Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b7d0f13e0021485c1c53fe9435839bcf5d790e372aba691c4fcf17a52f5dc33
+oid sha256:21bb5787ad12db0ae79cd5dda71719177f2d5b43a98d5d6de1efaa680c2747f9
 size 65309632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af01e9aa31d51aacc71b5bfa7ab524c90cd1786637049d945bfbc605d358472e
+oid sha256:95af512bdd81b6ef46441e0fa0b4e9a12072266814772e12cdd9f061e9284d34
 size 33424212

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dfe2677b95211609ab51117e6f4e73f3db090d1aa3ea445c10538d9269d95d1
+oid sha256:148f1afbe85e53f6df3756a21f8a0ab665094392e08503828b5e3a1004bdf711
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fec74e92563bbe4b510ec939dc1c78d591826119d26043cc49e0a868b67121a2
+oid sha256:59af5f5d66ecb18e9abb84f5d5074a625502d490e59b29de1e9974286a967cbf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.015028901734104046,
+  "epoch": 0.03005780346820809,
   "eval_steps": 13,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,21 @@
       "eval_samples_per_second": 36.353,
       "eval_steps_per_second": 18.226,
       "step": 13
+    },
+    {
+      "epoch": 0.023121387283236993,
+      "grad_norm": 25.738534927368164,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 10.5807,
+      "step": 20
+    },
+    {
+      "epoch": 0.03005780346820809,
+      "eval_loss": 2.4230074882507324,
+      "eval_runtime": 10.084,
+      "eval_samples_per_second": 36.196,
+      "eval_steps_per_second": 18.148,
+      "step": 26
     }
   ],
   "logging_steps": 10,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2163033390710784.0,
+  "total_flos": 4366878732189696.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null