Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ff4e214970c4585b77905e1566629a28e104930c9575a8f420a525bf9b4e80f
+oid sha256:52d3f18b62eb6473f017e7ff84c6dd353e6ecae32dd6e880f6692cb7581caa38
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38e65116436360aaea4c3a0bbf4cdff542e3ffe5325801c61845ed170844b786
+oid sha256:272e2779239584154c8538f59bcbd8f722565431877663ffc9760c36f31ec702
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f16f3b8874379bf8e1e039ef0bfa9f44be83be43b977ccd15b78395a275f501
+oid sha256:afbf885258eba70f5506df642b9914670073e12a659d870c912f419df3669557
 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": 0.020018767594619957,
+  "epoch": 0.025023459493274947,
   "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": 4.577,
       "eval_steps_per_second": 2.295,
       "step": 4
+    },
+    {
+      "epoch": 0.025023459493274947,
+      "grad_norm": 66.44071197509766,
+      "learning_rate": 5e-05,
+      "loss": 211.7811,
+      "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": 5065926676316160.0,
+  "total_flos": 6332408345395200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null