Training in progress, step 35000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afb3bed924cc247c9bf5ed900473d967e5a40406f2cf73dc437085a692cf3bff
+oid sha256:9b082085d9aa1da3efa2ad33dd1002ddb5511bf8eb3c2067b8fc30888db68b37
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a05edfe8bb04df2c7c74f795b9d1968a33f9e390875a83a3f66260f03453f92
+oid sha256:053d966c702b26ff46dde77ec6b0cff280c687a0dd1a4474041cda54900e0bf9
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a01c7cdcb43da92a58412eddd8d3aaca5d8f574d69ef13bdff2f6fb12bcfd85
+oid sha256:375e808faf0ee5ae5d50ffe1d1a4fc8f21560fc6eeedbd7f2acd27833efa40af
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90ba8e6b312d2e8ffeae2b414a4a618ae53a7f667d9bdc791713f23f485f4a64
+oid sha256:fd12236a2b04dcc8172c63d077f003702ceca140fc00b62558c7c08cdf884e4b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.5477160056657224,
   "best_model_checkpoint": "/mimer/NOBACKUP/groups/naiss2023-6-290/stefano/models//PROTAC-Splitter-EncoderDecoder-lr_cosine-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": 3.974038822893393e-05,
       "loss": 0.001,
       "step": 30000
+    },
+    {
+      "epoch": 3.008482935490235,
+      "grad_norm": 0.03636594116687775,
+      "learning_rate": 3.942108490409635e-05,
+      "loss": 0.0008,
+      "step": 30500
+    },
+    {
+      "epoch": 3.0578023278753204,
+      "grad_norm": 0.02662217803299427,
+      "learning_rate": 3.9098865507980035e-05,
+      "loss": 0.0011,
+      "step": 31000
+    },
+    {
+      "epoch": 3.1071217202604062,
+      "grad_norm": 0.014715551398694515,
+      "learning_rate": 3.8772518268796315e-05,
+      "loss": 0.0009,
+      "step": 31500
+    },
+    {
+      "epoch": 3.156441112645492,
+      "grad_norm": 0.024017762392759323,
+      "learning_rate": 3.8442766060418925e-05,
+      "loss": 0.0008,
+      "step": 32000
+    },
+    {
+      "epoch": 3.205760505030578,
+      "grad_norm": 0.042992159724235535,
+      "learning_rate": 3.8109690407234974e-05,
+      "loss": 0.0008,
+      "step": 32500
+    },
+    {
+      "epoch": 3.255079897415664,
+      "grad_norm": 0.05144192650914192,
+      "learning_rate": 3.777337365528434e-05,
+      "loss": 0.0009,
+      "step": 33000
+    },
+    {
+      "epoch": 3.3043992898007497,
+      "grad_norm": 0.02588796801865101,
+      "learning_rate": 3.7433898951901246e-05,
+      "loss": 0.0008,
+      "step": 33500
+    },
+    {
+      "epoch": 3.3537186821858356,
+      "grad_norm": 0.03916551172733307,
+      "learning_rate": 3.709135022515784e-05,
+      "loss": 0.0008,
+      "step": 34000
+    },
+    {
+      "epoch": 3.4030380745709214,
+      "grad_norm": 0.013717463240027428,
+      "learning_rate": 3.674581216311475e-05,
+      "loss": 0.0008,
+      "step": 34500
+    },
+    {
+      "epoch": 3.4523574669560073,
+      "grad_norm": 0.07564926147460938,
+      "learning_rate": 3.639806991778405e-05,
+      "loss": 0.0009,
+      "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