Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e56e1ce8b0033e9bc72e3cd37278cfd17c4724b14e008174c65c1401d6b11a4
+oid sha256:7ceeba5083fdf9c857707701d2450f99cfe28e13c96d3d5cc6df07e9a50d80f6
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f56a239371d1d3856d89231073ad8c4042aab0304b048b20f5298b06c0a824a
+oid sha256:de56b3356df15d33263663b97fba62a83c359d4a541ff99e89a4db63a62c86b1
 size 320082106

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e24d535c5c1523f0486038b5930228f33566ca520ba04d10e88741a42965211
+oid sha256:a098dffa38fa9c01aae74eebd50d55d442f41711e114eb99ba341d13be3779bf
 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": 0.00142602495543672,
+  "epoch": 0.0021390374331550803,
   "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": 3.29,
       "step": 18
+    },
+    {
+      "epoch": 0.001497326203208556,
+      "grad_norm": 4.456937313079834,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 2.9882,
+      "step": 21
+    },
+    {
+      "epoch": 0.001711229946524064,
+      "grad_norm": 2.675823211669922,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 3.06,
+      "step": 24
+    },
+    {
+      "epoch": 0.001711229946524064,
+      "eval_loss": 3.014272689819336,
+      "eval_runtime": 321.7999,
+      "eval_samples_per_second": 18.353,
+      "eval_steps_per_second": 9.177,
+      "step": 24
+    },
+    {
+      "epoch": 0.0019251336898395723,
+      "grad_norm": 2.242222547531128,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 3.0894,
+      "step": 27
+    },
+    {
+      "epoch": 0.0021390374331550803,
+      "grad_norm": 2.5812113285064697,
+      "learning_rate": 0.0,
+      "loss": 3.036,
+      "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": 6534582019031040.0,
+  "total_flos": 9801873028546560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null