Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03eabcbcbfa08f2ae0fa4f5be2d44e508d686a26aeb5834c27b6366ab3ac5b34
+oid sha256:7a3c5c0b3cfb4c4a21c2d8627bdd2824e7f9a1ca22bdd50cdab4f6c59d519157
 size 5327744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf915cbe688092f2fa21be2373f5657ef99cefd8dd32b84ae8fbfb9c9ee4d691
+oid sha256:8b9727ea31da3f8afe4b56672c2f3cdee34fbb7a41395c74e5f57ea989113bf6
 size 2857722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28a96d881868e206aa18e1f8342c5a245d4be1233a3353262c430c9fe1197650
+oid sha256:df39ba4882fc569ad47cee27630612f10760e2c8b0eac5d4ad14edacc7fd5511
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
+oid sha256:532138a5ca880d8da393ae449e5715b2766def36b8838785ca08d07228b119b7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.013377180759155009,
+  "epoch": 0.017836241012206676,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 179.321,
       "eval_steps_per_second": 89.708,
       "step": 15
+    },
+    {
+      "epoch": 0.014268992809765343,
+      "grad_norm": 3.708739757537842,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 4.4863,
+      "step": 16
+    },
+    {
+      "epoch": 0.015160804860375675,
+      "grad_norm": 3.605137348175049,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 6.333,
+      "step": 17
+    },
+    {
+      "epoch": 0.01605261691098601,
+      "grad_norm": 3.8756258487701416,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 11.4717,
+      "step": 18
+    },
+    {
+      "epoch": 0.016944428961596345,
+      "grad_norm": 3.9907853603363037,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 8.4492,
+      "step": 19
+    },
+    {
+      "epoch": 0.017836241012206676,
+      "grad_norm": 3.1043434143066406,
+      "learning_rate": 0.0,
+      "loss": 5.3618,
+      "step": 20
+    },
+    {
+      "epoch": 0.017836241012206676,
+      "eval_loss": 0.42673972249031067,
+      "eval_runtime": 10.6236,
+      "eval_samples_per_second": 177.812,
+      "eval_steps_per_second": 88.953,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 253161926295552.0,
+  "total_flos": 336487759478784.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null