Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:480dfa2ce2b46a00ccaf22e0f71836a8ff77c4d8c252bef4faed6744196eb0a7
+oid sha256:b946c35868cd1105114451afc896f9b302b6afc8c85ca5052856d7d6301b0d17
 size 9864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84aa3ae1e05edb1bc41cad6f33f003a4a7e5f238499b30f1fe0e36aa9f20c381
+oid sha256:6c4f3b43ae712f9dcc08dd07447cdf4870987c4b9613ec0489b7db124345bcfd
 size 27002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cbc589a06e2970f3d1e1f484146819e64848b461fbefd953e917f429a552096
+oid sha256:eed7443db706351be6dd27431c0a74aab9cc8fb80aac1c56005e8e16b28688cb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef527702b4e2147a500c0b29beb26751d245ebb60338b3910b449b6549ac4d59
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.003902439024390244,
+  "epoch": 0.007804878048780488,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,65 @@
       "eval_samples_per_second": 46.348,
       "eval_steps_per_second": 23.188,
       "step": 15
+    },
+    {
+      "epoch": 0.0046829268292682925,
+      "grad_norm": 2.7791644242824987e-05,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 46.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.005203252032520325,
+      "eval_loss": 11.5,
+      "eval_runtime": 34.4205,
+      "eval_samples_per_second": 47.036,
+      "eval_steps_per_second": 23.532,
+      "step": 20
+    },
+    {
+      "epoch": 0.005463414634146341,
+      "grad_norm": 2.0877587303402834e-05,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 46.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.006243902439024391,
+      "grad_norm": 3.659590583993122e-05,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 46.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.0065040650406504065,
+      "eval_loss": 11.5,
+      "eval_runtime": 35.6036,
+      "eval_samples_per_second": 45.473,
+      "eval_steps_per_second": 22.751,
+      "step": 25
+    },
+    {
+      "epoch": 0.007024390243902439,
+      "grad_norm": 2.650631358847022e-05,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 46.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.007804878048780488,
+      "grad_norm": 2.5651992473285645e-05,
+      "learning_rate": 0.0,
+      "loss": 46.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.007804878048780488,
+      "eval_loss": 11.5,
+      "eval_runtime": 34.7093,
+      "eval_samples_per_second": 46.645,
+      "eval_steps_per_second": 23.337,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -88,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 608415350784.0,
+  "total_flos": 1206856679424.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null