Training in progress, step 50000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87fd26095cc52b1b1fcb61aa241c45efbc7b650471ca5a054f91cf66241e51c2
+oid sha256:bbd952fb7ca0f8ddc9b0e7256bf820a3fc04551b8ae426ac98c3094dee2ea254
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c07bb32cd46c9fb53458473e6c056fc27d5f5b5b0c76311e6ffe2ee4772ef387
+oid sha256:0d7970449ed8a17f9c6c4492b954ad4964b40feccf1db02f9503f0b2b341dee5
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:482495ef335bd0cb4d91c4031a90b31c1acd8f32c3166de3bdbd2f81cf638e6a
+oid sha256:44f6a18681a37c28eaea9106736980f3cb0b876fb22eb09649d7485450746688
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:950318ed157dfaa6d9d1d461c0e1fb839308bf3fb8549cac2587ce9ecd744d04
+oid sha256:129967ad4aacd30894639b032d8517110a4963d1cc93db81c93bfda673142ba8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.5477160056657224,
   "best_model_checkpoint": "/mimer/NOBACKUP/groups/naiss2023-6-290/stefano/models//PROTAC-Splitter-EncoderDecoder-lr_cosine-opt25/checkpoint-10000",
-  "epoch": 4.438745314657724,
+  "epoch": 4.931939238508582,
   "eval_steps": 2500,
-  "global_step": 45000,
+  "global_step": 50000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -763,6 +763,76 @@
       "learning_rate": 2.8960549998903897e-05,
       "loss": 0.0005,
       "step": 45000
+    },
+    {
+      "epoch": 4.48806470704281,
+      "grad_norm": 0.06772090494632721,
+      "learning_rate": 2.857194840237535e-05,
+      "loss": 0.0005,
+      "step": 45500
+    },
+    {
+      "epoch": 4.537384099427895,
+      "grad_norm": 0.05354917794466019,
+      "learning_rate": 2.818246371576595e-05,
+      "loss": 0.0005,
+      "step": 46000
+    },
+    {
+      "epoch": 4.5867034918129805,
+      "grad_norm": 0.034519363194704056,
+      "learning_rate": 2.7792192231077896e-05,
+      "loss": 0.0005,
+      "step": 46500
+    },
+    {
+      "epoch": 4.636022884198066,
+      "grad_norm": 0.02402963489294052,
+      "learning_rate": 2.740123043483287e-05,
+      "loss": 0.0005,
+      "step": 47000
+    },
+    {
+      "epoch": 4.685342276583152,
+      "grad_norm": 0.03265873342752457,
+      "learning_rate": 2.7009674984217738e-05,
+      "loss": 0.0005,
+      "step": 47500
+    },
+    {
+      "epoch": 4.734661668968238,
+      "grad_norm": 0.04922989383339882,
+      "learning_rate": 2.661762268318811e-05,
+      "loss": 0.0005,
+      "step": 48000
+    },
+    {
+      "epoch": 4.783981061353324,
+      "grad_norm": 0.02939719334244728,
+      "learning_rate": 2.6225170458535525e-05,
+      "loss": 0.0005,
+      "step": 48500
+    },
+    {
+      "epoch": 4.83330045373841,
+      "grad_norm": 0.043153587728738785,
+      "learning_rate": 2.5832415335924354e-05,
+      "loss": 0.0005,
+      "step": 49000
+    },
+    {
+      "epoch": 4.882619846123496,
+      "grad_norm": 0.024349920451641083,
+      "learning_rate": 2.5439454415904175e-05,
+      "loss": 0.0005,
+      "step": 49500
+    },
+    {
+      "epoch": 4.931939238508582,
+      "grad_norm": 0.04341769590973854,
+      "learning_rate": 2.504638484990372e-05,
+      "loss": 0.0004,
+      "step": 50000
     }
   ],
   "logging_steps": 500,
@@ -782,7 +852,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.898212104814858e+17,
+  "total_flos": 4.3312528608288154e+17,
   "train_batch_size": 128,
   "trial_name": null,
   "trial_params": null