Training in progress, step 10000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41c2159e14ab8ebd91ec0daec06da82266fabb4a7dcb3648cef70bab2221618a
+oid sha256:332cd84d15ef2fb315780519f0d582e3337e9047ea7b44dc5428de90d43e58e0
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a321feb498a31c9ed973afbffd670e1c214a3a4a320e3389a6eab5400914fa9
+oid sha256:9909caa6f6726f14b143a92e634bdb0ea96f4213205030190cad08d20877bbcc
 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 sha256:5ae7dcec676f5b2e863c2e571b91e6ef2764d717c8affa130e11862bed5cbbc5
+oid sha256:604465ad0e65b5f81a0864bb03d101226966a1aafde4cf2fccf8bf9b80b3cb10
 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=22-learning_rate=6.6e-04-warmup_ratio=0.030-min_lr=0.000-factor=0.780/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": 0.9390079975128174,
+      "learning_rate": 0.0006583930582350292,
+      "loss": 3.5573,
+      "step": 5500
+    },
+    {
+      "epoch": 0.5918327086210298,
+      "grad_norm": 0.37822020053863525,
+      "learning_rate": 0.0006583930582350292,
+      "loss": 3.5582,
+      "step": 6000
+    },
+    {
+      "epoch": 0.6411521010061156,
+      "grad_norm": 0.9856277108192444,
+      "learning_rate": 0.0006583930582350292,
+      "loss": 3.5613,
+      "step": 6500
+    },
+    {
+      "epoch": 0.6904714933912014,
+      "grad_norm": 0.9074209928512573,
+      "learning_rate": 0.0006583930582350292,
+      "loss": 3.5565,
+      "step": 7000
+    },
+    {
+      "epoch": 0.7397908857762873,
+      "grad_norm": 0.9249660968780518,
+      "learning_rate": 0.0006583930582350292,
+      "loss": 3.5559,
+      "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": 0.0,
+      "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": 3.5794432163238525,
+      "eval_num_fragments": 1.0028281042863456,
+      "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": 5682.0008,
+      "eval_samples_per_second": 1.991,
+      "eval_steps_per_second": 0.031,
+      "eval_tanimoto_similarity": 0.0,
+      "eval_valid": 0.0,
+      "step": 7500
+    },
+    {
+      "epoch": 0.789110278161373,
+      "grad_norm": 0.8662272691726685,
+      "learning_rate": 0.0006583930582350292,
+      "loss": 3.5565,
+      "step": 8000
+    },
+    {
+      "epoch": 0.8384296705464589,
+      "grad_norm": 0.9421558976173401,
+      "learning_rate": 0.0006583930582350292,
+      "loss": 3.5563,
+      "step": 8500
+    },
+    {
+      "epoch": 0.8877490629315447,
+      "grad_norm": 0.826027512550354,
+      "learning_rate": 0.0006583930582350292,
+      "loss": 3.5562,
+      "step": 9000
+    },
+    {
+      "epoch": 0.9370684553166305,
+      "grad_norm": 0.883988618850708,
+      "learning_rate": 0.0006583930582350292,
+      "loss": 3.5554,
+      "step": 9500
+    },
+    {
+      "epoch": 0.9863878477017163,
+      "grad_norm": 0.8590209484100342,
+      "learning_rate": 0.0006583930582350292,
+      "loss": 3.5568,
+      "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": 3.5780739784240723,
+      "eval_num_fragments": 1.0027397260273974,
+      "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": 5630.8868,
+      "eval_samples_per_second": 2.009,
+      "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=22-learning_rate=6.6e-04-warmup_ratio=0.030-min_lr=0.000-factor=0.780",
   "trial_params": {