Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b67eda1b154b1a588b1a7d41cabf32fae3c15d400a4ce2b2914709bb93924531
+oid sha256:6602d1f852897cd4e0d00621cfb0fe715ea45cc7e7f35d3e682501317dc4ed27
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b11b74e8f893ec19386a7831a301ce9546079b50f3c25b6e450c2acecd47189b
+oid sha256:e10c74dfb43644d46b6da220280b70b607b11c3309382d55d9604d80ad99b3d6
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81feec53929608a3d2b539f66e29270211cb35072ffa9c1bcebaa955f7bdc514
+oid sha256:71e9af821c38bae7b342c85301f6dc4d8d96eaade7716ea8e604522769dc1743
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004924086992203529,
+  "epoch": 0.005471207769115032,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,13 @@
       "eval_samples_per_second": 31.035,
       "eval_steps_per_second": 15.517,
       "step": 9
+    },
+    {
+      "epoch": 0.005471207769115032,
+      "grad_norm": 59.159908294677734,
+      "learning_rate": 0.0002,
+      "loss": 10.4191,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -116,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1621220483137536.0,
+  "total_flos": 1796487562395648.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null