Training in progress, epoch 6, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a00e33a391d7f6dac1854ca690c36f5e517ea39ca5dcf2c02891d70aecb451dd
+oid sha256:6734f2bf0d7704285c0d776fbe9beaf3d69eecad7b1e8e52c4e2d6776716a958
 size 904009512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fa83855ac41600e01cdd2aa3fa86bbf2490c23c8004e1024ba195f739bb40a2
+oid sha256:f110224f9fae15a6c29e26f2ef2b6bad6d331cf6a18691fe5079ccd87a43664e
 size 1808174394

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac3038f55d3a561b06ae26808d7769794eb7ea6cbb18a398eda908db5b16f89c
+oid sha256:52fe3de68532b2dada9c45a3b3f6276496da58acf2d2a06fdf62a0ec13c2e0d8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8afcd779c2ecaf2394b38a40f987f6f544f5be2d8a19347150a4a2d340c1d0d9
+oid sha256:c79396e83949d8eceb0bea047df8b8384817261528a6131425263399e807f71c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.1894019991159439,
   "best_model_checkpoint": "./vit5_viqp/checkpoint-1079",
-  "epoch": 5.0,
+  "epoch": 6.0,
   "eval_steps": 500,
-  "global_step": 5395,
+  "global_step": 6474,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -117,6 +117,20 @@
       "eval_samples_per_second": 208.168,
       "eval_steps_per_second": 6.507,
       "step": 5395
+    },
+    {
+      "epoch": 5.097312326227989,
+      "grad_norm": 0.7390459775924683,
+      "learning_rate": 4.513438368860056e-06,
+      "loss": 0.054,
+      "step": 5500
+    },
+    {
+      "epoch": 5.560704355885079,
+      "grad_norm": 0.8077104687690735,
+      "learning_rate": 2.1964782205746062e-06,
+      "loss": 0.0506,
+      "step": 6000
     }
   ],
   "logging_steps": 500,
@@ -131,12 +145,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.31329381072896e+16,
+  "total_flos": 1.575952572874752e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null