Training in progress, epoch 4, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b4f351bdef37b99932bd495f8b0b0afe2c0f87f8454adc76cf3dbd858ba4617
+oid sha256:de87753c51b74ab8131c11f3f66daf5c80a47d1d7f8a402554fdff6546ad0ecb
 size 526442440

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ccbfc72547222586e45bfe7e86c78c37bb4febfde829ead16c399ddfde7a46b
+oid sha256:25783f1e6e355472ed9b7334d4f772e8b9bfee4e7121f9d95b415afec30cfbd8
 size 1052723962

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3095ebfab2ca941d53e571e1509e7ec0364952a9c7f0e86af9627565ed929ceb
+oid sha256:bd70ccb7e9acb04f2604ca4bf8b22933ab4dae5d9423c4cd37258b77233af304
 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": 0.34028616547584534,
   "best_model_checkpoint": "./vit5_viqp/checkpoint-2538",
-  "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": 513.642,
       "eval_steps_per_second": 16.232,
       "step": 2538
+    },
+    {
+      "epoch": 3.546099290780142,
+      "grad_norm": 0.9152936935424805,
+      "learning_rate": 8.723404255319149e-06,
+      "loss": 0.2195,
+      "step": 3000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.3464270532131195,
+      "eval_runtime": 4.467,
+      "eval_samples_per_second": 517.123,
+      "eval_steps_per_second": 16.342,
+      "step": 3384
     }
   ],
   "logging_steps": 500,
@@ -85,7 +100,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1932662400122880.0,
+  "total_flos": 2576883200163840.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null