Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:155b9086a463a09abb92e23c5a777b377255eaaf766868cace9702e5185a7ea7
+oid sha256:afa25201670d43fd5da6cd9a97ade0bdf3d20da3e094171b5ad54c7a5a783f93
 size 13587864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58114a34c6c3e1055c7caf68d5fba071eeec92cded273ec6b1641b24cbd27a44
+oid sha256:dd7a2f4c0d3baec8e953b3df77e8d2c1cf59ba8938494d70770642f2a0addb08
 size 7086458

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd0214bbe109dca9c79f696d3784ba0601ee4dda3eb56b95625502e9d6ad1cc2
+oid sha256:1c9be43f8c2b7b48385d84d63d40cbf9617ea3a7adb2ada338c2d141613b5054
 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": 0.03006012024048096,
+  "epoch": 0.04008016032064128,
   "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": 25.184,
       "eval_steps_per_second": 12.6,
       "step": 15
+    },
+    {
+      "epoch": 0.03206412825651302,
+      "grad_norm": 0.9710604548454285,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 3.2329,
+      "step": 16
+    },
+    {
+      "epoch": 0.03406813627254509,
+      "grad_norm": 0.9070257544517517,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 3.1751,
+      "step": 17
+    },
+    {
+      "epoch": 0.036072144288577156,
+      "grad_norm": 0.9331132769584656,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 3.1826,
+      "step": 18
+    },
+    {
+      "epoch": 0.03807615230460922,
+      "grad_norm": 0.9252903461456299,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 3.1469,
+      "step": 19
+    },
+    {
+      "epoch": 0.04008016032064128,
+      "grad_norm": 0.9361170530319214,
+      "learning_rate": 0.0,
+      "loss": 3.2011,
+      "step": 20
+    },
+    {
+      "epoch": 0.04008016032064128,
+      "eval_loss": 3.241048812866211,
+      "eval_runtime": 66.7398,
+      "eval_samples_per_second": 25.187,
+      "eval_steps_per_second": 12.601,
+      "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": 3332102066012160.0,
+  "total_flos": 4442802754682880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null