Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e7b005bfce54b91ee7009c6f8ca003a87dc56dc25d80daa1f0d8f9872bc08ef
+oid sha256:6a8c685a95b61582ba2bbd8d90e22bfe007c18a81808b3f5126faeeb5d32eed6
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcbdc551925a8e2036c92f12e072fbcad9d6fc1f673d17b194bea2b3d9b1db30
+oid sha256:e23cea9d8918da9e7576edccc22ba1e16e9ca750af9e3c9c6bfa6aa38eb5dfb9
 size 11710970

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bac3829fab9883fe52c921d069030dcfdb1acb7b3595ec28ffc5a7d8761e39a
+oid sha256:8c53fa0c87e8a58dcc70411994c79b9c7f65d5f8b8db287146f08250dc656d27
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b9b4b9e1c73ddbfb0db3e4e70221ab0ae763bc9eae2ed7a9179b0f835425c83
+oid sha256:0f4519a9887599cb0a87eeef5c384a4c8631bfe07fee0771a14a32f4fd230cd4
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6baf985c8a1ee6c433d8227f8c2313f719cddc8c10eef0a3d759226e562b24e
+oid sha256:6dce0ff9f94335448e0e6bb1ad0c4a527ee7b4ed3051ea261ab2f6e254cad1d2
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b85f5010c9e0a2db0ab3ae3a6293f198b1616cf44c35feb6eaefcdf88907877a
+oid sha256:25ee4e24d97e521c5142b9b33ca4c0d88243a23abbecbfda8c949c467d7fc3cb
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e555b1173ceea1f11ca45539c0fe5856e7571df97c436cc742ba6deb19b07e97
+oid sha256:fd82e2c4dd46a0c4163e78a1bb05a9e321fb40a1c884136f2f4f92fe2449cbde
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8727272727272727,
+  "epoch": 1.0472727272727274,
   "eval_steps": 4,
-  "global_step": 15,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -46,6 +46,14 @@
       "eval_samples_per_second": 263.42,
       "eval_steps_per_second": 8.553,
       "step": 12
+    },
+    {
+      "epoch": 0.9309090909090909,
+      "eval_loss": 0.7947056293487549,
+      "eval_runtime": 1.7541,
+      "eval_samples_per_second": 263.376,
+      "eval_steps_per_second": 8.551,
+      "step": 16
     }
   ],
   "logging_steps": 10,
@@ -60,12 +68,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.618473896411136e+16,
+  "total_flos": 5.542168675693363e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null