Training in progress, step 5000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae7335096cf5b1fd84c6e82b5759ed57ddf44a0e121f4e3c590a965600f0f28e
+oid sha256:69467c88089542112a33c720565df1937552a91acb51277f729bd81c6332402a
 size 498612824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b17f5e96de107e606342fe64d95fbbb83b976cdfb9761f3be3f5ff3925bb785
+oid sha256:f49b906dad2d7e5a5cabc2e5adbe1256d559062a1234b9044f503daee2087534
 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 sha256:012264319a2f0e83b703857fe0c90509f0ba126782a5ba9dccbac93f5b664216
+oid sha256:5f5c61836752c5cd874ae10fff449a3b3dbeeab2bd4bed5842bd633a119b55c5
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 4000,
   "best_metric": 0.04343162104487419,
   "best_model_checkpoint": "./training_output/checkpoint-4000",
-  "epoch": 0.2,
+  "epoch": 0.25,
   "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": 55.303,
       "eval_steps_per_second": 3.456,
       "step": 4000
+    },
+    {
+      "epoch": 0.225,
+      "grad_norm": 0.002397062722593546,
+      "learning_rate": 1.5501000000000003e-05,
+      "loss": 0.0491,
+      "step": 4500
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.02433067187666893,
+      "learning_rate": 1.5001000000000001e-05,
+      "loss": 0.0511,
+      "step": 5000
+    },
+    {
+      "epoch": 0.25,
+      "eval_accuracy": 0.9532,
+      "eval_loss": 0.07725899666547775,
+      "eval_runtime": 363.254,
+      "eval_samples_per_second": 55.058,
+      "eval_steps_per_second": 3.441,
+      "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