Training in progress, step 35000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c53ad604c14cc39ffcae940a2f3200a2873c2eb474d5228b2946874020f7daa7
+oid sha256:039842f075c59d724d698a37730d17724d4fd364d3e15cc20b3f1179fde1bca8
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f796440eb004ff6ebd1b963193cbfc5b6abdb7e8ecda4b453e700a71957824ea
+oid sha256:89eeaf45dca11e93dc975549990f3cbcb0ebdaffb489fed2b2340133a55bedd8
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56a0f11391c647e59bfa9023f9f5e7eabe7ca39b1ee44361e7400224bae3095b
+oid sha256:1f37fe3424153bca4b7fc59f99bd2c0b98d90aaf8d45d5b05abebae1157a8e7e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90ba8e6b312d2e8ffeae2b414a4a618ae53a7f667d9bdc791713f23f485f4a64
+oid sha256:fd12236a2b04dcc8172c63d077f003702ceca140fc00b62558c7c08cdf884e4b
 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": 2.959163543105149,
+  "epoch": 3.4523574669560073,
   "eval_steps": 2500,
-  "global_step": 30000,
+  "global_step": 35000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -553,6 +553,76 @@
       "learning_rate": 3.974038822893393e-05,
       "loss": 0.0014,
       "step": 30000
+    },
+    {
+      "epoch": 3.008482935490235,
+      "grad_norm": 0.02712525986135006,
+      "learning_rate": 3.942108490409635e-05,
+      "loss": 0.0014,
+      "step": 30500
+    },
+    {
+      "epoch": 3.0578023278753204,
+      "grad_norm": 0.04912711679935455,
+      "learning_rate": 3.9099514736586965e-05,
+      "loss": 0.0024,
+      "step": 31000
+    },
+    {
+      "epoch": 3.1071217202604062,
+      "grad_norm": 0.03684419021010399,
+      "learning_rate": 3.877317438846952e-05,
+      "loss": 0.0012,
+      "step": 31500
+    },
+    {
+      "epoch": 3.156441112645492,
+      "grad_norm": 0.034598346799612045,
+      "learning_rate": 3.8443428908946436e-05,
+      "loss": 0.0011,
+      "step": 32000
+    },
+    {
+      "epoch": 3.205760505030578,
+      "grad_norm": 0.023367149755358696,
+      "learning_rate": 3.8110359820741256e-05,
+      "loss": 0.0011,
+      "step": 32500
+    },
+    {
+      "epoch": 3.255079897415664,
+      "grad_norm": 0.04803726077079773,
+      "learning_rate": 3.777404946827081e-05,
+      "loss": 0.0011,
+      "step": 33000
+    },
+    {
+      "epoch": 3.3043992898007497,
+      "grad_norm": 0.02714533731341362,
+      "learning_rate": 3.743458099728716e-05,
+      "loss": 0.0011,
+      "step": 33500
+    },
+    {
+      "epoch": 3.3537186821858356,
+      "grad_norm": 0.04370482265949249,
+      "learning_rate": 3.7092038334321655e-05,
+      "loss": 0.0011,
+      "step": 34000
+    },
+    {
+      "epoch": 3.4030380745709214,
+      "grad_norm": 0.035204458981752396,
+      "learning_rate": 3.674650616593575e-05,
+      "loss": 0.0012,
+      "step": 34500
+    },
+    {
+      "epoch": 3.4523574669560073,
+      "grad_norm": 0.013022173196077347,
+      "learning_rate": 3.639806991778405e-05,
+      "loss": 0.0012,
+      "step": 35000
     }
   ],
   "logging_steps": 500,
@@ -572,7 +642,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.619102484842793e+17,
+  "total_flos": 3.055328543636475e+17,
   "train_batch_size": 128,
   "trial_name": null,
   "trial_params": null