Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60e13e2a38a8adb139c1b6e02e4aed73657ca99b92759fdfdefe2b6a16d32237
+oid sha256:0646da2931277b0763fde4368893e402226b42b1760a48feb2ccd74a8919a2ac
 size 132164608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:698d50220062f2c34c4e895e9864a2ac29215210c0438cca2ee7ff7a908f5353
+oid sha256:163fa41d7516a9de7e43a8f0f4b92dec27febd2d436948802d304450588a150c
 size 264524418

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fed1db699c6411ba8d3e0629a03db5e408e4791478a96cd4993cf2abe0fab4f6
+oid sha256:e7d5063a46fbc069bfae4940ffe85c0db9d8405a525d190064defe1a75df7653
 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": 0.017185821697099892,
+  "epoch": 0.02577873254564984,
   "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": 3.7622,
       "step": 18
+    },
+    {
+      "epoch": 0.01804511278195489,
+      "grad_norm": 1.8822708129882812,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 3.6641,
+      "step": 21
+    },
+    {
+      "epoch": 0.02062298603651987,
+      "grad_norm": 2.2596004009246826,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 3.664,
+      "step": 24
+    },
+    {
+      "epoch": 0.02062298603651987,
+      "eval_loss": 0.9132661819458008,
+      "eval_runtime": 114.593,
+      "eval_samples_per_second": 4.276,
+      "eval_steps_per_second": 2.138,
+      "step": 24
+    },
+    {
+      "epoch": 0.023200859291084855,
+      "grad_norm": 2.5175583362579346,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 3.6665,
+      "step": 27
+    },
+    {
+      "epoch": 0.02577873254564984,
+      "grad_norm": 1.8177056312561035,
+      "learning_rate": 0.0,
+      "loss": 3.5424,
+      "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": 9677809284096000.0,
+  "total_flos": 1.4733381298176e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null