Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a2021356a5d0ec02bec53ddeca167712eb8152ff805af07d1d0d28529477247
+oid sha256:445be9344694d4402004efb0ddf4fca619e4ed0a42d2e476733f8d743fe1828c
 size 33572288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e31879ed71c274452bbda6a54da33007c20b85091b089adfa0c10ee8cb763ce1
+oid sha256:74214ff4f46c85eb1bd5594c502955a0ffc93ce90962855fc8df8432464887fe
 size 67216698

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80c21c7c5c6bed36f1e7b5a430ea5722c2257ea00a632c24bd72e7f6c8675c89
+oid sha256:95859336487e6e4388a4b258384b2b4b3853f70361680f00277c4140a10b9ca9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0009409440020700768,
+  "epoch": 0.0014114160031051153,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 51.892,
       "eval_steps_per_second": 25.946,
       "step": 20
+    },
+    {
+      "epoch": 0.0009879912021735807,
+      "grad_norm": 1.8358335494995117,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 7.643,
+      "step": 21
+    },
+    {
+      "epoch": 0.0011291328024840921,
+      "grad_norm": 1.6776705980300903,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 7.5998,
+      "step": 24
+    },
+    {
+      "epoch": 0.001176180002587596,
+      "eval_loss": 1.9313894510269165,
+      "eval_runtime": 172.5931,
+      "eval_samples_per_second": 51.856,
+      "eval_steps_per_second": 25.928,
+      "step": 25
+    },
+    {
+      "epoch": 0.0012702744027946037,
+      "grad_norm": 1.7137739658355713,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 7.4771,
+      "step": 27
+    },
+    {
+      "epoch": 0.0014114160031051153,
+      "grad_norm": 1.9183655977249146,
+      "learning_rate": 0.0,
+      "loss": 8.0373,
+      "step": 30
+    },
+    {
+      "epoch": 0.0014114160031051153,
+      "eval_loss": 1.9244450330734253,
+      "eval_runtime": 172.6698,
+      "eval_samples_per_second": 51.833,
+      "eval_steps_per_second": 25.917,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -103,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1431278607925248.0,
+  "total_flos": 2197632508231680.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null