Training in progress, step 9000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ae3f4275b264bd8c5c34f45274bf4b8676b63aade815aec8ca835e7003d26cf
+oid sha256:79e8fedd947d21c1b068dc7570fae027d636f21be8675dd6fd8005c44d498fd4
 size 498612824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa2a770695a72b160657657ddc55c4bf4685f336e34287ab0602c40ccd7d5245
+oid sha256:4bff0a2b02dc8212ed9dbee7dadf3298e1df1329d89c3361a3c00a420080fcdb
 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": 0.07567641884088516,
-  "best_model_checkpoint": "./training_output/checkpoint-4000",
-  "epoch": 0.4,
+  "best_global_step": 9000,
+  "best_metric": 0.04935265704989433,
+  "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": 52.505,
       "eval_steps_per_second": 3.282,
       "step": 8000
+    },
+    {
+      "epoch": 0.425,
+      "grad_norm": 0.017685526981949806,
+      "learning_rate": 1.1501e-05,
+      "loss": 0.0384,
+      "step": 8500
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 16.736478805541992,
+      "learning_rate": 1.1001000000000002e-05,
+      "loss": 0.0364,
+      "step": 9000
+    },
+    {
+      "epoch": 0.45,
+      "eval_accuracy": 0.96285,
+      "eval_loss": 0.04935265704989433,
+      "eval_runtime": 380.5923,
+      "eval_samples_per_second": 52.55,
+      "eval_steps_per_second": 3.284,
+      "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