Training in progress, step 60000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93519581a984b3faeda34e9c51ea07efcda77f7a9d84f527caa96e5b89bf10a9
+oid sha256:27d41ba63ba593f2cfce363802b440927332dce61aafea879db261ae77cd52d0
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f6444aa8631df227f0ec6227d520da42c363645fbe759571e8f81c553923cf6
+oid sha256:d742eeb8d925c1a166af3e09a3e0fd4ebadea870bd4919c2660b4864e7654fcd
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2699a9b77fb475f94e0e7f2090ac73edfc720b8337803d7322ea61cd0cdd49e
+oid sha256:ac455c3f391185463b9c69f4fb71b00665f813b40d3fca5439822d6487ecd3b5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8da913cdb87fa0da659fbfc8e8d4a175dea1907bb6d7b316ea1a236f774834f
+oid sha256:8abde5ea6d7508710178712fe236e737431b4a593f0d18f03c2b4dfe63cb7155
 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": 5.425133162359439,
+  "epoch": 5.918327086210298,
   "eval_steps": 2500,
-  "global_step": 55000,
+  "global_step": 60000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -903,6 +903,76 @@
       "learning_rate": 2.1131851983700107e-05,
       "loss": 0.0005,
       "step": 55000
+    },
+    {
+      "epoch": 5.474452554744525,
+      "grad_norm": 0.006757025141268969,
+      "learning_rate": 2.074398781068747e-05,
+      "loss": 0.0005,
+      "step": 55500
+    },
+    {
+      "epoch": 5.523771947129611,
+      "grad_norm": 0.01942395232617855,
+      "learning_rate": 2.0357175848324307e-05,
+      "loss": 0.0005,
+      "step": 56000
+    },
+    {
+      "epoch": 5.573091339514697,
+      "grad_norm": 0.0312858484685421,
+      "learning_rate": 1.997228184710801e-05,
+      "loss": 0.0005,
+      "step": 56500
+    },
+    {
+      "epoch": 5.622410731899783,
+      "grad_norm": 0.013257316313683987,
+      "learning_rate": 1.958785833460854e-05,
+      "loss": 0.0005,
+      "step": 57000
+    },
+    {
+      "epoch": 5.671730124284869,
+      "grad_norm": 0.010021144524216652,
+      "learning_rate": 1.9204772861767664e-05,
+      "loss": 0.0005,
+      "step": 57500
+    },
+    {
+      "epoch": 5.721049516669955,
+      "grad_norm": 0.010143189691007137,
+      "learning_rate": 1.8823881951300727e-05,
+      "loss": 0.0005,
+      "step": 58000
+    },
+    {
+      "epoch": 5.7703689090550405,
+      "grad_norm": 0.028758643195033073,
+      "learning_rate": 1.844375318521728e-05,
+      "loss": 0.0005,
+      "step": 58500
+    },
+    {
+      "epoch": 5.819688301440126,
+      "grad_norm": 0.01780054345726967,
+      "learning_rate": 1.8065245315036443e-05,
+      "loss": 0.0005,
+      "step": 59000
+    },
+    {
+      "epoch": 5.869007693825212,
+      "grad_norm": 0.007259385660290718,
+      "learning_rate": 1.768845191897044e-05,
+      "loss": 0.0005,
+      "step": 59500
+    },
+    {
+      "epoch": 5.918327086210298,
+      "grad_norm": 0.014262279495596886,
+      "learning_rate": 1.7313466151363385e-05,
+      "loss": 0.0004,
+      "step": 60000
     }
   ],
   "logging_steps": 500,
@@ -922,7 +992,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.800723300014085e+17,
+  "total_flos": 5.2375401437785344e+17,
   "train_batch_size": 128,
   "trial_name": null,
   "trial_params": null