Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:632ee06cfdff8bd6e4bcf46ddae44a1b3ddf4774e8bbce8bda9e6010a740b82c
+oid sha256:100da7809700b65caf4b0cc33ab5c5e1101fbe935610318f13ba8a5a43988641
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9f4f3b82cdf4e8b07a8128462d70f6cbebed8ea19b47028bea8c6fa3e155d03
+oid sha256:7da2388a795e64d168f622ea1eebd8a766a407c46a30f2ad90c8aa1cf44082ee
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40aa061d5812098e87da46894e9dca7b6728f728c6bc9be9d09d01ce157c01f8
+oid sha256:3bf4939de73ae55f2e5899ab8e1d817c065a261d41c6d9dfcbbafbb9bc6505ec
 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": 0.08324661810613944,
+  "epoch": 0.12486992715920915,
   "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": 0.1725,
       "step": 18
+    },
+    {
+      "epoch": 0.08740894901144641,
+      "grad_norm": 0.5121894478797913,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.2956,
+      "step": 21
+    },
+    {
+      "epoch": 0.09989594172736732,
+      "grad_norm": 0.2800498604774475,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.1461,
+      "step": 24
+    },
+    {
+      "epoch": 0.09989594172736732,
+      "eval_loss": 0.21372172236442566,
+      "eval_runtime": 18.2385,
+      "eval_samples_per_second": 5.593,
+      "eval_steps_per_second": 2.796,
+      "step": 24
+    },
+    {
+      "epoch": 0.11238293444328824,
+      "grad_norm": 0.29954293370246887,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.1274,
+      "step": 27
+    },
+    {
+      "epoch": 0.12486992715920915,
+      "grad_norm": 0.4512592554092407,
+      "learning_rate": 0.0,
+      "loss": 0.2238,
+      "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": 9644534686285824.0,
+  "total_flos": 1.4281330208538624e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null