Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cb9098e983c50bff4125913be120927f8e266079ca962f7ff35ad5ef8aa164d
+oid sha256:be573dc907b95123c9d70afc0f8b6bc346f3c10adb17257f3d9b02328142edb7
 size 9864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7414c5b60048e908794eb366aa3618aa0cb141d067c8bfe881e48fd24bdf9d34
+oid sha256:13a3cfef7925fd69aaa167f42aa36f7c3d4d32e3fbfbbe4ab3747d0867e2d777
 size 27002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9aa473efab1261a29320d6ad268e7ec159fafb824b3f53d140f1f0fb43c8c484
+oid sha256:5b1dbe479f6756df2ff500203698c9f57bca85e9e4a1cdb231db97e90dac145f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1b54721e238deb0df3f26476ead882995a6359d0720944551e4d045b099778f
+oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00952683391552874,
+  "epoch": 0.012702445220704985,
   "eval_steps": 8,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,21 @@
       "learning_rate": 0.00013090169943749476,
       "loss": 46.0,
       "step": 15
+    },
+    {
+      "epoch": 0.010161956176563989,
+      "eval_loss": 11.5,
+      "eval_runtime": 7.2877,
+      "eval_samples_per_second": 90.975,
+      "eval_steps_per_second": 45.556,
+      "step": 16
+    },
+    {
+      "epoch": 0.011432200698634487,
+      "grad_norm": 5.0297352572670206e-05,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 46.0,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -77,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 598441328640.0,
+  "total_flos": 797921771520.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null