Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:320bf161d988e79d6b5f7c84009886da8a34b32cbc89a9547e1d6ad55711729b
+oid sha256:b4493538919160bafb599017ff18237c62d620f8f5f1c6be860a5988cdedd514
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0180866a4d3b86d772630b13d0b24fb64dcf2cd90e41163c3914054e38c043f5
+oid sha256:d083b2d18b1237a4ca874f04b84977440dce9539d2be4f85b130dfce95d4efbc
 size 323290986

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63baab6196b05b5b3ec16e085c1201e0102b31625ee3592d359ed2201809bbce
+oid sha256:1df267a9f3a77fe77a3fc44b25c83608ed40cf5325dac5b4c68660160c115716
 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": 0.0016858786588835268,
+  "epoch": 0.00252881798832529,
   "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": 1.6336,
       "step": 18
+    },
+    {
+      "epoch": 0.0017701725918277031,
+      "grad_norm": 0.9744684100151062,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 1.5937,
+      "step": 21
+    },
+    {
+      "epoch": 0.0020230543906602323,
+      "grad_norm": 0.7924067378044128,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.5408,
+      "step": 24
+    },
+    {
+      "epoch": 0.0020230543906602323,
+      "eval_loss": 1.5494054555892944,
+      "eval_runtime": 261.4684,
+      "eval_samples_per_second": 19.104,
+      "eval_steps_per_second": 9.554,
+      "step": 24
+    },
+    {
+      "epoch": 0.0022759361894927614,
+      "grad_norm": 0.6777858734130859,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 1.6079,
+      "step": 27
+    },
+    {
+      "epoch": 0.00252881798832529,
+      "grad_norm": 0.565368115901947,
+      "learning_rate": 0.0,
+      "loss": 1.2456,
+      "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": 6990386933268480.0,
+  "total_flos": 1.048558039990272e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null