Training in progress, step 360, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f71ccf5d1e38095d0550ef25eaf8142cfc6e91c44bbcd52a9b26ef54fd7f0de
+oid sha256:85ce698d83c9f7922bc9119a564d55ac3b0f8f8b0d788f8e47369591f2443811
 size 2066752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fa0b74037207edb69c5cb7e46115ced0b01214628bf235c30fc7fa7ba5c66cf
+oid sha256:15fe7e86e865e6f9a14e583a01c4503228349d2f43e8655dc0141d9cce65b898
 size 2162798

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:572dc22acc56b39f566c3fd3cffdea889adb8a7c20c07536c97592135eb24b9e
+oid sha256:e4f9ae2f2feb6cbd4decea5148f15d9bf058ec483071d42cc40902d474eaee2d
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecc681d4faad785e373f4f3e510befc4a0dd5c362d6b35fce077246bbe11af20
+oid sha256:75c2e94daa974447d60b044cde52283c4518ffe0892e16302da575a53d569fec
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:775af4447ea22c8fde6b9577374f0010f59aa5050c5eb44816a7c00e793e5d27
+oid sha256:abff5f72bffb1872fbb50b3d3804321242e45865d0e2233d397521c6e944caf4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 26.153846153846153,
+  "epoch": 27.692307692307693,
   "eval_steps": 40,
-  "global_step": 340,
+  "global_step": 360,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -317,6 +317,28 @@
       "learning_rate": 8.626464421815919e-05,
       "loss": 9.193,
       "step": 340
+    },
+    {
+      "epoch": 26.923076923076923,
+      "grad_norm": 0.41015625,
+      "learning_rate": 8.082893680762619e-05,
+      "loss": 9.1896,
+      "step": 350
+    },
+    {
+      "epoch": 27.692307692307693,
+      "grad_norm": 0.416015625,
+      "learning_rate": 7.54514512859201e-05,
+      "loss": 9.186,
+      "step": 360
+    },
+    {
+      "epoch": 27.692307692307693,
+      "eval_loss": 9.2018404006958,
+      "eval_runtime": 5.2765,
+      "eval_samples_per_second": 284.47,
+      "eval_steps_per_second": 4.548,
+      "step": 360
     }
   ],
   "logging_steps": 10,
@@ -336,7 +358,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 139113906831360.0,
+  "total_flos": 147297077821440.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null