Training in progress, step 45000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4eb13fae68b4da2fd0470aa5e44d87722b7f922b14cc45570ba15d7332a098a3
+oid sha256:b0c6cca2c6a9ac2adb2075297cbca19d4215769af04fc3b72aa6f7ffdaf1fbc7
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b4fb83a31c5f551867b73e4a04fb0792b6dcb81cfab8e97c9c7c1be40261673
+oid sha256:ef0ddd76d8b4525cbbad4aefefb74d4c462f82436fa56c207a7d0c37484c235e
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67ac518124b0903d77f498378aa78563fdd32b2c504118e8b67305a05ba8b32e
+oid sha256:ec0ea160082cc39ac30942ebcddc73a0bcdea69205d0069eef8edae7fc1a9d72
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b3d29e9416426ecd9d3676908bb6dd359c1ff73bc4326e4d53164f0d162e2cb
+oid sha256:dc36b8ae22f6cb108858cc00165c8e8672f7e966fabf0d057ddaa95d9238a73a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.5462110481586402,
   "best_model_checkpoint": "/mimer/NOBACKUP/groups/naiss2023-6-290/stefano/models//PROTAC-Splitter-EncoderDecoder-lr_cosine_restarts-opt25/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": 2.628603912310604e-06,
       "loss": 0.0005,
       "step": 40000
+    },
+    {
+      "epoch": 3.994870783191951,
+      "grad_norm": 0.02355390600860119,
+      "learning_rate": 4.999809317820512e-05,
+      "loss": 0.0005,
+      "step": 40500
+    },
+    {
+      "epoch": 4.044190175577037,
+      "grad_norm": 0.030535969883203506,
+      "learning_rate": 4.708895193055257e-05,
+      "loss": 0.0023,
+      "step": 41000
+    },
+    {
+      "epoch": 4.093509567962123,
+      "grad_norm": 0.030475422739982605,
+      "learning_rate": 3.9288202908042935e-05,
+      "loss": 0.0011,
+      "step": 41500
+    },
+    {
+      "epoch": 4.142828960347209,
+      "grad_norm": 0.03414959833025932,
+      "learning_rate": 2.8323325290683895e-05,
+      "loss": 0.0008,
+      "step": 42000
+    },
+    {
+      "epoch": 4.1921483527322945,
+      "grad_norm": 0.03184778243303299,
+      "learning_rate": 1.6622495877992905e-05,
+      "loss": 0.0006,
+      "step": 42500
+    },
+    {
+      "epoch": 4.24146774511738,
+      "grad_norm": 0.036285772919654846,
+      "learning_rate": 6.776868306745027e-06,
+      "loss": 0.0005,
+      "step": 43000
+    },
+    {
+      "epoch": 4.290787137502466,
+      "grad_norm": 0.020429372787475586,
+      "learning_rate": 9.667609789756588e-07,
+      "loss": 0.0005,
+      "step": 43500
+    },
+    {
+      "epoch": 4.340106529887552,
+      "grad_norm": 0.10811227560043335,
+      "learning_rate": 4.952579070517538e-05,
+      "loss": 0.0014,
+      "step": 44000
+    },
+    {
+      "epoch": 4.389425922272638,
+      "grad_norm": 0.05198413506150246,
+      "learning_rate": 4.460839084373921e-05,
+      "loss": 0.0019,
+      "step": 44500
+    },
+    {
+      "epoch": 4.438745314657724,
+      "grad_norm": 0.03819139301776886,
+      "learning_rate": 3.534411131835637e-05,
+      "loss": 0.001,
+      "step": 45000
     }
   ],
   "logging_steps": 500,
@@ -712,7 +782,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.465342568466058e+17,
+  "total_flos": 3.898212104814858e+17,
   "train_batch_size": 128,
   "trial_name": null,
   "trial_params": null