Training in progress, step 45000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a6c87098dee6f04ae2bceaaa2c0f617952d030c4e279874a01eb06fdd42c41e
+oid sha256:87fd26095cc52b1b1fcb61aa241c45efbc7b650471ca5a054f91cf66241e51c2
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5faf6a3e2939d75a948aba9447459c4e343a50ef20460c74841f4d26332215cf
+oid sha256:c07bb32cd46c9fb53458473e6c056fc27d5f5b5b0c76311e6ffe2ee4772ef387
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eeb57d6a99029070321c5cbe53e1de318ca2dbd673dc5c838164e987bf464c4d
+oid sha256:482495ef335bd0cb4d91c4031a90b31c1acd8f32c3166de3bdbd2f81cf638e6a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08e1d8ba2414508e50f3f6e207e18b230dc5f1405db079b8fc4d29a0585a5ea6
+oid sha256:950318ed157dfaa6d9d1d461c0e1fb839308bf3fb8549cac2587ce9ecd744d04
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.5477160056657224,
   "best_model_checkpoint": "/mimer/NOBACKUP/groups/naiss2023-6-290/stefano/models//PROTAC-Splitter-EncoderDecoder-lr_cosine-opt25/checkpoint-10000",
-  "epoch": 3.945551390806865,
+  "epoch": 4.438745314657724,
   "eval_steps": 2500,
-  "global_step": 40000,
+  "global_step": 45000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -693,6 +693,76 @@
       "learning_rate": 3.27755039594663e-05,
       "loss": 0.0006,
       "step": 40000
+    },
+    {
+      "epoch": 3.994870783191951,
+      "grad_norm": 0.028563622385263443,
+      "learning_rate": 3.2400962082482306e-05,
+      "loss": 0.0007,
+      "step": 40500
+    },
+    {
+      "epoch": 4.044190175577037,
+      "grad_norm": 0.012048379518091679,
+      "learning_rate": 3.2024590471283946e-05,
+      "loss": 0.0006,
+      "step": 41000
+    },
+    {
+      "epoch": 4.093509567962123,
+      "grad_norm": 0.01336103118956089,
+      "learning_rate": 3.164648217593777e-05,
+      "loss": 0.0006,
+      "step": 41500
+    },
+    {
+      "epoch": 4.142828960347209,
+      "grad_norm": 0.04073134437203407,
+      "learning_rate": 3.1266730675869434e-05,
+      "loss": 0.0006,
+      "step": 42000
+    },
+    {
+      "epoch": 4.1921483527322945,
+      "grad_norm": 0.03634357079863548,
+      "learning_rate": 3.088542985675283e-05,
+      "loss": 0.0006,
+      "step": 42500
+    },
+    {
+      "epoch": 4.24146774511738,
+      "grad_norm": 0.03682945668697357,
+      "learning_rate": 3.0502673987298837e-05,
+      "loss": 0.0007,
+      "step": 43000
+    },
+    {
+      "epoch": 4.290787137502466,
+      "grad_norm": 0.030003152787685394,
+      "learning_rate": 3.0119327223166655e-05,
+      "loss": 0.0007,
+      "step": 43500
+    },
+    {
+      "epoch": 4.340106529887552,
+      "grad_norm": 0.025118093937635422,
+      "learning_rate": 2.973471986909034e-05,
+      "loss": 0.0008,
+      "step": 44000
+    },
+    {
+      "epoch": 4.389425922272638,
+      "grad_norm": 0.01078966073691845,
+      "learning_rate": 2.9348172431675086e-05,
+      "loss": 0.0005,
+      "step": 44500
+    },
+    {
+      "epoch": 4.438745314657724,
+      "grad_norm": 0.020486511290073395,
+      "learning_rate": 2.8960549998903897e-05,
+      "loss": 0.0005,
+      "step": 45000
     }
   ],
   "logging_steps": 500,
@@ -712,7 +782,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.465342568466058e+17,
+  "total_flos": 3.898212104814858e+17,
   "train_batch_size": 128,
   "trial_name": null,
   "trial_params": null