Training in progress, step 50000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0c6cca2c6a9ac2adb2075297cbca19d4215769af04fc3b72aa6f7ffdaf1fbc7
+oid sha256:617b674267e2191b4addb7b6174d2a7b3b6be5e15b623c52cb202c65d1300fbc
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef0ddd76d8b4525cbbad4aefefb74d4c462f82436fa56c207a7d0c37484c235e
+oid sha256:fd83813d9dbd25af61d05bbd32798b812892a658328f22ee06646b799fb7b363
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec0ea160082cc39ac30942ebcddc73a0bcdea69205d0069eef8edae7fc1a9d72
+oid sha256:11d87c5b913e7a5b1cabf70de94edcbb67847e2292b7550ae53ff3dda1196c2a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc36b8ae22f6cb108858cc00165c8e8672f7e966fabf0d057ddaa95d9238a73a
+oid sha256:99fcfbd1683ab8df6f870c07c1a59edbf30ebbec5a46d6d0341019ab14692cb0
 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": 4.438745314657724,
+  "epoch": 4.931939238508582,
   "eval_steps": 2500,
-  "global_step": 45000,
+  "global_step": 50000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -763,6 +763,76 @@
       "learning_rate": 3.534411131835637e-05,
       "loss": 0.001,
       "step": 45000
+    },
+    {
+      "epoch": 4.48806470704281,
+      "grad_norm": 0.019216470420360565,
+      "learning_rate": 2.3789123953690796e-05,
+      "loss": 0.0007,
+      "step": 45500
+    },
+    {
+      "epoch": 4.537384099427895,
+      "grad_norm": 0.02267817035317421,
+      "learning_rate": 1.2502285603117597e-05,
+      "loss": 0.0005,
+      "step": 46000
+    },
+    {
+      "epoch": 4.5867034918129805,
+      "grad_norm": 0.01543174497783184,
+      "learning_rate": 3.983071407096459e-06,
+      "loss": 0.0005,
+      "step": 46500
+    },
+    {
+      "epoch": 4.636022884198066,
+      "grad_norm": 0.020069127902388573,
+      "learning_rate": 1.180649630719205e-07,
+      "loss": 0.0004,
+      "step": 47000
+    },
+    {
+      "epoch": 4.685342276583152,
+      "grad_norm": 0.06315533071756363,
+      "learning_rate": 4.8236826412442815e-05,
+      "loss": 0.0016,
+      "step": 47500
+    },
+    {
+      "epoch": 4.734661668968238,
+      "grad_norm": 0.05815032124519348,
+      "learning_rate": 4.1445912722173056e-05,
+      "loss": 0.0011,
+      "step": 48000
+    },
+    {
+      "epoch": 4.783981061353324,
+      "grad_norm": 0.03868298977613449,
+      "learning_rate": 3.103609665799435e-05,
+      "loss": 0.0009,
+      "step": 48500
+    },
+    {
+      "epoch": 4.83330045373841,
+      "grad_norm": 0.026825400069355965,
+      "learning_rate": 1.9271702808963772e-05,
+      "loss": 0.0006,
+      "step": 49000
+    },
+    {
+      "epoch": 4.882619846123496,
+      "grad_norm": 0.022513261064887047,
+      "learning_rate": 8.775842802754727e-06,
+      "loss": 0.0005,
+      "step": 49500
+    },
+    {
+      "epoch": 4.931939238508582,
+      "grad_norm": 0.04292171820998192,
+      "learning_rate": 1.8728292899447775e-06,
+      "loss": 0.0004,
+      "step": 50000
     }
   ],
   "logging_steps": 500,
@@ -782,7 +852,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.898212104814858e+17,
+  "total_flos": 4.3312528608288154e+17,
   "train_batch_size": 128,
   "trial_name": null,
   "trial_params": null