Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79f258110f82c8ed766d8d9539b16e06ffd92a7e591532d1bd2f07de20a71983
+oid sha256:b7d4d4018ff2acd63236135100b3cee3fbea09d6b6a5aad1f5cd50d88571df5b
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34356725ab8921ddbea9b324f00719c80c18ab25a158397fb63b3dd9acd5bbf1
+oid sha256:f06fefb228c7af86c90c70c559eb365ce8d42185b182c5ca4ebdd0c11b154fd3
 size 166439638

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db3de231cf2243134236eaf3ba947d1c449ce8a4b65b992400f5f9b2af278c5a
+oid sha256:e00a385c6a4231f4efe44b1f8946161a187c9748730e431ce536485fbb3ac425
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04338394793926247,
+  "epoch": 0.08676789587852494,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 8.671,
       "eval_steps_per_second": 4.335,
       "step": 10
+    },
+    {
+      "epoch": 0.052060737527114966,
+      "grad_norm": 2.3901684284210205,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 2.6058,
+      "step": 12
+    },
+    {
+      "epoch": 0.0650759219088937,
+      "grad_norm": 2.0866892337799072,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 2.1733,
+      "step": 15
+    },
+    {
+      "epoch": 0.0650759219088937,
+      "eval_loss": 2.4747469425201416,
+      "eval_runtime": 11.2685,
+      "eval_samples_per_second": 8.697,
+      "eval_steps_per_second": 4.348,
+      "step": 15
+    },
+    {
+      "epoch": 0.07809110629067245,
+      "grad_norm": 1.4665969610214233,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.1652,
+      "step": 18
+    },
+    {
+      "epoch": 0.08676789587852494,
+      "eval_loss": 2.3516483306884766,
+      "eval_runtime": 11.2826,
+      "eval_samples_per_second": 8.686,
+      "eval_steps_per_second": 4.343,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -71,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1005298290524160.0,
+  "total_flos": 2010596581048320.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null