Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76728aee1af537fc79bd5087c256e76e50369ce1ccb0b2fd8863206680de3da8
+oid sha256:0670f3b4a2dff296363dbebf8e10f3bca007fd65ee39a4d1f5df76a85e8dac0a
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fe6a1e0f5b2246bd39a3d67fb3bbaa83740038da5eab34f998e8b6d3b10507c
+oid sha256:1ece48b13e3167d4e21f1c642bcadad90bcfeb78326b3e1bbf6c710e7f79ae28
 size 49846260

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:582f196f4d63ab94921242b3722aa87da7ed90d76395ded941d5c7905c87f5ce
+oid sha256:f2c54788be2ab935864d57a82a9fbf815cdc03f9497d60f0a2cfa1a2386e6029
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c34451b9d575e5a4e8015e31b24170db1390190083092379b564ad7e1ac9475
+oid sha256:46f79ea8a2fd75efcc38fb270d516473775ccc226aa736c8e4e01b87dc05a117
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c7871c494508e55f881b9e8ecf04d8c9e09fb8fdb360ed9aa2a5b7d8f82ea03
+oid sha256:474ca476ee9b01146339a38dbb52e0d598fcbf3c80628c0d0edb217d3abee9e4
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3d8ad5e52356323e48f11c2fc575a33b6855e6a88e71799fcabb63afd2cdec4
+oid sha256:78f6737408e995e49b5b5481478ba9558bce997ff19dd0a778bb8ddf23f5020d
 size 15024

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": 0.08955223880597014,
+  "epoch": 0.09950248756218906,
   "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": 31.895,
       "eval_steps_per_second": 4.128,
       "step": 9
+    },
+    {
+      "epoch": 0.09950248756218906,
+      "grad_norm": 0.4322220981121063,
+      "learning_rate": 0.0002,
+      "loss": 0.8347,
+      "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": 2.0122869090484224e+16,
+  "total_flos": 2.235874343387136e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null