Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:646c144b477247a281155c00d73edf80cbc92114df821385ec9f8d51dd3c9a4c
+oid sha256:5a0e0d237c6db689e95798e50eb592055c24c6df12f3f33823d0758034cd63a0
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:369940c5a3787d59062c2769c230bdde483fa743398ba2e4d8f66ee03cdb349e
+oid sha256:dae60cbcfb9d977a3d925b3cab6ee9727c881308677c1fea0fee72e316d3c399
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf3a48248233b81e3f746e3d9f557dd750b90f8b04de7b95486ad9ac9a4f03ff
+oid sha256:6f00db97249fd560a6e1afb3a8bcbbd836998d202bbad32bbe904fee54f30cbe
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4adb065e8c7ee3fd0605a6d2c5e5b87339b435d7f44ee128ff65fc58e188fae9
+oid sha256:04f2377114f0045a9573af2c1b5089c23c13db9f92c475ef08d7a6bc3481f940
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6713286713286714,
+  "epoch": 1.062937062937063,
   "eval_steps": 2,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -39,6 +39,14 @@
       "eval_samples_per_second": 18.94,
       "eval_steps_per_second": 2.484,
       "step": 6
+    },
+    {
+      "epoch": 0.8951048951048951,
+      "eval_loss": 1.0419520139694214,
+      "eval_runtime": 3.2123,
+      "eval_samples_per_second": 18.99,
+      "eval_steps_per_second": 2.49,
+      "step": 8
     }
   ],
   "logging_steps": 10,
@@ -53,12 +61,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.6825649272455168e+16,
+  "total_flos": 2.523847390868275e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null