Training in progress, step 35000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:847704143a8fe1bda65db1fe2c65f7a5566407d3fa081a0f600bf66f16b8b3a0
+oid sha256:680cdd8ce09ed81d5904b52f855191e264cb3a8777e419668f407b84fc55713a
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5957f98f8279a93ad8e35cd4746546f5160d187ed7070c5aa9bbdb47408fe1c
+oid sha256:fe583685246694473b81b6159749d52ae9755ca3bd5d94c328cf706a1d1198e0
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c65c2745f22d1c4db409b96f64b6f71c3a2ee8bc2f8c7ff26a84d73ab1a44cb8
+oid sha256:86e4d6f5632dbc00793287b2f22a557709a70a15c41fc36f8e72a42acf0f499d
 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": 2.959163543105149,
+  "epoch": 3.4523574669560073,
   "eval_steps": 2500,
-  "global_step": 30000,
+  "global_step": 35000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -553,6 +553,76 @@
       "learning_rate": 5e-05,
       "loss": 0.0021,
       "step": 30000
+    },
+    {
+      "epoch": 3.008482935490235,
+      "grad_norm": 0.029712537303566933,
+      "learning_rate": 5e-05,
+      "loss": 0.0011,
+      "step": 30500
+    },
+    {
+      "epoch": 3.0578023278753204,
+      "grad_norm": 0.022233586758375168,
+      "learning_rate": 5e-05,
+      "loss": 0.001,
+      "step": 31000
+    },
+    {
+      "epoch": 3.1071217202604062,
+      "grad_norm": 0.04128130525350571,
+      "learning_rate": 5e-05,
+      "loss": 0.0011,
+      "step": 31500
+    },
+    {
+      "epoch": 3.156441112645492,
+      "grad_norm": 0.031225621700286865,
+      "learning_rate": 5e-05,
+      "loss": 0.0012,
+      "step": 32000
+    },
+    {
+      "epoch": 3.205760505030578,
+      "grad_norm": 0.04397075995802879,
+      "learning_rate": 5e-05,
+      "loss": 0.0011,
+      "step": 32500
+    },
+    {
+      "epoch": 3.255079897415664,
+      "grad_norm": 0.03178331255912781,
+      "learning_rate": 5e-05,
+      "loss": 0.0011,
+      "step": 33000
+    },
+    {
+      "epoch": 3.3043992898007497,
+      "grad_norm": 0.04911533370614052,
+      "learning_rate": 5e-05,
+      "loss": 0.0012,
+      "step": 33500
+    },
+    {
+      "epoch": 3.3537186821858356,
+      "grad_norm": 0.036495912820100784,
+      "learning_rate": 5e-05,
+      "loss": 0.0011,
+      "step": 34000
+    },
+    {
+      "epoch": 3.4030380745709214,
+      "grad_norm": 0.0601472444832325,
+      "learning_rate": 5e-05,
+      "loss": 0.0012,
+      "step": 34500
+    },
+    {
+      "epoch": 3.4523574669560073,
+      "grad_norm": 0.035126738250255585,
+      "learning_rate": 5e-05,
+      "loss": 0.0014,
+      "step": 35000
     }
   ],
   "logging_steps": 500,
@@ -572,7 +642,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.619102484842793e+17,
+  "total_flos": 3.055328543636475e+17,
   "train_batch_size": 128,
   "trial_name": null,
   "trial_params": null