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:d70833167fbddb74bba856ea6573a7e2d6d0b52bf45677a04007ad99926d91fa
+oid sha256:3588cfabc0e0443a98fd195efb1ff620f81670f8f6c17efaab8dfa736143afb6
 size 111454040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f547f2d2105e0ff7060abd0657f2fa5bcae463f1b5a41e76ed45c3a6583ab063
+oid sha256:37e370b867c26b462fe68af607abce8f288cfd1e9380916481852a950908de53
 size 56950676

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24b1eb022cc54a29d49cbd8d38d9e31c1e2478e072bc84f1055b9acb9bc9833f
+oid sha256:2b4fcafe51467334025a2305f8c44550e6e8bfc0bc4e21468cb79f88a0d21f9f
 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": 0.0008994448738669103,
+  "epoch": 0.0011243060923336377,
   "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": 12.971,
       "eval_steps_per_second": 6.486,
       "step": 4
+    },
+    {
+      "epoch": 0.0011243060923336377,
+      "grad_norm": 3.0922412872314453,
+      "learning_rate": 5e-05,
+      "loss": 22.5299,
+      "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": 9852365360332800.0,
+  "total_flos": 1.22305225162752e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null