Training in progress, step 30000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ca0d750d99e1c3abdda5023b44efb20fe341748524351bd9c2484fd4fb8a02a
+oid sha256:0da757dae7426ef048cb05007a9e8cc866c7809f526038bb402f16db5d389611
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdd4f7fabc73133f36f00dd9e92bf665c012f92cbca8392939d9c8d5b918fba6
+oid sha256:bf5ca0119d5695b7e96fe99dee15af21c07ac5cb203da9ebad40c75be6b9c6e8
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf017d3eea6b57db19282f6eee29e54feb61f16eae3223ac38dc126b589dd724
+oid sha256:25d275e5bd5686989d2ea4200feefdfb83eea3830cac3cc0405b8c50796be68a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db80857564c7a8e724accbcdddf81bb1d07b553a317cc95d91866b45748053fd
+oid sha256:eb270de604813702a7f44531d8515d6c4a3e260cf1bf92145b70cf4f160804ba
 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": 2.465969619254291,
+  "epoch": 2.959163543105149,
   "eval_steps": 2500,
-  "global_step": 25000,
+  "global_step": 30000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -483,6 +483,76 @@
       "learning_rate": 3.8511781678751205e-05,
       "loss": 0.0018,
       "step": 25000
+    },
+    {
+      "epoch": 2.5152890116393767,
+      "grad_norm": 0.053063150495290756,
+      "learning_rate": 2.739526815925299e-05,
+      "loss": 0.0013,
+      "step": 25500
+    },
+    {
+      "epoch": 2.5646084040244626,
+      "grad_norm": 0.026560774073004723,
+      "learning_rate": 1.574832148984774e-05,
+      "loss": 0.001,
+      "step": 26000
+    },
+    {
+      "epoch": 2.6139277964095484,
+      "grad_norm": 0.011897539719939232,
+      "learning_rate": 6.150162950953281e-06,
+      "loss": 0.0008,
+      "step": 26500
+    },
+    {
+      "epoch": 2.6632471887946343,
+      "grad_norm": 0.026670893654227257,
+      "learning_rate": 7.263088224173791e-07,
+      "loss": 0.0007,
+      "step": 27000
+    },
+    {
+      "epoch": 2.7125665811797197,
+      "grad_norm": 0.08923093229532242,
+      "learning_rate": 4.932760869209433e-05,
+      "loss": 0.0021,
+      "step": 27500
+    },
+    {
+      "epoch": 2.7618859735648056,
+      "grad_norm": 0.03337786719202995,
+      "learning_rate": 4.401529007475872e-05,
+      "loss": 0.003,
+      "step": 28000
+    },
+    {
+      "epoch": 2.8112053659498915,
+      "grad_norm": 0.01894857920706272,
+      "learning_rate": 3.448656676980336e-05,
+      "loss": 0.0014,
+      "step": 28500
+    },
+    {
+      "epoch": 2.8605247583349773,
+      "grad_norm": 0.02331797406077385,
+      "learning_rate": 2.2857039229600964e-05,
+      "loss": 0.001,
+      "step": 29000
+    },
+    {
+      "epoch": 2.909844150720063,
+      "grad_norm": 0.01910516433417797,
+      "learning_rate": 1.1702071261018568e-05,
+      "loss": 0.0008,
+      "step": 29500
+    },
+    {
+      "epoch": 2.959163543105149,
+      "grad_norm": 0.021712150424718857,
+      "learning_rate": 3.4919352524861338e-06,
+      "loss": 0.0007,
+      "step": 30000
     }
   ],
   "logging_steps": 500,
@@ -502,7 +572,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.1661693972804915e+17,
+  "total_flos": 2.599358235167017e+17,
   "train_batch_size": 128,
   "trial_name": null,
   "trial_params": null