Training in progress, step 10000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6ee2b86005e85896767e609f834b69ac9ca6694436c07e4fe0c796b09097875
+oid sha256:e6190de4856e64d34d586b21681ba9266183ad59856a4b97b3789dc5b36e69d5
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcdd6fe157498e9b14920b4c9290d8ed6399618cced27ea787c222e39a060182
+oid sha256:947f1171e40a48f03fbbc59ec258a1515761f14874494cbd31ad30c6941a095b
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:062484254f00dc6c661d11ef70c9c322a894bdef1a439c0ec9c383dd9f873e32
+oid sha256:5370136260b11eacaa32121ff0058da294c89a8bf8b55e542cc23877768e4b55
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d88f2f94b557ce0428a3d4d88fca9c0cebc972057a46963c7e12e41f2a890dd7
+oid sha256:8012529a3e966d06ac12c1db15f08af55229902300d42ae95c7b048e773619c1
 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-opt25-rand-smiles/trial-number=7-learning_rate=7.8e-04-warmup_ratio=0.090-num_cycles=2.000/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": 0.9997348652231551,
       "step": 5000
+    },
+    {
+      "epoch": 0.542513316235944,
+      "grad_norm": 0.27507615089416504,
+      "learning_rate": 0.000771165072704306,
+      "loss": 0.1772,
+      "step": 5500
+    },
+    {
+      "epoch": 0.5918327086210298,
+      "grad_norm": 0.23323027789592743,
+      "learning_rate": 0.0006387992943959788,
+      "loss": 0.165,
+      "step": 6000
+    },
+    {
+      "epoch": 0.6411521010061156,
+      "grad_norm": 0.23379911482334137,
+      "learning_rate": 0.000396921613090527,
+      "loss": 0.1559,
+      "step": 6500
+    },
+    {
+      "epoch": 0.6904714933912014,
+      "grad_norm": 0.31352663040161133,
+      "learning_rate": 0.00015177911497445075,
+      "loss": 0.15,
+      "step": 7000
+    },
+    {
+      "epoch": 0.7397908857762873,
+      "grad_norm": 0.30255958437919617,
+      "learning_rate": 1.1052988261315712e-05,
+      "loss": 0.1463,
+      "step": 7500
+    },
+    {
+      "epoch": 0.7397908857762873,
+      "eval_all_ligands_equal": 0.0,
+      "eval_e3_equal": 0.004860804242156429,
+      "eval_e3_graph_edit_distance": 9.999999999999999e+63,
+      "eval_e3_graph_edit_distance_norm": 1.0,
+      "eval_e3_has_attachment_point(s)": 1.0,
+      "eval_e3_heavy_atoms_difference": -5.131506849315069,
+      "eval_e3_heavy_atoms_difference_norm": -0.299063499116105,
+      "eval_e3_tanimoto_similarity": 0.0,
+      "eval_e3_valid": 1.0,
+      "eval_has_all_attachment_points": 1.0,
+      "eval_has_three_substructures": 1.0,
+      "eval_heavy_atoms_difference": -20.02129916040654,
+      "eval_heavy_atoms_difference_norm": -0.314300300668607,
+      "eval_linker_equal": 0.0016791869200176756,
+      "eval_linker_graph_edit_distance": 9.999999999999999e+63,
+      "eval_linker_graph_edit_distance_norm": 1.0,
+      "eval_linker_has_attachment_point(s)": 1.0,
+      "eval_linker_heavy_atoms_difference": -3.839681838267786,
+      "eval_linker_heavy_atoms_difference_norm": -0.5210048047300356,
+      "eval_linker_tanimoto_similarity": 0.0,
+      "eval_linker_valid": 1.0,
+      "eval_loss": 0.49704626202583313,
+      "eval_num_fragments": 3.0,
+      "eval_poi_equal": 0.0027397260273972603,
+      "eval_poi_graph_edit_distance": 9.999999999999999e+63,
+      "eval_poi_graph_edit_distance_norm": 1.0,
+      "eval_poi_has_attachment_point(s)": 0.9993813521873619,
+      "eval_poi_heavy_atoms_difference": -11.08157313300928,
+      "eval_poi_heavy_atoms_difference_norm": -0.5551499346711933,
+      "eval_poi_tanimoto_similarity": 0.0,
+      "eval_poi_valid": 0.9993813521873619,
+      "eval_reassembly": 0.0,
+      "eval_reassembly_nostereo": 0.0,
+      "eval_runtime": 1804.3653,
+      "eval_samples_per_second": 6.271,
+      "eval_steps_per_second": 0.098,
+      "eval_tanimoto_similarity": 0.0,
+      "eval_valid": 0.9993813521873619,
+      "step": 7500
+    },
+    {
+      "epoch": 0.789110278161373,
+      "grad_norm": 0.2914905250072479,
+      "learning_rate": 3.6558530802854075e-05,
+      "loss": 0.1451,
+      "step": 8000
+    },
+    {
+      "epoch": 0.8384296705464589,
+      "grad_norm": 0.2859417796134949,
+      "learning_rate": 0.00021709218895981126,
+      "loss": 0.1466,
+      "step": 8500
+    },
+    {
+      "epoch": 0.8877490629315447,
+      "grad_norm": 0.3361692726612091,
+      "learning_rate": 0.00047335282575153254,
+      "loss": 0.1634,
+      "step": 9000
+    },
+    {
+      "epoch": 0.9370684553166305,
+      "grad_norm": 1.0404810905456543,
+      "learning_rate": 0.0006927755041550175,
+      "loss": 0.1679,
+      "step": 9500
+    },
+    {
+      "epoch": 0.9863878477017163,
+      "grad_norm": 0.3088153898715973,
+      "learning_rate": 0.0007789767128938879,
+      "loss": 0.1925,
+      "step": 10000
+    },
+    {
+      "epoch": 0.9863878477017163,
+      "eval_all_ligands_equal": 0.0,
+      "eval_e3_equal": 0.008572691117984976,
+      "eval_e3_graph_edit_distance": 9.999999999999999e+63,
+      "eval_e3_graph_edit_distance_norm": 1.0,
+      "eval_e3_has_attachment_point(s)": 1.0,
+      "eval_e3_heavy_atoms_difference": -5.5740167918692,
+      "eval_e3_heavy_atoms_difference_norm": -0.3162344909098186,
+      "eval_e3_tanimoto_similarity": 0.0,
+      "eval_e3_valid": 1.0,
+      "eval_has_all_attachment_points": 1.0,
+      "eval_has_three_substructures": 1.0,
+      "eval_heavy_atoms_difference": -0.8163499779054353,
+      "eval_heavy_atoms_difference_norm": -0.049597444879744636,
+      "eval_linker_equal": 0.001590808661069377,
+      "eval_linker_graph_edit_distance": 9.999999999999999e+63,
+      "eval_linker_graph_edit_distance_norm": 1.0,
+      "eval_linker_has_attachment_point(s)": 0.9997348652231551,
+      "eval_linker_heavy_atoms_difference": -0.4775961113566063,
+      "eval_linker_heavy_atoms_difference_norm": -0.27010033853887316,
+      "eval_linker_tanimoto_similarity": 0.0,
+      "eval_linker_valid": 0.9997348652231551,
+      "eval_loss": 0.5193294286727905,
+      "eval_num_fragments": 3.0,
+      "eval_poi_equal": 0.0016791869200176756,
+      "eval_poi_graph_edit_distance": 9.999999999999999e+63,
+      "eval_poi_graph_edit_distance_norm": 1.0,
+      "eval_poi_has_attachment_point(s)": 0.9573133009279717,
+      "eval_poi_heavy_atoms_difference": 3.002032699955811,
+      "eval_poi_heavy_atoms_difference_norm": -0.03282844379746269,
+      "eval_poi_tanimoto_similarity": 0.0,
+      "eval_poi_valid": 0.9573133009279717,
+      "eval_reassembly": 0.0,
+      "eval_reassembly_nostereo": 0.0,
+      "eval_runtime": 1317.9182,
+      "eval_samples_per_second": 8.586,
+      "eval_steps_per_second": 0.134,
+      "eval_tanimoto_similarity": 0.0,
+      "eval_valid": 0.9570481661511269,
+      "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=7-learning_rate=7.8e-04-warmup_ratio=0.090-num_cycles=2.000",
   "trial_params": {