Training in progress, step 55000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe75c7d1d2a9fb1383fa16ca04fa9582f79bce9c2c6b619ccc5bf8f41a7349d3
+oid sha256:2ac0cc94f002a9b2de4003b50dc12b9040ae3e27bdbca22d780d51b88199614c
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c16c4ea2aeaf96ed945f3ff8d93677b434f48d1a77151570a2c01992d79bde54
+oid sha256:bdfa90c5490cac1bf800e23adbb848e931c94471254d21b4e0ebf5f49f539ba3
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cdbc5184733c39b403d000033558f016107ac570eaa5b3b5be67cc987ed4902
+oid sha256:4a0a71108ec81e8d23af17f0347ca933dbf48da5add452207f9012b1c9558bb0
 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": 4.931939238508582,
+  "epoch": 5.425133162359439,
   "eval_steps": 2500,
-  "global_step": 50000,
+  "global_step": 55000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -833,6 +833,76 @@
       "learning_rate": 5e-05,
       "loss": 0.0008,
       "step": 50000
+    },
+    {
+      "epoch": 4.9812586308936675,
+      "grad_norm": 0.024761617183685303,
+      "learning_rate": 5e-05,
+      "loss": 0.0012,
+      "step": 50500
+    },
+    {
+      "epoch": 5.030578023278753,
+      "grad_norm": 0.02904408425092697,
+      "learning_rate": 5e-05,
+      "loss": 0.0012,
+      "step": 51000
+    },
+    {
+      "epoch": 5.079897415663839,
+      "grad_norm": 0.026762697845697403,
+      "learning_rate": 5e-05,
+      "loss": 0.0009,
+      "step": 51500
+    },
+    {
+      "epoch": 5.129216808048925,
+      "grad_norm": 0.02316400595009327,
+      "learning_rate": 5e-05,
+      "loss": 0.0007,
+      "step": 52000
+    },
+    {
+      "epoch": 5.178536200434011,
+      "grad_norm": 0.01717398874461651,
+      "learning_rate": 5e-05,
+      "loss": 0.0006,
+      "step": 52500
+    },
+    {
+      "epoch": 5.227855592819097,
+      "grad_norm": 0.056246623396873474,
+      "learning_rate": 5e-05,
+      "loss": 0.0008,
+      "step": 53000
+    },
+    {
+      "epoch": 5.277174985204182,
+      "grad_norm": 0.030238812789320946,
+      "learning_rate": 5e-05,
+      "loss": 0.0008,
+      "step": 53500
+    },
+    {
+      "epoch": 5.326494377589268,
+      "grad_norm": 0.021439244970679283,
+      "learning_rate": 5e-05,
+      "loss": 0.0008,
+      "step": 54000
+    },
+    {
+      "epoch": 5.375813769974354,
+      "grad_norm": 0.01937209442257881,
+      "learning_rate": 5e-05,
+      "loss": 0.0008,
+      "step": 54500
+    },
+    {
+      "epoch": 5.425133162359439,
+      "grad_norm": 0.02833039127290249,
+      "learning_rate": 5e-05,
+      "loss": 0.0008,
+      "step": 55000
     }
   ],
   "logging_steps": 500,
@@ -852,7 +922,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.3642997987236454e+17,
+  "total_flos": 4.800723300014085e+17,
   "train_batch_size": 128,
   "trial_name": null,
   "trial_params": null