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:f16c14ff6ed54385d61fb0d21f5ebdff0a91575a25c1fb3c0757d474815d1bfa
+oid sha256:7898c205f29aa5476ab58c191a1792a4fb7a668b2f3593254636e5acc6737483
 size 59933632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82ca973d2902fddd0d903990f56c7fbe35a687275392a6bc458035e06da72bc6
+oid sha256:618c133aa4ecff4dcc044e1e71fe10d4bf6d7e56ea2d98ab97669b5c594ac1fd
 size 31822948

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:017583d2bd93fe9910a82ceabe249f8fabc7dfeef29c7c3f997a8f45e0fab04d
+oid sha256:a8636caf43895d122986dcf9c0f3f784244e32146c2903687980280124315561
 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": 0.0042697978517579555,
+  "epoch": 0.005337247314697445,
   "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": 26.934,
       "eval_steps_per_second": 13.467,
       "step": 4
+    },
+    {
+      "epoch": 0.005337247314697445,
+      "grad_norm": 1.1590626239776611,
+      "learning_rate": 5e-05,
+      "loss": 1.8603,
+      "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": 1302652608577536.0,
+  "total_flos": 1594035428917248.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null