Training in progress, step 5000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcf23d22c294138c1d68fa041e9886e20af2d855b16919fae100631b81dc7814
+oid sha256:246dbbbe125dd9f9b5a52cdf6d6ee9d82badf3792c8a46a80acda2adc93d1fcd
 size 498612824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce21121864b0c6f3980750c3950640885597182682d719816c98e710f1d97700
+oid sha256:6e079097585256a92e5e61dd33741254b38adb08fd5f29c4bfd0aa873d8b93c8
 size 997345931

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd8861c76c95a138fb74b2279a575c494edce4804040a54509842ed6fd8b90fe
+oid sha256:0803eee0cc4b44a8c79fa5161eb36c1013a59026d1e3aac33a448e1060b90877
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0033c7745b46bdca3ecab5787678834ca68f7f7e1288869dceeb38812abc253
+oid sha256:82ad8990572ad11a824b7db276c8af49c179ca7e7724b4e6906cd0ae480a80a8
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44bf4923ec42942364989fd2f30726b763bdfd466c393a6e0a85d3fa348231ab
+oid sha256:fbf6ddd2a66f70d37335fad267288a7ec7ed4054d23ff856f79d740bcdcd96fc
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 1000,
   "best_metric": 0.08424179255962372,
   "best_model_checkpoint": "./training_output/checkpoint-1000",
-  "epoch": 0.5,
+  "epoch": 0.625,
   "eval_steps": 1000,
-  "global_step": 4000,
+  "global_step": 5000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -100,6 +100,29 @@
       "eval_samples_per_second": 53.85,
       "eval_steps_per_second": 3.366,
       "step": 4000
+    },
+    {
+      "epoch": 0.5625,
+      "grad_norm": 0.641652524471283,
+      "learning_rate": 8.7525e-06,
+      "loss": 0.0463,
+      "step": 4500
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 0.1168695017695427,
+      "learning_rate": 7.502500000000001e-06,
+      "loss": 0.0426,
+      "step": 5000
+    },
+    {
+      "epoch": 0.625,
+      "eval_accuracy": 0.878375,
+      "eval_loss": 0.24468091130256653,
+      "eval_runtime": 148.7322,
+      "eval_samples_per_second": 53.788,
+      "eval_steps_per_second": 3.362,
+      "step": 5000
     }
   ],
   "logging_steps": 500,
@@ -119,7 +142,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4209776885760000.0,
+  "total_flos": 5262221107200000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null