Training in progress, step 10000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:daab2685c7d4d42bb5b182b38a51b023c9b2e6d344f09a2ed6796eed20ab1b48
+oid sha256:55a9106cdb8c62c8cb6c6cf2ccc75d943d297cbb37eb48f2888db56021a9cf39
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2c13dc0447209c48c887895a95ae8f34be534f2f5ac4affce2bd1fae4ed9d62
+oid sha256:0446a49c3bb5dd0c3ac104ec08d4544d44bed7f66667e91c392afa1b706980ca
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66a8f21c743fbbd6b01ebeadc5a65d9e0ab995588cfa53a2a2d84cf86cd007b5
+oid sha256:afe240b3e703829fba42c3f2a3fa53ecc7ce4171cc7b64de5bd39cdada6c5594
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d65c0dc8938f45175fc83c4b1c91e571df9245368b510bc2d6e3a799c35da4f7
+oid sha256:6f5f0f04e739bbfb1fc5cae716a665897a5f3c6c64a428de8cb172be54e15298
 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=7-learning_rate=1.8e-04-warmup_ratio=0.100-min_lr=0.000-factor=0.710/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": 0.23685993254184723,
+      "learning_rate": 0.00017553249516694252,
+      "loss": 0.147,
+      "step": 5500
+    },
+    {
+      "epoch": 0.5918327086210298,
+      "grad_norm": 0.20809854567050934,
+      "learning_rate": 0.00017553249516694252,
+      "loss": 0.142,
+      "step": 6000
+    },
+    {
+      "epoch": 0.6411521010061156,
+      "grad_norm": 0.2273290902376175,
+      "learning_rate": 0.00017553249516694252,
+      "loss": 0.1446,
+      "step": 6500
+    },
+    {
+      "epoch": 0.6904714933912014,
+      "grad_norm": 0.3077870309352875,
+      "learning_rate": 0.00017553249516694252,
+      "loss": 0.1399,
+      "step": 7000
+    },
+    {
+      "epoch": 0.7397908857762873,
+      "grad_norm": 5.584017276763916,
+      "learning_rate": 0.00017553249516694252,
+      "loss": 0.1386,
+      "step": 7500
+    },
+    {
+      "epoch": 0.7397908857762873,
+      "eval_all_ligands_equal": 0.0,
+      "eval_e3_equal": 0.03543968183826779,
+      "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": 1.34856385329209,
+      "eval_e3_heavy_atoms_difference_norm": -0.0034216972448036422,
+      "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": -0.8091913389306231,
+      "eval_heavy_atoms_difference_norm": -0.03921231630974343,
+      "eval_linker_equal": 0.0014140521431727795,
+      "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": -0.5910737958462219,
+      "eval_linker_heavy_atoms_difference_norm": -0.2813864737304455,
+      "eval_linker_tanimoto_similarity": 0.0,
+      "eval_linker_valid": 1.0,
+      "eval_loss": 0.5082502365112305,
+      "eval_num_fragments": 3.0,
+      "eval_poi_equal": 0.0021210782147591694,
+      "eval_poi_graph_edit_distance": 9.999999999999999e+63,
+      "eval_poi_graph_edit_distance_norm": 1.0,
+      "eval_poi_has_attachment_point(s)": 0.9996464869642068,
+      "eval_poi_heavy_atoms_difference": -1.581617322138754,
+      "eval_poi_heavy_atoms_difference_norm": -0.19857852436254525,
+      "eval_poi_tanimoto_similarity": 0.0,
+      "eval_poi_valid": 0.9996464869642068,
+      "eval_reassembly": 0.0,
+      "eval_reassembly_nostereo": 0.0,
+      "eval_runtime": 1485.1844,
+      "eval_samples_per_second": 7.619,
+      "eval_steps_per_second": 0.119,
+      "eval_tanimoto_similarity": 0.0,
+      "eval_valid": 0.9996464869642068,
+      "step": 7500
+    },
+    {
+      "epoch": 0.789110278161373,
+      "grad_norm": 0.2829979956150055,
+      "learning_rate": 0.00017553249516694252,
+      "loss": 0.1509,
+      "step": 8000
+    },
+    {
+      "epoch": 0.8384296705464589,
+      "grad_norm": 0.4774325489997864,
+      "learning_rate": 0.00017553249516694252,
+      "loss": 0.1483,
+      "step": 8500
+    },
+    {
+      "epoch": 0.8877490629315447,
+      "grad_norm": 0.4473247826099396,
+      "learning_rate": 0.00017553249516694252,
+      "loss": 0.1487,
+      "step": 9000
+    },
+    {
+      "epoch": 0.9370684553166305,
+      "grad_norm": 0.5797591209411621,
+      "learning_rate": 0.00017553249516694252,
+      "loss": 0.1435,
+      "step": 9500
+    },
+    {
+      "epoch": 0.9863878477017163,
+      "grad_norm": 0.8456087708473206,
+      "learning_rate": 0.00017553249516694252,
+      "loss": 0.1411,
+      "step": 10000
+    },
+    {
+      "epoch": 0.9863878477017163,
+      "eval_all_ligands_equal": 0.0,
+      "eval_e3_equal": 0.02483429076447194,
+      "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": 2.2069818824569154,
+      "eval_e3_heavy_atoms_difference_norm": 0.028085955508926997,
+      "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": 1.5678303137428193,
+      "eval_heavy_atoms_difference_norm": -0.009803369302753544,
+      "eval_linker_equal": 0.001855943437914273,
+      "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": -0.32832523199292973,
+      "eval_linker_heavy_atoms_difference_norm": -0.25687187670805983,
+      "eval_linker_tanimoto_similarity": 0.0,
+      "eval_linker_valid": 1.0,
+      "eval_loss": 0.558329701423645,
+      "eval_num_fragments": 3.0,
+      "eval_poi_equal": 0.001855943437914273,
+      "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": -0.3108263367211666,
+      "eval_poi_heavy_atoms_difference_norm": -0.15080735877161097,
+      "eval_poi_tanimoto_similarity": 0.0,
+      "eval_poi_valid": 1.0,
+      "eval_reassembly": 0.0,
+      "eval_reassembly_nostereo": 0.0,
+      "eval_runtime": 1427.9008,
+      "eval_samples_per_second": 7.924,
+      "eval_steps_per_second": 0.124,
+      "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=7-learning_rate=1.8e-04-warmup_ratio=0.100-min_lr=0.000-factor=0.710",
   "trial_params": {