Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcd3e954f97471903e6f7ad3e7cbecac8fb1160eca81eb1cf516ac2fba81ace2
+oid sha256:a3e1aa679d40a9a1acf08562cce1e33e7082f0e4b554075e2b8723645bfb490a
 size 338298

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fddecd30b14f1cbc86fcd4a0b66f76ebc53c145b2e1e61d7ae9d991373f53968
+oid sha256:8c045843135f55f6513beba9ce9b82f04db6e29af8edf75c7731a40f4020ee74
 size 418030

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c1a78e8cc4706bded81d43c19ec252b7fe917b88d916087e57308bdf7089fa5
+oid sha256:4bf4a70b2f1e0083900a8a144d37753c55636b180594109e7e6c3f925b4e7d11
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eca0ddb3ec890c90e8e6e7325bec40cdb8b59e4bebf5c0da8473b02809de875
+oid sha256:5ed723721bc2dad2381ab5522e40123ba4aa738fa3e449c48809fa9c2697eb95
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04591836734693878,
+  "epoch": 0.09183673469387756,
   "eval_steps": 9,
-  "global_step": 9,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 612.282,
       "eval_steps_per_second": 155.854,
       "step": 9
+    },
+    {
+      "epoch": 0.061224489795918366,
+      "grad_norm": 0.4804115891456604,
+      "learning_rate": 9.987820251299122e-05,
+      "loss": 6.9266,
+      "step": 12
+    },
+    {
+      "epoch": 0.07653061224489796,
+      "grad_norm": 0.5177415013313293,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 6.9163,
+      "step": 15
+    },
+    {
+      "epoch": 0.09183673469387756,
+      "grad_norm": 0.5697883367538452,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 6.9044,
+      "step": 18
+    },
+    {
+      "epoch": 0.09183673469387756,
+      "eval_loss": 6.897478103637695,
+      "eval_runtime": 0.271,
+      "eval_samples_per_second": 608.897,
+      "eval_steps_per_second": 154.992,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 86501523456.0,
+  "total_flos": 173003046912.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null