Training in progress, step 9500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d2fed1926239147914453e57ca85f79acce260462bc2afc598586f72fadfed2
+oid sha256:1b32feb03bef74682dd00478366b7ab6f3fe36e62ad6f43eb0b6a45298c8c420
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:374dfd8815428e9c5168f02a86bf74d702f63ce34b2283eb2726587be36c804f
+oid sha256:caf09d3b5479867cad574a9d4855fce3be35781906f4a4d330605331dc904195
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83d62ea030413978bd3636ba1f9d9d6f1ba38759b40011d5c2748b76c830d832
+oid sha256:237cdd142ba1e146dbe902d7b81dd4a005d04aa5a22539b30a7f706ed6c82716
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:306dd95734f7ad38a3bb53f9bba14ecb71a74aa00d06cd261b25b11270f7475e
+oid sha256:f0de9502ba6141c06b2056fb55ea065632b45dc42bb9ad6136e46e95f561ac79
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.7406483790523692,
+  "epoch": 3.9484621778886115,
   "eval_steps": 500,
-  "global_step": 9000,
+  "global_step": 9500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -157,6 +157,13 @@
       "learning_rate": 5.0423940149625935e-06,
       "loss": 0.316,
       "step": 9000
+    },
+    {
+      "epoch": 3.9484621778886115,
+      "grad_norm": 0.5943393707275391,
+      "learning_rate": 4.212801330008313e-06,
+      "loss": 0.3155,
+      "step": 9500
     }
   ],
   "logging_steps": 500,
@@ -176,7 +183,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.192065718648832e+16,
+  "total_flos": 2.313857296760832e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null