Training in progress, step 6000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69467c88089542112a33c720565df1937552a91acb51277f729bd81c6332402a
+oid sha256:7ea438799779b7d5df6829426c8563db0aaf689f4b71b2db885dde813b47a656
 size 498612824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f49b906dad2d7e5a5cabc2e5adbe1256d559062a1234b9044f503daee2087534
+oid sha256:ac7b943d7b3f892e05c3280199300655641226024c9d46fc2c36377844e09219
 size 997345931

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0803eee0cc4b44a8c79fa5161eb36c1013a59026d1e3aac33a448e1060b90877
+oid sha256:903ae64856702f56aca34b3a83e463f26492f960398b5b01c03e210465cf26b7
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82ad8990572ad11a824b7db276c8af49c179ca7e7724b4e6906cd0ae480a80a8
+oid sha256:7bb2b51b22f222dc6df63edb791d76de5de25b8bb724e885f8753e34cfb8ae10
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f5c61836752c5cd874ae10fff449a3b3dbeeab2bd4bed5842bd633a119b55c5
+oid sha256:d6ac56f1033e9e261dd3b41721e9cff6132800378e9f573cebb3fd9f04365c7d
 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": 0.25,
+  "epoch": 0.3,
   "eval_steps": 1000,
-  "global_step": 5000,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -123,6 +123,29 @@
       "eval_samples_per_second": 55.058,
       "eval_steps_per_second": 3.441,
       "step": 5000
+    },
+    {
+      "epoch": 0.275,
+      "grad_norm": 0.2668807804584503,
+      "learning_rate": 1.4501e-05,
+      "loss": 0.0442,
+      "step": 5500
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.0010613143676891923,
+      "learning_rate": 1.4001e-05,
+      "loss": 0.042,
+      "step": 6000
+    },
+    {
+      "epoch": 0.3,
+      "eval_accuracy": 0.93495,
+      "eval_loss": 0.15857931971549988,
+      "eval_runtime": 363.6803,
+      "eval_samples_per_second": 54.993,
+      "eval_steps_per_second": 3.437,
+      "step": 6000
     }
   ],
   "logging_steps": 500,
@@ -142,7 +165,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5262221107200000.0,
+  "total_flos": 6314665328640000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null