Training in progress, step 118000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4693ab1d7b89c8b62f59e3b745ac1d26958661e43128d0951c45a8dae2b0449
+oid sha256:dfed27d6337a699642afb264f3167a26d2ca21ac0273cb5e18c125ded3a387ba
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46a245f6ed22667309e57e9a46319a8b2fe7b589321a520f67f07d4b72b056ac
+oid sha256:c7801aee86c0670959119d2467b5f94581b85321743ff0b2c1de9d55040ef0a1
 size 268176506

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca5192042f50a136fba0493cd299946cbaf57e870dcaa2fe525804417d01654b
+oid sha256:d12692e3ded8e4b48e14a240df346a1d6bfd5fe5c760f7febc8f9669a6659e15
 size 14942

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:988ef2aca538b3b817a541deff8ad816e9a0af759270c4a157b0d1aedf5cd77c
+oid sha256:27b9b8c3bd8dd54ca219bcc622f7453fe04bec46ffa58e0fd1624344a5a69ef4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 28.182584607973023,
+  "epoch": 28.42346139949416,
   "eval_steps": 500,
-  "global_step": 117000,
+  "global_step": 118000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -826,6 +826,13 @@
       "learning_rate": 6.046735726331005e-05,
       "loss": 0.7535,
       "step": 117000
+    },
+    {
+      "epoch": 28.42346139949416,
+      "grad_norm": 0.5937727689743042,
+      "learning_rate": 5.243716373564603e-05,
+      "loss": 0.7453,
+      "step": 118000
     }
   ],
   "logging_steps": 1000,
@@ -845,7 +852,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.170425106950783e+18,
+  "total_flos": 1.1804289834313318e+18,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null