Training in progress, step 40000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:039842f075c59d724d698a37730d17724d4fd364d3e15cc20b3f1179fde1bca8
+oid sha256:3df87380109d29dca4926961e9f97b620aee35f53d36656b38807372b537c9be
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89eeaf45dca11e93dc975549990f3cbcb0ebdaffb489fed2b2340133a55bedd8
+oid sha256:f5fc238c5d795a910b52830af54cc0780bbea05ab4a8c991e81b09a6c2de7e3b
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f37fe3424153bca4b7fc59f99bd2c0b98d90aaf8d45d5b05abebae1157a8e7e
+oid sha256:b0963f4ce0cdba7b48e5ad52354a99a0b710c9dba5d5be3f901641a7087746ca
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd12236a2b04dcc8172c63d077f003702ceca140fc00b62558c7c08cdf884e4b
+oid sha256:595e7bd6b84a3e5df0100574e8bff7a6926e9fbf535eeac8a208de6027ce6ce4
 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": 3.4523574669560073,
+  "epoch": 3.945551390806865,
   "eval_steps": 2500,
-  "global_step": 35000,
+  "global_step": 40000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -623,6 +623,76 @@
       "learning_rate": 3.639806991778405e-05,
       "loss": 0.0012,
       "step": 35000
+    },
+    {
+      "epoch": 3.501676859341093,
+      "grad_norm": 0.027150381356477737,
+      "learning_rate": 3.6046815733494614e-05,
+      "loss": 0.0011,
+      "step": 35500
+    },
+    {
+      "epoch": 3.5509962517261786,
+      "grad_norm": 0.034229960292577744,
+      "learning_rate": 3.5692830453371675e-05,
+      "loss": 0.001,
+      "step": 36000
+    },
+    {
+      "epoch": 3.6003156441112645,
+      "grad_norm": 0.04263359308242798,
+      "learning_rate": 3.533620159292621e-05,
+      "loss": 0.001,
+      "step": 36500
+    },
+    {
+      "epoch": 3.6496350364963503,
+      "grad_norm": 0.026501759886741638,
+      "learning_rate": 3.497701732123957e-05,
+      "loss": 0.0011,
+      "step": 37000
+    },
+    {
+      "epoch": 3.698954428881436,
+      "grad_norm": 0.014317413792014122,
+      "learning_rate": 3.4615366439165435e-05,
+      "loss": 0.001,
+      "step": 37500
+    },
+    {
+      "epoch": 3.748273821266522,
+      "grad_norm": 0.04115162417292595,
+      "learning_rate": 3.425133835737574e-05,
+      "loss": 0.001,
+      "step": 38000
+    },
+    {
+      "epoch": 3.797593213651608,
+      "grad_norm": 0.01732572540640831,
+      "learning_rate": 3.388502307425566e-05,
+      "loss": 0.0011,
+      "step": 38500
+    },
+    {
+      "epoch": 3.8469126060366934,
+      "grad_norm": 0.02579200640320778,
+      "learning_rate": 3.3516511153653423e-05,
+      "loss": 0.0009,
+      "step": 39000
+    },
+    {
+      "epoch": 3.8962319984217793,
+      "grad_norm": 0.023984914645552635,
+      "learning_rate": 3.314663697789466e-05,
+      "loss": 0.0009,
+      "step": 39500
+    },
+    {
+      "epoch": 3.945551390806865,
+      "grad_norm": 0.05176176130771637,
+      "learning_rate": 3.2774009559667783e-05,
+      "loss": 0.001,
+      "step": 40000
     }
   ],
   "logging_steps": 500,
@@ -642,7 +712,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.055328543636475e+17,
+  "total_flos": 3.4915036992864614e+17,
   "train_batch_size": 128,
   "trial_name": null,
   "trial_params": null