Training in progress, step 10000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b66c7275f80108b914fa2d9ded74aab2e8e26ed98cefe3555195732ab6c3fa4c
+oid sha256:787881ee9b5fb42b24ea8dd93be1b19efaed709b345bb74400cded3aa172b59c
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e45132fc0710746ad8c9d408d8d8116f774e1274ae88a34c7b5cad8193e23d5
+oid sha256:3eeb1aac698b2c94e48d6d2484748ce471a1ea84c8bb02cf679ae7ac38bd18c1
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6732c671f36151cdd05b97be18c12b2988cffb1f309a2cb00d544de58eb0ce2
+oid sha256:f05568c9474927fa3f00b14190be9bec9b14406698bef27ced0d260778a147e1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71ee91cdf0c467c8e19d5529367174afb8e82cb29c7b4ac8c39d892b258405ec
+oid sha256:57565e873e1eeafb85801e1dabf9a50fc4f98f57a23907d58a18af6f5f603e5d
 size 1192

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_reduce-opt25-rand-smiles/trial-number=11-learning_rate=8.7e-04-warmup_ratio=0.080-min_lr=0.000-factor=0.280/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": 0.0,
       "step": 5000
+    },
+    {
+      "epoch": 0.542513316235944,
+      "grad_norm": 0.35782232880592346,
+      "learning_rate": 0.0008697519738924375,
+      "loss": 3.5575,
+      "step": 5500
+    },
+    {
+      "epoch": 0.5918327086210298,
+      "grad_norm": 0.8922480344772339,
+      "learning_rate": 0.0008697519738924375,
+      "loss": 3.5616,
+      "step": 6000
+    },
+    {
+      "epoch": 0.6411521010061156,
+      "grad_norm": 0.8578431010246277,
+      "learning_rate": 0.0008697519738924375,
+      "loss": 3.5598,
+      "step": 6500
+    },
+    {
+      "epoch": 0.6904714933912014,
+      "grad_norm": 0.754083514213562,
+      "learning_rate": 0.0008697519738924375,
+      "loss": 3.5569,
+      "step": 7000
+    },
+    {
+      "epoch": 0.7397908857762873,
+      "grad_norm": 0.4220362603664398,
+      "learning_rate": 0.0008697519738924375,
+      "loss": 3.5558,
+      "step": 7500
+    },
+    {
+      "epoch": 0.7397908857762873,
+      "eval_all_ligands_equal": 0.0,
+      "eval_e3_equal": 0.0,
+      "eval_e3_graph_edit_distance": 9.999999999999999e+63,
+      "eval_e3_graph_edit_distance_norm": 1.0,
+      "eval_e3_has_attachment_point(s)": 0.0,
+      "eval_e3_heavy_atoms_difference": 28.086433937251435,
+      "eval_e3_heavy_atoms_difference_norm": 1.0,
+      "eval_e3_tanimoto_similarity": 0.0,
+      "eval_e3_valid": 0.0,
+      "eval_has_all_attachment_points": 0.0,
+      "eval_has_three_substructures": 0.0002651347768448962,
+      "eval_heavy_atoms_difference": 75.67370746796288,
+      "eval_heavy_atoms_difference_norm": 1.0,
+      "eval_linker_equal": 0.0,
+      "eval_linker_graph_edit_distance": 9.999999999999999e+63,
+      "eval_linker_graph_edit_distance_norm": 1.0,
+      "eval_linker_has_attachment_point(s)": 0.0,
+      "eval_linker_heavy_atoms_difference": 16.430402121078213,
+      "eval_linker_heavy_atoms_difference_norm": 1.0,
+      "eval_linker_tanimoto_similarity": 0.0,
+      "eval_linker_valid": 0.0,
+      "eval_loss": 3.6163675785064697,
+      "eval_num_fragments": 1.0259832081307998,
+      "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)": 0.0,
+      "eval_poi_heavy_atoms_difference": 31.15687140963323,
+      "eval_poi_heavy_atoms_difference_norm": 1.0,
+      "eval_poi_tanimoto_similarity": 0.0,
+      "eval_poi_valid": 0.0,
+      "eval_reassembly": 0.0,
+      "eval_reassembly_nostereo": 0.0,
+      "eval_runtime": 5667.4561,
+      "eval_samples_per_second": 1.996,
+      "eval_steps_per_second": 0.031,
+      "eval_tanimoto_similarity": 0.0,
+      "eval_valid": 0.0,
+      "step": 7500
+    },
+    {
+      "epoch": 0.789110278161373,
+      "grad_norm": 0.7933610081672668,
+      "learning_rate": 0.0008697519738924375,
+      "loss": 3.5579,
+      "step": 8000
+    },
+    {
+      "epoch": 0.8384296705464589,
+      "grad_norm": 0.7799351215362549,
+      "learning_rate": 0.0008697519738924375,
+      "loss": 3.5574,
+      "step": 8500
+    },
+    {
+      "epoch": 0.8877490629315447,
+      "grad_norm": 0.5444666743278503,
+      "learning_rate": 0.0008697519738924375,
+      "loss": 3.5565,
+      "step": 9000
+    },
+    {
+      "epoch": 0.9370684553166305,
+      "grad_norm": 0.5839781165122986,
+      "learning_rate": 0.0008697519738924375,
+      "loss": 3.5569,
+      "step": 9500
+    },
+    {
+      "epoch": 0.9863878477017163,
+      "grad_norm": 0.7171167731285095,
+      "learning_rate": 0.0008697519738924375,
+      "loss": 3.5569,
+      "step": 10000
+    },
+    {
+      "epoch": 0.9863878477017163,
+      "eval_all_ligands_equal": 0.0,
+      "eval_e3_equal": 0.0,
+      "eval_e3_graph_edit_distance": 9.999999999999999e+63,
+      "eval_e3_graph_edit_distance_norm": 1.0,
+      "eval_e3_has_attachment_point(s)": 0.0,
+      "eval_e3_heavy_atoms_difference": 28.086433937251435,
+      "eval_e3_heavy_atoms_difference_norm": 1.0,
+      "eval_e3_tanimoto_similarity": 0.0,
+      "eval_e3_valid": 0.0,
+      "eval_has_all_attachment_points": 0.0,
+      "eval_has_three_substructures": 0.0,
+      "eval_heavy_atoms_difference": 75.67370746796288,
+      "eval_heavy_atoms_difference_norm": 1.0,
+      "eval_linker_equal": 0.0,
+      "eval_linker_graph_edit_distance": 9.999999999999999e+63,
+      "eval_linker_graph_edit_distance_norm": 1.0,
+      "eval_linker_has_attachment_point(s)": 0.0,
+      "eval_linker_heavy_atoms_difference": 16.430402121078213,
+      "eval_linker_heavy_atoms_difference_norm": 1.0,
+      "eval_linker_tanimoto_similarity": 0.0,
+      "eval_linker_valid": 0.0,
+      "eval_loss": 3.5786292552948,
+      "eval_num_fragments": 1.0031816173221388,
+      "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)": 0.0,
+      "eval_poi_heavy_atoms_difference": 31.15687140963323,
+      "eval_poi_heavy_atoms_difference_norm": 1.0,
+      "eval_poi_tanimoto_similarity": 0.0,
+      "eval_poi_valid": 0.0,
+      "eval_reassembly": 0.0,
+      "eval_reassembly_nostereo": 0.0,
+      "eval_runtime": 5621.5834,
+      "eval_samples_per_second": 2.013,
+      "eval_steps_per_second": 0.031,
+      "eval_tanimoto_similarity": 0.0,
+      "eval_valid": 0.0,
+      "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": 4.364959997072179e+16,
+  "total_flos": 8.729673191023411e+16,
   "train_batch_size": 128,
   "trial_name": "trial-number=11-learning_rate=8.7e-04-warmup_ratio=0.080-min_lr=0.000-factor=0.280",
   "trial_params": {