Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:109c107b72d6fe50d16bd7d554c76566112b7c006fe580076c00b816a6db5a3e
+oid sha256:2e6742ccedf577f28782f0584e2f5513e4cbdacfd5d9a310400ffd33ff1e10d9
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38713d62f90e9f2c90e6ad79ae398508fb6530c12f1dec19d5769420548876aa
+oid sha256:aa2e47794212ea8939c1f83a685d1cf5c4f07e499827bcca8215503953be6aff
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14c8875d4ee14548a832998e29081a46abf7ca4307283b93095809873a71480a
+oid sha256:95db10699871bcb8c18cc6a17504c7c914cc27123dbc145a892ad0684a08968c
 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": 0.03827751196172249,
+  "epoch": 0.04784688995215311,
   "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": 3.647,
       "eval_steps_per_second": 1.834,
       "step": 4
+    },
+    {
+      "epoch": 0.04784688995215311,
+      "grad_norm": 2.5525448322296143,
+      "learning_rate": 5e-05,
+      "loss": 20.1457,
+      "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": 7203114492887040.0,
+  "total_flos": 9102836996505600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null