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:d156eef60c3c0d4ce63627e25c8466d3b02347e91a76c6fb7d29b2393c615072
+oid sha256:9dea8f16d96f0384d560d2183f9be0d96a53496a1069807f6f42568e8f574d8c
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff5bf174c6f9c0f846645430436a83cb08f0abc198016645d8773fd5247c6f75
+oid sha256:6a216323848bc2cd27772fc25a778b04cf9fff1ee100370f969de27dc32483a6
 size 21505540

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": 0.0009756246284242137,
+  "epoch": 0.0012195307855302673,
   "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": 51.932,
       "eval_steps_per_second": 25.966,
       "step": 4
+    },
+    {
+      "epoch": 0.0012195307855302673,
+      "grad_norm": 2.600978374481201,
+      "learning_rate": 5e-05,
+      "loss": 3.0447,
+      "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": 800155729133568.0,
+  "total_flos": 1012697094684672.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null