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:efc165f98fe00876f13e8d514845dbfdaba88eeaf82051fcfe14fa93dc479758
+oid sha256:5422a0e7f73716ef6458f58c2d35672c8628558b59e2c46c2524aa4532b01d64
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41933031d745a105c06d494cef65225615bbbfb8a3e1ed1f2bdca4de159b1579
+oid sha256:8fce15589964905294abdb6bf09e81a67f58a45758bd8a6b0335e1d179ad2e0a
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4338e60828af3efb3dbfac479ffbce4cf22f201f32dd76c072dd2215e2af458f
+oid sha256:f2b17376c2094a7843882b205fe5baa2fba28ee9afa48547a0118f514aace90e
 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": 0.057091882247992866,
+  "epoch": 0.07136485280999108,
   "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": 27.75,
       "eval_steps_per_second": 13.875,
       "step": 4
+    },
+    {
+      "epoch": 0.07136485280999108,
+      "grad_norm": 130.52099609375,
+      "learning_rate": 5e-05,
+      "loss": 126.2317,
+      "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