Training in progress, step 65000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27d41ba63ba593f2cfce363802b440927332dce61aafea879db261ae77cd52d0
+oid sha256:b765806c32a71debbe5fcd75a03b9d683e507d65faff94e01c59c7581ed7ac5f
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d742eeb8d925c1a166af3e09a3e0fd4ebadea870bd4919c2660b4864e7654fcd
+oid sha256:973086399ebf7dfee4ca3fae615f7dbbcc6764ef896837b42c878ef225b08ff0
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac455c3f391185463b9c69f4fb71b00665f813b40d3fca5439822d6487ecd3b5
+oid sha256:d94c3d1ced5d6eccb982de07377a5bac97c708bdc2a2e2ec8462b5f4c3224ec7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8abde5ea6d7508710178712fe236e737431b4a593f0d18f03c2b4dfe63cb7155
+oid sha256:1ef1f0d7258e92b9f9871d81d52ebcc946c37081ef596ae367fa8c041eca7a05
 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": 5.918327086210298,
+  "epoch": 6.411521010061156,
   "eval_steps": 2500,
-  "global_step": 60000,
+  "global_step": 65000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -973,6 +973,76 @@
       "learning_rate": 1.7313466151363385e-05,
       "loss": 0.0004,
       "step": 60000
+    },
+    {
+      "epoch": 5.967646478595384,
+      "grad_norm": 0.011568223126232624,
+      "learning_rate": 1.6941124932601034e-05,
+      "loss": 0.0005,
+      "step": 60500
+    },
+    {
+      "epoch": 6.01696587098047,
+      "grad_norm": 0.04736906662583351,
+      "learning_rate": 1.6570027997553185e-05,
+      "loss": 0.0004,
+      "step": 61000
+    },
+    {
+      "epoch": 6.066285263365556,
+      "grad_norm": 0.01865927129983902,
+      "learning_rate": 1.6201015198057866e-05,
+      "loss": 0.0004,
+      "step": 61500
+    },
+    {
+      "epoch": 6.115604655750641,
+      "grad_norm": 0.014169979840517044,
+      "learning_rate": 1.5834177764868226e-05,
+      "loss": 0.0004,
+      "step": 62000
+    },
+    {
+      "epoch": 6.164924048135727,
+      "grad_norm": 0.009675228968262672,
+      "learning_rate": 1.5469606390923247e-05,
+      "loss": 0.0004,
+      "step": 62500
+    },
+    {
+      "epoch": 6.2142434405208125,
+      "grad_norm": 0.00304154260084033,
+      "learning_rate": 1.5107391208925827e-05,
+      "loss": 0.0004,
+      "step": 63000
+    },
+    {
+      "epoch": 6.263562832905898,
+      "grad_norm": 0.004374227486550808,
+      "learning_rate": 1.474762176905931e-05,
+      "loss": 0.0004,
+      "step": 63500
+    },
+    {
+      "epoch": 6.312882225290984,
+      "grad_norm": 0.006118281278759241,
+      "learning_rate": 1.439038701684809e-05,
+      "loss": 0.0004,
+      "step": 64000
+    },
+    {
+      "epoch": 6.36220161767607,
+      "grad_norm": 0.006160255055874586,
+      "learning_rate": 1.4035775271167664e-05,
+      "loss": 0.0004,
+      "step": 64500
+    },
+    {
+      "epoch": 6.411521010061156,
+      "grad_norm": 0.009528923779726028,
+      "learning_rate": 1.3684575241351546e-05,
+      "loss": 0.0004,
+      "step": 65000
     }
   ],
   "logging_steps": 500,
@@ -992,7 +1062,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.2375401437785344e+17,
+  "total_flos": 5.674161087565732e+17,
   "train_batch_size": 128,
   "trial_name": null,
   "trial_params": null