Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a2990a639c89d2e782564032c3d45b4cd5153b8f9aabdfd057f032b561521ba
+oid sha256:3d390ce3f322982e15e628c456aaffb016beee680ac61e8ab68fe1b7aeea9e9f
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acb3eb31cc110fc1491f9c2f470d530a6ba964b8818fbd0f5a6fd944823c4808
+oid sha256:b5649863d3b7dc315a189b9a7f1819ebdfc2c089522cb5433aac32af512ca4e4
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:652365ff63294ffff01ffedb52e831cc2560ab06b5699bca21d63e81dd0efbe7
+oid sha256:2edc13c60910e9acd555e90579b2ee1807926bb393c7c79b1e24163c3f5bfc9f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005798987035918406,
+  "epoch": 0.007434598763997956,
   "eval_steps": 13,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -312,6 +312,83 @@
       "eval_samples_per_second": 57.144,
       "eval_steps_per_second": 28.575,
       "step": 39
+    },
+    {
+      "epoch": 0.005947679011198364,
+      "grad_norm": 0.11559172719717026,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.4673,
+      "step": 40
+    },
+    {
+      "epoch": 0.006096370986478324,
+      "grad_norm": 0.13287204504013062,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 0.5629,
+      "step": 41
+    },
+    {
+      "epoch": 0.006245062961758282,
+      "grad_norm": 0.11092466861009598,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.5093,
+      "step": 42
+    },
+    {
+      "epoch": 0.006393754937038242,
+      "grad_norm": 0.1304820328950882,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 0.5968,
+      "step": 43
+    },
+    {
+      "epoch": 0.0065424469123182005,
+      "grad_norm": 0.1185159906744957,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.5457,
+      "step": 44
+    },
+    {
+      "epoch": 0.00669113888759816,
+      "grad_norm": 0.1245209202170372,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.5554,
+      "step": 45
+    },
+    {
+      "epoch": 0.006839830862878119,
+      "grad_norm": 0.11818329989910126,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.537,
+      "step": 46
+    },
+    {
+      "epoch": 0.006988522838158078,
+      "grad_norm": 0.11721956729888916,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 0.5176,
+      "step": 47
+    },
+    {
+      "epoch": 0.007137214813438038,
+      "grad_norm": 0.1277380883693695,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 0.5867,
+      "step": 48
+    },
+    {
+      "epoch": 0.007285906788717996,
+      "grad_norm": 0.11630207300186157,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 0.4884,
+      "step": 49
+    },
+    {
+      "epoch": 0.007434598763997956,
+      "grad_norm": 0.11541259288787842,
+      "learning_rate": 0.0,
+      "loss": 0.4698,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -326,12 +403,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9947849079914496.0,
+  "total_flos": 1.27692439289856e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null