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:c02ed020c7a50e75daacd1c65a72ab45d19047c9d342ef9d52152b11f52657c3
+oid sha256:57e320f95ec8f4799f4ca901fb495a89cb9b8238fa4b86b93be75dd2f828667f
 size 191968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c70bcefd891e95eaf8c4cb788928a949ac74ec87240c65f95ee2cacee2f313a
+oid sha256:76bdf8b95f1b89fbb558a5af8e14dbb0933594c0967ca0491fb673774661e1b9
 size 253144

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4020f3371cdababf78acf9c4e3422cf8a546d17a47b69e1ae00cbdc56bce942
+oid sha256:27329c1216f1c5f7cda2e86a6aeb0a3c23a20e2dccc0a105de491cbe776a9f86
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57e4906645ddc5e515c78c1628a7b7644a50c7260087a5e686773f47f350a1b4
+oid sha256:77527b22d28a8d828e7d18176e2a2c97a292ee736506db5e587ed8702bd1d1a3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:898e864d3067082fd9ef2d031e8dd381a4469dd45ff8a442c43bfc120c2d7d7d
+oid sha256:baa5163da2ebe59c5c9a3d88228c3600c7f17542df3fd51e38b7e6f68bd14948
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0febfedbed790b4f7eb615fd2996c3ed274fbaa103ac35587bb4a99c0145db9
+oid sha256:7be8b163fddc9655025c3da89f1d8416aa87d49006f72e224514edd0ccbe7c36
 size 15024

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": 0.0430622009569378,
+  "epoch": 0.0861244019138756,
   "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": 762.883,
       "eval_steps_per_second": 23.857,
       "step": 9
+    },
+    {
+      "epoch": 0.05741626794258373,
+      "grad_norm": 0.12390146404504776,
+      "learning_rate": 9.987820251299122e-05,
+      "loss": 10.3624,
+      "step": 12
+    },
+    {
+      "epoch": 0.07177033492822966,
+      "grad_norm": 0.14381946623325348,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 10.3584,
+      "step": 15
+    },
+    {
+      "epoch": 0.0861244019138756,
+      "grad_norm": 0.16828647255897522,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 10.3555,
+      "step": 18
+    },
+    {
+      "epoch": 0.0861244019138756,
+      "eval_loss": 10.352652549743652,
+      "eval_runtime": 1.87,
+      "eval_samples_per_second": 752.399,
+      "eval_steps_per_second": 23.529,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8031647563776.0,
+  "total_flos": 16063295127552.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null