Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c08b7b9367ee779b0737912d977fdf211cc52842a5f2336df6742dbe319d618
+oid sha256:aa09edb74323dfa541dd19f269b284743abc03b1a04ae96fefe7b8d77ed31840
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfe03babf2b2a2f413f669ab29c7dda992e8384bc0cd85ab3871952fe02c2f52
+oid sha256:d2bddd484b98f4dc3fbbd98462e930f2a37c6e1d5556ebc362fcd5b6c935bd76
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e27f5e2500362b73e47f5681fd7a7663702665386d5af57fd9a924c1cc3fc44b
+oid sha256:27c798405ea53bdde5a57e4140c86669e859c2276c92a1b14a686d703b68d844
 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": 0.0010837824005780173,
+  "epoch": 0.0021675648011560346,
   "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": 7.05,
       "eval_steps_per_second": 0.882,
       "step": 9
+    },
+    {
+      "epoch": 0.0014450432007706898,
+      "grad_norm": 25.98846435546875,
+      "learning_rate": 9.987820251299122e-05,
+      "loss": 7.6576,
+      "step": 12
+    },
+    {
+      "epoch": 0.001806304000963362,
+      "grad_norm": 32.36982727050781,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 7.2228,
+      "step": 15
+    },
+    {
+      "epoch": 0.0021675648011560346,
+      "grad_norm": 16.200027465820312,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 6.5358,
+      "step": 18
+    },
+    {
+      "epoch": 0.0021675648011560346,
+      "eval_loss": 1.6316649913787842,
+      "eval_runtime": 1985.2556,
+      "eval_samples_per_second": 7.045,
+      "eval_steps_per_second": 0.881,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.531269094355763e+16,
+  "total_flos": 5.062538188711526e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null