Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60612c1e475a19132fc3d4764d41232ce46edc58e55f8b80e13222e32159ab62
+oid sha256:f8726b1c336e2d2dff9b9299c5db0a422f048c46b1f75de803abce5b9766f327
 size 7586384

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e199194d6b4c3d03b0bc4883bf4b69dee380f871f19fd9f452f704367b764dd
+oid sha256:7c857c4f1a9a1acdb7c52ba1e0a23d267e8282065a30872da0a78a650d517092
 size 4027642

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aae73d941b6797a3bfb814f1cf4e45bc917320485d0450a95de60fac6e1799ae
+oid sha256:4d53c5874c105792eb677bdac110c1842e3bbce378d7eac46c9f5ccebd52d2ef
 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": 0.003616636528028933,
+  "epoch": 0.004018485031143259,
   "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": 31.872,
       "eval_steps_per_second": 15.936,
       "step": 9
+    },
+    {
+      "epoch": 0.004018485031143259,
+      "grad_norm": 2.4751334190368652,
+      "learning_rate": 0.0002,
+      "loss": 10.1359,
+      "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": 71692026642432.0,
+  "total_flos": 77002547134464.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null