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:f3db0cb965e3fad9d367f2619e94ec965bf91c29c1ea0185848651c02e1fc989
+oid sha256:2cce13259cb9f117f0607c9537572faad075a2911fc400d686c763554175fb7e
 size 119801528

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18a6b09ca23ed234554b6c6b78c6e7a40f1dddb06e33c6dffe3726b754185bdf
+oid sha256:939f6e697d3c0fea3fc36d93e85af0979e9f3876a3a36be5abd4fff025223906
 size 239892858

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:923203be89e132e3df1bfaa7749849ed90014352ffc9d75b3ff857e307988c31
+oid sha256:d9bf0a4c2ac57eb9d673f0725b2641f8149027d9359537d425c2b02bc78b22c9
 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": 0.0032512395350727465,
+  "epoch": 0.00487685930260912,
   "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": 2.2517,
       "step": 18
+    },
+    {
+      "epoch": 0.003413801511826384,
+      "grad_norm": 0.7542737126350403,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 2.0641,
+      "step": 21
+    },
+    {
+      "epoch": 0.003901487442087296,
+      "grad_norm": 0.7304168343544006,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 2.1134,
+      "step": 24
+    },
+    {
+      "epoch": 0.003901487442087296,
+      "eval_loss": 2.143785238265991,
+      "eval_runtime": 123.9677,
+      "eval_samples_per_second": 20.901,
+      "eval_steps_per_second": 10.454,
+      "step": 24
+    },
+    {
+      "epoch": 0.0043891733723482075,
+      "grad_norm": 0.6808849573135376,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 2.0507,
+      "step": 27
+    },
+    {
+      "epoch": 0.00487685930260912,
+      "grad_norm": 0.8048596978187561,
+      "learning_rate": 0.0,
+      "loss": 1.9766,
+      "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": 3618745582878720.0,
+  "total_flos": 5583207470727168.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null