Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d3e950bda35f2422a70d0bb81c46cc4cae106ec0696cda72f876498dc7dd565
+oid sha256:ae133444c88971d4c81ef544228ef3e3ed9bd0fe3f08b93bfa55e568b689ecb6
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8a85f26e79eb452db1da981f45314ba7214ec06b4873389382ffc2715d0b0c6
+oid sha256:74bf2a1c5013dde6ff3a115d5c5d6cdd86efe813860329aadf5e22e15c92f4e4
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8d6b9a0e9e9502751def1097143074ef257eab24506a0f12d159e188fa21987
+oid sha256:572c5653b97399d6dc550389d4e48df5479adab7c80147f357d4d04c0f7252da
 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": 0.0007969516599008791,
+  "epoch": 0.000996189574876099,
   "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": 12.392,
       "eval_steps_per_second": 6.196,
       "step": 4
+    },
+    {
+      "epoch": 0.000996189574876099,
+      "grad_norm": 2.4700844287872314,
+      "learning_rate": 5e-05,
+      "loss": 19.0701,
+      "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": 5303425711472640.0,
+  "total_flos": 6569915433615360.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null