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:bed32d06a8f2870dbb56d58c06e0381fbbfbb109f771686afb4a1807a4ee1b09
+oid sha256:7ba20da035b1270eb67739c24babe540d441fc2e4984058f1b42898a2b203028
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76326c51bfecd4aa28e4e844ebb47fddb9a03fe93e0baff4eeec796167ca5357
+oid sha256:bbc9082c87d2fd4bb0ba42ada39e023c3f90444bb05eeaa6f261fc1f9646f040
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:332759cf7b5cf921f7c9ebfe29466512b01ff3dba8f0377398688b0a48981a95
+oid sha256:6cf30c4e1dfd3b199f004d48c615f0058d9d8168fc7715316fa0d2b53a3286f2
 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": 0.23684210526315788,
+  "epoch": 0.47368421052631576,
   "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": 14.31,
       "eval_steps_per_second": 1.789,
       "step": 9
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 11.844976425170898,
+      "learning_rate": 9.987820251299122e-05,
+      "loss": 4.0152,
+      "step": 12
+    },
+    {
+      "epoch": 0.39473684210526316,
+      "grad_norm": 10.39311695098877,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 3.859,
+      "step": 15
+    },
+    {
+      "epoch": 0.47368421052631576,
+      "grad_norm": 9.025694847106934,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 3.9375,
+      "step": 18
+    },
+    {
+      "epoch": 0.47368421052631576,
+      "eval_loss": 0.8340747356414795,
+      "eval_runtime": 4.4933,
+      "eval_samples_per_second": 14.244,
+      "eval_steps_per_second": 1.78,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2656345471778816e+16,
+  "total_flos": 2.531269094355763e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null