Training in progress, step 55000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbd952fb7ca0f8ddc9b0e7256bf820a3fc04551b8ae426ac98c3094dee2ea254
+oid sha256:80a80ba1df1c841ee670f71a637fc2ff1df9f6633cdbb91661d95be8ee1a5bd3
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d7970449ed8a17f9c6c4492b954ad4964b40feccf1db02f9503f0b2b341dee5
+oid sha256:48e16df1d1836b7794f6a8635aea83ef2eb38c93ca6cc7736092c223e74883b7
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44f6a18681a37c28eaea9106736980f3cb0b876fb22eb09649d7485450746688
+oid sha256:1ef35073d449d7a3d7a21c34c4d41c4e76bf9563ca58e18dcc098f99e20f38b0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:129967ad4aacd30894639b032d8517110a4963d1cc93db81c93bfda673142ba8
+oid sha256:a8da913cdb87fa0da659fbfc8e8d4a175dea1907bb6d7b316ea1a236f774834f
 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": 4.931939238508582,
+  "epoch": 5.425133162359439,
   "eval_steps": 2500,
-  "global_step": 50000,
+  "global_step": 55000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -833,6 +833,76 @@
       "learning_rate": 2.504638484990372e-05,
       "loss": 0.0004,
       "step": 50000
+    },
+    {
+      "epoch": 4.9812586308936675,
+      "grad_norm": 0.04032417759299278,
+      "learning_rate": 2.4653303816212188e-05,
+      "loss": 0.0005,
+      "step": 50500
+    },
+    {
+      "epoch": 5.030578023278753,
+      "grad_norm": 0.008274455554783344,
+      "learning_rate": 2.42603084959539e-05,
+      "loss": 0.0005,
+      "step": 51000
+    },
+    {
+      "epoch": 5.079897415663839,
+      "grad_norm": 0.028657300397753716,
+      "learning_rate": 2.386749604906234e-05,
+      "loss": 0.0004,
+      "step": 51500
+    },
+    {
+      "epoch": 5.129216808048925,
+      "grad_norm": 0.006416209042072296,
+      "learning_rate": 2.3474963590259334e-05,
+      "loss": 0.0004,
+      "step": 52000
+    },
+    {
+      "epoch": 5.178536200434011,
+      "grad_norm": 0.014230284839868546,
+      "learning_rate": 2.3082808165045468e-05,
+      "loss": 0.0004,
+      "step": 52500
+    },
+    {
+      "epoch": 5.227855592819097,
+      "grad_norm": 0.014515167102217674,
+      "learning_rate": 2.2691126725707605e-05,
+      "loss": 0.0004,
+      "step": 53000
+    },
+    {
+      "epoch": 5.277174985204182,
+      "grad_norm": 0.0125635527074337,
+      "learning_rate": 2.2300797694611534e-05,
+      "loss": 0.0004,
+      "step": 53500
+    },
+    {
+      "epoch": 5.326494377589268,
+      "grad_norm": 0.022368459030985832,
+      "learning_rate": 2.191035315978832e-05,
+      "loss": 0.0004,
+      "step": 54000
+    },
+    {
+      "epoch": 5.375813769974354,
+      "grad_norm": 0.007136535365134478,
+      "learning_rate": 2.1520672475998373e-05,
+      "loss": 0.0004,
+      "step": 54500
+    },
+    {
+      "epoch": 5.425133162359439,
+      "grad_norm": 0.00662201177328825,
+      "learning_rate": 2.1131851983700107e-05,
+      "loss": 0.0004,
+      "step": 55000
     }
   ],
   "logging_steps": 500,
@@ -852,7 +922,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.3312528608288154e+17,
+  "total_flos": 4.7645419624832256e+17,
   "train_batch_size": 128,
   "trial_name": null,
   "trial_params": null