Training in progress, step 27, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f848dad3c8dccd4344eb1f32c7525180d7f2bf72ab2e543f3698467ef0782d3
+oid sha256:a431438022701030f2d80182cf3da792b6d5fc207a91102ffad7c54b1ec8b6c3
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d58d4a43a1af627c6e2e9db47f41ff0d4f8b5e3ca18e93a37861e4b68874b3f8
+oid sha256:18fe318f6269df8a30136ea73271127c2a0c9c9edda7922061cfdb8de453f81d
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4d11953e47b9a3f639761fcfec1e07d8e68d91a69c42fe9592aa1d1f633d38f
+oid sha256:6ca1fa80e450ffe15d2ab0b37f73cac467cd5f1bacf77be68bc42d48b1fa3932
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d403ac4d7711325e0c8bec676128002b741c5058ffa34f8bfc8e7d7e4547c436
+oid sha256:014898519bf1f31fef4a7ab39caf2eaa1ff4fbc5662e969211f7676259067ad2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.008540165465705898,
+  "epoch": 0.012810248198558846,
   "eval_steps": 9,
-  "global_step": 18,
+  "global_step": 27,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 9.723,
       "eval_steps_per_second": 4.861,
       "step": 18
+    },
+    {
+      "epoch": 0.009963526376656881,
+      "grad_norm": 14.844147682189941,
+      "learning_rate": 0.0001999229036240723,
+      "loss": 23.8388,
+      "step": 21
+    },
+    {
+      "epoch": 0.011386887287607865,
+      "grad_norm": 13.040925025939941,
+      "learning_rate": 0.00019876883405951377,
+      "loss": 23.2438,
+      "step": 24
+    },
+    {
+      "epoch": 0.012810248198558846,
+      "grad_norm": 13.732440948486328,
+      "learning_rate": 0.00019624552364536473,
+      "loss": 23.504,
+      "step": 27
+    },
+    {
+      "epoch": 0.012810248198558846,
+      "eval_loss": 0.708083987236023,
+      "eval_runtime": 2490.0558,
+      "eval_samples_per_second": 2.851,
+      "eval_steps_per_second": 1.426,
+      "step": 27
     }
   ],
   "logging_steps": 3,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.49925800134574e+16,
+  "total_flos": 1.4232452299594138e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null