Training in progress, step 40000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:483ae222a11ad65143d340dfeb9c147487c0e9d7650c854f6fa4e6913822f4ac
+oid sha256:4eb13fae68b4da2fd0470aa5e44d87722b7f922b14cc45570ba15d7332a098a3
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a57b7ac202a308e621e5caa585c7bf49d7660d1bf4e2e4136fe4ce9cfc2f2612
+oid sha256:7b4fb83a31c5f551867b73e4a04fb0792b6dcb81cfab8e97c9c7c1be40261673
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:484914ffc89ec808f83bedc7e13af0a69fde5616be4a86784457fcd8d54f74ae
+oid sha256:67ac518124b0903d77f498378aa78563fdd32b2c504118e8b67305a05ba8b32e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:253cb0c7aa8e83fabe20fc0de3d6da7c690f3ee9b7052b32a92753a48a7bfa6d
+oid sha256:3b3d29e9416426ecd9d3676908bb6dd359c1ff73bc4326e4d53164f0d162e2cb
 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": 3.4523574669560073,
+  "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": 3.6959108562141376e-05,
       "loss": 0.0012,
       "step": 35000
+    },
+    {
+      "epoch": 3.501676859341093,
+      "grad_norm": 0.021087462082505226,
+      "learning_rate": 2.559374318373061e-05,
+      "loss": 0.0009,
+      "step": 35500
+    },
+    {
+      "epoch": 3.5509962517261786,
+      "grad_norm": 0.022866034880280495,
+      "learning_rate": 1.409689312542472e-05,
+      "loss": 0.0007,
+      "step": 36000
+    },
+    {
+      "epoch": 3.6003156441112645,
+      "grad_norm": 0.042014122009277344,
+      "learning_rate": 5.014540709444851e-06,
+      "loss": 0.0006,
+      "step": 36500
+    },
+    {
+      "epoch": 3.6496350364963503,
+      "grad_norm": 0.012297836132347584,
+      "learning_rate": 3.5797673092126393e-07,
+      "loss": 0.0005,
+      "step": 37000
+    },
+    {
+      "epoch": 3.698954428881436,
+      "grad_norm": 0.06086747720837593,
+      "learning_rate": 4.884160074185018e-05,
+      "loss": 0.002,
+      "step": 37500
+    },
+    {
+      "epoch": 3.748273821266522,
+      "grad_norm": 0.03979231417179108,
+      "learning_rate": 4.279484393132507e-05,
+      "loss": 0.0017,
+      "step": 38000
+    },
+    {
+      "epoch": 3.797593213651608,
+      "grad_norm": 0.020537426695227623,
+      "learning_rate": 3.2793161758248515e-05,
+      "loss": 0.0011,
+      "step": 38500
+    },
+    {
+      "epoch": 3.8469126060366934,
+      "grad_norm": 0.012818257324397564,
+      "learning_rate": 2.1065680608053368e-05,
+      "loss": 0.0007,
+      "step": 39000
+    },
+    {
+      "epoch": 3.8962319984217793,
+      "grad_norm": 0.009783191606402397,
+      "learning_rate": 1.0209456156090146e-05,
+      "loss": 0.0006,
+      "step": 39500
+    },
+    {
+      "epoch": 3.945551390806865,
+      "grad_norm": 0.01907140202820301,
+      "learning_rate": 2.628603912310604e-06,
+      "loss": 0.0005,
+      "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