Training in progress, step 65000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c192e3fb64b6d2215ee80a1e81d4a7b40e6e392bdc630777c1cce4c375dfca9
+oid sha256:d083eeea3dfec5b1393fdd67d18cf350a19dba24cdccca76b8368e84aa14022e
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7b7fd64d9431210526488e5610bbb5649e83d0d57266f9036be41a3effe895d
+oid sha256:2a213c85232ab2700c00e507431ba4f57190afe0d7b163aaa4f39df7e540afea
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e889596228db17663ecb13b2fce77d8ba3c8a669b35fa2635f61decf3f846c99
+oid sha256:98a08e00b96f6b985f14cdeb757cc6ef40a66bb7f1e67d59cc3b39f4a794879e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef1d74469a9031736961603cae781746a8ba961151ce2a3fac12b55ae58cb63e
+oid sha256:d36242d950e4eda8219e3839a3feedd2928f349577003506dfd972c9ca136b2c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.5462110481586402,
   "best_model_checkpoint": "/mimer/NOBACKUP/groups/naiss2023-6-290/stefano/models//PROTAC-Splitter-EncoderDecoder-lr_cosine_restarts-opt25/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": 1.2481721485038734e-06,
       "loss": 0.0004,
       "step": 60000
+    },
+    {
+      "epoch": 5.967646478595384,
+      "grad_norm": 0.09385232627391815,
+      "learning_rate": 4.968972647856831e-05,
+      "loss": 0.0008,
+      "step": 60500
+    },
+    {
+      "epoch": 6.01696587098047,
+      "grad_norm": 0.03150836378335953,
+      "learning_rate": 4.5188130514991015e-05,
+      "loss": 0.0014,
+      "step": 61000
+    },
+    {
+      "epoch": 6.066285263365556,
+      "grad_norm": 0.01714126579463482,
+      "learning_rate": 3.620844809525939e-05,
+      "loss": 0.0007,
+      "step": 61500
+    },
+    {
+      "epoch": 6.115604655750641,
+      "grad_norm": 0.007772900629788637,
+      "learning_rate": 2.4746650090359677e-05,
+      "loss": 0.0005,
+      "step": 62000
+    },
+    {
+      "epoch": 6.164924048135727,
+      "grad_norm": 0.006022776942700148,
+      "learning_rate": 1.3340956530417454e-05,
+      "loss": 0.0004,
+      "step": 62500
+    },
+    {
+      "epoch": 6.2142434405208125,
+      "grad_norm": 0.009159950539469719,
+      "learning_rate": 4.517163092423821e-06,
+      "loss": 0.0004,
+      "step": 63000
+    },
+    {
+      "epoch": 6.263562832905898,
+      "grad_norm": 0.010325823910534382,
+      "learning_rate": 2.2930257615656205e-07,
+      "loss": 0.0003,
+      "step": 63500
+    },
+    {
+      "epoch": 6.312882225290984,
+      "grad_norm": 0.04627057537436485,
+      "learning_rate": 4.857307648820405e-05,
+      "loss": 0.0013,
+      "step": 64000
+    },
+    {
+      "epoch": 6.36220161767607,
+      "grad_norm": 0.028987212106585503,
+      "learning_rate": 4.2172457334497206e-05,
+      "loss": 0.0011,
+      "step": 64500
+    },
+    {
+      "epoch": 6.411521010061156,
+      "grad_norm": 0.009136197157204151,
+      "learning_rate": 3.198390069020853e-05,
+      "loss": 0.0007,
+      "step": 65000
     }
   ],
   "logging_steps": 500,
@@ -992,7 +1062,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.1976814397455616e+17,
+  "total_flos": 5.631143303584635e+17,
   "train_batch_size": 128,
   "trial_name": null,
   "trial_params": null