Training in progress, step 80000, checkpoint

last-checkpoint/generation_config.json

@@ -1,5 +1,4 @@
 {
-  "_from_model_config": true,
   "bos_token_id": 0,
   "do_sample": true,
   "eos_token_id": 2,

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d853c6f05a319f25e01c962a1fb3ee48c2db25e7027aae9ea5ba74c82184f6e4
+oid sha256:16bb8e66671fa879eb81e50b1d20542d42f89e18ffe9fd61565bb0857caa15ad
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83553605e7ddd6468c2b9dc770ee7a1e541ce642115183b055361a355442fe7d
+oid sha256:120489bbdc04717c894f6710efc07020c43a77fc8537101ec3b34f7b9815ffb4
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea587fc8ce98d035036ade6e290d9e6323d34aeaeb53c96eb93f1b8fb08d759f
+oid sha256:914bd1dd0f099eba1e42325565507da59f36a394e4f2144793ccc165c1e69e22
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec08642f74697f111f64e755e2fc9bd211b07cc951ee155be7841c13ee3a6fae
+oid sha256:a5c9c566793baf06739638fe04971034f3f78b78a5adee1b2735c35275a3ddc6
 size 1192

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 7.890583903208837,
+  "best_metric": 0.58967776203966,
+  "best_model_checkpoint": "/mimer/NOBACKUP/groups/naiss2023-6-290/stefano/models//PROTAC-Splitter-EncoderDecoder-lr_reduce-rand-smiles-train-0.75/checkpoint-80000",
+  "epoch": 10.520778537611783,
   "eval_steps": 20000,
-  "global_step": 60000,
+  "global_step": 80000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -91,6 +91,76 @@
       "learning_rate": 5e-05,
       "loss": 0.0008,
       "step": 60000
+    },
+    {
+      "epoch": 8.548132561809574,
+      "grad_norm": 0.008909576572477818,
+      "learning_rate": 5e-05,
+      "loss": 0.0008,
+      "step": 65000
+    },
+    {
+      "epoch": 9.20568122041031,
+      "grad_norm": 0.03536743298172951,
+      "learning_rate": 5e-05,
+      "loss": 0.0007,
+      "step": 70000
+    },
+    {
+      "epoch": 9.863229879011048,
+      "grad_norm": 0.032457005232572556,
+      "learning_rate": 5e-05,
+      "loss": 0.0007,
+      "step": 75000
+    },
+    {
+      "epoch": 10.520778537611783,
+      "grad_norm": 0.03012124076485634,
+      "learning_rate": 5e-05,
+      "loss": 0.0006,
+      "step": 80000
+    },
+    {
+      "epoch": 10.520778537611783,
+      "eval_all_ligands_equal": 0.58967776203966,
+      "eval_e3_equal": 0.8233888101983002,
+      "eval_e3_graph_edit_distance": Infinity,
+      "eval_e3_graph_edit_distance_norm": Infinity,
+      "eval_e3_has_attachment_point(s)": 0.9907046742209632,
+      "eval_e3_heavy_atoms_difference": 0.23973087818696884,
+      "eval_e3_heavy_atoms_difference_norm": 0.00245870041964951,
+      "eval_e3_tanimoto_similarity": 0.0,
+      "eval_e3_valid": 0.9907046742209632,
+      "eval_has_all_attachment_points": 0.9910587818696884,
+      "eval_has_three_substructures": 0.9999114730878187,
+      "eval_heavy_atoms_difference": 5.737960339943343,
+      "eval_heavy_atoms_difference_norm": 0.07681792432047847,
+      "eval_linker_equal": 0.8418024079320113,
+      "eval_linker_graph_edit_distance": 2.036118980169971e+61,
+      "eval_linker_graph_edit_distance_norm": Infinity,
+      "eval_linker_has_attachment_point(s)": 0.99796388101983,
+      "eval_linker_heavy_atoms_difference": 0.24318342776203966,
+      "eval_linker_heavy_atoms_difference_norm": 0.0017717587741049906,
+      "eval_linker_tanimoto_similarity": 0.0,
+      "eval_linker_valid": 0.99796388101983,
+      "eval_loss": 0.35464006662368774,
+      "eval_num_fragments": 2.9999114730878187,
+      "eval_poi_equal": 0.7881550991501416,
+      "eval_poi_graph_edit_distance": Infinity,
+      "eval_poi_graph_edit_distance_norm": Infinity,
+      "eval_poi_has_attachment_point(s)": 0.9406869688385269,
+      "eval_poi_heavy_atoms_difference": 1.742121104815864,
+      "eval_poi_heavy_atoms_difference_norm": 0.05507914134558919,
+      "eval_poi_tanimoto_similarity": 0.0,
+      "eval_poi_valid": 0.9406869688385269,
+      "eval_reassembly": 0.5964943342776204,
+      "eval_reassembly_nostereo": 0.6277443342776204,
+      "eval_runtime": 2335.5636,
+      "eval_samples_per_second": 4.837,
+      "eval_steps_per_second": 0.076,
+      "eval_tanimoto_similarity": 0.0,
+      "eval_valid": 0.9300637393767706,
+      "step": 80000
     }
   ],
   "logging_steps": 5000,
@@ -110,7 +180,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.2168028971708224e+17,
+  "total_flos": 6.955602225770995e+17,
   "train_batch_size": 128,
   "trial_name": null,
   "trial_params": null