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:bd6c7458a83ea284862aa32f5e893226cdb84fae65779d2e66a39e45bbf0df64
+oid sha256:2b38c3269b04a2e138d5ef4fbf97eb68599a60a9643031e600992f1d3c5ac38d
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62885f3d23e623d0b8efcd090a1ab0a231d359b875638617520d6f7cf184efee
+oid sha256:f76b4df8db3e48f946188c8990a4ad85216b60e5d94b72f71a9c0ed3af7727c4
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:877be02e72c90068c53b4cd4ac5f76683c34f6c6e1f29413737e7203851c9d33
+oid sha256:b52214f9bd9fd90e146416d19db727ff822d3ff4dfe457467cf1dd46cfde3948
 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": 0.0481203007518797,
+  "epoch": 0.06015037593984962,
   "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": 13.419,
       "eval_steps_per_second": 6.709,
       "step": 4
+    },
+    {
+      "epoch": 0.06015037593984962,
+      "grad_norm": 2.6269478797912598,
+      "learning_rate": 5e-05,
+      "loss": 27.97,
+      "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": 1.013185335263232e+16,
+  "total_flos": 1.26648166907904e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null