Training in progress, step 2500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21a8e3a7c437f2596088fad50489a7bb2ed9def0a75481fa3ea23cf009f8e2d7
+oid sha256:7df6efaf3479df75dd3f240aa0deaecfa553e8dd4922633b6fd9e3d93510d4c0
 size 2682482800

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:315ef2407c690abd058c31d25ca395651dae325fc56d06a59faa635e22d871e6
+oid sha256:402a389b6557c2fb0a540c46b58022ae6c3462bad9c7f07206dff1d510985d12
 size 5365108834

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ea26f59a420497cca21bbb6c5a76b307a2356fa2099a000f1378e8c6c7dd674
+oid sha256:49aeb81dec758bb845227eb0ece2bc88efabbe9639e92f4b77310c772ef30111
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed285da3bd9884d1b491678c6c4c4443831eaa068a1151035b5d832ffe3502b2
+oid sha256:584dc0282c266e7acbd2b133cd5329f45751980f00c2875f476a8bdc1ebbeb4e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdf537be4628de0ed5f960b43d5cc07c3b03484d41ff68f24d8ec2c14b057a9a
+oid sha256:933292b2d94ca70b4493534389dbddf5888e0d81ecc65103071a3ee2cc561863
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e611ba9650a64094177d437392c96ee2158ab3d2635b77d9b1072b9aa35c974
+oid sha256:64dba4ebc106a15b3d3dc6ad915f8de1d3566136ab0566e7f79333b0f1ff1c71
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e949960d3d4b878da9fe1bb0cd20ae8736c4aa4b7e2ccd57b11e5b880260dcdd
+oid sha256:c8da03d8897acf9728edfb4d452369c8865b03641c697f2b4969095966c59c18
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.15344189347296547,
+  "epoch": 0.19180236684120683,
   "eval_steps": 500,
-  "global_step": 2000,
+  "global_step": 2500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -287,6 +287,76 @@
       "learning_rate": 8.46555163418751e-05,
       "loss": 63.123,
       "step": 2000
+    },
+    {
+      "epoch": 0.1572779408097896,
+      "grad_norm": 31.457361221313477,
+      "learning_rate": 8.427190425042197e-05,
+      "loss": 63.1952,
+      "step": 2050
+    },
+    {
+      "epoch": 0.16111398814661373,
+      "grad_norm": 19.572940826416016,
+      "learning_rate": 8.388829215896885e-05,
+      "loss": 62.8529,
+      "step": 2100
+    },
+    {
+      "epoch": 0.16495003548343787,
+      "grad_norm": 34.743125915527344,
+      "learning_rate": 8.350468006751573e-05,
+      "loss": 62.6967,
+      "step": 2150
+    },
+    {
+      "epoch": 0.168786082820262,
+      "grad_norm": 27.31527328491211,
+      "learning_rate": 8.312106797606261e-05,
+      "loss": 62.6359,
+      "step": 2200
+    },
+    {
+      "epoch": 0.17262213015708613,
+      "grad_norm": 35.15655517578125,
+      "learning_rate": 8.273745588460949e-05,
+      "loss": 62.3291,
+      "step": 2250
+    },
+    {
+      "epoch": 0.17645817749391027,
+      "grad_norm": 38.50543212890625,
+      "learning_rate": 8.235384379315636e-05,
+      "loss": 62.4786,
+      "step": 2300
+    },
+    {
+      "epoch": 0.1802942248307344,
+      "grad_norm": 33.36336135864258,
+      "learning_rate": 8.197023170170324e-05,
+      "loss": 62.0836,
+      "step": 2350
+    },
+    {
+      "epoch": 0.18413027216755853,
+      "grad_norm": 50.12577438354492,
+      "learning_rate": 8.158661961025011e-05,
+      "loss": 61.8858,
+      "step": 2400
+    },
+    {
+      "epoch": 0.1879663195043827,
+      "grad_norm": 62.16424560546875,
+      "learning_rate": 8.120300751879699e-05,
+      "loss": 61.8654,
+      "step": 2450
+    },
+    {
+      "epoch": 0.19180236684120683,
+      "grad_norm": 47.132232666015625,
+      "learning_rate": 8.081939542734386e-05,
+      "loss": 61.6991,
+      "step": 2500
     }
   ],
   "logging_steps": 50,
@@ -306,7 +376,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.4284373374266245e+18,
+  "total_flos": 4.285389072253321e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null