Training in progress, step 25000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:835536a9f4bc9598d2aa3d301a8969869c1e49d0f59b9b2fd55cab35a3ffcfcf
+oid sha256:bf584d7532aca183ba3375c7e2b4cabba44bb42e2ada64266474944d71e8bc4b
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a29aea1f4bc620e4c56dc629ab7626d669e605a3ac2ec6a60c73ef081803e046
+oid sha256:2a5c2142f0e58a50a3708ce303ed8fdbdc0637809e5a24cca846334043ca8b38
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d17dc07ba223f477f407e44715d157a31fe9df81f7f77bc0d31d54494107c73d
+oid sha256:2d57b37b13c2760795173d6cc56195de8db4b64e0ea9a20349975e5a8a5a1457
 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": 1.9727756954034326,
+  "epoch": 2.465969619254291,
   "eval_steps": 2500,
-  "global_step": 20000,
+  "global_step": 25000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -413,6 +413,76 @@
       "learning_rate": 5e-05,
       "loss": 0.0019,
       "step": 20000
+    },
+    {
+      "epoch": 2.0220950877885184,
+      "grad_norm": 0.05095202848315239,
+      "learning_rate": 5e-05,
+      "loss": 0.0024,
+      "step": 20500
+    },
+    {
+      "epoch": 2.0714144801736043,
+      "grad_norm": 0.027557415887713432,
+      "learning_rate": 5e-05,
+      "loss": 0.0016,
+      "step": 21000
+    },
+    {
+      "epoch": 2.12073387255869,
+      "grad_norm": 0.04820004105567932,
+      "learning_rate": 5e-05,
+      "loss": 0.0016,
+      "step": 21500
+    },
+    {
+      "epoch": 2.170053264943776,
+      "grad_norm": 0.041186604648828506,
+      "learning_rate": 5e-05,
+      "loss": 0.0016,
+      "step": 22000
+    },
+    {
+      "epoch": 2.219372657328862,
+      "grad_norm": 0.028476761654019356,
+      "learning_rate": 5e-05,
+      "loss": 0.0016,
+      "step": 22500
+    },
+    {
+      "epoch": 2.2686920497139473,
+      "grad_norm": 0.045205824077129364,
+      "learning_rate": 5e-05,
+      "loss": 0.0016,
+      "step": 23000
+    },
+    {
+      "epoch": 2.318011442099033,
+      "grad_norm": 0.04366511106491089,
+      "learning_rate": 5e-05,
+      "loss": 0.0016,
+      "step": 23500
+    },
+    {
+      "epoch": 2.367330834484119,
+      "grad_norm": 0.022254638373851776,
+      "learning_rate": 5e-05,
+      "loss": 0.0016,
+      "step": 24000
+    },
+    {
+      "epoch": 2.416650226869205,
+      "grad_norm": 0.039716288447380066,
+      "learning_rate": 5e-05,
+      "loss": 0.0015,
+      "step": 24500
+    },
+    {
+      "epoch": 2.465969619254291,
+      "grad_norm": 0.055284593254327774,
+      "learning_rate": 5e-05,
+      "loss": 0.0015,
+      "step": 25000
     }
   ],
   "logging_steps": 500,
@@ -432,7 +502,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.746034901972567e+17,
+  "total_flos": 2.1826558457597645e+17,
   "train_batch_size": 128,
   "trial_name": null,
   "trial_params": null