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:f99663b5ab2d829fa3d53b5d1a132c9ee04ee03cbad030671cfbb87e03e5f14f
+oid sha256:8db84525577da4260110d3f3cc48b4b97d5f18676150511f73b284682991dc99
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fab613ae9a194c8f0e018c16baf64a41067be70e4148fb81a421d03ff2393c59
+oid sha256:ed5a11ff6b808fc0fa479a3a5f79968c393ab09e0cfbbe01346ec914ddb85ec3
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc7c3dcfd2fbfcccbf5177669f5b109776dfbae391c64a8d0d5e2326b72c5b68
+oid sha256:94eb3af0be59b8022e591483a56634de67b6ec709d4a7976205940027b927a1a
 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": 0.0011350536490201295,
+  "epoch": 0.0014188170612751618,
   "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": 5.979,
       "eval_steps_per_second": 2.989,
       "step": 4
+    },
+    {
+      "epoch": 0.0014188170612751618,
+      "grad_norm": 68.01908111572266,
+      "learning_rate": 5e-05,
+      "loss": 93.0721,
+      "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": 2605973017460736.0,
+  "total_flos": 3257466271825920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null