Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68639ddb39ba72c88766b970b3233e382babce8e9264c893338e2d8899d03811
+oid sha256:03c1a6a16ac1f5237015486024855ad26cbf583b6e079339a44c282483a76f42
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bd98879bffa21930b691d262f8043ea423e8f78167d8fd3e14ce89fcfb13821
+oid sha256:113faeed05d357f55f5700313e9620a0bac84d02345cb2f454f5aeaefbb571aa
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dec486592e12b5686692fb2db60f7dacbc5ae0413674e38bebce55a8bce13d37
+oid sha256:563a001728d0d9d28b69390538cf129a42f108202d3a1d8a50bee89040c233bb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
+oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.013748657357679914,
+  "epoch": 0.017185821697099892,
   "eval_steps": 2,
-  "global_step": 4,
+  "global_step": 5,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -59,6 +59,13 @@
       "eval_samples_per_second": 21.173,
       "eval_steps_per_second": 10.586,
       "step": 4
+    },
+    {
+      "epoch": 0.017185821697099892,
+      "grad_norm": 78.39874267578125,
+      "learning_rate": 5e-05,
+      "loss": 134.3888,
+      "step": 5
     }
   ],
   "logging_steps": 1,
@@ -73,12 +80,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4560452780556288.0,
+  "total_flos": 5700565975695360.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null