Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:812f5748fa88b1d1bda81ee2d1235c7dec481519ae637598b81e2eb50238edcd
+oid sha256:ea2b9c006a9b477084335e76176ca157be5920693c97100e119eacb0033d8d93
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13b460eb7d805a55c6d92a9bf57c5735b2cf23f71e3958167b35c5f8a0134b5d
+oid sha256:ebe54471058018e14239140fbdbd1526007226caef3d3d151ee5f42c974b84a1
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28903fd1aac92e346442663b9f2b5539c4576c035a060f8b841d0ff180c806d1
+oid sha256:4e0ad2d77e37d8546af7e226e84e209b283d93ca48ee5b2463c3f03a5cf090eb
 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": 0.004968558341743654,
+  "epoch": 0.006210697927179567,
   "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": 3.59,
       "eval_steps_per_second": 1.795,
       "step": 4
+    },
+    {
+      "epoch": 0.006210697927179567,
+      "grad_norm": 0.8162658214569092,
+      "learning_rate": 5e-05,
+      "loss": 2.901,
+      "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": 9419517308436480.0,
+  "total_flos": 1.179418553745408e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null