Training in progress, epoch 14, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3de4b0293b6ae284da61699df810e8089b5960d6736db0db2bbdffa8599a26a
+oid sha256:083faa43828a99a56c585d817ed3ae1708e32b7f455c8a9c3bf8a95772b0f6cf
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d916cabc38e1cd2f32e353c50ebc7271eac4cc80bcdb2b48581c6f344399b5cf
+oid sha256:996cab41dbd391fa461558c4d5bf549108ea54bc75ff133e50c202aac06918d0
 size 1002078330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c805478669907ab7cdf80056fca836d2b0d0d1e2c3e5458cd0e21df0eda159a8
+oid sha256:d9889c4b2dffaef9f1b04d335e5ce632f9bdd1c387979994a25e1673b8fa60ac
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07ac6ad5120138ecf2bb8980f9039b9dec2c6826a69bdc87a32eb924b62ea41a
+oid sha256:d5baf4a33d40f5c059efa3c37d7b6bda92acb1271e13513f6d15bdb0b60ac4dc
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3332167863845825,
-  "best_model_checkpoint": "./opt_trained/checkpoint-264",
-  "epoch": 13.0,
+  "best_metric": 1.3279589414596558,
+  "best_model_checkpoint": "./opt_trained/checkpoint-308",
+  "epoch": 14.0,
   "eval_steps": 500,
-  "global_step": 286,
+  "global_step": 308,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -111,6 +111,14 @@
       "eval_samples_per_second": 36.952,
       "eval_steps_per_second": 9.238,
       "step": 286
+    },
+    {
+      "epoch": 14.0,
+      "eval_loss": 1.3279589414596558,
+      "eval_runtime": 8.1077,
+      "eval_samples_per_second": 37.002,
+      "eval_steps_per_second": 9.25,
+      "step": 308
     }
   ],
   "logging_steps": 500,
@@ -130,7 +138,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9222461494272000.0,
+  "total_flos": 9931881609216000.0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null