Training in progress, step 50000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99d99ef005366c768182dbd5fbbed197e6391e6fc6d0c746b5feb7b2fd2a2764
+oid sha256:fe75c7d1d2a9fb1383fa16ca04fa9582f79bce9c2c6b619ccc5bf8f41a7349d3
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f6b17853dc9aaa706ba3ed378aef704b5d5535f20af1ae291d3e1c2ee5cb5bc
+oid sha256:c16c4ea2aeaf96ed945f3ff8d93677b434f48d1a77151570a2c01992d79bde54
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76ef189c202797a47ce62889d21e7c97c6a4ce5ace6abf783017722de7ad98b2
+oid sha256:1cdbc5184733c39b403d000033558f016107ac570eaa5b3b5be67cc987ed4902
 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": 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": 5e-05,
       "loss": 0.0009,
       "step": 45000
+    },
+    {
+      "epoch": 4.48806470704281,
+      "grad_norm": 0.03474525734782219,
+      "learning_rate": 5e-05,
+      "loss": 0.0008,
+      "step": 45500
+    },
+    {
+      "epoch": 4.537384099427895,
+      "grad_norm": 0.036050453782081604,
+      "learning_rate": 5e-05,
+      "loss": 0.0009,
+      "step": 46000
+    },
+    {
+      "epoch": 4.5867034918129805,
+      "grad_norm": 0.027342744171619415,
+      "learning_rate": 5e-05,
+      "loss": 0.0012,
+      "step": 46500
+    },
+    {
+      "epoch": 4.636022884198066,
+      "grad_norm": 0.03911557421088219,
+      "learning_rate": 5e-05,
+      "loss": 0.0008,
+      "step": 47000
+    },
+    {
+      "epoch": 4.685342276583152,
+      "grad_norm": 0.04079333692789078,
+      "learning_rate": 5e-05,
+      "loss": 0.0009,
+      "step": 47500
+    },
+    {
+      "epoch": 4.734661668968238,
+      "grad_norm": 0.03646528348326683,
+      "learning_rate": 5e-05,
+      "loss": 0.0008,
+      "step": 48000
+    },
+    {
+      "epoch": 4.783981061353324,
+      "grad_norm": 0.0461641363799572,
+      "learning_rate": 5e-05,
+      "loss": 0.001,
+      "step": 48500
+    },
+    {
+      "epoch": 4.83330045373841,
+      "grad_norm": 0.050128430128097534,
+      "learning_rate": 5e-05,
+      "loss": 0.0009,
+      "step": 49000
+    },
+    {
+      "epoch": 4.882619846123496,
+      "grad_norm": 0.02025548741221428,
+      "learning_rate": 5e-05,
+      "loss": 0.0008,
+      "step": 49500
+    },
+    {
+      "epoch": 4.931939238508582,
+      "grad_norm": 0.03685050085186958,
+      "learning_rate": 5e-05,
+      "loss": 0.0008,
+      "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