Training in progress, step 30000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf584d7532aca183ba3375c7e2b4cabba44bb42e2ada64266474944d71e8bc4b
+oid sha256:847704143a8fe1bda65db1fe2c65f7a5566407d3fa081a0f600bf66f16b8b3a0
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a5c2142f0e58a50a3708ce303ed8fdbdc0637809e5a24cca846334043ca8b38
+oid sha256:c5957f98f8279a93ad8e35cd4746546f5160d187ed7070c5aa9bbdb47408fe1c
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d57b37b13c2760795173d6cc56195de8db4b64e0ea9a20349975e5a8a5a1457
+oid sha256:c65c2745f22d1c4db409b96f64b6f71c3a2ee8bc2f8c7ff26a84d73ab1a44cb8
 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": 2.465969619254291,
+  "epoch": 2.959163543105149,
   "eval_steps": 2500,
-  "global_step": 25000,
+  "global_step": 30000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -483,6 +483,76 @@
       "learning_rate": 5e-05,
       "loss": 0.0015,
       "step": 25000
+    },
+    {
+      "epoch": 2.5152890116393767,
+      "grad_norm": 0.045403581112623215,
+      "learning_rate": 5e-05,
+      "loss": 0.0015,
+      "step": 25500
+    },
+    {
+      "epoch": 2.5646084040244626,
+      "grad_norm": 0.059790823608636856,
+      "learning_rate": 5e-05,
+      "loss": 0.0018,
+      "step": 26000
+    },
+    {
+      "epoch": 2.6139277964095484,
+      "grad_norm": 0.05007553473114967,
+      "learning_rate": 5e-05,
+      "loss": 0.0015,
+      "step": 26500
+    },
+    {
+      "epoch": 2.6632471887946343,
+      "grad_norm": 0.03945387527346611,
+      "learning_rate": 5e-05,
+      "loss": 0.0014,
+      "step": 27000
+    },
+    {
+      "epoch": 2.7125665811797197,
+      "grad_norm": 0.033401645720005035,
+      "learning_rate": 5e-05,
+      "loss": 0.0013,
+      "step": 27500
+    },
+    {
+      "epoch": 2.7618859735648056,
+      "grad_norm": 0.05006084218621254,
+      "learning_rate": 5e-05,
+      "loss": 0.0013,
+      "step": 28000
+    },
+    {
+      "epoch": 2.8112053659498915,
+      "grad_norm": 0.04564574733376503,
+      "learning_rate": 5e-05,
+      "loss": 0.0014,
+      "step": 28500
+    },
+    {
+      "epoch": 2.8605247583349773,
+      "grad_norm": 0.0373481847345829,
+      "learning_rate": 5e-05,
+      "loss": 0.0013,
+      "step": 29000
+    },
+    {
+      "epoch": 2.909844150720063,
+      "grad_norm": 0.030000342056155205,
+      "learning_rate": 5e-05,
+      "loss": 0.0019,
+      "step": 29500
+    },
+    {
+      "epoch": 2.959163543105149,
+      "grad_norm": 0.012932154349982738,
+      "learning_rate": 5e-05,
+      "loss": 0.0021,
+      "step": 30000
     }
   ],
   "logging_steps": 500,
@@ -502,7 +572,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.1826558457597645e+17,
+  "total_flos": 2.619102484842793e+17,
   "train_batch_size": 128,
   "trial_name": null,
   "trial_params": null