Training in progress, step 40000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b082085d9aa1da3efa2ad33dd1002ddb5511bf8eb3c2067b8fc30888db68b37
+oid sha256:3a6c87098dee6f04ae2bceaaa2c0f617952d030c4e279874a01eb06fdd42c41e
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:053d966c702b26ff46dde77ec6b0cff280c687a0dd1a4474041cda54900e0bf9
+oid sha256:5faf6a3e2939d75a948aba9447459c4e343a50ef20460c74841f4d26332215cf
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:375e808faf0ee5ae5d50ffe1d1a4fc8f21560fc6eeedbd7f2acd27833efa40af
+oid sha256:eeb57d6a99029070321c5cbe53e1de318ca2dbd673dc5c838164e987bf464c4d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd12236a2b04dcc8172c63d077f003702ceca140fc00b62558c7c08cdf884e4b
+oid sha256:08e1d8ba2414508e50f3f6e207e18b230dc5f1405db079b8fc4d29a0585a5ea6
 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": 3.4523574669560073,
+  "epoch": 3.945551390806865,
   "eval_steps": 2500,
-  "global_step": 35000,
+  "global_step": 40000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -623,6 +623,76 @@
       "learning_rate": 3.639806991778405e-05,
       "loss": 0.0009,
       "step": 35000
+    },
+    {
+      "epoch": 3.501676859341093,
+      "grad_norm": 0.023237833753228188,
+      "learning_rate": 3.604752099655735e-05,
+      "loss": 0.0009,
+      "step": 35500
+    },
+    {
+      "epoch": 3.5509962517261786,
+      "grad_norm": 0.034029532223939896,
+      "learning_rate": 3.569354109150707e-05,
+      "loss": 0.0006,
+      "step": 36000
+    },
+    {
+      "epoch": 3.6003156441112645,
+      "grad_norm": 0.04032694920897484,
+      "learning_rate": 3.533691743044375e-05,
+      "loss": 0.0007,
+      "step": 36500
+    },
+    {
+      "epoch": 3.6496350364963503,
+      "grad_norm": 0.03434913605451584,
+      "learning_rate": 3.497773818116328e-05,
+      "loss": 0.0007,
+      "step": 37000
+    },
+    {
+      "epoch": 3.698954428881436,
+      "grad_norm": 0.012562757357954979,
+      "learning_rate": 3.461609214327767e-05,
+      "loss": 0.0007,
+      "step": 37500
+    },
+    {
+      "epoch": 3.748273821266522,
+      "grad_norm": 0.03795718029141426,
+      "learning_rate": 3.4253529436582336e-05,
+      "loss": 0.0012,
+      "step": 38000
+    },
+    {
+      "epoch": 3.797593213651608,
+      "grad_norm": 0.036550700664520264,
+      "learning_rate": 3.3887227607163154e-05,
+      "loss": 0.0007,
+      "step": 38500
+    },
+    {
+      "epoch": 3.8469126060366934,
+      "grad_norm": 0.009776749648153782,
+      "learning_rate": 3.3518728595236816e-05,
+      "loss": 0.0006,
+      "step": 39000
+    },
+    {
+      "epoch": 3.8962319984217793,
+      "grad_norm": 0.010442009195685387,
+      "learning_rate": 3.314812350453317e-05,
+      "loss": 0.0006,
+      "step": 39500
+    },
+    {
+      "epoch": 3.945551390806865,
+      "grad_norm": 0.023100633174180984,
+      "learning_rate": 3.27755039594663e-05,
+      "loss": 0.0006,
+      "step": 40000
     }
   ],
   "logging_steps": 500,
@@ -642,7 +712,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.032375853388385e+17,
+  "total_flos": 3.465342568466058e+17,
   "train_batch_size": 128,
   "trial_name": null,
   "trial_params": null