Training in progress, step 60000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80a80ba1df1c841ee670f71a637fc2ff1df9f6633cdbb91661d95be8ee1a5bd3
+oid sha256:b6a123f0f4c5a11cb72b99972714ce78828980a28225a86c5c52efa0dfd4317d
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48e16df1d1836b7794f6a8635aea83ef2eb38c93ca6cc7736092c223e74883b7
+oid sha256:15ee547f4d1e2effb0117ee97acb3ccd85c719ade258b1abcb9b39428c1fc01e
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ef35073d449d7a3d7a21c34c4d41c4e76bf9563ca58e18dcc098f99e20f38b0
+oid sha256:3146ea4f58eeba70ef991619520fba1220f5a6969c7140f3e94b740993fab985
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8da913cdb87fa0da659fbfc8e8d4a175dea1907bb6d7b316ea1a236f774834f
+oid sha256:8abde5ea6d7508710178712fe236e737431b4a593f0d18f03c2b4dfe63cb7155
 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": 5.425133162359439,
+  "epoch": 5.918327086210298,
   "eval_steps": 2500,
-  "global_step": 55000,
+  "global_step": 60000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -903,6 +903,76 @@
       "learning_rate": 2.1131851983700107e-05,
       "loss": 0.0004,
       "step": 55000
+    },
+    {
+      "epoch": 5.474452554744525,
+      "grad_norm": 0.004521891940385103,
+      "learning_rate": 2.074398781068747e-05,
+      "loss": 0.0004,
+      "step": 55500
+    },
+    {
+      "epoch": 5.523771947129611,
+      "grad_norm": 0.010427785106003284,
+      "learning_rate": 2.0357175848324307e-05,
+      "loss": 0.0004,
+      "step": 56000
+    },
+    {
+      "epoch": 5.573091339514697,
+      "grad_norm": 0.01812533475458622,
+      "learning_rate": 1.997228184710801e-05,
+      "loss": 0.0004,
+      "step": 56500
+    },
+    {
+      "epoch": 5.622410731899783,
+      "grad_norm": 0.01055191457271576,
+      "learning_rate": 1.958785833460854e-05,
+      "loss": 0.0004,
+      "step": 57000
+    },
+    {
+      "epoch": 5.671730124284869,
+      "grad_norm": 0.02802406996488571,
+      "learning_rate": 1.9204772861767664e-05,
+      "loss": 0.0004,
+      "step": 57500
+    },
+    {
+      "epoch": 5.721049516669955,
+      "grad_norm": 0.02212759293615818,
+      "learning_rate": 1.8823120138514845e-05,
+      "loss": 0.0004,
+      "step": 58000
+    },
+    {
+      "epoch": 5.7703689090550405,
+      "grad_norm": 0.020376645028591156,
+      "learning_rate": 1.8442994520561926e-05,
+      "loss": 0.0004,
+      "step": 58500
+    },
+    {
+      "epoch": 5.819688301440126,
+      "grad_norm": 0.004514740779995918,
+      "learning_rate": 1.8064489986075706e-05,
+      "loss": 0.0004,
+      "step": 59000
+    },
+    {
+      "epoch": 5.869007693825212,
+      "grad_norm": 0.014004266820847988,
+      "learning_rate": 1.768845191897044e-05,
+      "loss": 0.0004,
+      "step": 59500
+    },
+    {
+      "epoch": 5.918327086210298,
+      "grad_norm": 0.020170176401734352,
+      "learning_rate": 1.7313466151363385e-05,
+      "loss": 0.0004,
+      "step": 60000
     }
   ],
   "logging_steps": 500,
@@ -922,7 +992,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.7645419624832256e+17,
+  "total_flos": 5.1976814397455616e+17,
   "train_batch_size": 128,
   "trial_name": null,
   "trial_params": null