Training in progress, step 20000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3efb1b806a1369fca34a3e3273471a9c86ec0acbe20b2e1c6271278f4ada404a
+oid sha256:835536a9f4bc9598d2aa3d301a8969869c1e49d0f59b9b2fd55cab35a3ffcfcf
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:110a93e7b792f45fc0500576ccbd59c0bb82a66066fe3977c2bcd7d8084b21d3
+oid sha256:a29aea1f4bc620e4c56dc629ab7626d669e605a3ac2ec6a60c73ef081803e046
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed8a996caa4721c8629cbedbae34cd38c3fcc2d3348e4fa1f806a13c16379e70
+oid sha256:d17dc07ba223f477f407e44715d157a31fe9df81f7f77bc0d31d54494107c73d
 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": 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": 5e-05,
       "loss": 0.0035,
       "step": 15000
+    },
+    {
+      "epoch": 1.5289011639376602,
+      "grad_norm": 0.044646210968494415,
+      "learning_rate": 5e-05,
+      "loss": 0.0022,
+      "step": 15500
+    },
+    {
+      "epoch": 1.578220556322746,
+      "grad_norm": 0.04811064526438713,
+      "learning_rate": 5e-05,
+      "loss": 0.0021,
+      "step": 16000
+    },
+    {
+      "epoch": 1.627539948707832,
+      "grad_norm": 0.054762303829193115,
+      "learning_rate": 5e-05,
+      "loss": 0.0024,
+      "step": 16500
+    },
+    {
+      "epoch": 1.6768593410929178,
+      "grad_norm": 0.04429342970252037,
+      "learning_rate": 5e-05,
+      "loss": 0.0022,
+      "step": 17000
+    },
+    {
+      "epoch": 1.7261787334780037,
+      "grad_norm": 0.06518573313951492,
+      "learning_rate": 5e-05,
+      "loss": 0.0022,
+      "step": 17500
+    },
+    {
+      "epoch": 1.7754981258630895,
+      "grad_norm": 0.043648600578308105,
+      "learning_rate": 5e-05,
+      "loss": 0.0021,
+      "step": 18000
+    },
+    {
+      "epoch": 1.8248175182481752,
+      "grad_norm": 0.044574983417987823,
+      "learning_rate": 5e-05,
+      "loss": 0.0021,
+      "step": 18500
+    },
+    {
+      "epoch": 1.874136910633261,
+      "grad_norm": 0.05319111794233322,
+      "learning_rate": 5e-05,
+      "loss": 0.0021,
+      "step": 19000
+    },
+    {
+      "epoch": 1.9234563030183467,
+      "grad_norm": 0.05567469820380211,
+      "learning_rate": 5e-05,
+      "loss": 0.0021,
+      "step": 19500
+    },
+    {
+      "epoch": 1.9727756954034326,
+      "grad_norm": 0.045425355434417725,
+      "learning_rate": 5e-05,
+      "loss": 0.0019,
+      "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