Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d36fb38ba62ea0b30298e6257e5008ef0ece2f803d2e20629c8ee59e3031f7ab
+oid sha256:a45899dbe03c63408c6a44fc2d109bb5ba09c50b70e87e60c162d6ed52f312de
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac5c703b6fc2aeea1bd5c9b2d10afd1e3045af299a72a63ff6c9a69cdb834867
+oid sha256:61a31ad12723e73acfb37e14efce9475f2c3f10dc7be901570a766aecf82d320
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faa06e8ace51be63917050556bfbf035a7666e400d0af6b1f03f62a5d7cf6d3f
+oid sha256:7078979d804256506c394e692c7bc63469425b000a01f38ecb38e19b29b0a800
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01a4e7013bdf0cfef44b18348c4082377d680816016af2638e8995bf0bb3c8d9
+oid sha256:cf6a9a1e39c0655c6941309388d2a028b5b8dbbca031ca2500bdfcdc9f2c01aa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.3012145748987853,
+  "epoch": 2.3530364372469634,
   "eval_steps": 8,
-  "global_step": 88,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -306,6 +306,13 @@
       "eval_samples_per_second": 2.926,
       "eval_steps_per_second": 1.463,
       "step": 88
+    },
+    {
+      "epoch": 2.3530364372469634,
+      "grad_norm": 2.2677857875823975,
+      "learning_rate": 0.0,
+      "loss": 0.009,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -320,12 +327,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.6280575575864115e+17,
+  "total_flos": 4.7332406838951936e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null