Training in progress, epoch 4, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f2dba795f983ebfa8bc576c2f1d0d68296df56e8cdfb19ab93c07a517c039c9
+oid sha256:1043c74c3a92d18439b7043caff5a787d6315315dd1820accd6784773028a811
 size 1681761380

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b49159967826626106b29ea921c88d63e5e48f8a6ecef631fca48dc69cdff71d
+oid sha256:9134e09d2dd21e49165eb54a2f77e6481a7ee43f98f2381623a2f31de07e6e0f
 size 3363321371

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09a19aaef42f111888555280649b47e17e8b9aef6b0f2751e3d38c36a7455ffc
+oid sha256:fbd412a0b107b364d2f427b65fd6d02a0700f0f3303694808f7c945a280cf8cc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef991e6d54a748def1d15e9aa5db59645cdada4b710e9a0cf204cbb19b5a98f0
+oid sha256:474f9af054726b2ab5c7025bd689cd3ce2cb05c72768370e2f2f3ad60a4c4028
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.33980002999305725,
   "best_model_checkpoint": "./vit5_viqp/checkpoint-846",
-  "epoch": 3.0,
+  "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 2538,
+  "global_step": 3384,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -66,6 +66,21 @@
       "eval_samples_per_second": 183.769,
       "eval_steps_per_second": 5.807,
       "step": 2538
+    },
+    {
+      "epoch": 3.546099290780142,
+      "grad_norm": 0.963591992855072,
+      "learning_rate": 8.723404255319149e-06,
+      "loss": 0.1599,
+      "step": 3000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.37597477436065674,
+      "eval_runtime": 12.5485,
+      "eval_samples_per_second": 184.086,
+      "eval_steps_per_second": 5.817,
+      "step": 3384
     }
   ],
   "logging_steps": 500,
@@ -85,7 +100,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6868870175784960.0,
+  "total_flos": 9158493567713280.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null