Training in progress, step 10000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cf54048ff6ce5f26f03250a92a606f60efbae0415a3b7f8681a8968362595bf
+oid sha256:cbf75cde23b6c646d55822f2a45ab66bf00142ff327a2200bc22f071dd94177e
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:388052508f8be7a5883de0167af2eac1b9aa3f0bcdd6471f638a37875f6e0479
+oid sha256:f7edf7a97840df4248b9e19732919637ff2db5a5c8f5429b5036b6a064bb0d01
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5386966d61db93c46fabe29a53106681f3a13cc982ada0c0fb3a658a4744683
+oid sha256:732be29be99acd09266dc2e0ba96080d83b2496202117183ae58c55514b47bac
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68744b2af62e2aa71c76b1d74061d9e0f739c35e0ac563090643963a5233c522
+oid sha256:9247298e5578f56ef1333daeb30603e498e6590f0329d842b028b226399f0764
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.0,
   "best_model_checkpoint": "/mimer/NOBACKUP/groups/naiss2023-6-290/stefano/models//PROTAC-Splitter-EncoderDecoder-lr_cosine_restarts-opt25/trial-number=5-learning_rate=1.3e-06-warmup_ratio=0.080-num_cycles=4/checkpoint-5000",
-  "epoch": 0.49319392385085814,
+  "epoch": 0.9863878477017163,
   "eval_steps": 2500,
-  "global_step": 5000,
+  "global_step": 10000,
   "is_hyper_param_search": true,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -119,6 +119,160 @@
       "eval_tanimoto_similarity": 0.0,
       "eval_valid": 0.1367211665930181,
       "step": 5000
+    },
+    {
+      "epoch": 0.542513316235944,
+      "grad_norm": 1.2895699739456177,
+      "learning_rate": 1.2424144776927155e-06,
+      "loss": 0.86,
+      "step": 5500
+    },
+    {
+      "epoch": 0.5918327086210298,
+      "grad_norm": 1.2580499649047852,
+      "learning_rate": 9.15580095966108e-07,
+      "loss": 0.7773,
+      "step": 6000
+    },
+    {
+      "epoch": 0.6411521010061156,
+      "grad_norm": 1.316585898399353,
+      "learning_rate": 4.949582104735502e-07,
+      "loss": 0.7239,
+      "step": 6500
+    },
+    {
+      "epoch": 0.6904714933912014,
+      "grad_norm": 1.3320051431655884,
+      "learning_rate": 1.4436400409257678e-07,
+      "loss": 0.6969,
+      "step": 7000
+    },
+    {
+      "epoch": 0.7397908857762873,
+      "grad_norm": 1.3062090873718262,
+      "learning_rate": 3.397158625263245e-10,
+      "loss": 0.6874,
+      "step": 7500
+    },
+    {
+      "epoch": 0.7397908857762873,
+      "eval_all_ligands_equal": 0.0,
+      "eval_e3_equal": 0.03994697304463102,
+      "eval_e3_graph_edit_distance": 9.999999999999999e+63,
+      "eval_e3_graph_edit_distance_norm": 1.0,
+      "eval_e3_has_attachment_point(s)": 0.9336279275298277,
+      "eval_e3_heavy_atoms_difference": 2.293150684931507,
+      "eval_e3_heavy_atoms_difference_norm": 0.028751527532461223,
+      "eval_e3_tanimoto_similarity": 0.0,
+      "eval_e3_valid": 0.9336279275298277,
+      "eval_has_all_attachment_points": 0.628104286345559,
+      "eval_has_three_substructures": 0.936986301369863,
+      "eval_heavy_atoms_difference": 66.52054794520548,
+      "eval_heavy_atoms_difference_norm": 0.865724037271663,
+      "eval_linker_equal": 0.0013256738842244808,
+      "eval_linker_graph_edit_distance": 9.999999999999999e+63,
+      "eval_linker_graph_edit_distance_norm": 1.0,
+      "eval_linker_has_attachment_point(s)": 0.8955368979231109,
+      "eval_linker_heavy_atoms_difference": 9.49085285019885,
+      "eval_linker_heavy_atoms_difference_norm": 0.4873965592905604,
+      "eval_linker_tanimoto_similarity": 0.0,
+      "eval_linker_valid": 0.8955368979231109,
+      "eval_loss": 0.752865195274353,
+      "eval_num_fragments": 3.0488731771984092,
+      "eval_poi_equal": 0.0,
+      "eval_poi_graph_edit_distance": 9.999999999999999e+63,
+      "eval_poi_graph_edit_distance_norm": 1.0,
+      "eval_poi_has_attachment_point(s)": 0.26124613345117104,
+      "eval_poi_heavy_atoms_difference": 26.506760936809545,
+      "eval_poi_heavy_atoms_difference_norm": 0.8160066823783104,
+      "eval_poi_tanimoto_similarity": 0.0,
+      "eval_poi_valid": 0.26124613345117104,
+      "eval_reassembly": 0.0,
+      "eval_reassembly_nostereo": 0.0,
+      "eval_runtime": 1408.5549,
+      "eval_samples_per_second": 8.033,
+      "eval_steps_per_second": 0.126,
+      "eval_tanimoto_similarity": 0.0,
+      "eval_valid": 0.2479010163499779,
+      "step": 7500
+    },
+    {
+      "epoch": 0.789110278161373,
+      "grad_norm": 1.4089298248291016,
+      "learning_rate": 1.2305541561751468e-06,
+      "loss": 0.6626,
+      "step": 8000
+    },
+    {
+      "epoch": 0.8384296705464589,
+      "grad_norm": 1.3903034925460815,
+      "learning_rate": 8.954597621178985e-07,
+      "loss": 0.6095,
+      "step": 8500
+    },
+    {
+      "epoch": 0.8877490629315447,
+      "grad_norm": 1.2159473896026611,
+      "learning_rate": 4.744139191520028e-07,
+      "loss": 0.5772,
+      "step": 9000
+    },
+    {
+      "epoch": 0.9370684553166305,
+      "grad_norm": 1.2193936109542847,
+      "learning_rate": 1.313969244141942e-07,
+      "loss": 0.56,
+      "step": 9500
+    },
+    {
+      "epoch": 0.9863878477017163,
+      "grad_norm": 1.1179561614990234,
+      "learning_rate": 0.0,
+      "loss": 0.555,
+      "step": 10000
+    },
+    {
+      "epoch": 0.9863878477017163,
+      "eval_all_ligands_equal": 0.0,
+      "eval_e3_equal": 0.06716747680070703,
+      "eval_e3_graph_edit_distance": 9.999999999999999e+63,
+      "eval_e3_graph_edit_distance_norm": 1.0,
+      "eval_e3_has_attachment_point(s)": 0.9695978789217853,
+      "eval_e3_heavy_atoms_difference": 0.30614228899690676,
+      "eval_e3_heavy_atoms_difference_norm": -0.032830889402402384,
+      "eval_e3_tanimoto_similarity": 0.0,
+      "eval_e3_valid": 0.9695978789217853,
+      "eval_has_all_attachment_points": 0.7517454706142289,
+      "eval_has_three_substructures": 0.9703049049933716,
+      "eval_heavy_atoms_difference": 61.65877154220062,
+      "eval_heavy_atoms_difference_norm": 0.7972451444666561,
+      "eval_linker_equal": 0.0015024304021210783,
+      "eval_linker_graph_edit_distance": 9.999999999999999e+63,
+      "eval_linker_graph_edit_distance_norm": 1.0,
+      "eval_linker_has_attachment_point(s)": 0.9423773751657092,
+      "eval_linker_heavy_atoms_difference": 8.06593018117543,
+      "eval_linker_heavy_atoms_difference_norm": 0.3886527812652782,
+      "eval_linker_tanimoto_similarity": 0.0,
+      "eval_linker_valid": 0.9423773751657092,
+      "eval_loss": 0.6390168070793152,
+      "eval_num_fragments": 3.018029164825453,
+      "eval_poi_equal": 0.00344675209898365,
+      "eval_poi_graph_edit_distance": 9.999999999999999e+63,
+      "eval_poi_graph_edit_distance_norm": 1.0,
+      "eval_poi_has_attachment_point(s)": 0.3026071586389748,
+      "eval_poi_heavy_atoms_difference": 25.082722050375608,
+      "eval_poi_heavy_atoms_difference_norm": 0.7593849046591564,
+      "eval_poi_tanimoto_similarity": 0.0,
+      "eval_poi_valid": 0.3026071586389748,
+      "eval_reassembly": 0.0,
+      "eval_reassembly_nostereo": 0.0,
+      "eval_runtime": 1397.9415,
+      "eval_samples_per_second": 8.094,
+      "eval_steps_per_second": 0.127,
+      "eval_tanimoto_similarity": 0.0,
+      "eval_valid": 0.29235528060097216,
+      "step": 10000
     }
   ],
   "logging_steps": 500,
@@ -133,12 +287,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.33139477262336e+16,
+  "total_flos": 8.663036348367667e+16,
   "train_batch_size": 128,
   "trial_name": "trial-number=5-learning_rate=1.3e-06-warmup_ratio=0.080-num_cycles=4",
   "trial_params": {