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:eefaaad5036063a54e80d29725c875d91e1bc1454084107cb4e678b9aaaa1537
+oid sha256:be14a59c3c68da31966d8f948d4faaaf3c168e3b104789c2852fc13058b1b354
 size 767856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:131aca896cee1277d2b1064bdfa23815d6b6cb4b9776b65e9060d7c6201f43bb
+oid sha256:a20500661402b411433caac66f17da6056ee5a53f54dff717e00eb7728060308
 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": 0.16822429906542055,
+  "epoch": 0.18691588785046728,
   "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": 33.717,
       "eval_steps_per_second": 17.592,
       "step": 9
+    },
+    {
+      "epoch": 0.18691588785046728,
+      "grad_norm": 11.965997695922852,
+      "learning_rate": 0.0002,
+      "loss": 7.4087,
+      "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