Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62e02e31d15a8cfeabb187b11e790e86985e17bf18116fc0a34bf49f3d2b521d
+oid sha256:5adf2e1791982892d479498639971ca18524a0822314af38ad26cf054c039574
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c61c76fee99b9a4e289be8d96c7c49eb997784cac02133c5e038b64b28af506
+oid sha256:7118719a90ccc46e391f3bf499470cd900261eb87ce48868229b7637bfc54785
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:094837089fa2ed1c4f9dc6c25bac04422ed41c22630725ca5cdf86ffa65f03cf
+oid sha256:787ef78ee12881294c4aa83ed64603709fff88fc133de1a040e06eba2a245935
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03127715030408341,
+  "epoch": 0.03475238922675934,
   "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": 4.779,
       "eval_steps_per_second": 4.779,
       "step": 9
+    },
+    {
+      "epoch": 0.03475238922675934,
+      "grad_norm": 4.4422430992126465,
+      "learning_rate": 0.00018,
+      "loss": 2.787,
+      "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": 6676985552044032.0,
+  "total_flos": 7418872835604480.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null