Training in progress, step 13000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b26e8e16384250dfca41d5b3113059194b29807c89da51582025e4529d9ae296
+oid sha256:9c836278b7290e3e1896a49b1ed1811705853cf4d3dd2c6474be5b82adbfc1d4
 size 242041896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:629a724d9972ef7a8933f7437a0565e520bac2b2044fad926b33012443389cde
+oid sha256:3d74fd1d5d574b05a0b990abd9fe0572fbee9a3adacc5419dc683f035f71bd3e
 size 484163514

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f563e7cc48c77e38c0f0ffecfd66cc9b3f531cdfe2db350ed1aad55e38faa0c9
+oid sha256:3520465f4b64d33b613219596832eaa86d9d9caca67db1dba7a5ee9f85c826e9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea81a152c31c603b6ecca61515ae365bc23ec1d05ea6e8887eb0cd80e26b497b
+oid sha256:fdce871353a4b772225d512e5446733be63e4b22f36f5990fbc3659210ff174d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.918354818907305,
+  "epoch": 1.9950890116635973,
   "eval_steps": 500,
-  "global_step": 12500,
+  "global_step": 13000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -167,13 +167,19 @@
       "learning_rate": 0.000616451810926949,
       "loss": 0.5671,
       "step": 12500
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0006011049723756906,
+      "loss": 0.5687,
+      "step": 13000
     }
   ],
   "logging_steps": 500,
   "max_steps": 32580,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 6626905573294080.0,
+  "total_flos": 6891710266736640.0,
   "trial_name": null,
   "trial_params": null
 }