Training in progress, step 123000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fce8febb2716108038efaaf937387d62f02be7c96e83f3460099c8d88b73dbfc
+oid sha256:cf3347db068ed8381d72d2614b99d290079b5c267bb2297bc18668d9746413ee
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdd7d351278922d4e3181ae6bf23825526c0663f6c38a764181920285733d7a9
+oid sha256:4d71f57dd221410708221eda3423c39de5dcd636994583f199f84f393a1e9480
 size 268176506

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9342fe6807deef12394bcdf0dc46806c9965d5485e123099bca4e5a6f2e9f9a0
+oid sha256:bd569f1a705a1ad9d99351673332581a558f2e1131cc249f63637b426b1267b1
 size 14942

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16b6e7175e1fcf2517ba9872702af9426a0051ef5f446636eb4dab154365c7ce
+oid sha256:d32025f87bd47ef75385673d365a029e9e810c5fd5b698fddba7741fb9b51c62
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 29.386968565578705,
+  "epoch": 29.627845357099844,
   "eval_steps": 500,
-  "global_step": 122000,
+  "global_step": 123000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -861,6 +861,13 @@
       "learning_rate": 2.0316389624989963e-05,
       "loss": 0.7424,
       "step": 122000
+    },
+    {
+      "epoch": 29.627845357099844,
+      "grad_norm": 0.6154918074607849,
+      "learning_rate": 1.2286196097325946e-05,
+      "loss": 0.7431,
+      "step": 123000
     }
   ],
   "logging_steps": 1000,
@@ -880,7 +887,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2204434735937618e+18,
+  "total_flos": 1.2304473500743107e+18,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null