Training in progress, step 60000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ac0cc94f002a9b2de4003b50dc12b9040ae3e27bdbca22d780d51b88199614c
+oid sha256:a0716e05b7be0802eaf3e025833847e8a3cae599b796d778d586c13f3d195761
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdfa90c5490cac1bf800e23adbb848e931c94471254d21b4e0ebf5f49f539ba3
+oid sha256:ac850fbcce728867ed8902fa223176fea14017c30527b0b8a62896ea10e17974
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a0a71108ec81e8d23af17f0347ca933dbf48da5add452207f9012b1c9558bb0
+oid sha256:cc90a600027e1aba1caa11eec2a0f46a3006ea83630bb9dfb9aa44a091d77fcf
 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": 5.425133162359439,
+  "epoch": 5.918327086210298,
   "eval_steps": 2500,
-  "global_step": 55000,
+  "global_step": 60000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -903,6 +903,76 @@
       "learning_rate": 5e-05,
       "loss": 0.0008,
       "step": 55000
+    },
+    {
+      "epoch": 5.474452554744525,
+      "grad_norm": 0.013502424582839012,
+      "learning_rate": 5e-05,
+      "loss": 0.0009,
+      "step": 55500
+    },
+    {
+      "epoch": 5.523771947129611,
+      "grad_norm": 0.05730258300900459,
+      "learning_rate": 5e-05,
+      "loss": 0.0008,
+      "step": 56000
+    },
+    {
+      "epoch": 5.573091339514697,
+      "grad_norm": 0.031574029475450516,
+      "learning_rate": 5e-05,
+      "loss": 0.0007,
+      "step": 56500
+    },
+    {
+      "epoch": 5.622410731899783,
+      "grad_norm": 0.03838383033871651,
+      "learning_rate": 5e-05,
+      "loss": 0.0007,
+      "step": 57000
+    },
+    {
+      "epoch": 5.671730124284869,
+      "grad_norm": 0.027948297560214996,
+      "learning_rate": 5e-05,
+      "loss": 0.0007,
+      "step": 57500
+    },
+    {
+      "epoch": 5.721049516669955,
+      "grad_norm": 0.03251497074961662,
+      "learning_rate": 5e-05,
+      "loss": 0.0007,
+      "step": 58000
+    },
+    {
+      "epoch": 5.7703689090550405,
+      "grad_norm": 0.04168747738003731,
+      "learning_rate": 5e-05,
+      "loss": 0.001,
+      "step": 58500
+    },
+    {
+      "epoch": 5.819688301440126,
+      "grad_norm": 0.02773544192314148,
+      "learning_rate": 5e-05,
+      "loss": 0.0009,
+      "step": 59000
+    },
+    {
+      "epoch": 5.869007693825212,
+      "grad_norm": 0.019883353263139725,
+      "learning_rate": 5e-05,
+      "loss": 0.0007,
+      "step": 59500
+    },
+    {
+      "epoch": 5.918327086210298,
+      "grad_norm": 0.03476933389902115,
+      "learning_rate": 5e-05,
+      "loss": 0.0007,
+      "step": 60000
     }
   ],
   "logging_steps": 500,
@@ -922,7 +992,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.800723300014085e+17,
+  "total_flos": 5.2375401437785344e+17,
   "train_batch_size": 128,
   "trial_name": null,
   "trial_params": null