Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e3913117ecf7d763340e0e4cd001302ef22e379e06e3ef45a21aea18a044c69
+oid sha256:2315a0cdc4b23b633b40ed8c94c39d28077e2ab7fb505983e20c1e1ff056e60f
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b5c802ce1ae82e083a8a02e8420c8b6905c9fcf39f2c1be61e6cf235219db14
+oid sha256:1318fc225ac947100592e9dd83e6f4b001397289fbc29e646d625db7285b9b24
 size 37965300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00985fb7e13fdc811c91a3bd76996817a61857ebcea9547c13e16980b6a4ce57
+oid sha256:882f931c75a63dbadf1613ab2f34ceb65bcdc210992aa9cbd7ce762e1fde05cb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bdda546a1390be3b85a90dd4ef31050dfb7b691765ffc12ed691b6786ed6e3d
+oid sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007074081351935547,
+  "epoch": 0.007860090391039498,
   "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": 10.996,
       "eval_steps_per_second": 10.996,
       "step": 9
+    },
+    {
+      "epoch": 0.007860090391039498,
+      "grad_norm": 39.99613952636719,
+      "learning_rate": 0.00016,
+      "loss": 15.2566,
+      "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": 1175641953140736.0,
+  "total_flos": 1306268836823040.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null