Training in progress, step 10000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86f29d82923f7d0075178353725bdc7e7571975c7cb1aba108dca249132153e6
+oid sha256:f5d836d240e1fb6654c71a5c366bc648aa6f27896cf6c242a9e259f9d5662369
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2738d0fa911801a048835cc9ab59b46e1c26ebdadd2645b7bbc244df8449c3c3
+oid sha256:f19a35bcbde9822c6916d58897ae5c1a423551a64368e4dc9004952ac9065f5d
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd15187330b82b39cd3456f9d0ffdd9953cf17a8d229a03ac8c20637ba8bab1e
+oid sha256:bd0e6dd469f21059e2d07f08eea580c71ac1ebab8c3e65d3e0fa7e4672abd238
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78bf02c675dec0fd9b3b1ab69586d0efb5e14496c50eb3d649d5377260b3f3a1
+oid sha256:0222fc18936629176687fb7759a7397d9c6a96011f20f72101a9e2f365b891ad
 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=23-learning_rate=5.9e-04-warmup_ratio=0.070-num_cycles=4.500/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": 1.0,
       "step": 5000
+    },
+    {
+      "epoch": 0.542513316235944,
+      "grad_norm": 0.2779979109764099,
+      "learning_rate": 0.00016604047694869232,
+      "loss": 0.1604,
+      "step": 5500
+    },
+    {
+      "epoch": 0.5918327086210298,
+      "grad_norm": 0.4124259352684021,
+      "learning_rate": 2.331808450085655e-05,
+      "loss": 0.1502,
+      "step": 6000
+    },
+    {
+      "epoch": 0.6411521010061156,
+      "grad_norm": 0.21570533514022827,
+      "learning_rate": 0.0003954565085914005,
+      "loss": 0.1524,
+      "step": 6500
+    },
+    {
+      "epoch": 0.6904714933912014,
+      "grad_norm": 0.3348117172718048,
+      "learning_rate": 0.0005759973903650225,
+      "loss": 0.194,
+      "step": 7000
+    },
+    {
+      "epoch": 0.7397908857762873,
+      "grad_norm": 0.27428340911865234,
+      "learning_rate": 0.00022220639553258275,
+      "loss": 0.159,
+      "step": 7500
+    },
+    {
+      "epoch": 0.7397908857762873,
+      "eval_all_ligands_equal": 0.0,
+      "eval_e3_equal": 0.012814847547503314,
+      "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": 7.809368095448519,
+      "eval_e3_heavy_atoms_difference_norm": 0.20705526692701953,
+      "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": 2.762704374723818,
+      "eval_heavy_atoms_difference_norm": -0.0012221925796804898,
+      "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)": 1.0,
+      "eval_linker_heavy_atoms_difference": -0.28475475033141845,
+      "eval_linker_heavy_atoms_difference_norm": -0.25379907073206714,
+      "eval_linker_tanimoto_similarity": 0.0,
+      "eval_linker_valid": 1.0,
+      "eval_loss": 0.49679282307624817,
+      "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)": 1.0,
+      "eval_poi_heavy_atoms_difference": -4.761908970393283,
+      "eval_poi_heavy_atoms_difference_norm": -0.3188147951833394,
+      "eval_poi_tanimoto_similarity": 0.0,
+      "eval_poi_valid": 1.0,
+      "eval_reassembly": 0.0,
+      "eval_reassembly_nostereo": 0.0,
+      "eval_runtime": 1371.6409,
+      "eval_samples_per_second": 8.249,
+      "eval_steps_per_second": 0.129,
+      "eval_tanimoto_similarity": 0.0,
+      "eval_valid": 1.0,
+      "step": 7500
+    },
+    {
+      "epoch": 0.789110278161373,
+      "grad_norm": 0.33566632866859436,
+      "learning_rate": 5.711578084813873e-06,
+      "loss": 0.149,
+      "step": 8000
+    },
+    {
+      "epoch": 0.8384296705464589,
+      "grad_norm": 0.2673715353012085,
+      "learning_rate": 0.0003375013324843544,
+      "loss": 0.1496,
+      "step": 8500
+    },
+    {
+      "epoch": 0.8877490629315447,
+      "grad_norm": 0.5765497088432312,
+      "learning_rate": 0.0005877983141489226,
+      "loss": 0.1833,
+      "step": 9000
+    },
+    {
+      "epoch": 0.9370684553166305,
+      "grad_norm": 0.3018956184387207,
+      "learning_rate": 0.0002822468013685018,
+      "loss": 0.1676,
+      "step": 9500
+    },
+    {
+      "epoch": 0.9863878477017163,
+      "grad_norm": 0.342344731092453,
+      "learning_rate": 1.2247955938074163e-08,
+      "loss": 0.1495,
+      "step": 10000
+    },
+    {
+      "epoch": 0.9863878477017163,
+      "eval_all_ligands_equal": 0.0,
+      "eval_e3_equal": 0.005479452054794521,
+      "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": -7.567830313742819,
+      "eval_e3_heavy_atoms_difference_norm": -0.39426694299155357,
+      "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": -27.066725585505967,
+      "eval_heavy_atoms_difference_norm": -0.41020453906828314,
+      "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)": 1.0,
+      "eval_linker_heavy_atoms_difference": -2.8962439239946973,
+      "eval_linker_heavy_atoms_difference_norm": -0.45440469806308115,
+      "eval_linker_tanimoto_similarity": 0.0,
+      "eval_linker_valid": 1.0,
+      "eval_loss": 0.4956156313419342,
+      "eval_num_fragments": 3.0,
+      "eval_poi_equal": 0.002209456473707468,
+      "eval_poi_graph_edit_distance": 9.999999999999999e+63,
+      "eval_poi_graph_edit_distance_norm": 1.0,
+      "eval_poi_has_attachment_point(s)": 1.0,
+      "eval_poi_heavy_atoms_difference": -16.60265134776845,
+      "eval_poi_heavy_atoms_difference_norm": -0.7496805484668819,
+      "eval_poi_tanimoto_similarity": 0.0,
+      "eval_poi_valid": 1.0,
+      "eval_reassembly": 0.0,
+      "eval_reassembly_nostereo": 0.0,
+      "eval_runtime": 1779.5717,
+      "eval_samples_per_second": 6.358,
+      "eval_steps_per_second": 0.099,
+      "eval_tanimoto_similarity": 0.0,
+      "eval_valid": 1.0,
+      "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=23-learning_rate=5.9e-04-warmup_ratio=0.070-num_cycles=4.500",
   "trial_params": {