Training in progress, step 18000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29092f5f5db264a2400cbdf899cfe4d1d0b56eea50bccf442b1a8266a8341365
+oid sha256:291bc79b9db42319a0e705f95801bc181e2ec040ec5f3f8683ff056aa24bccef
 size 498612824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2006153fb5c31670f4af411fe67c8d23146ccd874f0518cd0d2d69cb0d6a474c
+oid sha256:ea5deaec9d6d51b4e065d8d01eda0554814baac9a55131683c2276ac37c8912d
 size 997345931

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78bd9fea4ddfe3f89b1b98598cf1ed1a56bdd71a677e5b5657ad459f1c6e4adf
+oid sha256:1c1d07e9b3e83f290cfcee2249ad6d7c66e591173b28c2b836185f26e0c2c7f9
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c792eca26ddd2cafb935aabba9dbf816b7c25feaa4b191867652327a92bef5c
+oid sha256:01c05ba122243a39f315dc30d2972d3429dad6971e9d39b7f754d7c36b9c6f87
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfc30f32fda7dd6d5c4749a3c53203c86e0c2f047676577a42c798629798e937
+oid sha256:5a8365ada6b8e6626f775dc50f7ca875a98c9f858d772af7e8a4a80106eb2109
 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": 0.85,
+  "epoch": 0.9,
   "eval_steps": 1000,
-  "global_step": 17000,
+  "global_step": 18000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -399,6 +399,29 @@
       "eval_samples_per_second": 52.582,
       "eval_steps_per_second": 3.286,
       "step": 17000
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 0.000398589443648234,
+      "learning_rate": 2.5010000000000003e-06,
+      "loss": 0.014,
+      "step": 17500
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.0027746970299631357,
+      "learning_rate": 2.001e-06,
+      "loss": 0.0186,
+      "step": 18000
+    },
+    {
+      "epoch": 0.9,
+      "eval_accuracy": 0.96805,
+      "eval_loss": 0.06131412461400032,
+      "eval_runtime": 380.5623,
+      "eval_samples_per_second": 52.554,
+      "eval_steps_per_second": 3.285,
+      "step": 18000
     }
   ],
   "logging_steps": 500,
@@ -418,7 +441,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.789155176448e+16,
+  "total_flos": 1.894399598592e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null