Training in progress, epoch 13, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06de0c909deed20e1208a403267a8b9becdefebc13a97a5e488e1cc8dbcc736f
+oid sha256:e3de4b0293b6ae284da61699df810e8089b5960d6736db0db2bbdffa8599a26a
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db172d07973ebe41ada05766c94cc260a12bcbf89680ae87b257a418c9502b38
+oid sha256:d916cabc38e1cd2f32e353c50ebc7271eac4cc80bcdb2b48581c6f344399b5cf
 size 1002078330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28d7cc0432a0bb11367a1b81ab0d3d42eac554116c5178476ad84855e3a6093e
+oid sha256:c805478669907ab7cdf80056fca836d2b0d0d1e2c3e5458cd0e21df0eda159a8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef0269bc208414eb97e009c66d90836f5c207f79b2289af505d56f8cafbb21e3
+oid sha256:07ac6ad5120138ecf2bb8980f9039b9dec2c6826a69bdc87a32eb924b62ea41a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.3332167863845825,
   "best_model_checkpoint": "./opt_trained/checkpoint-264",
-  "epoch": 12.0,
+  "epoch": 13.0,
   "eval_steps": 500,
-  "global_step": 264,
+  "global_step": 286,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -103,6 +103,14 @@
       "eval_samples_per_second": 36.952,
       "eval_steps_per_second": 9.238,
       "step": 264
+    },
+    {
+      "epoch": 13.0,
+      "eval_loss": 1.3333313465118408,
+      "eval_runtime": 8.1186,
+      "eval_samples_per_second": 36.952,
+      "eval_steps_per_second": 9.238,
+      "step": 286
     }
   ],
   "logging_steps": 500,
@@ -122,7 +130,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8513041379328000.0,
+  "total_flos": 9222461494272000.0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null