Training in progress, step 20000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ce939ea0d2042e8f7b8de53f40fc48161cfd9c3b12ef07723fc24e541193318
+oid sha256:67db7fb5753287fec24d570fb9e463675efaa498fa6d43a9b9c5b7d5276de37e
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc213f17bb4d889fe875f4e1c0e8389aeae5a422956458396c47435748d4d97a
+oid sha256:885da78fc800f2d8b7fb905e4b00218a8293bb01d93c369ccba96ed84cdd299b
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a1f3e2cec1aef6a799ee4c0a11b97705b1f9de4d321cafe7e6d1e44c37bbd8e
+oid sha256:6129e57ccde2e74721074ef039aefd879898938d0c6bc6383123ae34cb563028
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f8505dca5683fd41f551839def713c06fc6ff169c4cc28d8304f4059ef769f2
+oid sha256:62ab762d9f0d3d15a42cef5723b0f5f86203957cf86c4aa9da4491b50bed6eb5
 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": 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": 4.73054217089226e-05,
       "loss": 0.0027,
       "step": 15000
+    },
+    {
+      "epoch": 1.5289011639376602,
+      "grad_norm": 0.07365080714225769,
+      "learning_rate": 4.712514849304219e-05,
+      "loss": 0.003,
+      "step": 15500
+    },
+    {
+      "epoch": 1.578220556322746,
+      "grad_norm": 0.04787248373031616,
+      "learning_rate": 4.693940529356444e-05,
+      "loss": 0.0025,
+      "step": 16000
+    },
+    {
+      "epoch": 1.627539948707832,
+      "grad_norm": 0.0840035229921341,
+      "learning_rate": 4.674823803163899e-05,
+      "loss": 0.0023,
+      "step": 16500
+    },
+    {
+      "epoch": 1.6768593410929178,
+      "grad_norm": 0.05743684619665146,
+      "learning_rate": 4.655169396940229e-05,
+      "loss": 0.0024,
+      "step": 17000
+    },
+    {
+      "epoch": 1.7261787334780037,
+      "grad_norm": 0.048048391938209534,
+      "learning_rate": 4.6349821698293025e-05,
+      "loss": 0.0022,
+      "step": 17500
+    },
+    {
+      "epoch": 1.7754981258630895,
+      "grad_norm": 0.062112707644701004,
+      "learning_rate": 4.6142671127038905e-05,
+      "loss": 0.0026,
+      "step": 18000
+    },
+    {
+      "epoch": 1.8248175182481752,
+      "grad_norm": 0.034723177552223206,
+      "learning_rate": 4.593029346931777e-05,
+      "loss": 0.0028,
+      "step": 18500
+    },
+    {
+      "epoch": 1.874136910633261,
+      "grad_norm": 0.0403965599834919,
+      "learning_rate": 4.571274123109606e-05,
+      "loss": 0.0016,
+      "step": 19000
+    },
+    {
+      "epoch": 1.9234563030183467,
+      "grad_norm": 0.022397898137569427,
+      "learning_rate": 4.549006819764779e-05,
+      "loss": 0.0016,
+      "step": 19500
+    },
+    {
+      "epoch": 1.9727756954034326,
+      "grad_norm": 0.04490479454398155,
+      "learning_rate": 4.52623294202573e-05,
+      "loss": 0.0017,
+      "step": 20000
     }
   ],
   "logging_steps": 500,
@@ -362,7 +432,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2998395396121242e+17,
+  "total_flos": 1.7329296562502707e+17,
   "train_batch_size": 128,
   "trial_name": null,
   "trial_params": null