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:efff1503c16ebb8627aa07d1db313d3cd2c4d01af105d01926ec7146295f226e
+oid sha256:44da5359f97c8183b6b912307c5cef292addd3043b48045c7a283f22c2ba50ca
 size 39256456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed7efd0ad7c08870e9dc8db75b2d3f4f16dcf8e1e5eb429acfa8c260abaf5566
+oid sha256:d746c526c6a0dc40e79bc81677a9b81b14c8b5945671c222de32bd6d37db0109
 size 20632826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abd033918d0ec9be7b0057f0d36df7507acb2080dc148b8d779c63bff8270321
+oid sha256:b700466baf3098da9bee6346e89e2a7037a0a2bc78d455fa465ff2d30392f054
 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": 0.0028415818138763913,
+  "epoch": 0.0031573131265293236,
   "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": 22.327,
       "eval_steps_per_second": 11.164,
       "step": 9
+    },
+    {
+      "epoch": 0.0031573131265293236,
+      "grad_norm": 1.7280672788619995,
+      "learning_rate": 0.0002,
+      "loss": 2.2445,
+      "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": 452766958878720.0,
+  "total_flos": 501714738216960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null