Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e9237af1920a2e4f3af0e0539309fab49ba2f5e767fa09350ec9e963c5328d0
+oid sha256:ef35f2bbbce4547bdec242303ca34c1afe9474900584304d6c50fcb265461e4d
 size 390888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9acaf5a7b2ebde4dd6e9d720368471a12d78aa870950134b25aa61702294323c
+oid sha256:489f33c42173986b5374f6c603ad49d36eed3fdf5aa40fe3021149ef81e1ab69
 size 819770

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": 0.02574416733708769,
+  "epoch": 0.032180209171359615,
   "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": 244.046,
       "eval_steps_per_second": 122.023,
       "step": 4
+    },
+    {
+      "epoch": 0.032180209171359615,
+      "grad_norm": 19.842269897460938,
+      "learning_rate": 5e-05,
+      "loss": 12.6079,
+      "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": 2097873420288.0,
+  "total_flos": 2622341775360.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null