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:d21229bebaa5d0019cdada04ed7a1e38e43ddb95872fbee7a7bd9e7980045564
+oid sha256:a2aa69f77cd51fe0452130492849d62cf46b65a6240108a6372bd920321a39fc
 size 36220072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f921485c15f8e57d0ae04f4ef989e662c6c56eb3a80c4ddeb3f9076ce848b89d
+oid sha256:ad9a297f4519ea264a4e01bfe0459e5dec274802435c6a0e58ed6849158ee466
 size 18763860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16e192b0589cb76aab58b5f5ff6b1a79c987a5044492d36eb1539979e1cae814
+oid sha256:6afb32ab20a5701c0676d3f7d419d1cc6c891228aa8d78693e6f90b447e80732
 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": 0.01646843549862763,
+  "epoch": 0.018298261665141813,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -94,6 +94,13 @@
       "eval_samples_per_second": 15.197,
       "eval_steps_per_second": 7.631,
       "step": 9
+    },
+    {
+      "epoch": 0.018298261665141813,
+      "grad_norm": 0.176015704870224,
+      "learning_rate": 0.0002,
+      "loss": 1.271,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -108,12 +115,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 696625114644480.0,
+  "total_flos": 766287626108928.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null