Training in progress, step 65000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0716e05b7be0802eaf3e025833847e8a3cae599b796d778d586c13f3d195761
+oid sha256:5eb7417fd05987e94e77dc15f6dd9ec3188574d18a6f308eef6ee01d32c516aa
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac850fbcce728867ed8902fa223176fea14017c30527b0b8a62896ea10e17974
+oid sha256:536d9d4ac5a4e3b8f8430f128ced2edec56ca8ac219ebb21b6d3a5db6375c3ad
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc90a600027e1aba1caa11eec2a0f46a3006ea83630bb9dfb9aa44a091d77fcf
+oid sha256:8b8012fbd0d7e4287f476308b3defe2cd698e9d90522ea0a0958949b79663329
 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": 5.918327086210298,
+  "epoch": 6.411521010061156,
   "eval_steps": 2500,
-  "global_step": 60000,
+  "global_step": 65000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -973,6 +973,76 @@
       "learning_rate": 5e-05,
       "loss": 0.0007,
       "step": 60000
+    },
+    {
+      "epoch": 5.967646478595384,
+      "grad_norm": 0.0135957645252347,
+      "learning_rate": 5e-05,
+      "loss": 0.0007,
+      "step": 60500
+    },
+    {
+      "epoch": 6.01696587098047,
+      "grad_norm": 0.016737064346671104,
+      "learning_rate": 5e-05,
+      "loss": 0.0007,
+      "step": 61000
+    },
+    {
+      "epoch": 6.066285263365556,
+      "grad_norm": 0.0470641553401947,
+      "learning_rate": 5e-05,
+      "loss": 0.0008,
+      "step": 61500
+    },
+    {
+      "epoch": 6.115604655750641,
+      "grad_norm": 0.037444982677698135,
+      "learning_rate": 5e-05,
+      "loss": 0.0009,
+      "step": 62000
+    },
+    {
+      "epoch": 6.164924048135727,
+      "grad_norm": 0.03800535574555397,
+      "learning_rate": 5e-05,
+      "loss": 0.0006,
+      "step": 62500
+    },
+    {
+      "epoch": 6.2142434405208125,
+      "grad_norm": 0.02700197882950306,
+      "learning_rate": 5e-05,
+      "loss": 0.0006,
+      "step": 63000
+    },
+    {
+      "epoch": 6.263562832905898,
+      "grad_norm": 0.03783607482910156,
+      "learning_rate": 5e-05,
+      "loss": 0.0008,
+      "step": 63500
+    },
+    {
+      "epoch": 6.312882225290984,
+      "grad_norm": 0.03808404505252838,
+      "learning_rate": 5e-05,
+      "loss": 0.0011,
+      "step": 64000
+    },
+    {
+      "epoch": 6.36220161767607,
+      "grad_norm": 0.016872331500053406,
+      "learning_rate": 5e-05,
+      "loss": 0.0011,
+      "step": 64500
+    },
+    {
+      "epoch": 6.411521010061156,
+      "grad_norm": 0.032465968281030655,
+      "learning_rate": 5e-05,
+      "loss": 0.0005,
+      "step": 65000
     }
   ],
   "logging_steps": 500,
@@ -992,7 +1062,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.2375401437785344e+17,
+  "total_flos": 5.674161087565732e+17,
   "train_batch_size": 128,
   "trial_name": null,
   "trial_params": null