Training in progress, step 55000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06bc14bbbd27d253e78bd89df250f8a3729fff02beb78d421639b61a114eebe7
+oid sha256:93519581a984b3faeda34e9c51ea07efcda77f7a9d84f527caa96e5b89bf10a9
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32d96311d632155e63ab79cdb6ae5d13eac2ccb218ce46d58a4f410d578c97c9
+oid sha256:6f6444aa8631df227f0ec6227d520da42c363645fbe759571e8f81c553923cf6
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eddbb822fd8c77685fb0b027be7260417141436b826497b6aee7db3cba27626a
+oid sha256:f2699a9b77fb475f94e0e7f2090ac73edfc720b8337803d7322ea61cd0cdd49e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:129967ad4aacd30894639b032d8517110a4963d1cc93db81c93bfda673142ba8
+oid sha256:a8da913cdb87fa0da659fbfc8e8d4a175dea1907bb6d7b316ea1a236f774834f
 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": 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": 2.504638484990372e-05,
       "loss": 0.0006,
       "step": 50000
+    },
+    {
+      "epoch": 4.9812586308936675,
+      "grad_norm": 0.015657415613532066,
+      "learning_rate": 2.4653303816212188e-05,
+      "loss": 0.0006,
+      "step": 50500
+    },
+    {
+      "epoch": 5.030578023278753,
+      "grad_norm": 0.009272584691643715,
+      "learning_rate": 2.42603084959539e-05,
+      "loss": 0.0006,
+      "step": 51000
+    },
+    {
+      "epoch": 5.079897415663839,
+      "grad_norm": 0.016377432271838188,
+      "learning_rate": 2.386749604906234e-05,
+      "loss": 0.0005,
+      "step": 51500
+    },
+    {
+      "epoch": 5.129216808048925,
+      "grad_norm": 0.02414529025554657,
+      "learning_rate": 2.3475748311231863e-05,
+      "loss": 0.0005,
+      "step": 52000
+    },
+    {
+      "epoch": 5.178536200434011,
+      "grad_norm": 0.023295147344470024,
+      "learning_rate": 2.3083592035157375e-05,
+      "loss": 0.0005,
+      "step": 52500
+    },
+    {
+      "epoch": 5.227855592819097,
+      "grad_norm": 0.020559698343276978,
+      "learning_rate": 2.2691909551163278e-05,
+      "loss": 0.0005,
+      "step": 53000
+    },
+    {
+      "epoch": 5.277174985204182,
+      "grad_norm": 0.022504296153783798,
+      "learning_rate": 2.2300797694611534e-05,
+      "loss": 0.0005,
+      "step": 53500
+    },
+    {
+      "epoch": 5.326494377589268,
+      "grad_norm": 0.006661570630967617,
+      "learning_rate": 2.191035315978832e-05,
+      "loss": 0.0005,
+      "step": 54000
+    },
+    {
+      "epoch": 5.375813769974354,
+      "grad_norm": 0.011046066880226135,
+      "learning_rate": 2.1520672475998373e-05,
+      "loss": 0.0005,
+      "step": 54500
+    },
+    {
+      "epoch": 5.425133162359439,
+      "grad_norm": 0.02395332045853138,
+      "learning_rate": 2.1131851983700107e-05,
+      "loss": 0.0005,
+      "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