Training in progress, step 10000, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebb0d1344d85e1fc40cd8989c7c6db8bce3a550c89c85b825448ecbec3b9d6c1
+oid sha256:ff5f848615af7284182bf34bb526cf66a4611210963f90a45f3c9021871e1d85
 size 1600779

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2abc969de4ce645f9d76eb977581465612165dd82ab373f63378a5f647630661
+oid sha256:2b4c790553f3e4092f7857a64225265bb38246a5d8a25fe76b1107d5f0509e1f
 size 621149155

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2f17c67fa754158f3c03c5f9856c1aa1a0efb60e8b2ba7ff0933cd7e615deac
+oid sha256:189ca5f500a151c520561b912184d219fb4a14e37e0545ece3a7916f40a7b6f6
 size 14469

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:418ff55ed0dbe835354a2c0bf4053deea4eb6d628f7fb25addc88d7dd433e1a0
+oid sha256:585e6d762d92f384f163db69802c96c5f70ee11af325886531da1e25dbdd3c46
 size 14469

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a35f8395aebcabd2d2ff704dcd0a2516f18acacf15eaa6f6de4d80c3f5a64ac
+oid sha256:23411dc088849538602b2c97c02e11f26fb822081e4a284d2b43ea9891ec5924
 size 14469

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20538af5e8a8c67556fafaef54a8d5e99ae679aaa736d860c04c1a2e37c3c03c
+oid sha256:a96d850263b64569ae2096b8d72bc91a5ebdd71deb02d3267c85822dd6891262
 size 14469

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7766e34119d4055998fe3273163a12ee2907d627abe9c4714c8b112cc18d1fb5
+oid sha256:14acad3fcc328519114bc488b787139326de9b018d7a082a9a787fbad2c61513
 size 14469

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b86ea660b800de8c8f56b525f1c8ec70de64ab61f7f595cc6d7a9eec27f020ed
+oid sha256:4d9d4bb8960e987a9f4826d17f0ffbf80325efd81a2b4fbccc2aba1b74b8cb51
 size 14469

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afea3cb817289360580454c91b5d591d50af9204d37e43c3818d916f106c73a9
+oid sha256:ca2326a5fbe6bf3c05da0cff924b9b40c864d3c0c3f624c13f7edec4700ef239
 size 14469

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f608549c3734c6d52376589878069a475672b0ca9e5e32be42d15b90c85b8d1
+oid sha256:df1ed186896b3430710bec5fd2c1b85c275cbb3ef74ad87064fdc0302116db5c
 size 14469

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9567d76a2efaa946d19913fd9fe6f6f70f6f7101d7dcb8866c09743534f2d4d
+oid sha256:833776bf99a0597a4bf38df86be38e8ac151736eba1d084c9cbb84cab1caf4e9
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.16,
+  "epoch": 0.2,
   "eval_steps": 1000,
-  "global_step": 8000,
+  "global_step": 10000,
   "is_hyper_param_search": false,
   "is_local_process_zero": false,
   "is_world_process_zero": true,
@@ -640,6 +640,164 @@
       "eval_samples_per_second": 38.613,
       "eval_steps_per_second": 0.618,
       "step": 8000
+    },
+    {
+      "epoch": 0.162,
+      "grad_norm": 1.4030160903930664,
+      "learning_rate": 0.0019322148017972016,
+      "loss": 32.8396,
+      "step": 8100
+    },
+    {
+      "epoch": 0.164,
+      "grad_norm": 2.127406597137451,
+      "learning_rate": 0.001929800831168135,
+      "loss": 32.9587,
+      "step": 8200
+    },
+    {
+      "epoch": 0.166,
+      "grad_norm": 1.437472939491272,
+      "learning_rate": 0.001927346188038576,
+      "loss": 33.9238,
+      "step": 8300
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 1.5702464580535889,
+      "learning_rate": 0.0019248509797825672,
+      "loss": 33.8778,
+      "step": 8400
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 1.6056277751922607,
+      "learning_rate": 0.0019223153155486009,
+      "loss": 33.6902,
+      "step": 8500
+    },
+    {
+      "epoch": 0.172,
+      "grad_norm": 1.6342443227767944,
+      "learning_rate": 0.0019197393062548454,
+      "loss": 33.2568,
+      "step": 8600
+    },
+    {
+      "epoch": 0.174,
+      "grad_norm": 1.5210442543029785,
+      "learning_rate": 0.0019171230645842923,
+      "loss": 33.2864,
+      "step": 8700
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 2.7911336421966553,
+      "learning_rate": 0.0019144667049798272,
+      "loss": 32.8163,
+      "step": 8800
+    },
+    {
+      "epoch": 0.178,
+      "grad_norm": 1.7785000801086426,
+      "learning_rate": 0.0019117703436392253,
+      "loss": 32.6067,
+      "step": 8900
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.7542123794555664,
+      "learning_rate": 0.001909034098510066,
+      "loss": 33.2589,
+      "step": 9000
+    },
+    {
+      "epoch": 0.18,
+      "eval_accuracy": 0.2880078277886497,
+      "eval_loss": 33.28087615966797,
+      "eval_runtime": 3.2266,
+      "eval_samples_per_second": 38.74,
+      "eval_steps_per_second": 0.62,
+      "step": 9000
+    },
+    {
+      "epoch": 0.182,
+      "grad_norm": 1.2243378162384033,
+      "learning_rate": 0.001906258089284576,
+      "loss": 33.5476,
+      "step": 9100
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 1.503909707069397,
+      "learning_rate": 0.0019034424373943915,
+      "loss": 33.7592,
+      "step": 9200
+    },
+    {
+      "epoch": 0.186,
+      "grad_norm": 1.6347205638885498,
+      "learning_rate": 0.0019005872660052478,
+      "loss": 33.2045,
+      "step": 9300
+    },
+    {
+      "epoch": 0.188,
+      "grad_norm": 1.5243566036224365,
+      "learning_rate": 0.001897692700011591,
+      "loss": 32.841,
+      "step": 9400
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 1.8256958723068237,
+      "learning_rate": 0.0018947588660311143,
+      "loss": 32.7556,
+      "step": 9500
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 1.5017831325531006,
+      "learning_rate": 0.0018917858923992211,
+      "loss": 32.2029,
+      "step": 9600
+    },
+    {
+      "epoch": 0.194,
+      "grad_norm": 2.1232316493988037,
+      "learning_rate": 0.0018887739091634085,
+      "loss": 32.9246,
+      "step": 9700
+    },
+    {
+      "epoch": 0.196,
+      "grad_norm": 2.373900890350342,
+      "learning_rate": 0.0018857230480775807,
+      "loss": 33.4374,
+      "step": 9800
+    },
+    {
+      "epoch": 0.198,
+      "grad_norm": 1.6649442911148071,
+      "learning_rate": 0.0018826334425962855,
+      "loss": 33.1861,
+      "step": 9900
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 2.6526882648468018,
+      "learning_rate": 0.0018795052278688753,
+      "loss": 33.3808,
+      "step": 10000
+    },
+    {
+      "epoch": 0.2,
+      "eval_accuracy": 0.2909138943248532,
+      "eval_loss": 33.03311538696289,
+      "eval_runtime": 3.1811,
+      "eval_samples_per_second": 39.294,
+      "eval_steps_per_second": 0.629,
+      "step": 10000
     }
   ],
   "logging_steps": 100,