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:a72f1267dde76b3d47c73be5d906281ce194e5b78cdd50d1770d32ced9c4ea05
+oid sha256:787049ebf6b4d61eba0f43e7f286d54fbdb497e76d7d355df938821fd52fff56
 size 25192688

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfa77a285190a8ec469260b536369189b3bf8f2e651cc6f133e3f2c82adfe1ef
+oid sha256:b9fe16cbea6e9b0d3f949482af39db2c87fe95edb906870d9ddc25bc2f096c23
 size 13005178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:833d120c280ff24b97b71744ae5a3efdbac986fe33d325e68c54ac2c30c576ba
+oid sha256:f592bf86b4fd2e71efe8302e785834bcc22f802bc4e707ef42478cdb4e0a73fb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4d20cdfdd80bd4f7336e0d1d85ea3a727e6acd58210dc60f9f2cd451325f653
+oid sha256:e7f75dad5b4fa698adb63b89c53682112a536ec6b4f570bd7793123dfd2a0133
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00299028158484924,
+  "epoch": 0.00598056316969848,
   "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": 22.905,
       "eval_steps_per_second": 2.865,
       "step": 9
+    },
+    {
+      "epoch": 0.00398704211313232,
+      "grad_norm": 7.021877765655518,
+      "learning_rate": 4.993910125649561e-05,
+      "loss": 9.0723,
+      "step": 12
+    },
+    {
+      "epoch": 0.0049838026414154,
+      "grad_norm": 10.367716789245605,
+      "learning_rate": 4.962019382530521e-05,
+      "loss": 8.6656,
+      "step": 15
+    },
+    {
+      "epoch": 0.00598056316969848,
+      "grad_norm": 3.396527051925659,
+      "learning_rate": 4.9031542398457974e-05,
+      "loss": 6.5636,
+      "step": 18
+    },
+    {
+      "epoch": 0.00598056316969848,
+      "eval_loss": 1.8593316078186035,
+      "eval_runtime": 221.3173,
+      "eval_samples_per_second": 22.904,
+      "eval_steps_per_second": 2.865,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 803933119315968.0,
+  "total_flos": 1532023491526656.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null