Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56338500c30425f1b6cb27e0274b8773fe9c9de1e8e71cde2a740a31f0981ac8
+oid sha256:b4039206e86598c2d64834858a27811dba5022a2c71a494abec57165711e9ba2
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11e58a98af2f188b3887d3fb0502880cb534604c6e4ef277db2353ad89518049
+oid sha256:72f80edc3472e983f60ee95239a4ca617f04dacb5a7abd7fe7b78f630daf9c47
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f07a6b76bf9c5f4bf889b1042df67f890d1b03821222333d3420211875253e54
+oid sha256:013337ad52bc9d9a9b23d8707de8b3d1582fd61a009a0b870c0cd5aeb513eb01
 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": 0.006253664256400234,
+  "epoch": 0.007817080320500294,
   "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": 16.77,
       "eval_steps_per_second": 8.385,
       "step": 4
+    },
+    {
+      "epoch": 0.007817080320500294,
+      "grad_norm": 7.054184436798096,
+      "learning_rate": 5e-05,
+      "loss": 15.166,
+      "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": 6094943032442880.0,
+  "total_flos": 7915510431744000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null