Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:709709e22b78bae815a3d072a01903459ec0dac8eb824e11ec6f3df94e38e4cb
+oid sha256:bbcf205a39c831cf1b13d0ee5d29f1252690994384afe2716c67372f09f0a89e
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac8243294a2143316b8b00a306299104d09f63c37b190d61b0dca85f59111d42
+oid sha256:8dabe79cc62c61a06b3b8e82fb585e841d62c1fd3e3b7397276827cfec4ad263
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8d6b9a0e9e9502751def1097143074ef257eab24506a0f12d159e188fa21987
+oid sha256:572c5653b97399d6dc550389d4e48df5479adab7c80147f357d4d04c0f7252da
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
+oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006804891015417331,
+  "epoch": 0.008506113769271665,
   "eval_steps": 2,
-  "global_step": 4,
+  "global_step": 5,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -59,6 +59,13 @@
       "eval_samples_per_second": 56.996,
       "eval_steps_per_second": 28.498,
       "step": 4
+    },
+    {
+      "epoch": 0.008506113769271665,
+      "grad_norm": 0.10489768534898758,
+      "learning_rate": 5e-05,
+      "loss": 0.6557,
+      "step": 5
     }
   ],
   "logging_steps": 1,
@@ -73,12 +80,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 956679862616064.0,
+  "total_flos": 1191796100038656.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null