Training in progress, step 19000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:291bc79b9db42319a0e705f95801bc181e2ec040ec5f3f8683ff056aa24bccef
+oid sha256:509c85f8b7820829daf992dcbc30bd588eced94f8811842fdda462a26e404231
 size 498612824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea5deaec9d6d51b4e065d8d01eda0554814baac9a55131683c2276ac37c8912d
+oid sha256:500ffd76170b7fb618ea379239932a47631205a4d9705066b56afb09614f681d
 size 997345931

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c1d07e9b3e83f290cfcee2249ad6d7c66e591173b28c2b836185f26e0c2c7f9
+oid sha256:b55a329a0239ddf130bd7462fbf7a0a0ef8b1d6f911f297c641c27e874c66d55
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01c05ba122243a39f315dc30d2972d3429dad6971e9d39b7f754d7c36b9c6f87
+oid sha256:b400ca8205b43e6749673f0c9bba4f696903aed85274c2c9d26d93646bd0fb05
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a8365ada6b8e6626f775dc50f7ca875a98c9f858d772af7e8a4a80106eb2109
+oid sha256:202696b444f08037309fb90beb295bcdd49728ed9311c345563ca13fa1f8e257
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 16000,
   "best_metric": 0.042671315371990204,
   "best_model_checkpoint": "./training_output/checkpoint-16000",
-  "epoch": 0.9,
+  "epoch": 0.95,
   "eval_steps": 1000,
-  "global_step": 18000,
+  "global_step": 19000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -422,6 +422,29 @@
       "eval_samples_per_second": 52.554,
       "eval_steps_per_second": 3.285,
       "step": 18000
+    },
+    {
+      "epoch": 0.925,
+      "grad_norm": 0.0007658928516320884,
+      "learning_rate": 1.5010000000000003e-06,
+      "loss": 0.0148,
+      "step": 18500
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 44.06643295288086,
+      "learning_rate": 1.001e-06,
+      "loss": 0.0211,
+      "step": 19000
+    },
+    {
+      "epoch": 0.95,
+      "eval_accuracy": 0.95135,
+      "eval_loss": 0.09501199424266815,
+      "eval_runtime": 380.4677,
+      "eval_samples_per_second": 52.567,
+      "eval_steps_per_second": 3.285,
+      "step": 19000
     }
   ],
   "logging_steps": 500,
@@ -441,7 +464,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.894399598592e+16,
+  "total_flos": 1.999644020736e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null