Training in progress, step 9000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23750eae96fff9283e7ae8f0bab6faf349cb0a7eb7d62a4385617e3c105b050a
+oid sha256:7d2fed1926239147914453e57ca85f79acce260462bc2afc598586f72fadfed2
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c090d1b505cdd524b425c56d229c74e521a9cfcd2e83913f4b04cd9a688c0244
+oid sha256:374dfd8815428e9c5168f02a86bf74d702f63ce34b2283eb2726587be36c804f
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d6f9191f2eaf4a4097874de4a821f2a97252f64a38cda2d145c006040151b30
+oid sha256:83d62ea030413978bd3636ba1f9d9d6f1ba38759b40011d5c2748b76c830d832
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:432af5fdf516a60295d78030fa17670f1cdc61fda7d1429429265938440f5257
+oid sha256:306dd95734f7ad38a3bb53f9bba14ecb71a74aa00d06cd261b25b11270f7475e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.5328345802161265,
+  "epoch": 3.7406483790523692,
   "eval_steps": 500,
-  "global_step": 8500,
+  "global_step": 9000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -150,6 +150,13 @@
       "learning_rate": 5.873649210307565e-06,
       "loss": 0.3219,
       "step": 8500
+    },
+    {
+      "epoch": 3.7406483790523692,
+      "grad_norm": 0.8144080638885498,
+      "learning_rate": 5.0423940149625935e-06,
+      "loss": 0.316,
+      "step": 9000
     }
   ],
   "logging_steps": 500,
@@ -169,7 +176,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.070274140536832e+16,
+  "total_flos": 2.192065718648832e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null