Training in progress, step 1000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd3f9d192f5a816e59fb112bb1b2bf884e9355b4c87749592150eb4e3ca63999
+oid sha256:fa6629809084d1e0509d4cc289b87169dfa3c861eb012cb080133c56d08207b9
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfc839f69c5de2d1b7b9fa0fbb77dba2374cd6db2e764c061208fa6aac20118e
+oid sha256:b1908de56824c88e293a5e966e8bc8e8f85075aeb828d353732f2c6728fb86b3
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:850fdb4a4c5ca926a1d2d289abd08e04af5e5a7720f1895ef9773ba33f82e5da
+oid sha256:1ca8c345ce95ec23bc2370ba6a62dd7ae760ebb2dcd90f0e2732ef0d124176db
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea31b43fad77e528bb398791d33c59471b96f3e351d60e5432e2dc6e9bfc6c71
+oid sha256:ec90df4419bc1788183d4b14708fe72f6455a84f3d58e7a9984c89581a48157e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:981f653c329838c2984567bec763c5d51584a3bc2569713648bb11a9bab0a732
+oid sha256:c1698f2a3c275181ded2c6f52ffcec238e637f047d2463fda1dc456783c969fd
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f19bd524a4b5807f003926535dbbc8387b715186e497583a1d544522d618d3c2
+oid sha256:4d359f360893dcdb0304a82318ef91c90d17ea356410731fe6784d4cb1aae8f5
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36d4923f2032c364a94f4eb28ac470bd0071fde9669df68c8f0e5888ff61a040
+oid sha256:2ef20705a321e73d88ef11b6e524f85650644866cb653bf90dea905b2590f2fe
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.0223731994628906,
   "best_model_checkpoint": "mgh6/TCS_MLM_All/checkpoint-700",
-  "epoch": 8.571428571428571,
+  "epoch": 9.523809523809524,
   "eval_steps": 100,
-  "global_step": 900,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -142,6 +142,21 @@
       "eval_samples_per_second": 86.964,
       "eval_steps_per_second": 4.577,
       "step": 900
+    },
+    {
+      "epoch": 9.523809523809524,
+      "grad_norm": 0.17410966753959656,
+      "learning_rate": 4.761904761904762e-05,
+      "loss": 1.1496,
+      "step": 1000
+    },
+    {
+      "epoch": 9.523809523809524,
+      "eval_loss": 1.027449131011963,
+      "eval_runtime": 0.217,
+      "eval_samples_per_second": 87.54,
+      "eval_steps_per_second": 4.607,
+      "step": 1000
     }
   ],
   "logging_steps": 100,
@@ -156,7 +171,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 3
       }
     },
     "TrainerControl": {
@@ -170,7 +185,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.638554505150464e+16,
+  "total_flos": 2.93172722794496e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null