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:db398a55a666335fb71da525039e05bc5584593d63f694b381b0ae46488b041b
+oid sha256:417f46136e3a13bca9802501d3a4521dead02e592ca1ce9b3bc6f0b727136668
 size 30322120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3f7b82441f131ee3e06cc79dfd7b0e7d6f84990205d559c494baaa67bfe2c99
+oid sha256:b179128018dfe0b8830ee80b3e017fda18d3234352c463f1815c847accc1364c
 size 60753722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d796153af1b23c8d27ec2a40cb8e4b76b1ce856194bb2837b0df7672f2ffea72
+oid sha256:e37224de670c69583a766c3e614daa998f0bc8dd77d75ee56d895923256ee064
 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": 0.012202562538133009,
+  "epoch": 0.018303843807199512,
   "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": 5.3258,
       "step": 18
+    },
+    {
+      "epoch": 0.012812690665039659,
+      "grad_norm": 1.5968464612960815,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 5.0502,
+      "step": 21
+    },
+    {
+      "epoch": 0.01464307504575961,
+      "grad_norm": 1.8229084014892578,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 5.0783,
+      "step": 24
+    },
+    {
+      "epoch": 0.01464307504575961,
+      "eval_loss": 5.213924884796143,
+      "eval_runtime": 20.8012,
+      "eval_samples_per_second": 33.219,
+      "eval_steps_per_second": 16.634,
+      "step": 24
+    },
+    {
+      "epoch": 0.01647345942647956,
+      "grad_norm": 1.4516856670379639,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 4.8755,
+      "step": 27
+    },
+    {
+      "epoch": 0.018303843807199512,
+      "grad_norm": 1.560184359550476,
+      "learning_rate": 0.0,
+      "loss": 4.8852,
+      "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": 310615725834240.0,
+  "total_flos": 465923588751360.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null