Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9859694ecc7157ec8602675da7e5c809e28fa4aec99ff8079246a1227879f461
+oid sha256:379594befb27f1f484256a86bfb31374329d77df17dcc154b39ceb4388918fde
 size 50365768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b5c22a3a782af5212f23136f03a0298b14833eec19e58e39be5d57eab32bafa
+oid sha256:0756ae220c300d355aa8ff00b8022cf8846cf96509fdc3656675fb774de8b734
 size 25859156

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4101b28c6ee7a03bac8e108257595cf1a61284383497cd62b6f891e7f4ad7adc
+oid sha256:a6c49b160312fde33241fee7279169d85b2462a8fc682ea93e6c2fc100e5a1d8
 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": 0.018223234624145785,
+  "epoch": 0.022779043280182234,
   "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": 40.526,
       "eval_steps_per_second": 20.263,
       "step": 4
+    },
+    {
+      "epoch": 0.022779043280182234,
+      "grad_norm": 4.315094470977783,
+      "learning_rate": 5e-05,
+      "loss": 14.4391,
+      "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": 2593218292088832.0,
+  "total_flos": 3258734490943488.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null