Training in progress, step 40000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:680cdd8ce09ed81d5904b52f855191e264cb3a8777e419668f407b84fc55713a
+oid sha256:503ce751da80aa8b1f118a861d5757c844ce8de1db073fef17acad2029b59e2b
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe583685246694473b81b6159749d52ae9755ca3bd5d94c328cf706a1d1198e0
+oid sha256:6fbaedfb0a4123dcead5a29fb791a66763b1c12ca90eb39e7c861a4cb61e314d
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86e4d6f5632dbc00793287b2f22a557709a70a15c41fc36f8e72a42acf0f499d
+oid sha256:39417990b3af4b754d49ef8161883cbdefa4e1231e6e279b71d13d553fe650cf
 size 14244

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.5455028328611898,
   "best_model_checkpoint": "/mimer/NOBACKUP/groups/naiss2023-6-290/stefano/models//PROTAC-Splitter-EncoderDecoder-lr_reduce-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": 5e-05,
       "loss": 0.0014,
       "step": 35000
+    },
+    {
+      "epoch": 3.501676859341093,
+      "grad_norm": 0.021409129723906517,
+      "learning_rate": 5e-05,
+      "loss": 0.0014,
+      "step": 35500
+    },
+    {
+      "epoch": 3.5509962517261786,
+      "grad_norm": 0.01704758033156395,
+      "learning_rate": 5e-05,
+      "loss": 0.001,
+      "step": 36000
+    },
+    {
+      "epoch": 3.6003156441112645,
+      "grad_norm": 0.03872734308242798,
+      "learning_rate": 5e-05,
+      "loss": 0.001,
+      "step": 36500
+    },
+    {
+      "epoch": 3.6496350364963503,
+      "grad_norm": 0.030823158100247383,
+      "learning_rate": 5e-05,
+      "loss": 0.0012,
+      "step": 37000
+    },
+    {
+      "epoch": 3.698954428881436,
+      "grad_norm": 0.03794977068901062,
+      "learning_rate": 5e-05,
+      "loss": 0.001,
+      "step": 37500
+    },
+    {
+      "epoch": 3.748273821266522,
+      "grad_norm": 0.042292773723602295,
+      "learning_rate": 5e-05,
+      "loss": 0.0013,
+      "step": 38000
+    },
+    {
+      "epoch": 3.797593213651608,
+      "grad_norm": 0.040720898658037186,
+      "learning_rate": 5e-05,
+      "loss": 0.0015,
+      "step": 38500
+    },
+    {
+      "epoch": 3.8469126060366934,
+      "grad_norm": 0.017985910177230835,
+      "learning_rate": 5e-05,
+      "loss": 0.001,
+      "step": 39000
+    },
+    {
+      "epoch": 3.8962319984217793,
+      "grad_norm": 0.04241044074296951,
+      "learning_rate": 5e-05,
+      "loss": 0.0009,
+      "step": 39500
+    },
+    {
+      "epoch": 3.945551390806865,
+      "grad_norm": 0.02607624977827072,
+      "learning_rate": 5e-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