Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:581f191ba9b855c60a23027342ae7844f77916a6cb811432f84ce97526f274c5
+oid sha256:7c17fe250b43481cb3bf90090a71523bc6c4bc7f3ffb0e13b4890826d84ee442
 size 216151256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2489ccc3de60b3b10d55b5541684c497a4bf5319309b5df566133a2b9934dcd1
+oid sha256:93cbb16ab9d4d85b32251bae6359987c784f384c05d988adc963e46212934131
 size 432640054

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06b575a09cf2bb420aea0f8ad94caa76d06dc55ba726b37aa80f754b994562e0
+oid sha256:bca8e8136afa70e7c13c8304ca5d9088723951b5ae1540e278bea8c962c65424
 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": 0.0014594012806246237,
+  "epoch": 0.002189101920936936,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 6.545084971874738e-05,
       "loss": 1.4409,
       "step": 18
+    },
+    {
+      "epoch": 0.0015323713446558549,
+      "grad_norm": 0.6480987071990967,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 1.4124,
+      "step": 21
+    },
+    {
+      "epoch": 0.0017512815367495486,
+      "grad_norm": 0.7756116986274719,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.264,
+      "step": 24
+    },
+    {
+      "epoch": 0.0017512815367495486,
+      "eval_loss": 1.3948931694030762,
+      "eval_runtime": 1739.7537,
+      "eval_samples_per_second": 3.317,
+      "eval_steps_per_second": 1.659,
+      "step": 24
+    },
+    {
+      "epoch": 0.001970191728843242,
+      "grad_norm": 0.7044386863708496,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 1.4413,
+      "step": 27
+    },
+    {
+      "epoch": 0.002189101920936936,
+      "grad_norm": 0.7354962229728699,
+      "learning_rate": 0.0,
+      "loss": 1.4491,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.1015817749594112e+16,
+  "total_flos": 1.6884057111527424e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null