Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:112533773708c4f8e76b486a71c777b15d683f92782cc485bf3eb5d93520c54b
+oid sha256:ac2a1b90ff9a1bc200a53ca216b2498d2bac1dff18754f27af629c3d27637d76
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96e2f1096e16b5b823a9cb676e047abdcafc1f8296cb4914c87ba98da25a3b04
+oid sha256:e283cb4e3b2a8c2e43e3354014c143f0d1ffcf20f59c8a49efeb5533151974f7
 size 148047722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54190408dc379d03159f6e457fb1a7686dad72e0b750e7867aed9ebb5aa323d5
+oid sha256:3a737b284adb526842f43d1c2667ee811e357afd097996c1a557c56374268de7
 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": 0.0006446985631280775,
+  "epoch": 0.0009670478446921161,
   "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": 4.7105,
       "step": 18
+    },
+    {
+      "epoch": 0.0006769334912844813,
+      "grad_norm": 0.4588887095451355,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 4.6608,
+      "step": 21
+    },
+    {
+      "epoch": 0.0007736382757536929,
+      "grad_norm": 0.5872651934623718,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 4.588,
+      "step": 24
+    },
+    {
+      "epoch": 0.0007736382757536929,
+      "eval_loss": 4.554722309112549,
+      "eval_runtime": 586.3558,
+      "eval_samples_per_second": 22.277,
+      "eval_steps_per_second": 11.138,
+      "step": 24
+    },
+    {
+      "epoch": 0.0008703430602229046,
+      "grad_norm": 0.5140621066093445,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 4.4738,
+      "step": 27
+    },
+    {
+      "epoch": 0.0009670478446921161,
+      "grad_norm": 0.5304310917854309,
+      "learning_rate": 0.0,
+      "loss": 4.6474,
+      "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": 1355253918203904.0,
+  "total_flos": 2008388336615424.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null