Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fae595b9eaa9abacd06c2fe2e1f21795a0d878968b9df0d307ec08a46154a3c
+oid sha256:658538ffdb2c5633d86b5279e765e90f64db1b5f265a779bddad416f2f276fa1
 size 56662952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba6a89040f4761f73715edf3cd767f3c3d8e0f08275bbe8eb579750a161c7566
+oid sha256:25b65530444a446224da94fb6ccc854a518fee3ba55b9034328a6c26632a00a2
 size 113488058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6eacaf126875d012a3f9f4bdf60d2fff46f053b87a7d5774e37ae5621d3495b
+oid sha256:f5253772cd86b47b6517739cd8b4acf306f270c181d7d1ad9df7570086f33c99
 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": 0.0935672514619883,
+  "epoch": 0.14035087719298245,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 28.094,
       "eval_steps_per_second": 14.047,
       "step": 20
+    },
+    {
+      "epoch": 0.09824561403508772,
+      "grad_norm": 2.9884283542633057,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 6.1712,
+      "step": 21
+    },
+    {
+      "epoch": 0.11228070175438597,
+      "grad_norm": 2.5718295574188232,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 5.9903,
+      "step": 24
+    },
+    {
+      "epoch": 0.11695906432748537,
+      "eval_loss": 1.4295446872711182,
+      "eval_runtime": 3.2324,
+      "eval_samples_per_second": 27.843,
+      "eval_steps_per_second": 13.922,
+      "step": 25
+    },
+    {
+      "epoch": 0.12631578947368421,
+      "grad_norm": 2.819051504135132,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 5.7862,
+      "step": 27
+    },
+    {
+      "epoch": 0.14035087719298245,
+      "grad_norm": 2.808319568634033,
+      "learning_rate": 0.0,
+      "loss": 5.712,
+      "step": 30
+    },
+    {
+      "epoch": 0.14035087719298245,
+      "eval_loss": 1.4244388341903687,
+      "eval_runtime": 3.2052,
+      "eval_samples_per_second": 28.079,
+      "eval_steps_per_second": 14.04,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -103,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1202020417536000.0,
+  "total_flos": 1803030626304000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null