Training in progress, step 35000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0da757dae7426ef048cb05007a9e8cc866c7809f526038bb402f16db5d389611
+oid sha256:483ae222a11ad65143d340dfeb9c147487c0e9d7650c854f6fa4e6913822f4ac
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf5ca0119d5695b7e96fe99dee15af21c07ac5cb203da9ebad40c75be6b9c6e8
+oid sha256:a57b7ac202a308e621e5caa585c7bf49d7660d1bf4e2e4136fe4ce9cfc2f2612
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25d275e5bd5686989d2ea4200feefdfb83eea3830cac3cc0405b8c50796be68a
+oid sha256:484914ffc89ec808f83bedc7e13af0a69fde5616be4a86784457fcd8d54f74ae
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb270de604813702a7f44531d8515d6c4a3e260cf1bf92145b70cf4f160804ba
+oid sha256:253cb0c7aa8e83fabe20fc0de3d6da7c690f3ee9b7052b32a92753a48a7bfa6d
 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": 2.959163543105149,
+  "epoch": 3.4523574669560073,
   "eval_steps": 2500,
-  "global_step": 30000,
+  "global_step": 35000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -553,6 +553,76 @@
       "learning_rate": 3.4919352524861338e-06,
       "loss": 0.0007,
       "step": 30000
+    },
+    {
+      "epoch": 3.008482935490235,
+      "grad_norm": 0.02103266492486,
+      "learning_rate": 4.476930572223925e-08,
+      "loss": 0.0006,
+      "step": 30500
+    },
+    {
+      "epoch": 3.0578023278753204,
+      "grad_norm": 0.05578412860631943,
+      "learning_rate": 4.787605021812086e-05,
+      "loss": 0.0031,
+      "step": 31000
+    },
+    {
+      "epoch": 3.1071217202604062,
+      "grad_norm": 0.028496012091636658,
+      "learning_rate": 4.073095871744838e-05,
+      "loss": 0.0016,
+      "step": 31500
+    },
+    {
+      "epoch": 3.156441112645492,
+      "grad_norm": 0.01569642685353756,
+      "learning_rate": 3.01022397359359e-05,
+      "loss": 0.001,
+      "step": 32000
+    },
+    {
+      "epoch": 3.205760505030578,
+      "grad_norm": 0.043978385627269745,
+      "learning_rate": 1.8343627600599105e-05,
+      "loss": 0.0008,
+      "step": 32500
+    },
+    {
+      "epoch": 3.255079897415664,
+      "grad_norm": 0.045741546899080276,
+      "learning_rate": 8.05907195665312e-06,
+      "loss": 0.0006,
+      "step": 33000
+    },
+    {
+      "epoch": 3.3043992898007497,
+      "grad_norm": 0.01765783689916134,
+      "learning_rate": 1.526092014020153e-06,
+      "loss": 0.0006,
+      "step": 33500
+    },
+    {
+      "epoch": 3.3537186821858356,
+      "grad_norm": 0.06937197595834732,
+      "learning_rate": 4.980858104780184e-05,
+      "loss": 0.0009,
+      "step": 34000
+    },
+    {
+      "epoch": 3.4030380745709214,
+      "grad_norm": 0.03800417482852936,
+      "learning_rate": 4.567612427657311e-05,
+      "loss": 0.0025,
+      "step": 34500
+    },
+    {
+      "epoch": 3.4523574669560073,
+      "grad_norm": 0.015555808320641518,
+      "learning_rate": 3.6959108562141376e-05,
+      "loss": 0.0012,
+      "step": 35000
     }
   ],
   "logging_steps": 500,
@@ -572,7 +642,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.599358235167017e+17,
+  "total_flos": 3.032375853388385e+17,
   "train_batch_size": 128,
   "trial_name": null,
   "trial_params": null