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:b36f6aa2398273b62e32dbfb00c601589fb41011e537464526cad6b1128a5622
+oid sha256:c92a1f3d237ee81ce00482ffac9728e7537766bf1f8c33a032e66cc6c2939d1e
 size 25192496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7838ecba53a53b93d1f5261f87ade720bac5032b8af700146d668ec499f7c46f
+oid sha256:ce62f5a41abc286cfac3996cebd4cb1f5903c57b0c351e61689927e3d77ba7a8
 size 13005178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90384182705d69a10eb7aa26085504559145f0c755cd85f72c0a72716a70220f
+oid sha256:77fbd1b238ef647f4c2a32d9e5c00271ce36d4399e9b56c02703b864526f37c0
 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": 0.00631911532385466,
+  "epoch": 0.00810142990237777,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 5.45,
       "step": 35
+    },
+    {
+      "epoch": 0.006481143921902216,
+      "grad_norm": 3.458681106567383,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 5.4916,
+      "step": 40
+    },
+    {
+      "epoch": 0.006481143921902216,
+      "eval_loss": 1.2964999675750732,
+      "eval_runtime": 72.1242,
+      "eval_samples_per_second": 36.035,
+      "eval_steps_per_second": 18.024,
+      "step": 40
+    },
+    {
+      "epoch": 0.007291286912139993,
+      "grad_norm": 3.525883436203003,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 5.1703,
+      "step": 45
+    },
+    {
+      "epoch": 0.00810142990237777,
+      "grad_norm": 4.081028461456299,
+      "learning_rate": 0.0,
+      "loss": 5.3712,
+      "step": 50
+    },
+    {
+      "epoch": 0.00810142990237777,
+      "eval_loss": 1.2944227457046509,
+      "eval_runtime": 71.8904,
+      "eval_samples_per_second": 36.152,
+      "eval_steps_per_second": 18.083,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1291325496360960.0,
+  "total_flos": 1649612339281920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null