Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41fbc35e4c1e1a87f8c9ef5a6f09b5bb26960dedf26df4284495e523aa4a6026
+oid sha256:a7b303f8c32f144e6a440d12d4a59a1ebc85b69cc1b11ecebbb1c96bc75f91e9
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:595acd5bab790b4e225921d7e5845fad66b3930d29337ed0ac2f03b0aab798a2
+oid sha256:179218d927de16c4b2f674452d8536c6fa9c2d6d41cc48837c72c6ddadd23396
 size 51244020

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": 0.0056372764907953845,
+  "epoch": 0.00704659561349423,
   "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": 17.042,
       "eval_steps_per_second": 8.528,
       "step": 4
+    },
+    {
+      "epoch": 0.00704659561349423,
+      "grad_norm": 20.616239547729492,
+      "learning_rate": 5e-05,
+      "loss": 12.7332,
+      "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": 3201078122250240.0,
+  "total_flos": 4013291974164480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null