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:ca1375f8458e9e373c2256977695e9e7f015b50b4a2fde024062621674de454f
+oid sha256:bb112ac8cc94492bb1e98fb3d48ec799222720e576f81e94accdd03c8c188e45
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a19f32aadc7811fbcf92b6627797f6a461f55b6323f5032098169db5fb1f1963
+oid sha256:faa400c07149d31e66aa2e4f7e98ebb1837c7c5681cccc2024893ca4f8cb03e6
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93308e217a5f9d0ee72ce9f8325b523438e98fcaa74f92d8cc4641b4eee325a7
+oid sha256:7f3e0d009e0ec3fd5ee7f335d17337d83548753eb73ecf4cd0160baac45f5971
 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": 0.0063257775434897206,
+  "epoch": 0.012651555086979441,
   "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": 7.121,
       "eval_steps_per_second": 0.891,
       "step": 9
+    },
+    {
+      "epoch": 0.008434370057986295,
+      "grad_norm": 0.5994438529014587,
+      "learning_rate": 4.993910125649561e-05,
+      "loss": 1.0264,
+      "step": 12
+    },
+    {
+      "epoch": 0.010542962572482868,
+      "grad_norm": 0.25993818044662476,
+      "learning_rate": 4.962019382530521e-05,
+      "loss": 0.8913,
+      "step": 15
+    },
+    {
+      "epoch": 0.012651555086979441,
+      "grad_norm": 0.2148323357105255,
+      "learning_rate": 4.9031542398457974e-05,
+      "loss": 0.9068,
+      "step": 18
+    },
+    {
+      "epoch": 0.012651555086979441,
+      "eval_loss": 0.8854690194129944,
+      "eval_runtime": 336.5338,
+      "eval_samples_per_second": 7.123,
+      "eval_steps_per_second": 0.891,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.379938820784128e+16,
+  "total_flos": 4.759877641568256e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null