Training in progress, step 380, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85ce698d83c9f7922bc9119a564d55ac3b0f8f8b0d788f8e47369591f2443811
+oid sha256:4d194837bfa168aa3eda84e48aaee114c991e8d206f6c7f7e4df24ccb8cb89b7
 size 2066752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15fe7e86e865e6f9a14e583a01c4503228349d2f43e8655dc0141d9cce65b898
+oid sha256:a8d815c461c61fd30ed0dc73cc86c2b1aa1fa376dce1c1a113c3fd96c48c8fdf
 size 2162798

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4f9ae2f2feb6cbd4decea5148f15d9bf058ec483071d42cc40902d474eaee2d
+oid sha256:b8f261f6dfb4eb05280385874f96d4bbb80c17684a3d0ee60f31105f1343260a
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75c2e94daa974447d60b044cde52283c4518ffe0892e16302da575a53d569fec
+oid sha256:4b73ca3a50ea8f8955b531fe7086eac3562d0d0cd978970f2ba2615091a0e6b8
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abff5f72bffb1872fbb50b3d3804321242e45865d0e2233d397521c6e944caf4
+oid sha256:6b73473ec1a5a599a5ea9ab4e72021cbbeb65e0e85e988871ca89e952f6adc26
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 27.692307692307693,
+  "epoch": 29.23076923076923,
   "eval_steps": 40,
-  "global_step": 360,
+  "global_step": 380,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -339,6 +339,20 @@
       "eval_samples_per_second": 284.47,
       "eval_steps_per_second": 4.548,
       "step": 360
+    },
+    {
+      "epoch": 28.46153846153846,
+      "grad_norm": 0.412109375,
+      "learning_rate": 7.014851889983057e-05,
+      "loss": 9.182,
+      "step": 370
+    },
+    {
+      "epoch": 29.23076923076923,
+      "grad_norm": 0.416015625,
+      "learning_rate": 6.493624448072457e-05,
+      "loss": 9.1822,
+      "step": 380
     }
   ],
   "logging_steps": 10,
@@ -358,7 +372,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 147297077821440.0,
+  "total_flos": 155480248811520.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null