Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60a2dfc81fc2ff06c32bac3806ba27258c2bbf3b04df8613ae768503f70eb9c6
+oid sha256:5a58a74eca6241d1567a8152300e725277083af923bc08086e2e3567df1e8e42
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:138b8d5573d1a11654292b1910bb08daf558c70eab4083107d09e138bbcdd5ac
+oid sha256:a9ed0e194a568dfc2d6b2d254a21acf200974b300491027275ee92378091003a
 size 11710970

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": 0.012711022840119166,
+  "epoch": 0.015888778550148957,
   "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": 86.066,
       "eval_steps_per_second": 43.033,
       "step": 4
+    },
+    {
+      "epoch": 0.015888778550148957,
+      "grad_norm": 0.4515919089317322,
+      "learning_rate": 5e-05,
+      "loss": 2.3747,
+      "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": 517172858191872.0,
+  "total_flos": 667513805340672.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null