Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d2c928b4655e2e1269f6dffec315c020bb77c508994bc63b1bd6fafb6616b87
+oid sha256:e7a4f25ef6e12d94770ec29079f4cbc8f553e7f7787c71e03acae288618163d0
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7aaa496e5f813260ff3e3c50ad1846d6e3bd9e5c2b533e8e19f59279248f3d8b
+oid sha256:6bc7731c2cf642e9eb741fd239f25bcd267c113b1cb963dec3a48835671a8db1
 size 166439638

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd2a09b7e33a9a1891ab228fd0d720c2b11610de82bb6932c8cc60caba3eaf09
+oid sha256:bbf0f18b69bba90437d73844293d98c6cf5831f12f5480bbf0e9b6970acfad3c
 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": 0.009085746734809767,
+  "epoch": 0.013628620102214651,
   "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": 0.3898,
       "step": 18
+    },
+    {
+      "epoch": 0.009540034071550256,
+      "grad_norm": 2.2107276916503906,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.4252,
+      "step": 21
+    },
+    {
+      "epoch": 0.01090289608177172,
+      "grad_norm": 1.2082346677780151,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.3324,
+      "step": 24
+    },
+    {
+      "epoch": 0.01090289608177172,
+      "eval_loss": 0.33602961897850037,
+      "eval_runtime": 35.692,
+      "eval_samples_per_second": 25.972,
+      "eval_steps_per_second": 13.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.012265758091993186,
+      "grad_norm": 1.107161283493042,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.325,
+      "step": 27
+    },
+    {
+      "epoch": 0.013628620102214651,
+      "grad_norm": 0.9933003783226013,
+      "learning_rate": 0.0,
+      "loss": 0.2946,
+      "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": 2010596581048320.0,
+  "total_flos": 3015894871572480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null