Training in progress, step 25000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4970b6682a1c930084e40f6b66854251c8db1858d69b870ca1e393e61e954fbb
+oid sha256:4ca0d750d99e1c3abdda5023b44efb20fe341748524351bd9c2484fd4fb8a02a
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:849764d845446bd3d7144aa94ca0667e5c1b39746e443c98875eb8b189928c2b
+oid sha256:fdd4f7fabc73133f36f00dd9e92bf665c012f92cbca8392939d9c8d5b918fba6
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99e606ce353d140175992ac0b0aff4bee3d8fbdc73c16a9db59465a42c097743
+oid sha256:cf017d3eea6b57db19282f6eee29e54feb61f16eae3223ac38dc126b589dd724
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb3093310f6b86f18bebb2d480e5705bfd30aebf684148c9e831e07105b40020
+oid sha256:db80857564c7a8e724accbcdddf81bb1d07b553a317cc95d91866b45748053fd
 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": 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": 4.480913969818085e-06,
       "loss": 0.0011,
       "step": 20000
+    },
+    {
+      "epoch": 2.0220950877885184,
+      "grad_norm": 0.02433215267956257,
+      "learning_rate": 2.2082315395764165e-07,
+      "loss": 0.0009,
+      "step": 20500
+    },
+    {
+      "epoch": 2.0714144801736043,
+      "grad_norm": 0.04352913051843643,
+      "learning_rate": 4.855190843835337e-05,
+      "loss": 0.0041,
+      "step": 21000
+    },
+    {
+      "epoch": 2.12073387255869,
+      "grad_norm": 0.03815969452261925,
+      "learning_rate": 4.210905991658837e-05,
+      "loss": 0.0028,
+      "step": 21500
+    },
+    {
+      "epoch": 2.170053264943776,
+      "grad_norm": 0.020274870097637177,
+      "learning_rate": 3.1877402818861966e-05,
+      "loss": 0.0016,
+      "step": 22000
+    },
+    {
+      "epoch": 2.219372657328862,
+      "grad_norm": 0.021578455343842506,
+      "learning_rate": 2.0122741949596797e-05,
+      "loss": 0.0012,
+      "step": 22500
+    },
+    {
+      "epoch": 2.2686920497139473,
+      "grad_norm": 0.018344903364777565,
+      "learning_rate": 9.448151944460648e-06,
+      "loss": 0.001,
+      "step": 23000
+    },
+    {
+      "epoch": 2.318011442099033,
+      "grad_norm": 0.023422742262482643,
+      "learning_rate": 2.2175252881083937e-06,
+      "loss": 0.0009,
+      "step": 23500
+    },
+    {
+      "epoch": 2.367330834484119,
+      "grad_norm": 0.04089091718196869,
+      "learning_rate": 4.996791267927632e-05,
+      "loss": 0.0008,
+      "step": 24000
+    },
+    {
+      "epoch": 2.416650226869205,
+      "grad_norm": 0.040251534432172775,
+      "learning_rate": 4.663610541397389e-05,
+      "loss": 0.0039,
+      "step": 24500
+    },
+    {
+      "epoch": 2.465969619254291,
+      "grad_norm": 0.04687808081507683,
+      "learning_rate": 3.8511781678751205e-05,
+      "loss": 0.0018,
+      "step": 25000
     }
   ],
   "logging_steps": 500,
@@ -432,7 +502,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.7329296562502707e+17,
+  "total_flos": 2.1661693972804915e+17,
   "train_batch_size": 128,
   "trial_name": null,
   "trial_params": null