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:ec6f9b2e70ccc732a35b6e378f107fdd5a9a3672117da6450ca0368dec14f08e
+oid sha256:24166d06f8cf704c274d46c2b2c380aa66d158843d6fab27997ed7e0f9466397
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76fc1276660a99fcaea1de155443d582606f30500bd6240611b76e06b21c9657
+oid sha256:388532a80bbafa0652d92ba753c4d07dc4f283b2e2f0d5ec247b25f514ff5f3d
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:113786fe81b4cc603fbc0388faa5bf86e33a11a5456e3cb2350330c8c40f0d3c
+oid sha256:09715699eeae01693df3f115fe8d170ec3e15ee90fe832d7e7637cd1e40fe26d
 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": 0.004093380236648545,
+  "epoch": 0.005116725295810681,
   "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": 4.183,
       "eval_steps_per_second": 2.091,
       "step": 4
+    },
+    {
+      "epoch": 0.005116725295810681,
+      "grad_norm": 10.295353889465332,
+      "learning_rate": 5e-05,
+      "loss": 19.8071,
+      "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": 5382547093585920.0,
+  "total_flos": 6728183866982400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null