Training in progress, step 10000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b5f285acc071dd37545026f8745dfc2ad33cd676f3134d1b250026234818507
+oid sha256:9bb81a97041242cc2fc31203b495a4bebce526ab5850a33935de548ecba8f405
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce9cbb7820bc2b39d77f8c224e6f19e73c794cb423ff14d4bac830f2ae39c821
+oid sha256:db1fa98ce0cd0b5bab5ec7deb8147d179b46673a3ebff6e8680af47246ee7161
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c967bac04224a045e483051512ca448f79bf724bc99bb47d4b01b58ff850227
+oid sha256:eb8e3701c78801c3682fb8fe005ef92c2dac8de0928d1ca26b5d0b626cec9b96
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa6f186f8e8e35a0f499566da465dc331252fecac77e9a134d2b06a39da36227
+oid sha256:d222911452edcfb89948637f60e982596ac5a98020aa9b5c2785b3504ae6ab43
 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=15-learning_rate=2.3e-04-warmup_ratio=0.070-num_cycles=9/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": 0.40334638953208923,
+      "learning_rate": 4.72798198719592e-06,
+      "loss": 0.1524,
+      "step": 5500
+    },
+    {
+      "epoch": 0.5918327086210298,
+      "grad_norm": 0.25897476077079773,
+      "learning_rate": 0.00016227132655286433,
+      "loss": 0.1571,
+      "step": 6000
+    },
+    {
+      "epoch": 0.6411521010061156,
+      "grad_norm": 0.42913806438446045,
+      "learning_rate": 1.8343376701997453e-05,
+      "loss": 0.1525,
+      "step": 6500
+    },
+    {
+      "epoch": 0.6904714933912014,
+      "grad_norm": 0.30887413024902344,
+      "learning_rate": 0.0001896220976501263,
+      "loss": 0.1542,
+      "step": 7000
+    },
+    {
+      "epoch": 0.7397908857762873,
+      "grad_norm": 0.3643406927585602,
+      "learning_rate": 3.974361254751187e-05,
+      "loss": 0.1528,
+      "step": 7500
+    },
+    {
+      "epoch": 0.7397908857762873,
+      "eval_all_ligands_equal": 0.0,
+      "eval_e3_equal": 0.004684047724259832,
+      "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": -4.8929739284136105,
+      "eval_e3_heavy_atoms_difference_norm": -0.28970659073238636,
+      "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": -19.629253203711887,
+      "eval_heavy_atoms_difference_norm": -0.3094509206668312,
+      "eval_linker_equal": 0.002209456473707468,
+      "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": -3.4003535130357934,
+      "eval_linker_heavy_atoms_difference_norm": -0.48975559440086974,
+      "eval_linker_tanimoto_similarity": 0.0,
+      "eval_linker_valid": 1.0,
+      "eval_loss": 0.49861598014831543,
+      "eval_num_fragments": 3.0,
+      "eval_poi_equal": 0.0017675651789659744,
+      "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": -11.335925762262484,
+      "eval_poi_heavy_atoms_difference_norm": -0.5637834471539719,
+      "eval_poi_tanimoto_similarity": 0.0,
+      "eval_poi_valid": 1.0,
+      "eval_reassembly": 0.0,
+      "eval_reassembly_nostereo": 0.0,
+      "eval_runtime": 1775.4646,
+      "eval_samples_per_second": 6.373,
+      "eval_steps_per_second": 0.1,
+      "eval_tanimoto_similarity": 0.0,
+      "eval_valid": 1.0,
+      "step": 7500
+    },
+    {
+      "epoch": 0.789110278161373,
+      "grad_norm": 0.23480825126171112,
+      "learning_rate": 0.00021088172654065888,
+      "loss": 0.1496,
+      "step": 8000
+    },
+    {
+      "epoch": 0.8384296705464589,
+      "grad_norm": 0.397032767534256,
+      "learning_rate": 6.719496968763895e-05,
+      "loss": 0.1523,
+      "step": 8500
+    },
+    {
+      "epoch": 0.8877490629315447,
+      "grad_norm": 0.23358654975891113,
+      "learning_rate": 0.0002243278845276328,
+      "loss": 0.1473,
+      "step": 9000
+    },
+    {
+      "epoch": 0.9370684553166305,
+      "grad_norm": 0.35571378469467163,
+      "learning_rate": 9.847350242639196e-05,
+      "loss": 0.1557,
+      "step": 9500
+    },
+    {
+      "epoch": 0.9863878477017163,
+      "grad_norm": 0.4071267247200012,
+      "learning_rate": 1.8668323142670654e-09,
+      "loss": 0.1463,
+      "step": 10000
+    },
+    {
+      "epoch": 0.9863878477017163,
+      "eval_all_ligands_equal": 0.0,
+      "eval_e3_equal": 0.006716747680070702,
+      "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": -5.479010163499779,
+      "eval_e3_heavy_atoms_difference_norm": -0.31248932677521146,
+      "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": -16.36579761378701,
+      "eval_heavy_atoms_difference_norm": -0.2639458185695727,
+      "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": -2.0755634114007955,
+      "eval_linker_heavy_atoms_difference_norm": -0.38850172612130895,
+      "eval_linker_tanimoto_similarity": 0.0,
+      "eval_linker_valid": 1.0,
+      "eval_loss": 0.5050681829452515,
+      "eval_num_fragments": 3.0,
+      "eval_poi_equal": 0.0013256738842244808,
+      "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": -8.811224038886435,
+      "eval_poi_heavy_atoms_difference_norm": -0.46859326736968265,
+      "eval_poi_tanimoto_similarity": 0.0,
+      "eval_poi_valid": 1.0,
+      "eval_reassembly": 0.0,
+      "eval_reassembly_nostereo": 0.0,
+      "eval_runtime": 1641.1843,
+      "eval_samples_per_second": 6.894,
+      "eval_steps_per_second": 0.108,
+      "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": 4.33139477262336e+16,
+  "total_flos": 8.663036348367667e+16,
   "train_batch_size": 128,
   "trial_name": "trial-number=15-learning_rate=2.3e-04-warmup_ratio=0.070-num_cycles=9",
   "trial_params": {