Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74990d5c900d26b0ab035b62dda006bcb0a09cb9abd0bb0604d8630ec2add5c7
+oid sha256:3a6d645885d69d046039b499f389557b1286248296ea2d45f9c3c264d535c407
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:daa8b8ec74bef651602031a344bce1dffac7e7be9d1907182c1be1ce56b62a23
+oid sha256:72a5792b8e996f0d3765430c8700407a47cd029b366594ea2a7a26eeeb9d90da
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89fa8ac371a5d659948365d7c799bf69558c73b93c260685c8661740a2c99b2c
+oid sha256:0e24d535c5c1523f0486038b5930228f33566ca520ba04d10e88741a42965211
 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": 0.0004280821917808219,
+  "epoch": 0.0005351027397260274,
   "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": 10.497,
       "eval_steps_per_second": 5.249,
       "step": 4
+    },
+    {
+      "epoch": 0.0005351027397260274,
+      "grad_norm": 4.008087158203125,
+      "learning_rate": 5e-05,
+      "loss": 18.7957,
+      "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": 5211946034921472.0,
+  "total_flos": 6514932543651840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null