Training in progress, step 250, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0650e9f09511b1cc1e42cd63046fce421973b923521e96713c8da34ea84b2b45
+oid sha256:94637eea4e99509d40ab1ed6398c072e67eb1d9232e15a346ea5d4259614ff54
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c7b7b33587d43397f67dc03128b6686730f01d2d4f91d14439ad8dc63a2a5d9
+oid sha256:d4c00b8a857030b80ef97e2546c577647c0835e1271c5b67eafdc4a450f90066
 size 127788180

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7ab1caf45ff1dc6565b7a13b56a56be136404cd6b4c407abb9e6d1d57fafacc
+oid sha256:a39f55c16c939d991ce6dd489d711f09d9824bfb49dd85a9eafee8b04bfaf2d4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65558e26afbfb87dd1928966282919939bdee4084add607d42e008ed52d680cd
+oid sha256:6088f970b1f0429ad85e576795204ef9269ce142d6ce9c2595b5649efde833b6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01597970830691186,
+  "epoch": 0.02113718030014796,
   "eval_steps": 63,
-  "global_step": 189,
+  "global_step": 250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -165,6 +165,55 @@
       "eval_samples_per_second": 11.155,
       "eval_steps_per_second": 5.578,
       "step": 189
+    },
+    {
+      "epoch": 0.01606425702811245,
+      "grad_norm": NaN,
+      "learning_rate": 2.8165064990227252e-05,
+      "loss": 2.4595,
+      "step": 190
+    },
+    {
+      "epoch": 0.016909744240118367,
+      "grad_norm": NaN,
+      "learning_rate": 1.985863781320435e-05,
+      "loss": 0.9487,
+      "step": 200
+    },
+    {
+      "epoch": 0.017755231452124286,
+      "grad_norm": NaN,
+      "learning_rate": 1.286812958766106e-05,
+      "loss": 5.5434,
+      "step": 210
+    },
+    {
+      "epoch": 0.018600718664130204,
+      "grad_norm": NaN,
+      "learning_rate": 7.308324265397836e-06,
+      "loss": 0.4902,
+      "step": 220
+    },
+    {
+      "epoch": 0.019446205876136123,
+      "grad_norm": NaN,
+      "learning_rate": 3.270513696097055e-06,
+      "loss": 6.1206,
+      "step": 230
+    },
+    {
+      "epoch": 0.020291693088142042,
+      "grad_norm": NaN,
+      "learning_rate": 8.209986176753948e-07,
+      "loss": 4.3294,
+      "step": 240
+    },
+    {
+      "epoch": 0.02113718030014796,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.5533,
+      "step": 250
     }
   ],
   "logging_steps": 10,
@@ -179,12 +228,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6.012055119200256e+16,
+  "total_flos": 7.944501407514624e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null