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:ce834ffb9116f270b82f6870e0f05c457a67cdb15e3936e94814e62c16557227
+oid sha256:4c6538a17e6e7e8111cc57761ffde177377aa3715c1fd069aa5d3ebb9a913400
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f74cc7624b8547d6ef451e24abbef1226c8ade31eed50fa4a2e8009fac36ea09
+oid sha256:fcbdab3a2fb8221d3e619ddec8da2d39d9b13674ea96c31eccd055eed8a07f1b
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2081d9acf756707a23e0c9f3e558216eddd7b78a9258b41b74e4cf8ac6d2479c
+oid sha256:026da980db2382b90ac8479b0ef555298a984835e43e08bad94d30b560934281
 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": 0.0003812065186314686,
+  "epoch": 0.0004765081482893357,
   "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": 4.734,
       "eval_steps_per_second": 2.367,
       "step": 4
+    },
+    {
+      "epoch": 0.0004765081482893357,
+      "grad_norm": 8.376543998718262,
+      "learning_rate": 5e-05,
+      "loss": 41.5706,
+      "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": 7598890014474240.0,
+  "total_flos": 9261147205140480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null