Training in progress, step 130, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4bc4a91559ec824f1fbc56295d9f782d2ff4ed5ae6ada32ec08c77634493a68
+oid sha256:a6d295a5a7fcb5fae0eebc663a6b5b8464d827143f0cb5ddb71102882515dca5
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dcc73f76d8bb1f9b2ac33f17d640952304e1a1e7ad719aa95368a59859d9fc0
+oid sha256:af514a87c4fb89e819a0de6991ca4d8b39dfdf48dc925262f1e975aeec90cc78
 size 1386414411

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9008b459b5e2e7510f9b1147b0bc700431b3625231c93d35c550ef35f3d4b139
+oid sha256:5d3db644955f6e2a187227317743d07ffbb076761cb028b27ef16d496ba7ec50
 size 14917

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68b4ee4460edbc9eb4534fd16fe1b370a3b5348fe21dec9512c9ac09a43f7dd1
+oid sha256:635a41db05223968dc5ce13f82d086b8ff5047cb0e8da854e4e7ef09ab47f41a
 size 14917

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23aac2921f9ec292e8c9abc5d0945d71b183f542cd598117a742dbca2be40eb7
+oid sha256:767fe410c841707b701d3e837145bc5c2e9de990fa720929b20bfefc7ae3ad3a
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.12,
+  "epoch": 0.13,
   "eval_steps": 5,
-  "global_step": 120,
+  "global_step": 130,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -231,6 +231,24 @@
       "eval_samples_per_second": 14.348,
       "eval_steps_per_second": 7.174,
       "step": 120
+    },
+    {
+      "epoch": 0.125,
+      "eval_accuracy": 0.0676,
+      "eval_loss": 16.717758178710938,
+      "eval_runtime": 39.1101,
+      "eval_samples_per_second": 12.784,
+      "eval_steps_per_second": 6.392,
+      "step": 125
+    },
+    {
+      "epoch": 0.13,
+      "eval_accuracy": 0.07173333333333333,
+      "eval_loss": 16.712247848510742,
+      "eval_runtime": 35.0018,
+      "eval_samples_per_second": 14.285,
+      "eval_steps_per_second": 7.142,
+      "step": 130
     }
   ],
   "logging_steps": 100,