Training in progress, step 27, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:495ee1ed71e7349cdbfeb34358d8c4765d6e8a4d29744d7baa56f5c626a1fce6
+oid sha256:f090a967c768682a5c33da5adf53c647384951be19662b908338cdb28a9d17ca
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0470e2308f8321fc41c5df5aede03ac6f5c7087adf88392b8b1c0fed044208c
+oid sha256:9345b9d1e697822621ea85e4941ac524a4dff70444e09d39085bce12b1ba34e8
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e8641384676c0c3ca843dcc47e3f6d9bd5a859182c78c26888d7b28bf27a1bf
+oid sha256:926c539986362599115d4154ffc69906160c0ab960c9d9ae1b2884107080e0e2
 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": 0.00984009840098401,
+  "epoch": 0.014760147601476014,
   "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": 7.285,
       "eval_steps_per_second": 0.913,
       "step": 18
+    },
+    {
+      "epoch": 0.011480114801148012,
+      "grad_norm": 0.23741497099399567,
+      "learning_rate": 9.635919272833938e-05,
+      "loss": 0.6668,
+      "step": 21
+    },
+    {
+      "epoch": 0.013120131201312012,
+      "grad_norm": 0.3272160291671753,
+      "learning_rate": 9.414737964294636e-05,
+      "loss": 0.6661,
+      "step": 24
+    },
+    {
+      "epoch": 0.014760147601476014,
+      "grad_norm": 0.21630150079727173,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 0.5646,
+      "step": 27
+    },
+    {
+      "epoch": 0.014760147601476014,
+      "eval_loss": 0.6439428329467773,
+      "eval_runtime": 422.9121,
+      "eval_samples_per_second": 7.285,
+      "eval_steps_per_second": 0.913,
+      "step": 27
     }
   ],
   "logging_steps": 3,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.693768229879808e+16,
+  "total_flos": 7.073707050663936e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null