Training in progress, step 45000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3df87380109d29dca4926961e9f97b620aee35f53d36656b38807372b537c9be
+oid sha256:5e76e2b1a2a56e66260a8b24222402fb6411337a94fc1ff21dd2fed0f6176b3e
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5fc238c5d795a910b52830af54cc0780bbea05ab4a8c991e81b09a6c2de7e3b
+oid sha256:c90a12cb152d8a5960479824e00fe42bc60c63a3a82282630a1fa6788db5ca6a
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0963f4ce0cdba7b48e5ad52354a99a0b710c9dba5d5be3f901641a7087746ca
+oid sha256:af53b8b54dc8f23640a2242053c5d32aa1e77f56497336f222b5262feb7ef177
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:595e7bd6b84a3e5df0100574e8bff7a6926e9fbf535eeac8a208de6027ce6ce4
+oid sha256:9299d1257fb2340390546c30a874d076b53bb55c63dc6155e353a5f573ba664d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.5389518413597734,
   "best_model_checkpoint": "/mimer/NOBACKUP/groups/naiss2023-6-290/stefano/models//PROTAC-Splitter-EncoderDecoder-lr_cosine-opt25-rand-smiles/checkpoint-10000",
-  "epoch": 3.945551390806865,
+  "epoch": 4.438745314657724,
   "eval_steps": 2500,
-  "global_step": 40000,
+  "global_step": 45000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -693,6 +693,76 @@
       "learning_rate": 3.2774009559667783e-05,
       "loss": 0.001,
       "step": 40000
+    },
+    {
+      "epoch": 3.994870783191951,
+      "grad_norm": 0.018639806658029556,
+      "learning_rate": 3.239946017898311e-05,
+      "loss": 0.0009,
+      "step": 40500
+    },
+    {
+      "epoch": 4.044190175577037,
+      "grad_norm": 0.026381010189652443,
+      "learning_rate": 3.202308143539852e-05,
+      "loss": 0.0008,
+      "step": 41000
+    },
+    {
+      "epoch": 4.093509567962123,
+      "grad_norm": 0.025508331134915352,
+      "learning_rate": 3.164572428162694e-05,
+      "loss": 0.0007,
+      "step": 41500
+    },
+    {
+      "epoch": 4.142828960347209,
+      "grad_norm": 0.015003887936472893,
+      "learning_rate": 3.1265969589091056e-05,
+      "loss": 0.0008,
+      "step": 42000
+    },
+    {
+      "epoch": 4.1921483527322945,
+      "grad_norm": 0.02331295795738697,
+      "learning_rate": 3.0884665765669805e-05,
+      "loss": 0.0008,
+      "step": 42500
+    },
+    {
+      "epoch": 4.24146774511738,
+      "grad_norm": 0.01973959244787693,
+      "learning_rate": 3.0501907080816822e-05,
+      "loss": 0.0008,
+      "step": 43000
+    },
+    {
+      "epoch": 4.290787137502466,
+      "grad_norm": 0.027150608599185944,
+      "learning_rate": 3.0118557695949296e-05,
+      "loss": 0.0008,
+      "step": 43500
+    },
+    {
+      "epoch": 4.340106529887552,
+      "grad_norm": 0.02721910923719406,
+      "learning_rate": 2.9733175947482144e-05,
+      "loss": 0.0007,
+      "step": 44000
+    },
+    {
+      "epoch": 4.389425922272638,
+      "grad_norm": 0.01915474608540535,
+      "learning_rate": 2.9346624019533298e-05,
+      "loss": 0.0008,
+      "step": 44500
+    },
+    {
+      "epoch": 4.438745314657724,
+      "grad_norm": 0.01952786184847355,
+      "learning_rate": 2.8958997479041255e-05,
+      "loss": 0.0008,
+      "step": 45000
     }
   ],
   "logging_steps": 500,
@@ -712,7 +782,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.4915036992864614e+17,
+  "total_flos": 3.927828479328522e+17,
   "train_batch_size": 128,
   "trial_name": null,
   "trial_params": null