Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0736a64cef86e7f34de21f46df00b9089cbaa788fe39e47c164ffbf6244acf62
+oid sha256:a5a1c5344bbd68f534b3092b1122e752d445906539ede792a9cb243e83ddf78d
 size 767856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8e918072883223340f556f0385bb0f4fe1b32c32ebe84343c2196630b1a2f69
+oid sha256:27cb7a53aab782b3218b3322b613e2516b4fad8a26c16c05e70f3684503efe40
 size 1003002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18f6a101d6015c664d83d03fe11b031664c6a0081efa54d2524c3a9caa94c172
+oid sha256:ea7119004b9c3b59757390dcefc6d215d8b586501d4d3465000762ea0d6de0de
 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": 0.08411214953271028,
+  "epoch": 0.09345794392523364,
   "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": 35.282,
       "eval_steps_per_second": 18.033,
       "step": 9
+    },
+    {
+      "epoch": 0.09345794392523364,
+      "grad_norm": 7.0427446365356445,
+      "learning_rate": 0.0002,
+      "loss": 7.1759,
+      "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": 4886913613824.0,
+  "total_flos": 5429904015360.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null