Training in progress, step 45000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:503ce751da80aa8b1f118a861d5757c844ce8de1db073fef17acad2029b59e2b
+oid sha256:99d99ef005366c768182dbd5fbbed197e6391e6fc6d0c746b5feb7b2fd2a2764
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fbaedfb0a4123dcead5a29fb791a66763b1c12ca90eb39e7c861a4cb61e314d
+oid sha256:8f6b17853dc9aaa706ba3ed378aef704b5d5535f20af1ae291d3e1c2ee5cb5bc
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39417990b3af4b754d49ef8161883cbdefa4e1231e6e279b71d13d553fe650cf
+oid sha256:76ef189c202797a47ce62889d21e7c97c6a4ce5ace6abf783017722de7ad98b2
 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": 3.945551390806865,
+  "epoch": 4.438745314657724,
   "eval_steps": 2500,
-  "global_step": 40000,
+  "global_step": 45000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -693,6 +693,76 @@
       "learning_rate": 5e-05,
       "loss": 0.001,
       "step": 40000
+    },
+    {
+      "epoch": 3.994870783191951,
+      "grad_norm": 0.02784532681107521,
+      "learning_rate": 5e-05,
+      "loss": 0.0011,
+      "step": 40500
+    },
+    {
+      "epoch": 4.044190175577037,
+      "grad_norm": 0.03348594531416893,
+      "learning_rate": 5e-05,
+      "loss": 0.001,
+      "step": 41000
+    },
+    {
+      "epoch": 4.093509567962123,
+      "grad_norm": 0.06848876923322678,
+      "learning_rate": 5e-05,
+      "loss": 0.0009,
+      "step": 41500
+    },
+    {
+      "epoch": 4.142828960347209,
+      "grad_norm": 0.023778628557920456,
+      "learning_rate": 5e-05,
+      "loss": 0.0009,
+      "step": 42000
+    },
+    {
+      "epoch": 4.1921483527322945,
+      "grad_norm": 0.014797426760196686,
+      "learning_rate": 5e-05,
+      "loss": 0.0009,
+      "step": 42500
+    },
+    {
+      "epoch": 4.24146774511738,
+      "grad_norm": 0.019765177741646767,
+      "learning_rate": 5e-05,
+      "loss": 0.0009,
+      "step": 43000
+    },
+    {
+      "epoch": 4.290787137502466,
+      "grad_norm": 0.03716424107551575,
+      "learning_rate": 5e-05,
+      "loss": 0.001,
+      "step": 43500
+    },
+    {
+      "epoch": 4.340106529887552,
+      "grad_norm": 0.04304041340947151,
+      "learning_rate": 5e-05,
+      "loss": 0.0009,
+      "step": 44000
+    },
+    {
+      "epoch": 4.389425922272638,
+      "grad_norm": 0.07148012518882751,
+      "learning_rate": 5e-05,
+      "loss": 0.0011,
+      "step": 44500
+    },
+    {
+      "epoch": 4.438745314657724,
+      "grad_norm": 0.025658031925559044,
+      "learning_rate": 5e-05,
+      "loss": 0.0009,
+      "step": 45000
     }
   ],
   "logging_steps": 500,
@@ -712,7 +782,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.4915036992864614e+17,
+  "total_flos": 3.927828479328522e+17,
   "train_batch_size": 128,
   "trial_name": null,
   "trial_params": null