Training in progress, step 20000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a54a4c80d51d6ae31232f91761e1722e6ce4ed1b9394cd8a03c07bcdd430a876
+oid sha256:5db9208c25f459a434dff4893eb8c9ac551e11b3e0619ec019a28465a8395524
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6bdef4bf235b2e7a1dd15a7ee3861111c5457dc62228d7de07fb2f4d8c8d82b
+oid sha256:beaf0630be4f6c976e46d3c6904ffe9ec6370b369d76dc6d38856a38bdd05481
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fafa6c9a89eed395afbdd93c97e61dd14c21bfa70e8a1195a35586745b982c55
+oid sha256:235351173a451302da70c9d458b9d741b6be9a6cb59cf7d0fe6f93d67fba8289
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f8505dca5683fd41f551839def713c06fc6ff169c4cc28d8304f4059ef769f2
+oid sha256:62ab762d9f0d3d15a42cef5723b0f5f86203957cf86c4aa9da4491b50bed6eb5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.5389518413597734,
   "best_model_checkpoint": "/mimer/NOBACKUP/groups/naiss2023-6-290/stefano/models//PROTAC-Splitter-EncoderDecoder-lr_cosine-opt25-rand-smiles/checkpoint-10000",
-  "epoch": 1.4795817715525745,
+  "epoch": 1.9727756954034326,
   "eval_steps": 2500,
-  "global_step": 15000,
+  "global_step": 20000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -343,6 +343,76 @@
       "learning_rate": 4.73054217089226e-05,
       "loss": 0.0042,
       "step": 15000
+    },
+    {
+      "epoch": 1.5289011639376602,
+      "grad_norm": 0.06894150376319885,
+      "learning_rate": 4.712514849304219e-05,
+      "loss": 0.0039,
+      "step": 15500
+    },
+    {
+      "epoch": 1.578220556322746,
+      "grad_norm": 0.057050593197345734,
+      "learning_rate": 4.693940529356444e-05,
+      "loss": 0.0053,
+      "step": 16000
+    },
+    {
+      "epoch": 1.627539948707832,
+      "grad_norm": 0.04995543137192726,
+      "learning_rate": 4.674823803163899e-05,
+      "loss": 0.0034,
+      "step": 16500
+    },
+    {
+      "epoch": 1.6768593410929178,
+      "grad_norm": 0.06972987949848175,
+      "learning_rate": 4.655169396940229e-05,
+      "loss": 0.0031,
+      "step": 17000
+    },
+    {
+      "epoch": 1.7261787334780037,
+      "grad_norm": 0.05143571272492409,
+      "learning_rate": 4.6349821698293025e-05,
+      "loss": 0.0031,
+      "step": 17500
+    },
+    {
+      "epoch": 1.7754981258630895,
+      "grad_norm": 0.06793902069330215,
+      "learning_rate": 4.6142671127038905e-05,
+      "loss": 0.0029,
+      "step": 18000
+    },
+    {
+      "epoch": 1.8248175182481752,
+      "grad_norm": 0.05504274740815163,
+      "learning_rate": 4.593029346931777e-05,
+      "loss": 0.0029,
+      "step": 18500
+    },
+    {
+      "epoch": 1.874136910633261,
+      "grad_norm": 0.07636507600545883,
+      "learning_rate": 4.571274123109606e-05,
+      "loss": 0.0028,
+      "step": 19000
+    },
+    {
+      "epoch": 1.9234563030183467,
+      "grad_norm": 0.08288216590881348,
+      "learning_rate": 4.549006819764779e-05,
+      "loss": 0.0027,
+      "step": 19500
+    },
+    {
+      "epoch": 1.9727756954034326,
+      "grad_norm": 0.07712626457214355,
+      "learning_rate": 4.52623294202573e-05,
+      "loss": 0.0027,
+      "step": 20000
     }
   ],
   "logging_steps": 500,
@@ -362,7 +432,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.309637623513728e+17,
+  "total_flos": 1.746034901972567e+17,
   "train_batch_size": 128,
   "trial_name": null,
   "trial_params": null