Training in progress, step 215800, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bddab7f4957d27a6847ca06f0925360cad688d5126cb8b0f0b14295a0f6c1a07
+oid sha256:27e5940bc93f7cff15956075e09a7ca10ff525d1b7c9454eb76d35a49ab214d0
 size 1715561468

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe9dcb39294a7f1e2d978dc41deec0cbca2c66ade4bb3b5570648b11c203243d
+oid sha256:5cd2491474ec7e902135dfb582471eb48d09d9194e1783a1a027f37f00e527d0
 size 3431474364

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b6a5e7fd21b9523549665ff67e6ec11ccd4e947f5af3b8c0a472299c1e46c0b
+oid sha256:b7be69f4f5a92bd2333e98a6ee6690d48a2a8d1f1f78465c4960abc5c608a82c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 21.57510257180026,
+  "epoch": 21.595116581607126,
   "eval_steps": 1000,
-  "global_step": 215600,
+  "global_step": 215800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -9273,6 +9273,13 @@
       "learning_rate": 3.0338827527763924e-05,
       "loss": 0.3548,
       "step": 215600
+    },
+    {
+      "epoch": 21.595116581607126,
+      "grad_norm": 2.6156089305877686,
+      "learning_rate": 3.030811030135342e-05,
+      "loss": 0.3513,
+      "step": 215800
     }
   ],
   "logging_steps": 200,
@@ -9292,7 +9299,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.090851329086259e+18,
+  "total_flos": 3.0937185381113856e+18,
   "train_batch_size": 6,
   "trial_name": null,
   "trial_params": null