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:cadf689988f354ed93b8ee50608db0335744d1450f8207ce6f23da9453aa93b8
+oid sha256:abb43806a67ae596f542785fee1d8fa2914e3d3d309e1b53ae671fe66bcaa45b
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b151e492dd8652d8547b516c3114cce6df82c5987ed14f634a510671b930399
+oid sha256:ecc5e0a8e1792eeec946859d856a2c9250f86aadbca622a2526dd9a1c7b31d38
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54b3ee8f06a13ef0f4d0831c0c1d7840f1b54d75135d2aeb006e8d093e0945fe
+oid sha256:d01db2ee336282e9fa52adde814dca6a22070d1f49093cdf705c3bc6c64432f2
 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": 0.00024955288441542235,
+  "epoch": 0.00027728098268380263,
   "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": 20.899,
       "eval_steps_per_second": 10.45,
       "step": 9
+    },
+    {
+      "epoch": 0.00027728098268380263,
+      "grad_norm": 10.181532859802246,
+      "learning_rate": 0.0002,
+      "loss": 6.2723,
+      "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": 2820585478422528.0,
+  "total_flos": 3190498328051712.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null