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:cb913a530b1bdc0b138b27c7049f0b65b09b9fe30cb9ce151e0ba804e76219d8
+oid sha256:12721453c9ebed4b7a21ea8ff0450c5b4681eaa052fc56e49d2744dcec120824
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d59bf7c3771b2a28f78ac12f514513bdb01cb2699a5819b3d46f3b6cb8440fb0
+oid sha256:9e2a14dacbb1d7c765f5593215150b6e06a5350f2e246d847d8b630043311151
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dc7abb9a8f5513c25167ffc6647a6dd72435c4cccb991257a65be6dcbc564f0
+oid sha256:df73a91d02fb9a3c91e727470cb829560bb0688aaed3fe5efc647ee409642afe
 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": 0.013420004193751311,
+  "epoch": 0.01677500524218914,
   "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": 5.964,
       "eval_steps_per_second": 2.982,
       "step": 4
+    },
+    {
+      "epoch": 0.01677500524218914,
+      "grad_norm": 1.4947220087051392,
+      "learning_rate": 5e-05,
+      "loss": 14.9883,
+      "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": 5936670572544000.0,
+  "total_flos": 7519782725222400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null