Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d2b5a045b43fbbba45f8f707c2f4fc8454cb0af27fd8ad395b4d19ee074b7af
+oid sha256:b0585b1ec0a195297d724bdf3e2d5bb6f9ace01580251c733b0a9951e096add2
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e208087bc976addb19cd0843b2a71d45581ad558f58db05b28da59c5d9e84fc6
+oid sha256:fcd8302ab39ecd7b85bd52d9a2a956f505a17b4c9f2b98d57a58a03027dcfd7b
 size 166439638

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f177fba86f95758b7675327511161a70001a51962c0ecd15afb51307101d603b
+oid sha256:d518c9ea5ab877454a628269f8dd9ff071889ff3dc67f91bf536f9bd11c81e75
 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": 0.018726591760299626,
+  "epoch": 0.028089887640449437,
   "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": 25.953,
       "eval_steps_per_second": 12.976,
       "step": 20
+    },
+    {
+      "epoch": 0.019662921348314606,
+      "grad_norm": 2.2143537998199463,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 2.4941,
+      "step": 21
+    },
+    {
+      "epoch": 0.02247191011235955,
+      "grad_norm": 2.414954662322998,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 2.4648,
+      "step": 24
+    },
+    {
+      "epoch": 0.023408239700374533,
+      "eval_loss": 2.4180245399475098,
+      "eval_runtime": 17.3252,
+      "eval_samples_per_second": 25.974,
+      "eval_steps_per_second": 12.987,
+      "step": 25
+    },
+    {
+      "epoch": 0.025280898876404494,
+      "grad_norm": 2.5250325202941895,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 2.2861,
+      "step": 27
+    },
+    {
+      "epoch": 0.028089887640449437,
+      "grad_norm": 2.655407428741455,
+      "learning_rate": 0.0,
+      "loss": 2.3158,
+      "step": 30
+    },
+    {
+      "epoch": 0.028089887640449437,
+      "eval_loss": 2.4034595489501953,
+      "eval_runtime": 17.3258,
+      "eval_samples_per_second": 25.973,
+      "eval_steps_per_second": 12.986,
+      "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": 2010596581048320.0,
+  "total_flos": 3041027328835584.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null