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:aa05d9562521a3be8461c555f8e2e33d4bc6ec54ad5e92cd7a64fc77802055b0
+oid sha256:6b14ec7ff36f18899fa1fec312099a8f541efe00fc1e5960529eae20642eb95c
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a128e42f14923adacd93099a1b7f1daa7ca836a1d9d331ad002db27f1bc3752
+oid sha256:e8eb07fccd879a61b8b87e7b41c7b8bf9f75d8f93df173cf8806a29d52808dff
 size 203713238

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea9b3cb071fb5edf463f62e94083e2a383e07000b99a11f181c47793324f9ea9
+oid sha256:7f883e251c51ad7e072fb56e21402ff7ebbc845ab9d620ac95bf9a777721d3cb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.019975031210986267,
+  "epoch": 0.0299625468164794,
   "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": 6.545084971874738e-05,
       "loss": 1.0109,
       "step": 18
+    },
+    {
+      "epoch": 0.020973782771535582,
+      "grad_norm": 0.5732462406158447,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 0.9486,
+      "step": 21
+    },
+    {
+      "epoch": 0.02397003745318352,
+      "grad_norm": 0.6724739670753479,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.9357,
+      "step": 24
+    },
+    {
+      "epoch": 0.02397003745318352,
+      "eval_loss": 0.9655663371086121,
+      "eval_runtime": 49.8183,
+      "eval_samples_per_second": 8.471,
+      "eval_steps_per_second": 4.235,
+      "step": 24
+    },
+    {
+      "epoch": 0.02696629213483146,
+      "grad_norm": 0.5934033989906311,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.9882,
+      "step": 27
+    },
+    {
+      "epoch": 0.0299625468164794,
+      "grad_norm": 0.5445597171783447,
+      "learning_rate": 0.0,
+      "loss": 0.9398,
+      "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": 3292692008140800.0,
+  "total_flos": 4939038012211200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null