Training in progress, step 60000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7492c7bf922a3eb50cfa4081fec5e81f8de3ef95639132c619339ba07befabc1
+oid sha256:3c192e3fb64b6d2215ee80a1e81d4a7b40e6e392bdc630777c1cce4c375dfca9
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfd83dccf1b07606afabe5fdded3e70c80b15a1881b1ff52715b129c8766202f
+oid sha256:b7b7fd64d9431210526488e5610bbb5649e83d0d57266f9036be41a3effe895d
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2915ca4a6fbfe4a8c8b438dcf3502a8e4e6cc49eb1760c5072daaa5ca3a37cb
+oid sha256:e889596228db17663ecb13b2fce77d8ba3c8a669b35fa2635f61decf3f846c99
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:409aa698ded6143db955deb4e5b7664a1227e243cdfc2f5415f3c7211cca6584
+oid sha256:ef1d74469a9031736961603cae781746a8ba961151ce2a3fac12b55ae58cb63e
 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": 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": 3.3652926426937384e-05,
       "loss": 0.0008,
       "step": 55000
+    },
+    {
+      "epoch": 5.474452554744525,
+      "grad_norm": 0.007345585618168116,
+      "learning_rate": 2.1967237218238608e-05,
+      "loss": 0.0006,
+      "step": 55500
+    },
+    {
+      "epoch": 5.523771947129611,
+      "grad_norm": 0.016498006880283356,
+      "learning_rate": 1.0953154614018291e-05,
+      "loss": 0.0005,
+      "step": 56000
+    },
+    {
+      "epoch": 5.573091339514697,
+      "grad_norm": 0.023072505369782448,
+      "learning_rate": 3.049751879006049e-06,
+      "loss": 0.0004,
+      "step": 56500
+    },
+    {
+      "epoch": 5.622410731899783,
+      "grad_norm": 0.018147263675928116,
+      "learning_rate": 7.823803658785211e-09,
+      "loss": 0.0004,
+      "step": 57000
+    },
+    {
+      "epoch": 5.671730124284869,
+      "grad_norm": 0.03701692819595337,
+      "learning_rate": 4.752127641360646e-05,
+      "loss": 0.0017,
+      "step": 57500
+    },
+    {
+      "epoch": 5.721049516669955,
+      "grad_norm": 0.03156555816531181,
+      "learning_rate": 4.006363587728823e-05,
+      "loss": 0.0009,
+      "step": 58000
+    },
+    {
+      "epoch": 5.7703689090550405,
+      "grad_norm": 0.003923078067600727,
+      "learning_rate": 2.9270146786152846e-05,
+      "loss": 0.0006,
+      "step": 58500
+    },
+    {
+      "epoch": 5.819688301440126,
+      "grad_norm": 0.012611697427928448,
+      "learning_rate": 1.7531031877885103e-05,
+      "loss": 0.0005,
+      "step": 59000
+    },
+    {
+      "epoch": 5.869007693825212,
+      "grad_norm": 0.008357984013855457,
+      "learning_rate": 7.445923128495683e-06,
+      "loss": 0.0004,
+      "step": 59500
+    },
+    {
+      "epoch": 5.918327086210298,
+      "grad_norm": 0.01403570082038641,
+      "learning_rate": 1.2481721485038734e-06,
+      "loss": 0.0004,
+      "step": 60000
     }
   ],
   "logging_steps": 500,
@@ -922,7 +992,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.7645419624832256e+17,
+  "total_flos": 5.1976814397455616e+17,
   "train_batch_size": 128,
   "trial_name": null,
   "trial_params": null