Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:304e9882de79cbc3a0f2eefeb019624e65dc2af1cbef2b43f34059587772d45f
+oid sha256:e552a66e211feea29943f171f43bdee81d30bd27020d86d2cc4e8d99120f30d7
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7205a4f7ab79e46d11519bed021b824867f48a4473105d48bd404a61e6ceb8f
+oid sha256:1c7a3f15ba5d4f937ffb5469f662a80e5e7345f1f0452e911e1f228e3c541c49
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2eaba35994b5fdae940b870b4b7b8c4d1d8ec611c62a2347945f85508d465b28
+oid sha256:47ebb2ee5ea45d9ccec5929c4c48c38612f1a12e160537e8ac2c2ee7610ed4c7
 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": 0.0012687671812222456,
+  "epoch": 0.0014097413124691618,
   "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": 14.89,
       "eval_steps_per_second": 7.447,
       "step": 9
+    },
+    {
+      "epoch": 0.0014097413124691618,
+      "grad_norm": 0.40287280082702637,
+      "learning_rate": 0.0002,
+      "loss": 0.8795,
+      "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": 3878601652961280.0,
+  "total_flos": 4353532467609600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null