Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dfe98581114617518830b6703f65d61ea43ce051d78d9416d909d0617681ec7
+oid sha256:071b088e6ffd8d4a12e338d0c456bc0e680a352d502bf733925d3a73486279ec
 size 111454040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb2a1cd53b90d56b9d922e736e52a7a519667c2be6b46905ec333d3316363610
+oid sha256:8b69239b0e0e05b37aadb104e1411a59089549f6a2c6140c55bbf0bcb7b01f49
 size 56950676

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a3fd2aaf2311cd9d97d6239a6c81d74833efc2f7447be6d7e57848f15b0f961
+oid sha256:4c04f03e67585d311f682885f37dd1a17835bf0b8d5d623c27733f1fc229b8d5
 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": 0.009229881742140178,
+  "epoch": 0.011537352177675224,
   "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": 2.888,
       "eval_steps_per_second": 1.444,
       "step": 4
+    },
+    {
+      "epoch": 0.011537352177675224,
+      "grad_norm": 7.151191711425781,
+      "learning_rate": 5e-05,
+      "loss": 23.9754,
+      "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": 6200195442278400.0,
+  "total_flos": 7729010756812800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null