Training in progress, step 9000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff9b9d13a403999251eff19aff272b0a61c5298f7f1d3344e06bf7caf317cb99
+oid sha256:a7993fcf68be828d73fa2ee6b4a5dc32e8cace8dc797569a99953ce1a3ae5d83
 size 498612824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7193b006558d2bce0208a235024debcbfc43b1c84dbc39142f881781de7f37e9
+oid sha256:b02915a79788add5d714c8aaeec8c9d2926b4de85c51dc0ca45b65e8d73f63ed
 size 997345931

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:042657cac1c2755ceda7b4749a7e1933e6cec85079f3b4906e9ed3ef4793888e
+oid sha256:3106ce26d8876d17e74b10716d47cadecb00ff3a2233d08bdb01a7952809d554
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:022915fa8ac65fae0f13853519b8aa7ee79efd632a399c1f64c6b87bab0b057a
+oid sha256:00b4eb0c27b559cfd649f7c80a6d3394a55880d92b3ee2ca98f71b67e7b2333a
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd51c370580a538c410b01e5fc06950a0bc0c9f5c6db475a5d46f392f1675e7e
+oid sha256:fe28f7d29e7f98f2600c3c6c7c0177a5ef0e8009ada6a2b943e31e01e5a4324e
 size 1465

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 4000,
-  "best_metric": 0.04343162104487419,
-  "best_model_checkpoint": "./training_output/checkpoint-4000",
-  "epoch": 0.4,
+  "best_global_step": 9000,
+  "best_metric": 0.035129010677337646,
+  "best_model_checkpoint": "./training_output/checkpoint-9000",
+  "epoch": 0.45,
   "eval_steps": 1000,
-  "global_step": 8000,
+  "global_step": 9000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -192,6 +192,29 @@
       "eval_samples_per_second": 55.178,
       "eval_steps_per_second": 3.449,
       "step": 8000
+    },
+    {
+      "epoch": 0.425,
+      "grad_norm": 0.002914857817813754,
+      "learning_rate": 1.1501e-05,
+      "loss": 0.0383,
+      "step": 8500
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 40.46672821044922,
+      "learning_rate": 1.1001000000000002e-05,
+      "loss": 0.0387,
+      "step": 9000
+    },
+    {
+      "epoch": 0.45,
+      "eval_accuracy": 0.9744,
+      "eval_loss": 0.035129010677337646,
+      "eval_runtime": 362.2389,
+      "eval_samples_per_second": 55.212,
+      "eval_steps_per_second": 3.451,
+      "step": 9000
     }
   ],
   "logging_steps": 500,
@@ -211,7 +234,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8419553771520000.0,
+  "total_flos": 9471997992960000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null