Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f994a4018fa71c94fbdc2c5d53cefe31e9b57daebcacd4522bf0fe082019199
+oid sha256:e9ffdcefa0c8c036fcf1cfff0deb245e6d19fa300bd794908a6e6fcc322da72c
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e23ea3985ab49df9ce1eaeacd07a7e7ca7f261d7b5d614a6a0b3fe80429652ae
+oid sha256:8d7c6e9957aad4451bd6a7a013d1582ffada90aff15c53db1feb32b83f167f26
 size 42608388

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c587c90db37dd17929ca520ca809393eec3527e02b375ea20b5c0f12fbd18ecb
+oid sha256:f9369f22bbec349db2f8cb019622ad7c25bb800a1a30a149143b9cb28d86b645
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eca0ddb3ec890c90e8e6e7325bec40cdb8b59e4bebf5c0da8473b02809de875
+oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.032593933906745136,
+  "epoch": 0.0362154821186057,
   "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": 14.151,
       "eval_steps_per_second": 7.091,
       "step": 9
+    },
+    {
+      "epoch": 0.0362154821186057,
+      "grad_norm": 16.777368545532227,
+      "learning_rate": 0.0001,
+      "loss": 6.1656,
+      "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": 1.4476295383547904e+16,
+  "total_flos": 1.608477264838656e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null