Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48e2af98904bde6f4ff94b54884a814fc03d7bb61c95484738814d15b522b20d
+oid sha256:680a9e8d054c3da3d614478716fd6a72cbc4c51c440200038c3cc7cff7000a18
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb5773d1d01123a694ff7cdab81b7241b1f471b6d7372015ec57891c662e2564
+oid sha256:556a779df4ba5a72abdb414cd7f71f55342c616ea358ed3d80ee08a0c52a43de
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8d9358611d5238c19c59fb3aa3eac2040cbac245a7cfcfe56e1467f677e36cf
+oid sha256:372c9c91189dafe7a0013b948ff9907e60fc7ad4b32cc7ac3bccb3f603cf2268
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.011286681715575621,
+  "epoch": 0.016930022573363433,
   "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": 0.00013090169943749476,
       "loss": 10.3735,
       "step": 18
+    },
+    {
+      "epoch": 0.011851015801354402,
+      "grad_norm": 0.3252118229866028,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 10.3792,
+      "step": 21
+    },
+    {
+      "epoch": 0.013544018058690745,
+      "grad_norm": 0.2174423635005951,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 10.3536,
+      "step": 24
+    },
+    {
+      "epoch": 0.013544018058690745,
+      "eval_loss": 10.363819122314453,
+      "eval_runtime": 3.0627,
+      "eval_samples_per_second": 243.899,
+      "eval_steps_per_second": 122.113,
+      "step": 24
+    },
+    {
+      "epoch": 0.015237020316027089,
+      "grad_norm": 0.27528172731399536,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 10.3679,
+      "step": 27
+    },
+    {
+      "epoch": 0.016930022573363433,
+      "grad_norm": 0.22619220614433289,
+      "learning_rate": 0.0,
+      "loss": 10.3562,
+      "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": 523024465920.0,
+  "total_flos": 784536698880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null