Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60650739a65a81ce6f77eefbf0a51414477d7793dd24fdf5f202f9e88b691531
+oid sha256:81bde0aae8837ed19571f0f8c5dc71f3c6989da9bec55ad16bb9dec1e3643c97
 size 180385008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe51c10ae8b51806e9a4d4e0f69e4e762671d3d8616b9991e263f46dc2c79738
+oid sha256:41f5be0378705aada461003107f16b5c332b7ef8b7e5239415d5a1de983b751c
 size 91850362

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c67e3f354d332558d71a6e74fff042f2e6dc9a3fd62453938cf2b8dac23d58a6
+oid sha256:0dbe0665e344abacc9ba1e04db32045ed0d8c84a58a5f55b900778977fb22211
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92b4cf85d7ba7a497f88ff799bf4dec5af7dd95be6e00f78bf46ba5deb56bbf8
+oid sha256:1eca0ddb3ec890c90e8e6e7325bec40cdb8b59e4bebf5c0da8473b02809de875
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5106382978723404,
+  "epoch": 0.7659574468085106,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -45,6 +45,21 @@
       "eval_samples_per_second": 48.473,
       "eval_steps_per_second": 7.271,
       "step": 6
+    },
+    {
+      "epoch": 0.7659574468085106,
+      "grad_norm": 3.4452314376831055,
+      "learning_rate": 9e-05,
+      "loss": 3.432,
+      "step": 9
+    },
+    {
+      "epoch": 0.7659574468085106,
+      "eval_loss": 3.062047243118286,
+      "eval_runtime": 0.416,
+      "eval_samples_per_second": 48.077,
+      "eval_steps_per_second": 7.211,
+      "step": 9
     }
   ],
   "logging_steps": 3,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1201158739722240.0,
+  "total_flos": 1801738109583360.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null