Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13ffe4664a235436601e39d8b6eb3f196ac3894fcec2c4a0237b1808c432e2e8
+oid sha256:4e4dd726f7adaf7d5cc876efb152fdeb1f55ca92186e3209c73d9772bbf4ec30
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:929bb5fec9436f892a991ba3be35d7bb0b77bf1fd982f6c87788c5602b0ab051
+oid sha256:3969aaca2e7b1d0ddebbd91c39a85a0c7b43a24a002a476987dad33a70c468b8
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06f7a776eb140b6aebd6cf0a67e09ea2f64ccd47b4895b84cbd24827bc294150
+oid sha256:cdf2462c0051b4d386662af4bcbcf4f8bd2a644cbd8d4354a2d1a1c1c1b63fbe
 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": 0.01703940362087327,
+  "epoch": 0.021299254526091587,
   "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": 12.254,
       "eval_steps_per_second": 6.127,
       "step": 4
+    },
+    {
+      "epoch": 0.021299254526091587,
+      "grad_norm": 18.34703826904297,
+      "learning_rate": 5e-05,
+      "loss": 14.4113,
+      "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": 5170375868547072.0,
+  "total_flos": 6528694952656896.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null