Training in progress, step 270, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3e35886bdcf00795dc56e4c37d7f8b9156e3af207c4f5197e9b99f856611064
+oid sha256:12e70752b751619eca556d581de22f95ebd6c29351c9409ce88f9658d65a441e
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e666486e8cc62b97d906ea52ffc730c72ad81956be23d6dde2d1167414d1fd1
+oid sha256:ee29f0e47a32e109a2136050325592d682eb66f3b314d215d6ffb567d8b9b52f
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db7e8cfd6e7b1242076647967dbc1bd8afa97abb68b4228e97c7e65538d0340d
+oid sha256:67e770fb11b58b411b8e274fe1728430d5130bebebd0fbd2dda121e2908cc002
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e07629d02aee1dc6fe60d67e7c3e731bc344bba13e8c3da66188957923131f6
+oid sha256:208227daf0fc218aab910a008fc4c360acd465f7afe242046281eec474cdc16d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3429310902620511,
+  "epoch": 0.3494014881915238,
   "eval_steps": 386,
-  "global_step": 265,
+  "global_step": 270,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1870,6 +1870,41 @@
       "learning_rate": 9.921633765188886e-05,
       "loss": 0.9117,
       "step": 265
+    },
+    {
+      "epoch": 0.34422516984794566,
+      "grad_norm": 0.9448872208595276,
+      "learning_rate": 9.92090501417771e-05,
+      "loss": 1.1399,
+      "step": 266
+    },
+    {
+      "epoch": 0.34551924943384016,
+      "grad_norm": 0.8711137175559998,
+      "learning_rate": 9.920172917406789e-05,
+      "loss": 0.8158,
+      "step": 267
+    },
+    {
+      "epoch": 0.3468133290197347,
+      "grad_norm": 0.7883780598640442,
+      "learning_rate": 9.919437475373882e-05,
+      "loss": 1.0259,
+      "step": 268
+    },
+    {
+      "epoch": 0.3481074086056292,
+      "grad_norm": 0.7776859402656555,
+      "learning_rate": 9.91869868857902e-05,
+      "loss": 0.9145,
+      "step": 269
+    },
+    {
+      "epoch": 0.3494014881915238,
+      "grad_norm": 0.8383511900901794,
+      "learning_rate": 9.91795655752451e-05,
+      "loss": 0.8769,
+      "step": 270
     }
   ],
   "logging_steps": 1,
@@ -1889,7 +1924,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.962533504987955e+17,
+  "total_flos": 3.0184303635726336e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null