Training in progress, step 268, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53a1f1c3e2a923e2982197cd900077574f24b219229aa019511f875042742237
+oid sha256:4ad73acc7a44c1fcd562883c85272c2e33e24df2154f4b3d1668ef117da46401
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06ce5385174b266947c6bbd0cded6839fb22865d7049d84dd957347235517437
+oid sha256:064b2a9e45b619870f65440ad9ebda6135d621bd81ea4fa5c9d2073e6847a8a5
 size 37431220

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b539f01b7ad3345aa5a738855f4967eed8463acf8b5cd8b2265ca0e07cf0599
+oid sha256:b9d3048c859719401ed6523107918b9f1d6ac0f3668115efc907a5a4c443c081
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7242798353909465,
+  "epoch": 0.7352537722908093,
   "eval_steps": 500,
-  "global_step": 264,
+  "global_step": 268,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1855,6 +1855,34 @@
       "learning_rate": 7.575757575757576e-05,
       "loss": 1.2125,
       "step": 264
+    },
+    {
+      "epoch": 0.7270233196159122,
+      "grad_norm": 0.1578194946050644,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 1.2006,
+      "step": 265
+    },
+    {
+      "epoch": 0.7297668038408779,
+      "grad_norm": 0.15539692342281342,
+      "learning_rate": 7.424242424242424e-05,
+      "loss": 1.1045,
+      "step": 266
+    },
+    {
+      "epoch": 0.7325102880658436,
+      "grad_norm": 0.15170246362686157,
+      "learning_rate": 7.348484848484849e-05,
+      "loss": 1.1653,
+      "step": 267
+    },
+    {
+      "epoch": 0.7352537722908093,
+      "grad_norm": 0.18623769283294678,
+      "learning_rate": 7.272727272727273e-05,
+      "loss": 1.2259,
+      "step": 268
     }
   ],
   "logging_steps": 1,
@@ -1874,7 +1902,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.264356883202867e+17,
+  "total_flos": 3.3135793961210266e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null