38525936007499695,
+      "learning_rate": 1.6356997580944175e-05,
+      "loss": 0.078,
+      "step": 9344
+    },
+    {
+      "epoch": 0.823246096142712,
+      "eval_f1": 0.5945,
+      "eval_jaccard": 0.4407,
+      "eval_loss": 0.07891988009214401,
+      "eval_num_drugs": 17.43,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7321,
+      "eval_recall": 0.5239,
+      "eval_runtime": 195.6748,
+      "eval_samples_per_second": 77.169,
+      "eval_steps_per_second": 1.61,
+      "step": 9344
+    },
+    {
+      "epoch": 0.8345234399254889,
+      "grad_norm": 0.3766573369503021,
+      "learning_rate": 1.6246101403438635e-05,
+      "loss": 0.0775,
+      "step": 9472
+    },
+    {
+      "epoch": 0.8345234399254889,
+      "eval_f1": 0.5861,
+      "eval_jaccard": 0.4337,
+      "eval_loss": 0.07892133295536041,
+      "eval_num_drugs": 16.75,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7404,
+      "eval_recall": 0.5067,
+      "eval_runtime": 195.583,
+      "eval_samples_per_second": 77.205,
+      "eval_steps_per_second": 1.611,
+      "step": 9472
+    },
+    {
+      "epoch": 0.8458007837082658,
+      "grad_norm": 0.4568697214126587,
+      "learning_rate": 1.613743060919757e-05,
+      "loss": 0.0758,
+      "step": 9600
+    },
+    {
+      "epoch": 0.8458007837082658,
+      "eval_f1": 0.5978,
+      "eval_jaccard": 0.4443,
+      "eval_loss": 0.0791362076997757,
+      "eval_num_drugs": 17.33,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7394,
+      "eval_recall": 0.5233,
+      "eval_runtime": 195.6035,
+      "eval_samples_per_second": 77.197,
+      "eval_steps_per_second": 1.61,
+      "step": 9600
+    },
+    {
+      "epoch": 0.8570781274910427,
+      "grad_norm": 0.47970256209373474,
+      "learning_rate": 1.6030911751330536e-05,
+      "loss": 0.0766,
+      "step": 9728
+    },
+    {
+      "epoch": 0.8570781274910427,
+      "eval_f1": 0.5712,
+      "eval_jaccard": 0.4201,
+      "eval_loss": 0.07883810997009277,
+      "eval_num_drugs": 15.38,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7548,
+      "eval_recall": 0.4783,
+      "eval_runtime": 195.622,
+      "eval_samples_per_second": 77.19,
+      "eval_steps_per_second": 1.61,
+      "step": 9728
+    },
+    {
+      "epoch": 0.8683554712738196,
+      "grad_norm": 0.4435725510120392,
+      "learning_rate": 1.5926474732425798e-05,
+      "loss": 0.0751,
+      "step": 9856
+    },
+    {
+      "epoch": 0.8683554712738196,
+      "eval_f1": 0.5988,
+      "eval_jaccard": 0.4461,
+      "eval_loss": 0.07905417680740356,
+      "eval_num_drugs": 17.44,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7354,
+      "eval_recall": 0.5294,
+      "eval_runtime": 195.6283,
+      "eval_samples_per_second": 77.187,
+      "eval_steps_per_second": 1.61,
+      "step": 9856
+    },
+    {
+      "epoch": 0.8796328150565965,
+      "grad_norm": 0.44593748450279236,
+      "learning_rate": 1.582405261068229e-05,
+      "loss": 0.0739,
+      "step": 9984
+    },
+    {
+      "epoch": 0.8796328150565965,
+      "eval_f1": 0.5861,
+      "eval_jaccard": 0.4368,
+      "eval_loss": 0.07844545692205429,
+      "eval_num_drugs": 16.53,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7405,
+      "eval_recall": 0.5069,
+      "eval_runtime": 195.5497,
+      "eval_samples_per_second": 77.218,
+      "eval_steps_per_second": 1.611,
+      "step": 9984
+    },
+    {
+      "epoch": 0.8909101588393734,
+      "grad_norm": 0.4424314796924591,
+      "learning_rate": 1.572358141958211e-05,
+      "loss": 0.0767,
+      "step": 10112
+    },
+    {
+      "epoch": 0.8909101588393734,
+      "eval_f1": 0.5993,
+      "eval_jaccard": 0.4471,
+      "eval_loss": 0.07896988093852997,
+      "eval_num_drugs": 17.54,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7243,
+      "eval_recall": 0.5324,
+      "eval_runtime": 195.5885,
+      "eval_samples_per_second": 77.203,
+      "eval_steps_per_second": 1.611,
+      "step": 10112
+    },
+    {
+      "epoch": 0.9021875026221502,
+      "grad_norm": 0.38866597414016724,
+      "learning_rate": 1.5625e-05,
+      "loss": 0.0763,
+      "step": 10240
+    },
+    {
+      "epoch": 0.9021875026221502,
+      "eval_f1": 0.6029,
+      "eval_jaccard": 0.4488,
+      "eval_loss": 0.07891592383384705,
+      "eval_num_drugs": 17.38,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7385,
+      "eval_recall": 0.5336,
+      "eval_runtime": 195.5746,
+      "eval_samples_per_second": 77.208,
+      "eval_steps_per_second": 1.611,
+      "step": 10240
+    },
+    {
+      "epoch": 0.9134648464049271,
+      "grad_norm": 0.31933003664016724,
+      "learning_rate": 1.5528249843748542e-05,
+      "loss": 0.0739,
+      "step": 10368
+    },
+    {
+      "epoch": 0.9134648464049271,
+      "eval_f1": 0.5874,
+      "eval_jaccard": 0.4346,
+      "eval_loss": 0.07923928648233414,
+      "eval_num_drugs": 16.42,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7319,
+      "eval_recall": 0.5088,
+      "eval_runtime": 195.5846,
+      "eval_samples_per_second": 77.204,
+      "eval_steps_per_second": 1.611,
+      "step": 10368
+    },
+    {
+      "epoch": 0.924742190187704,
+      "grad_norm": 0.5055702328681946,
+      "learning_rate": 1.543327494764984e-05,
+      "loss": 0.0763,
+      "step": 10496
+    },
+    {
+      "epoch": 0.924742190187704,
+      "eval_f1": 0.6055,
+      "eval_jaccard": 0.4534,
+      "eval_loss": 0.07852223515510559,
+      "eval_num_drugs": 17.92,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7339,
+      "eval_recall": 0.5405,
+      "eval_runtime": 195.6205,
+      "eval_samples_per_second": 77.19,
+      "eval_steps_per_second": 1.61,
+      "step": 10496
+    },
+    {
+      "epoch": 0.9360195339704809,
+      "grad_norm": 0.41461578011512756,
+      "learning_rate": 1.5340021677306748e-05,
+      "loss": 0.0772,
+      "step": 10624
+    },
+    {
+      "epoch": 0.9360195339704809,
+      "eval_f1": 0.5872,
+      "eval_jaccard": 0.4358,
+      "eval_loss": 0.07860737293958664,
+      "eval_num_drugs": 16.33,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7361,
+      "eval_recall": 0.5047,
+      "eval_runtime": 195.5859,
+      "eval_samples_per_second": 77.204,
+      "eval_steps_per_second": 1.611,
+      "step": 10624
+    },
+    {
+      "epoch": 0.9472968777532578,
+      "grad_norm": 0.3936142325401306,
+      "learning_rate": 1.524843863982083e-05,
+      "loss": 0.0751,
+      "step": 10752
+    },
+    {
+      "epoch": 0.9472968777532578,
+      "eval_f1": 0.5702,
+      "eval_jaccard": 0.4192,
+      "eval_loss": 0.07872913777828217,
+      "eval_num_drugs": 15.19,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.747,
+      "eval_recall": 0.4772,
+      "eval_runtime": 195.5586,
+      "eval_samples_per_second": 77.215,
+      "eval_steps_per_second": 1.611,
+      "step": 10752
+    },
+    {
+      "epoch": 0.9585742215360347,
+      "grad_norm": 0.5581151843070984,
+      "learning_rate": 1.515847656477081e-05,
+      "loss": 0.0732,
+      "step": 10880
+    },
+    {
+      "epoch": 0.9585742215360347,
+      "eval_f1": 0.6048,
+      "eval_jaccard": 0.452,
+      "eval_loss": 0.07890180498361588,
+      "eval_num_drugs": 17.9,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7269,
+      "eval_recall": 0.5396,
+      "eval_runtime": 195.611,
+      "eval_samples_per_second": 77.194,
+      "eval_steps_per_second": 1.61,
+      "step": 10880
+    },
+    {
+      "epoch": 0.9698515653188116,
+      "grad_norm": 0.45057618618011475,
+      "learning_rate": 1.507008819282538e-05,
+      "loss": 0.0737,
+      "step": 11008
+    },
+    {
+      "epoch": 0.9698515653188116,
+      "eval_f1": 0.5884,
+      "eval_jaccard": 0.4361,
+      "eval_loss": 0.0796256959438324,
+      "eval_num_drugs": 16.49,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7428,
+      "eval_recall": 0.5092,
+      "eval_runtime": 195.6093,
+      "eval_samples_per_second": 77.195,
+      "eval_steps_per_second": 1.61,
+      "step": 11008
+    },
+    {
+      "epoch": 0.9811289091015883,
+      "grad_norm": 0.41492125391960144,
+      "learning_rate": 1.4983228171418256e-05,
+      "loss": 0.0746,
+      "step": 11136
+    },
+    {
+      "epoch": 0.9811289091015883,
+      "eval_f1": 0.5962,
+      "eval_jaccard": 0.4437,
+      "eval_loss": 0.07860623300075531,
+      "eval_num_drugs": 17.6,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7246,
+      "eval_recall": 0.5282,
+      "eval_runtime": 195.559,
+      "eval_samples_per_second": 77.215,
+      "eval_steps_per_second": 1.611,
+      "step": 11136
+    },
+    {
+      "epoch": 0.9924062528843652,
+      "grad_norm": 0.4617977440357208,
+      "learning_rate": 1.489785295696238e-05,
+      "loss": 0.0766,
+      "step": 11264
+    },
+    {
+      "epoch": 0.9924062528843652,
+      "eval_f1": 0.622,
+      "eval_jaccard": 0.4689,
+      "eval_loss": 0.0785478949546814,
+      "eval_num_drugs": 18.99,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.7236,
+      "eval_recall": 0.5703,
+      "eval_runtime": 195.5595,
+      "eval_samples_per_second": 77.214,
+      "eval_steps_per_second": 1.611,
+      "step": 11264
+    },
+    {
+      "epoch": 1.0036835966671422,
+      "grad_norm": 0.395907998085022,
+      "learning_rate": 1.4813920723124289e-05,
+      "loss": 0.0742,
+      "step": 11392
+    },
+    {
+      "epoch": 1.0036835966671422,
+      "eval_f1": 0.6299,
+      "eval_jaccard": 0.4764,
+      "eval_loss": 0.07868505269289017,
+      "eval_num_drugs": 20.14,
+      "eval_num_drugs_gt": 24.12,
+      "eval_precision": 0.711,
+      "eval_recall": 0.5893,
+      "eval_runtime": 195.5113,
+      "eval_samples_per_second": 77.233,
+      "eval_steps_per_second": 1.611,
+      "step": 11392
+    }
+  ],
+  "logging_steps": 128,
+  "max_steps": 227000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 128,
+  "stateful_callbacks": {
+    "MyEarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 25,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.1789895853022904e+19,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

pi_cls/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1468745b4bc3bf5209701c04eeed508615562f58d3ba966dae36ad0a56f142a3
+size 4795

pi_list/README.md

@@ -0,0 +1,202 @@
+---
+base_model: ./Models/sft_rethink
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.1

pi_list/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "./Models/sft_rethink",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "down_proj",
+    "up_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

pi_list/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6313c8f0c6669688e04e26ad341dfffc65060a3306a461447c30d4d21b4f3f2e
+size 335604696

pi_list/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b76883cc8d4447ff73bf0dfae9feccf4bf4a32dae216822d08d3e03a8339cef
+size 671466706

pi_list/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef95a06678320fc110d5013e7fc733c2b62a425298dcd4e860d113fd7105ed14
+size 14244

pi_list/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3309cbdbec746f1916fd30e66a9c619384dd502c8a6a4e9b9e6aeb5cc725fe15
+size 1064

pi_list/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b21bc6853b9795dfe54a2e8bf066103b04653958599d3b9f8d3b0d0922604d39
+size 20613671

pi_list/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17efbaab563c2ae438281f901c8076f1dc455cbc1aa28dadbbdad34dbcb91a8a
+size 5816