Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74c9c94f69f0d717d4b4525f90330b6e64508947c1fbce8cfc368bb8b81b438e
+oid sha256:03ed603f515c8ef4d2567adcc19e2d435a2f16ebc41244d3f6d950fc09068754
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e193b1c0e45eabdbb61e05c75aab86d7c3bb304827ab816b8fe2accf68ed2474
+oid sha256:fe16370c50388bab3b65a69f4d7ac4f68e11f0fa891ccecefd8bbc15072b9c75
 size 203713238

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0f6aab0ede0461cd9d0c82c37b11b02e4e50ddf39f260cc74be0fadde97ea0e
+oid sha256:aa1f740d5cc072019923fceab4e287e97deaacb74bad1353719ac7cae63df407
 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": 0.0350109409190372,
+  "epoch": 0.0525164113785558,
   "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": 0.7796,
       "step": 18
+    },
+    {
+      "epoch": 0.036761487964989056,
+      "grad_norm": 1.1303590536117554,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 0.5243,
+      "step": 21
+    },
+    {
+      "epoch": 0.04201312910284464,
+      "grad_norm": 0.8288921117782593,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.4169,
+      "step": 24
+    },
+    {
+      "epoch": 0.04201312910284464,
+      "eval_loss": 0.37522444128990173,
+      "eval_runtime": 14.2321,
+      "eval_samples_per_second": 16.934,
+      "eval_steps_per_second": 8.502,
+      "step": 24
+    },
+    {
+      "epoch": 0.04726477024070022,
+      "grad_norm": 0.8327887654304504,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.3294,
+      "step": 27
+    },
+    {
+      "epoch": 0.0525164113785558,
+      "grad_norm": 0.7396832704544067,
+      "learning_rate": 0.0,
+      "loss": 0.349,
+      "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