Training in progress, step 27, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21f512f9ad2a9aac7d0e1e510bb137e2ebb0fcf36ee0511b6f9da9d4752d8ded
+oid sha256:fab77eb416bace56c13beb3a8a21df1739be662a3102d27ce20434f9345664f5
 size 17425352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d05c9a3bb2429322dfe7ee59f64dbd4ef0a8649d8490e98dc6deb655cf9d8175
+oid sha256:7c716351e5a57659df6560287d8cbddb07137316c8ac19a38eadfd87d82392f7
 size 10251668

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72e3379b97382001bdd566ec44641d53d705aadf1c63d214e37febd171c0679c
+oid sha256:ac6758c94dff08e90104766708e33ff8cbf1018bfc9134136ef3e1f7d88a92f7
 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": 0.04186046511627907,
+  "epoch": 0.06279069767441861,
   "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": 69.427,
       "eval_steps_per_second": 8.726,
       "step": 18
+    },
+    {
+      "epoch": 0.04883720930232558,
+      "grad_norm": 1.3651623725891113,
+      "learning_rate": 9.635919272833938e-05,
+      "loss": 5.5186,
+      "step": 21
+    },
+    {
+      "epoch": 0.05581395348837209,
+      "grad_norm": 1.554046630859375,
+      "learning_rate": 9.414737964294636e-05,
+      "loss": 5.3002,
+      "step": 24
+    },
+    {
+      "epoch": 0.06279069767441861,
+      "grad_norm": 1.4339934587478638,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 5.1694,
+      "step": 27
+    },
+    {
+      "epoch": 0.06279069767441861,
+      "eval_loss": 5.061354637145996,
+      "eval_runtime": 10.4152,
+      "eval_samples_per_second": 69.514,
+      "eval_steps_per_second": 8.737,
+      "step": 27
     }
   ],
   "logging_steps": 3,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1128841598730240.0,
+  "total_flos": 1693262398095360.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null