Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55f6fec4dabcbfc0cfa0f4a79622ecc31315d0e652e2837b087e6e8aa275fabe
+oid sha256:b0fbb86ea4e75005f7e0407a306dbd74ccabe5a19a086869c334b312e0322f1d
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f69fda602f49d1a0a050670acc6aabee9a30b4e7042b5e90ffaaf97b83bfcff
+oid sha256:f4ba0189582cc705721730ed568de1a8d59ad2df186f74f831f7cde9b4ca6751
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93c053e16d7f83703cebaad6496a567cd5cda468439832ce178034d1a20a52d0
+oid sha256:914c9638bc5dd4d18a28aa52fa2c858bb5c4794e9c11cdfd14c5e243e071b2e3
 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": 0.018369690011481057,
+  "epoch": 0.022962112514351322,
   "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": 2.272,
       "eval_steps_per_second": 1.139,
       "step": 4
+    },
+    {
+      "epoch": 0.022962112514351322,
+      "grad_norm": 24.172510147094727,
+      "learning_rate": 5e-05,
+      "loss": 104.5061,
+      "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": 5065958888570880.0,
+  "total_flos": 6332448610713600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null