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:e34661e987b95afae72847417447c7f8b2bb1947e3fb1f2822860814e926d083
+oid sha256:3e85b61a3b8ed82d81452194e6f9fd45efec8d4ce3cd15dfe758a9d9e2815a68
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c16e539be2eba819a242addf13a15381598214dd75d01a4823c9e2537824ff7b
+oid sha256:b6d92faa14f39649a9a9364d53dd80ed2d8de24b0fbcb01c6137f2a451dd6ecb
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39dd70f78833b407302ec7a08a5ddbe1954a321879cf7446f5acb83d55b840c1
+oid sha256:648a063f91ae3ab228fd410ffbd4321ad14a00c1e969d3c92bcd911e862ae5e7
 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": 0.0007268927606024124,
+  "epoch": 0.0009086159507530155,
   "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": 126.348,
       "eval_steps_per_second": 63.174,
       "step": 4
+    },
+    {
+      "epoch": 0.0009086159507530155,
+      "grad_norm": 10.335015296936035,
+      "learning_rate": 5e-05,
+      "loss": 9.591,
+      "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": 384872824700928.0,
+  "total_flos": 481091030876160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null