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:bb6e5bb63c85901b1feb0d5b708351e81c5fd5dbc08c349aa5760adb16976f98
+oid sha256:d596b9d7e3f4a7928ad7adb8751642c2df0e2ede6415faa3e8c5f82daf255fe7
 size 111454040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8280829507377bc7e176a90a8ddc684518fa234c081ef4a2fa058a946596df26
+oid sha256:af723ff336997fab0fde6cb738619ccb1baa5f9d5b59ef5c9ce20176aa777af2
 size 56950676

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94eb3af0be59b8022e591483a56634de67b6ec709d4a7976205940027b927a1a
+oid sha256:1b99edc2cdea6f0c1d1aed5d91b76e8be44663e4d42de5d330eadafb52aec11f
 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": 0.00062708210856359,
+  "epoch": 0.0007838526357044876,
   "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": 6.502,
       "eval_steps_per_second": 3.251,
       "step": 4
+    },
+    {
+      "epoch": 0.0007838526357044876,
+      "grad_norm": 21.542518615722656,
+      "learning_rate": 5e-05,
+      "loss": 106.4952,
+      "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": 5435787785011200.0,
+  "total_flos": 6794734731264000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null