Training in progress, step 27, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:483003ea8c174cd65927a0957c9a19821dfcf5267d4430b0fcc402094ac15abc
+oid sha256:7eda8397ad89989c83aba37f52555ab7281baf1f64b352149c83dfc5dc7b072d
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5776f92afdcc65df6dc3704691ea5e126f2abd2c05b91058f37a9410ed5acf9
+oid sha256:4e9015c6cb3462064c51c1eefdfc9abf4bce1130827614ebde8e383d7c3d21fc
 size 51418196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be8423cc9920092dc49fdcbf5a44ed945910b1f86985bc15e34fe153a16334ac
+oid sha256:ff93520091d57f01cce58bfab74743fddd24cdfb7496c38df30e015d2dbc68bd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ed723721bc2dad2381ab5522e40123ba4aa738fa3e449c48809fa9c2697eb95
+oid sha256:bd4a07944f7914b974e23583756a2e0907223f4627a9b1ba247bd8f732140689
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0010366872084317227,
+  "epoch": 0.001555030812647584,
   "eval_steps": 9,
-  "global_step": 18,
+  "global_step": 27,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 21.87,
       "eval_steps_per_second": 2.734,
       "step": 18
+    },
+    {
+      "epoch": 0.0012094684098370098,
+      "grad_norm": 1.1920151710510254,
+      "learning_rate": 9.635919272833938e-05,
+      "loss": 10.2468,
+      "step": 21
+    },
+    {
+      "epoch": 0.001382249611242297,
+      "grad_norm": 0.8807956576347351,
+      "learning_rate": 9.414737964294636e-05,
+      "loss": 9.8125,
+      "step": 24
+    },
+    {
+      "epoch": 0.001555030812647584,
+      "grad_norm": 0.8759644627571106,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 9.77,
+      "step": 27
+    },
+    {
+      "epoch": 0.001555030812647584,
+      "eval_loss": 2.4928576946258545,
+      "eval_runtime": 1338.7702,
+      "eval_samples_per_second": 21.843,
+      "eval_steps_per_second": 2.731,
+      "step": 27
     }
   ],
   "logging_steps": 3,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3263058860244992e+16,
+  "total_flos": 1.989458829036749e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null