Training in progress, step 11000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba0cfcfae75cac3b1e3a9de6399eb42004558382974cabded94c595bf6d208de
+oid sha256:494c66eb6b674f51436f4513b4c9351a943d1d674fb3f18af798b7a2a6686de9
 size 498612824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a3eba2787f787ff71a4d66f9dac89222b1befcd50b4672cfd05ee43b86019bb
+oid sha256:77840905c13cb9385a51c293cbe0a2bcb18e80be93245e995e886437de62501f
 size 997345931

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba7e7aeb52209ad5d8132c35dc5dea4045b9348ce56da3f145b30c0fd7a0758b
+oid sha256:92b860bdc3e5de508c782673fa65ec92d555dc444109c980e964a866ddf5d27c
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e6fd97f105f8edb4cfe7d5753c1c5716920ac3feb07414e58ddd6a461f2d28f
+oid sha256:01903b6f628f65f68918eac51237e59dd0d0b2affabd2cd100779d9eb7ee7430
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3eb90156edd50a6f5a58999d9f241525ea76a46a3dd6243488805187f9dab05f
+oid sha256:bed6182874e1b92e628fa7d9cd2ddaf65f3929f6ef8ce9c0a0094022a1bb4538
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 9000,
   "best_metric": 0.04935265704989433,
   "best_model_checkpoint": "./training_output/checkpoint-9000",
-  "epoch": 0.5,
+  "epoch": 0.55,
   "eval_steps": 1000,
-  "global_step": 10000,
+  "global_step": 11000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -238,6 +238,29 @@
       "eval_samples_per_second": 52.57,
       "eval_steps_per_second": 3.286,
       "step": 10000
+    },
+    {
+      "epoch": 0.525,
+      "grad_norm": 0.005820299498736858,
+      "learning_rate": 9.501000000000001e-06,
+      "loss": 0.0359,
+      "step": 10500
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.010061199776828289,
+      "learning_rate": 9.001e-06,
+      "loss": 0.0281,
+      "step": 11000
+    },
+    {
+      "epoch": 0.55,
+      "eval_accuracy": 0.96895,
+      "eval_loss": 0.05543893575668335,
+      "eval_runtime": 380.3496,
+      "eval_samples_per_second": 52.583,
+      "eval_steps_per_second": 3.286,
+      "step": 11000
     }
   ],
   "logging_steps": 500,
@@ -257,7 +280,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.05244422144e+16,
+  "total_flos": 1.157688643584e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null