Training in progress, step 30000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d464023b8f1474910766ee80ad14a28e66f63573ca2b6fb03947ac68b967bb41
+oid sha256:afb3bed924cc247c9bf5ed900473d967e5a40406f2cf73dc437085a692cf3bff
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2d33601ea1dc880400999b7420e298be3e4cbc04c3e87157fb01b29ee13561d
+oid sha256:3a05edfe8bb04df2c7c74f795b9d1968a33f9e390875a83a3f66260f03453f92
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13af011930134dbe96e128214e5fbcde3960d4f80e067bf43289611e2726c1ea
+oid sha256:0a01c7cdcb43da92a58412eddd8d3aaca5d8f574d69ef13bdff2f6fb12bcfd85
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01c6651fb3b50890a831e967efdfa4694c1d4e9a2df9e75a1dc5c40d85362105
+oid sha256:90ba8e6b312d2e8ffeae2b414a4a618ae53a7f667d9bdc791713f23f485f4a64
 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": 2.465969619254291,
+  "epoch": 2.959163543105149,
   "eval_steps": 2500,
-  "global_step": 25000,
+  "global_step": 30000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -483,6 +483,76 @@
       "learning_rate": 4.2719868638689734e-05,
       "loss": 0.0012,
       "step": 25000
+    },
+    {
+      "epoch": 2.5152890116393767,
+      "grad_norm": 0.03915947675704956,
+      "learning_rate": 4.244039660132742e-05,
+      "loss": 0.0013,
+      "step": 25500
+    },
+    {
+      "epoch": 2.5646084040244626,
+      "grad_norm": 0.02655004896223545,
+      "learning_rate": 4.2156612788007085e-05,
+      "loss": 0.0012,
+      "step": 26000
+    },
+    {
+      "epoch": 2.6139277964095484,
+      "grad_norm": 0.030596962198615074,
+      "learning_rate": 4.186858735838457e-05,
+      "loss": 0.0012,
+      "step": 26500
+    },
+    {
+      "epoch": 2.6632471887946343,
+      "grad_norm": 0.03012579120695591,
+      "learning_rate": 4.15763915207673e-05,
+      "loss": 0.0012,
+      "step": 27000
+    },
+    {
+      "epoch": 2.7125665811797197,
+      "grad_norm": 0.015622408129274845,
+      "learning_rate": 4.1280097514509486e-05,
+      "loss": 0.001,
+      "step": 27500
+    },
+    {
+      "epoch": 2.7618859735648056,
+      "grad_norm": 0.03695574030280113,
+      "learning_rate": 4.097977859215244e-05,
+      "loss": 0.0011,
+      "step": 28000
+    },
+    {
+      "epoch": 2.8112053659498915,
+      "grad_norm": 0.03273458406329155,
+      "learning_rate": 4.0675509001314444e-05,
+      "loss": 0.0011,
+      "step": 28500
+    },
+    {
+      "epoch": 2.8605247583349773,
+      "grad_norm": 0.023473775014281273,
+      "learning_rate": 4.036798407361931e-05,
+      "loss": 0.0011,
+      "step": 29000
+    },
+    {
+      "epoch": 2.909844150720063,
+      "grad_norm": 0.0245220847427845,
+      "learning_rate": 4.005604729882533e-05,
+      "loss": 0.0009,
+      "step": 29500
+    },
+    {
+      "epoch": 2.959163543105149,
+      "grad_norm": 0.025120645761489868,
+      "learning_rate": 3.974038822893393e-05,
+      "loss": 0.001,
+      "step": 30000
     }
   ],
   "logging_steps": 500,
@@ -502,7 +572,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.1661693972804915e+17,
+  "total_flos": 2.599358235167017e+17,
   "train_batch_size": 128,
   "trial_name": null,
   "trial_params": null