Training in progress, step 25000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67db7fb5753287fec24d570fb9e463675efaa498fa6d43a9b9c5b7d5276de37e
+oid sha256:d464023b8f1474910766ee80ad14a28e66f63573ca2b6fb03947ac68b967bb41
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:885da78fc800f2d8b7fb905e4b00218a8293bb01d93c369ccba96ed84cdd299b
+oid sha256:d2d33601ea1dc880400999b7420e298be3e4cbc04c3e87157fb01b29ee13561d
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6129e57ccde2e74721074ef039aefd879898938d0c6bc6383123ae34cb563028
+oid sha256:13af011930134dbe96e128214e5fbcde3960d4f80e067bf43289611e2726c1ea
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62ab762d9f0d3d15a42cef5723b0f5f86203957cf86c4aa9da4491b50bed6eb5
+oid sha256:01c6651fb3b50890a831e967efdfa4694c1d4e9a2df9e75a1dc5c40d85362105
 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": 1.9727756954034326,
+  "epoch": 2.465969619254291,
   "eval_steps": 2500,
-  "global_step": 20000,
+  "global_step": 25000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -413,6 +413,76 @@
       "learning_rate": 4.52623294202573e-05,
       "loss": 0.0017,
       "step": 20000
+    },
+    {
+      "epoch": 2.0220950877885184,
+      "grad_norm": 0.047866348177194595,
+      "learning_rate": 4.502958120260894e-05,
+      "loss": 0.0017,
+      "step": 20500
+    },
+    {
+      "epoch": 2.0714144801736043,
+      "grad_norm": 0.053165681660175323,
+      "learning_rate": 4.479188108686714e-05,
+      "loss": 0.0019,
+      "step": 21000
+    },
+    {
+      "epoch": 2.12073387255869,
+      "grad_norm": 0.04063253104686737,
+      "learning_rate": 4.4549287839450324e-05,
+      "loss": 0.0017,
+      "step": 21500
+    },
+    {
+      "epoch": 2.170053264943776,
+      "grad_norm": 0.059268295764923096,
+      "learning_rate": 4.4301861436502156e-05,
+      "loss": 0.0015,
+      "step": 22000
+    },
+    {
+      "epoch": 2.219372657328862,
+      "grad_norm": 0.021407226100564003,
+      "learning_rate": 4.404966304906363e-05,
+      "loss": 0.0014,
+      "step": 22500
+    },
+    {
+      "epoch": 2.2686920497139473,
+      "grad_norm": 0.027945173904299736,
+      "learning_rate": 4.379275502794983e-05,
+      "loss": 0.0014,
+      "step": 23000
+    },
+    {
+      "epoch": 2.318011442099033,
+      "grad_norm": 0.03261112794280052,
+      "learning_rate": 4.353120088833501e-05,
+      "loss": 0.0014,
+      "step": 23500
+    },
+    {
+      "epoch": 2.367330834484119,
+      "grad_norm": 0.05259308964014053,
+      "learning_rate": 4.326506529404972e-05,
+      "loss": 0.0013,
+      "step": 24000
+    },
+    {
+      "epoch": 2.416650226869205,
+      "grad_norm": 0.0584435798227787,
+      "learning_rate": 4.2994959806435226e-05,
+      "loss": 0.0015,
+      "step": 24500
+    },
+    {
+      "epoch": 2.465969619254291,
+      "grad_norm": 0.022548576816916466,
+      "learning_rate": 4.2719868638689734e-05,
+      "loss": 0.0012,
+      "step": 25000
     }
   ],
   "logging_steps": 500,
@@ -432,7 +502,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.7329296562502707e+17,
+  "total_flos": 2.1661693972804915e+17,
   "train_batch_size": 128,
   "trial_name": null,
   "trial_params": null