Training in progress, step 50000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e76e2b1a2a56e66260a8b24222402fb6411337a94fc1ff21dd2fed0f6176b3e
+oid sha256:06bc14bbbd27d253e78bd89df250f8a3729fff02beb78d421639b61a114eebe7
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c90a12cb152d8a5960479824e00fe42bc60c63a3a82282630a1fa6788db5ca6a
+oid sha256:32d96311d632155e63ab79cdb6ae5d13eac2ccb218ce46d58a4f410d578c97c9
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af53b8b54dc8f23640a2242053c5d32aa1e77f56497336f222b5262feb7ef177
+oid sha256:eddbb822fd8c77685fb0b027be7260417141436b826497b6aee7db3cba27626a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9299d1257fb2340390546c30a874d076b53bb55c63dc6155e353a5f573ba664d
+oid sha256:129967ad4aacd30894639b032d8517110a4963d1cc93db81c93bfda673142ba8
 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": 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": 2.8958997479041255e-05,
       "loss": 0.0008,
       "step": 45000
+    },
+    {
+      "epoch": 4.48806470704281,
+      "grad_norm": 0.05904557555913925,
+      "learning_rate": 2.857039215862017e-05,
+      "loss": 0.0007,
+      "step": 45500
+    },
+    {
+      "epoch": 4.537384099427895,
+      "grad_norm": 0.025458356365561485,
+      "learning_rate": 2.8180904132867185e-05,
+      "loss": 0.0007,
+      "step": 46000
+    },
+    {
+      "epoch": 4.5867034918129805,
+      "grad_norm": 0.025726348161697388,
+      "learning_rate": 2.7791410964224228e-05,
+      "loss": 0.0009,
+      "step": 46500
+    },
+    {
+      "epoch": 4.636022884198066,
+      "grad_norm": 0.01956965960562229,
+      "learning_rate": 2.740123043483287e-05,
+      "loss": 0.0007,
+      "step": 47000
+    },
+    {
+      "epoch": 4.685342276583152,
+      "grad_norm": 0.038180191069841385,
+      "learning_rate": 2.7009674984217738e-05,
+      "loss": 0.0007,
+      "step": 47500
+    },
+    {
+      "epoch": 4.734661668968238,
+      "grad_norm": 0.0360223725438118,
+      "learning_rate": 2.661762268318811e-05,
+      "loss": 0.0007,
+      "step": 48000
+    },
+    {
+      "epoch": 4.783981061353324,
+      "grad_norm": 0.03571155667304993,
+      "learning_rate": 2.6225170458535525e-05,
+      "loss": 0.0007,
+      "step": 48500
+    },
+    {
+      "epoch": 4.83330045373841,
+      "grad_norm": 0.012124253436923027,
+      "learning_rate": 2.5832415335924354e-05,
+      "loss": 0.0007,
+      "step": 49000
+    },
+    {
+      "epoch": 4.882619846123496,
+      "grad_norm": 0.029337838292121887,
+      "learning_rate": 2.5439454415904175e-05,
+      "loss": 0.0006,
+      "step": 49500
+    },
+    {
+      "epoch": 4.931939238508582,
+      "grad_norm": 0.04516094923019409,
+      "learning_rate": 2.504638484990372e-05,
+      "loss": 0.0006,
+      "step": 50000
     }
   ],
   "logging_steps": 500,
@@ -782,7 +852,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.927828479328522e+17,
+  "total_flos": 4.3642997987236454e+17,
   "train_batch_size": 128,
   "trial_name": null,
   "trial_params": null