Training in progress, step 1150, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f382b6ccfd043cff4d723cdc6ac700faa9657c5dbdd56fbaa8164408bcfd8def
+oid sha256:372c4fa1ddcbc2d26080c15a7dedb5ecb25425eaf74867f4ee058237d145e6ae
 size 136989964

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:879d83143eb40f7b4f9b6418d0640c94081c7a12d29bd7369a6e5df52110185b
+oid sha256:5ef58bea9349779441101ebf61d67a464de8e9c348578f265a12c5a9726c618d
 size 270158266

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61d690a0fe27fa8dfbd79d7d99d9c69ad6925b6ad05e7c913531a6a3877cfe9a
+oid sha256:3dc0a25c5d51592899639c4ec8e73a958601ed51e527e87a4334bd2223af7933
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12b91ebc34e64aba6cb3a9ef5447a63d39a4180753196351265ef608207c50e2
+oid sha256:5a06e38b8724ec8e02cc840fc04391511b1d93865956c0d0c5b9029f53c86a64
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1bed57204bbe38f59efd71adaccc9e12a170bd5f3d998d602668b27ad499468
+oid sha256:4eeb1a2739daf8c0c81fa36b37335a341e63bbc54f8ca37af8dfa337c1d558f5
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ae1774904c3d5cc7e9b870421269b7d274cef2c01e34b8ca1f75569589d4512
+oid sha256:e9d0afd84fc4e5776b42eea358a416175d56a29059dcef96a293d9266ec4bbf2
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa1171bff7e5fc8b86386c74357e71c79ad184d753150ca3bdb776946bffb42f
+oid sha256:79506734c4478e9272f2e0231a801f504a65b47290ff0a985140f63aa7c5b3bd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.2798523008823395,
   "best_model_checkpoint": "mgh6/TCS_Pair_base/checkpoint-950",
-  "epoch": 0.2588539828215084,
+  "epoch": 0.2706200729497588,
   "eval_steps": 50,
-  "global_step": 1100,
+  "global_step": 1150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -337,6 +337,21 @@
       "eval_samples_per_second": 916.664,
       "eval_steps_per_second": 3.594,
       "step": 1100
+    },
+    {
+      "epoch": 0.2706200729497588,
+      "grad_norm": 0.29601240158081055,
+      "learning_rate": 0.0009729348081901624,
+      "loss": 0.2786,
+      "step": 1150
+    },
+    {
+      "epoch": 0.2706200729497588,
+      "eval_loss": 0.2799623906612396,
+      "eval_runtime": 6.117,
+      "eval_samples_per_second": 917.282,
+      "eval_steps_per_second": 3.597,
+      "step": 1150
     }
   ],
   "logging_steps": 50,
@@ -351,7 +366,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 3
+        "early_stopping_patience_counter": 4
       }
     },
     "TrainerControl": {