Training in progress, step 55000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:617b674267e2191b4addb7b6174d2a7b3b6be5e15b623c52cb202c65d1300fbc
+oid sha256:7492c7bf922a3eb50cfa4081fec5e81f8de3ef95639132c619339ba07befabc1
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd83813d9dbd25af61d05bbd32798b812892a658328f22ee06646b799fb7b363
+oid sha256:bfd83dccf1b07606afabe5fdded3e70c80b15a1881b1ff52715b129c8766202f
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11d87c5b913e7a5b1cabf70de94edcbb67847e2292b7550ae53ff3dda1196c2a
+oid sha256:a2915ca4a6fbfe4a8c8b438dcf3502a8e4e6cc49eb1760c5072daaa5ca3a37cb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99fcfbd1683ab8df6f870c07c1a59edbf30ebbec5a46d6d0341019ab14692cb0
+oid sha256:409aa698ded6143db955deb4e5b7664a1227e243cdfc2f5415f3c7211cca6584
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.5462110481586402,
   "best_model_checkpoint": "/mimer/NOBACKUP/groups/naiss2023-6-290/stefano/models//PROTAC-Splitter-EncoderDecoder-lr_cosine_restarts-opt25/checkpoint-10000",
-  "epoch": 4.931939238508582,
+  "epoch": 5.425133162359439,
   "eval_steps": 2500,
-  "global_step": 50000,
+  "global_step": 55000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -833,6 +833,76 @@
       "learning_rate": 1.8728292899447775e-06,
       "loss": 0.0004,
       "step": 50000
+    },
+    {
+      "epoch": 4.9812586308936675,
+      "grad_norm": 0.09393975138664246,
+      "learning_rate": 4.9908662458888896e-05,
+      "loss": 0.0005,
+      "step": 50500
+    },
+    {
+      "epoch": 5.030578023278753,
+      "grad_norm": 0.019034981727600098,
+      "learning_rate": 4.61993375092424e-05,
+      "loss": 0.0019,
+      "step": 51000
+    },
+    {
+      "epoch": 5.079897415663839,
+      "grad_norm": 0.008647086098790169,
+      "learning_rate": 3.7791398273089494e-05,
+      "loss": 0.0009,
+      "step": 51500
+    },
+    {
+      "epoch": 5.129216808048925,
+      "grad_norm": 0.013575778342783451,
+      "learning_rate": 2.655079846342193e-05,
+      "loss": 0.0006,
+      "step": 52000
+    },
+    {
+      "epoch": 5.178536200434011,
+      "grad_norm": 0.009713593870401382,
+      "learning_rate": 1.496677367620188e-05,
+      "loss": 0.0005,
+      "step": 52500
+    },
+    {
+      "epoch": 5.227855592819097,
+      "grad_norm": 0.024831971153616905,
+      "learning_rate": 5.604611114346173e-06,
+      "loss": 0.0004,
+      "step": 53000
+    },
+    {
+      "epoch": 5.277174985204182,
+      "grad_norm": 0.005304230377078056,
+      "learning_rate": 5.37565648481686e-07,
+      "loss": 0.0004,
+      "step": 53500
+    },
+    {
+      "epoch": 5.326494377589268,
+      "grad_norm": 0.055664077401161194,
+      "learning_rate": 4.911226335360363e-05,
+      "loss": 0.0012,
+      "step": 54000
+    },
+    {
+      "epoch": 5.375813769974354,
+      "grad_norm": 0.050345055758953094,
+      "learning_rate": 4.342242140793571e-05,
+      "loss": 0.0011,
+      "step": 54500
+    },
+    {
+      "epoch": 5.425133162359439,
+      "grad_norm": 0.015438569709658623,
+      "learning_rate": 3.3652926426937384e-05,
+      "loss": 0.0008,
+      "step": 55000
     }
   ],
   "logging_steps": 500,
@@ -852,7 +922,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.3312528608288154e+17,
+  "total_flos": 4.7645419624832256e+17,
   "train_batch_size": 128,
   "trial_name": null,
   "trial_params": null