Duplicate from MolGen/llama_ZINC_1B-raw_atomwise_SAFE_a0df739a

Co-authored-by: Kamran Chitsaz <kmchiti@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,105 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
+tmp-spec-checkpoint-5000/generated_smiles_1M.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-10000/generated_smiles_1M.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-15000/generated_smiles_1M.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-20000/generated_smiles_1M.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-25000/generated_smiles_1M.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-30000/generated_smiles_1M.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-35000/generated_smiles_1M.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-40000/generated_smiles_1M.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-45000/generated_smiles_1M.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-50000/generated_smiles_1M.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-55000/generated_smiles_1M.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-60000/generated_smiles_1M.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-65000/generated_smiles_1M.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-70000/generated_smiles_1M.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-75000/generated_smiles_1M.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-75000/result_unique@1k_unique@10k_IntDiv_IntDiv2_filters_FCD_SNN_Scaf_Frag_logP_SA_QED_weight_NP_NumRings_Bertz_TPSA_AliphaticRings_AromaticRings_RotatableBonds_175k_100k.json filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-75000/result_unique@1k_unique@10k_IntDiv_IntDiv2_filters_FCD_SNN_Scaf_Frag_logP_SA_QED_weight_NP_NumRings_Bertz_TPSA_AliphaticRings_AromaticRings_RotatableBonds_500k_100k.json filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-75000/result_unique@1k_unique@10k_IntDiv_IntDiv2_filters_FCD_SNN_Scaf_Frag_logP_SA_QED_weight_NP_NumRings_Bertz_TPSA_AliphaticRings_AromaticRings_RotatableBonds_1M_100k.json filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-75000/result_unique@1k_unique@10k_IntDiv_IntDiv2_filters_FCD_SNN_Scaf_Frag_logP_SA_QED_weight_NP_NumRings_Bertz_TPSA_AliphaticRings_AromaticRings_RotatableBonds_3M_100k.json filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-5000/generated_smiles_1M_0.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-10000/generated_smiles_1M_0.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-15000/generated_smiles_1M_0.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-20000/generated_smiles_1M_0.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-25000/generated_smiles_1M_0.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-30000/generated_smiles_1M_0.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-35000/generated_smiles_1M_0.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-40000/generated_smiles_1M_0.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-45000/generated_smiles_1M_0.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-50000/generated_smiles_1M_0.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-55000/generated_smiles_1M_0.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-60000/generated_smiles_1M_0.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-65000/generated_smiles_1M_0.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-70000/generated_smiles_1M_0.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-75000/generated_smiles_1M_0.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-5000/generated_smiles_1M_1.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-10000/generated_smiles_1M_1.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-15000/generated_smiles_1M_1.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-20000/generated_smiles_1M_1.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-25000/generated_smiles_1M_1.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-30000/generated_smiles_1M_1.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-35000/generated_smiles_1M_1.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-40000/generated_smiles_1M_1.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-45000/generated_smiles_1M_1.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-50000/generated_smiles_1M_1.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-55000/generated_smiles_1M_1.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-60000/generated_smiles_1M_1.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-65000/generated_smiles_1M_1.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-70000/generated_smiles_1M_1.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-75000/generated_smiles_1M_1.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-5000/generated_smiles_1M_2.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-10000/generated_smiles_1M_2.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-15000/generated_smiles_1M_2.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-20000/generated_smiles_1M_2.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-25000/generated_smiles_1M_2.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-30000/generated_smiles_1M_2.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-35000/generated_smiles_1M_2.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-40000/generated_smiles_1M_2.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-45000/generated_smiles_1M_2.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-50000/generated_smiles_1M_2.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-55000/generated_smiles_1M_2.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-60000/generated_smiles_1M_2.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-65000/generated_smiles_1M_2.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-70000/generated_smiles_1M_2.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-75000/generated_smiles_1M_2.csv filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-75000/result_unique@1k_unique@10k_IntDiv_IntDiv2_filters_FCD_SNN_Scaf_Frag_logP_SA_QED_weight_NP_NumRings_Bertz_TPSA_AliphaticRings_AromaticRings_RotatableBonds_175k_100k_0.json filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-75000/result_unique@1k_unique@10k_IntDiv_IntDiv2_filters_FCD_SNN_Scaf_Frag_logP_SA_QED_weight_NP_NumRings_Bertz_TPSA_AliphaticRings_AromaticRings_RotatableBonds_1M_100k_0.json filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-75000/result_unique@1k_unique@10k_IntDiv_IntDiv2_filters_FCD_SNN_Scaf_Frag_logP_SA_QED_weight_NP_NumRings_Bertz_TPSA_AliphaticRings_AromaticRings_RotatableBonds_175k_100k_1.json filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-75000/result_unique@1k_unique@10k_IntDiv_IntDiv2_filters_FCD_SNN_Scaf_Frag_logP_SA_QED_weight_NP_NumRings_Bertz_TPSA_AliphaticRings_AromaticRings_RotatableBonds_175k_100k_2.json filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-75000/result_unique@1k_unique@10k_IntDiv_IntDiv2_filters_FCD_SNN_Scaf_Frag_logP_SA_QED_weight_NP_NumRings_Bertz_TPSA_AliphaticRings_AromaticRings_RotatableBonds_1M_100k_1.json filter=lfs diff=lfs merge=lfs -text
+tmp-spec-checkpoint-75000/result_unique@1k_unique@10k_IntDiv_IntDiv2_filters_FCD_SNN_Scaf_Frag_logP_SA_QED_weight_NP_NumRings_Bertz_TPSA_AliphaticRings_AromaticRings_RotatableBonds_1M_100k_2.json filter=lfs diff=lfs merge=lfs -text

tmp-spec-checkpoint-10000/config.json

@@ -0,0 +1,30 @@
+{
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 3,
+  "fused_bias_fc": false,
+  "fused_dropout_add_ln": false,
+  "fused_mlp": false,
+  "hidden_act": "silu",
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "max_position_embeddings": 2048,
+  "max_seq_length": 128,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "residual_in_fp32": true,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.43.4",
+  "use_cache": true,
+  "use_flash_attn": true,
+  "vocab_size": 74
+}

tmp-spec-checkpoint-10000/generated_smiles_1M.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e934f218777b44d9fd97b365133f58d2d3619bf0ce88ecafe19371fa7208c097
+size 47094848

tmp-spec-checkpoint-10000/generated_smiles_1M_0.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:731ed4e88cfa6047580d7ad90edbecbce18285785693b55b5c63e4bc46da3a56
+size 47089287

tmp-spec-checkpoint-10000/generated_smiles_1M_1.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d69d253f5cdb360207fc8540d4b0dec98dcdc1fafcf7da3a1b007eb1bd95557a
+size 47084395

tmp-spec-checkpoint-10000/generated_smiles_1M_2.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdb2bae6e87ae6ee5cf4ea15ff03f67cfb0fd67b129cd9f4865a8e9f121d77bd
+size 47057693

tmp-spec-checkpoint-10000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b23fb00abc522e12ddd7ab4a3a81859e4b4208927bea9b1f002540a9e97ec865
+size 63115855

tmp-spec-checkpoint-10000/result_FCD_SNN_Frag_Scaf.json

@@ -0,0 +1,19 @@
+{
+    "validity": 1.0,
+    "FCD": {
+        "FCD": 1.014371570941769,
+        "FCD/test": 1.2840516297559006
+    },
+    "SNN": {
+        "SNN": 0.5403234519492657,
+        "SNN/test": 0.5177344154944686
+    },
+    "Frag": {
+        "Frag": 0.9954628107892446,
+        "Frag/test": 0.9932640709949498
+    },
+    "Scaf": {
+        "Scaf": 0.6604473255551877,
+        "Scaf/test": 0.013251719284644577
+    }
+}

tmp-spec-checkpoint-10000/result_SA_wasserstein.json

@@ -0,0 +1,7 @@
+{
+    "validity": 1.0,
+    "SA_wasserstein": {
+        "SA_wasserstein": 0.03531485684710113,
+        "SA_wasserstein/test": 0.0633226642649299
+    }
+}

tmp-spec-checkpoint-10000/result_novelty_total.json

@@ -0,0 +1,3 @@
+{
+    "novelty_total": 0.998974949008943
+}

tmp-spec-checkpoint-10000/result_unique@1k_unique@10k_IntDiv_IntDiv2_logP_wasserstein_QED_wasserstein_weight_wasserstein_NP_wasserstein.json

@@ -0,0 +1,23 @@
+{
+    "validity": 1.0,
+    "unique@1k": 1.0,
+    "unique@10k": 1.0,
+    "IntDiv": 0.853450210055646,
+    "IntDiv2": 0.8493021878803156,
+    "logP_wasserstein": {
+        "logP_wasserstein": 0.13093312964571951,
+        "logP_wasserstein/test": 0.10780172952943484
+    },
+    "QED_wasserstein": {
+        "QED_wasserstein": 0.005999451053057837,
+        "QED_wasserstein/test": 0.008760303916285503
+    },
+    "weight_wasserstein": {
+        "weight_wasserstein": 3.6379066160855205,
+        "weight_wasserstein/test": 5.916868278108168
+    },
+    "NP_wasserstein": {
+        "NP_wasserstein": 0.049366192344106656,
+        "NP_wasserstein/test": 0.07572631593283732
+    }
+}

tmp-spec-checkpoint-10000/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tmp-spec-checkpoint-10000/tokenizer.json

@@ -0,0 +1,193 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 0,
+      "content": "<unk>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 1,
+      "content": "<pad>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 2,
+      "content": "<bos>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 3,
+      "content": "<eos>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "Split",
+    "pattern": {
+      "Regex": "(\\[[^\\]]+]|Br?|Cl?|N|O|S|P|F|I|b|c|n|o|s|p|\\(|\\)|\\.|=|#|-|\\+|\\\\\\\\|\\/|:|~|@|\\?|>>?|\\*|\\$|\\%[0-9]{2}|[0-9])"
+    },
+    "behavior": "Isolated",
+    "invert": false
+  },
+  "post_processor": {
+    "type": "TemplateProcessing",
+    "single": [
+      {
+        "SpecialToken": {
+          "id": "<bos>",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "<eos>",
+          "type_id": 0
+        }
+      }
+    ],
+    "pair": [
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "B",
+          "type_id": 1
+        }
+      }
+    ],
+    "special_tokens": {
+      "<bos>": {
+        "id": "<bos>",
+        "ids": [
+          2
+        ],
+        "tokens": [
+          "<bos>"
+        ]
+      },
+      "<eos>": {
+        "id": "<eos>",
+        "ids": [
+          3
+        ],
+        "tokens": [
+          "<eos>"
+        ]
+      }
+    }
+  },
+  "decoder": {
+    "type": "BPEDecoder",
+    "suffix": "</w>"
+  },
+  "model": {
+    "type": "WordLevel",
+    "vocab": {
+      "<unk>": 0,
+      "<pad>": 1,
+      "<bos>": 2,
+      "<eos>": 3,
+      "C": 4,
+      ".": 5,
+      "1": 6,
+      "c": 7,
+      "O": 8,
+      "=": 9,
+      "(": 10,
+      ")": 11,
+      "N": 12,
+      "5": 13,
+      "6": 14,
+      "4": 15,
+      "7": 16,
+      "8": 17,
+      "3": 18,
+      "2": 19,
+      "n": 20,
+      "9": 21,
+      "F": 22,
+      "%10": 23,
+      "%11": 24,
+      "S": 25,
+      "s": 26,
+      "Cl": 27,
+      "[nH]": 28,
+      "o": 29,
+      "#": 30,
+      "Br": 31,
+      "%12": 32,
+      "[N+]": 33,
+      "[O-]": 34,
+      "%13": 35,
+      "I": 36,
+      "[N-]": 37,
+      "P": 38,
+      "[n+]": 39,
+      "%14": 40,
+      "-": 41,
+      "[Si]": 42,
+      "[S+]": 43,
+      "%15": 44,
+      "B": 45,
+      "%16": 46,
+      "[NH+]": 47,
+      "[B-]": 48,
+      "%17": 49,
+      "[NH2+]": 50,
+      "[O]": 51,
+      "[NH3+]": 52,
+      "[PH]": 53,
+      "[n-]": 54,
+      "%18": 55,
+      "[nH+]": 56,
+      "[Sn]": 57,
+      "[s+]": 58,
+      "%19": 59,
+      "[Se]": 60,
+      "[Cl-]": 61,
+      "%20": 62,
+      "[N]": 63,
+      "[C-]": 64,
+      "[C]": 65,
+      "[SiH]": 66,
+      "%21": 67,
+      "[O+]": 68,
+      "[SH]": 69,
+      "[NH]": 70,
+      "[P+]": 71,
+      "[c-]": 72,
+      "[o+]": 73
+    },
+    "unk_token": "<unk>"
+  }
+}

tmp-spec-checkpoint-10000/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<eos>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}

tmp-spec-checkpoint-10000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:634148355b42ee0de306ebb5fc5e0474a7658df467b360eba0c60e507cf38172
+size 6584

tmp-spec-checkpoint-15000/config.json

@@ -0,0 +1,30 @@
+{
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 3,
+  "fused_bias_fc": false,
+  "fused_dropout_add_ln": false,
+  "fused_mlp": false,
+  "hidden_act": "silu",
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "max_position_embeddings": 2048,
+  "max_seq_length": 128,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "residual_in_fp32": true,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.43.4",
+  "use_cache": true,
+  "use_flash_attn": true,
+  "vocab_size": 74
+}

tmp-spec-checkpoint-15000/generated_smiles_1M.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2232d0bab162da91fc2180f6d75f8aeb8619ffca8e72bdac100b3ffa65d83295
+size 47298381

tmp-spec-checkpoint-15000/generated_smiles_1M_0.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe29ffbc52aa4bf86ea6a418fb1a04927771efccf191d5fa6500d38161f1707d
+size 47315469

tmp-spec-checkpoint-15000/generated_smiles_1M_1.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f52211d12daca2fe0e55661f719a078aab322850a36cf387b38ce69ac4621908
+size 47330945

tmp-spec-checkpoint-15000/generated_smiles_1M_2.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3af8c0201ed464d343c7dab853b3e7e525d0111e88a7e2cf21a6968e64681851
+size 47298298

tmp-spec-checkpoint-15000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b1d86a6466f9eaa4f20e70229d2fed4e81e52000a8a334a64b55b1b05ef70a4
+size 63115855

tmp-spec-checkpoint-15000/result_FCD_SNN_Frag_Scaf.json

@@ -0,0 +1,19 @@
+{
+    "validity": 1.0,
+    "FCD": {
+        "FCD": 1.002989927399483,
+        "FCD/test": 1.2865087128018615
+    },
+    "SNN": {
+        "SNN": 0.5417524048349963,
+        "SNN/test": 0.5186626958462258
+    },
+    "Frag": {
+        "Frag": 0.9954620308507153,
+        "Frag/test": 0.9930898868011179
+    },
+    "Scaf": {
+        "Scaf": 0.6705683290696588,
+        "Scaf/test": 0.008874388198630616
+    }
+}

tmp-spec-checkpoint-15000/result_SA_wasserstein.json

@@ -0,0 +1,7 @@
+{
+    "validity": 1.0,
+    "SA_wasserstein": {
+        "SA_wasserstein": 0.026378598518104434,
+        "SA_wasserstein/test": 0.054440884921422565
+    }
+}

tmp-spec-checkpoint-15000/result_novelty_total.json

@@ -0,0 +1,3 @@
+{
+    "novelty_total": 0.9991406413749738
+}

tmp-spec-checkpoint-15000/result_unique@1k_unique@10k_IntDiv_IntDiv2_logP_wasserstein_QED_wasserstein_weight_wasserstein_NP_wasserstein.json

@@ -0,0 +1,23 @@
+{
+    "validity": 1.0,
+    "unique@1k": 1.0,
+    "unique@10k": 1.0,
+    "IntDiv": 0.8539086081502472,
+    "IntDiv2": 0.8497642859746146,
+    "logP_wasserstein": {
+        "logP_wasserstein": 0.1386001593623254,
+        "logP_wasserstein/test": 0.11556755788981397
+    },
+    "QED_wasserstein": {
+        "QED_wasserstein": 0.005218756412930638,
+        "QED_wasserstein/test": 0.009414825617739903
+    },
+    "weight_wasserstein": {
+        "weight_wasserstein": 2.698026518070816,
+        "weight_wasserstein/test": 4.977317290493286
+    },
+    "NP_wasserstein": {
+        "NP_wasserstein": 0.046379309027314096,
+        "NP_wasserstein/test": 0.07274505519831714
+    }
+}

tmp-spec-checkpoint-15000/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tmp-spec-checkpoint-15000/tokenizer.json

@@ -0,0 +1,193 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 0,
+      "content": "<unk>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 1,
+      "content": "<pad>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 2,
+      "content": "<bos>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 3,
+      "content": "<eos>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "Split",
+    "pattern": {
+      "Regex": "(\\[[^\\]]+]|Br?|Cl?|N|O|S|P|F|I|b|c|n|o|s|p|\\(|\\)|\\.|=|#|-|\\+|\\\\\\\\|\\/|:|~|@|\\?|>>?|\\*|\\$|\\%[0-9]{2}|[0-9])"
+    },
+    "behavior": "Isolated",
+    "invert": false
+  },
+  "post_processor": {
+    "type": "TemplateProcessing",
+    "single": [
+      {
+        "SpecialToken": {
+          "id": "<bos>",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "<eos>",
+          "type_id": 0
+        }
+      }
+    ],
+    "pair": [
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "B",
+          "type_id": 1
+        }
+      }
+    ],
+    "special_tokens": {
+      "<bos>": {
+        "id": "<bos>",
+        "ids": [
+          2
+        ],
+        "tokens": [
+          "<bos>"
+        ]
+      },
+      "<eos>": {
+        "id": "<eos>",
+        "ids": [
+          3
+        ],
+        "tokens": [
+          "<eos>"
+        ]
+      }
+    }
+  },
+  "decoder": {
+    "type": "BPEDecoder",
+    "suffix": "</w>"
+  },
+  "model": {
+    "type": "WordLevel",
+    "vocab": {
+      "<unk>": 0,
+      "<pad>": 1,
+      "<bos>": 2,
+      "<eos>": 3,
+      "C": 4,
+      ".": 5,
+      "1": 6,
+      "c": 7,
+      "O": 8,
+      "=": 9,
+      "(": 10,
+      ")": 11,
+      "N": 12,
+      "5": 13,
+      "6": 14,
+      "4": 15,
+      "7": 16,
+      "8": 17,
+      "3": 18,
+      "2": 19,
+      "n": 20,
+      "9": 21,
+      "F": 22,
+      "%10": 23,
+      "%11": 24,
+      "S": 25,
+      "s": 26,
+      "Cl": 27,
+      "[nH]": 28,
+      "o": 29,
+      "#": 30,
+      "Br": 31,
+      "%12": 32,
+      "[N+]": 33,
+      "[O-]": 34,
+      "%13": 35,
+      "I": 36,
+      "[N-]": 37,
+      "P": 38,
+      "[n+]": 39,
+      "%14": 40,
+      "-": 41,
+      "[Si]": 42,
+      "[S+]": 43,
+      "%15": 44,
+      "B": 45,
+      "%16": 46,
+      "[NH+]": 47,
+      "[B-]": 48,
+      "%17": 49,
+      "[NH2+]": 50,
+      "[O]": 51,
+      "[NH3+]": 52,
+      "[PH]": 53,
+      "[n-]": 54,
+      "%18": 55,
+      "[nH+]": 56,
+      "[Sn]": 57,
+      "[s+]": 58,
+      "%19": 59,
+      "[Se]": 60,
+      "[Cl-]": 61,
+      "%20": 62,
+      "[N]": 63,
+      "[C-]": 64,
+      "[C]": 65,
+      "[SiH]": 66,
+      "%21": 67,
+      "[O+]": 68,
+      "[SH]": 69,
+      "[NH]": 70,
+      "[P+]": 71,
+      "[c-]": 72,
+      "[o+]": 73
+    },
+    "unk_token": "<unk>"
+  }
+}

tmp-spec-checkpoint-15000/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<eos>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}

tmp-spec-checkpoint-15000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:634148355b42ee0de306ebb5fc5e0474a7658df467b360eba0c60e507cf38172
+size 6584

tmp-spec-checkpoint-20000/config.json

@@ -0,0 +1,30 @@
+{
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 3,
+  "fused_bias_fc": false,
+  "fused_dropout_add_ln": false,
+  "fused_mlp": false,
+  "hidden_act": "silu",
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "max_position_embeddings": 2048,
+  "max_seq_length": 128,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "residual_in_fp32": true,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.43.4",
+  "use_cache": true,
+  "use_flash_attn": true,
+  "vocab_size": 74
+}