Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03070b525a254ba9d8d848bb2fa3ec3497b48d666b5267b6736e9ada158a2753
+oid sha256:9c6037baea718201fd094a6f521efde389df35c243677557f6e36a3f7d17cb95
 size 25192592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abc4f9ac653138edab9687b9ae9f54721d9c890e93c0fe5bca5131da11e6558f
+oid sha256:e0d206cf9640d40cfd5e0845262f7ab4c939fc78dd9b2c76d315c263a8ea9303
 size 50493050

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73aa535a34327d8ff7e12fc9f716f24d876cbdb9f9fc9bc13d972c1b7c68dd32
+oid sha256:200897803867d9476163ce84baa477ea4bfc2d20fbca1d606afa2d969206fa8c
 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": 0.00909194226616661,
+  "epoch": 0.013637913399249914,
   "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": 6.378,
       "step": 18
+    },
+    {
+      "epoch": 0.00954653937947494,
+      "grad_norm": 77.85978698730469,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 5.2652,
+      "step": 21
+    },
+    {
+      "epoch": 0.010910330719399931,
+      "grad_norm": 79.27323150634766,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 5.2201,
+      "step": 24
+    },
+    {
+      "epoch": 0.010910330719399931,
+      "eval_loss": 1.182474136352539,
+      "eval_runtime": 12.7175,
+      "eval_samples_per_second": 72.891,
+      "eval_steps_per_second": 36.485,
+      "step": 24
+    },
+    {
+      "epoch": 0.012274122059324924,
+      "grad_norm": 94.6389389038086,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 4.6894,
+      "step": 27
+    },
+    {
+      "epoch": 0.013637913399249914,
+      "grad_norm": 58.191741943359375,
+      "learning_rate": 0.0,
+      "loss": 4.983,
+      "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": 354006639575040.0,
+  "total_flos": 531009959362560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null