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:dda10328c7e5a81ac30c1e9291bc2cc14c731bf92e097dd4d1f361c57fa72fe0
+oid sha256:be266c3dd1ae78e20f512d3ea6d882401295699152d9f88664963751123c84ff
 size 104902272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2ed58abe02a110e6644f1815d0609c825b1e68bcd6c703ae7018500f65727ee
+oid sha256:ca1bf56fbb83d2f6df2b06856ac65b51189dcd76bb6a0305279b7fd51373ec79
 size 53622996

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d68475fe228eccc7e5f235d9fe80ba228ed3d40fa0323774b16cea03e3b868c7
+oid sha256:9a8523072024c5c9ae7a19d57142b80369d4054ec4342e5d3c1481d7956cab59
 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": 0.00020952159236410197,
+  "epoch": 0.00023280176929344664,
   "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": 20.685,
       "eval_steps_per_second": 10.343,
       "step": 9
+    },
+    {
+      "epoch": 0.00023280176929344664,
+      "grad_norm": 3.402151346206665,
+      "learning_rate": 0.0002,
+      "loss": 7.9627,
+      "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": 3137325131366400.0,
+  "total_flos": 3529490772787200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null