Training in progress, step 8000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b090f420e4a4b79bb9b83dba51d26dd4e2b6d29f1d12b1510721e2bf6bd1ba5
+oid sha256:ff9b9d13a403999251eff19aff272b0a61c5298f7f1d3344e06bf7caf317cb99
 size 498612824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59ebdd708712721a1fa8df534d43f59d69e107f5088893e47e9475f1c9a8e242
+oid sha256:7193b006558d2bce0208a235024debcbfc43b1c84dbc39142f881781de7f37e9
 size 997345931

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db4e3de49d1806c7044e452123303f3ec21f0d1186d1b23be8ec33eb1e34488d
+oid sha256:042657cac1c2755ceda7b4749a7e1933e6cec85079f3b4906e9ed3ef4793888e
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be40a03f70bb2a35bb567114fb5ceb05ce1222c8df24b1e1100746c617c5be10
+oid sha256:022915fa8ac65fae0f13853519b8aa7ee79efd632a399c1f64c6b87bab0b057a
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5503916e083484344eb90ffdd7cef8671b9c273655dd45784cda2988a30dceb9
+oid sha256:bd51c370580a538c410b01e5fc06950a0bc0c9f5c6db475a5d46f392f1675e7e
 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": 0.35,
+  "epoch": 0.4,
   "eval_steps": 1000,
-  "global_step": 7000,
+  "global_step": 8000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -169,6 +169,29 @@
       "eval_samples_per_second": 55.067,
       "eval_steps_per_second": 3.442,
       "step": 7000
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 0.01402213703840971,
+      "learning_rate": 1.2501000000000001e-05,
+      "loss": 0.0418,
+      "step": 7500
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.30465877056121826,
+      "learning_rate": 1.2001e-05,
+      "loss": 0.0428,
+      "step": 8000
+    },
+    {
+      "epoch": 0.4,
+      "eval_accuracy": 0.92455,
+      "eval_loss": 0.11909274756908417,
+      "eval_runtime": 362.4651,
+      "eval_samples_per_second": 55.178,
+      "eval_steps_per_second": 3.449,
+      "step": 8000
     }
   ],
   "logging_steps": 500,
@@ -188,7 +211,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7367109550080000.0,
+  "total_flos": 8419553771520000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null