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:b8638d1aec6d299346d3fe8f50131faa2c3b73c466c70d4c201430888555fd2d
+oid sha256:84d8ed9060677932e30e5eec5262149c6e57d8bb3019137addfd3bee204633ae
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d1312735cc4d334a7dc28e951ba446062df4d66b9c42d8854f2123a3e2d3b31
+oid sha256:59d89dab04e435ae615bf053b6a9111ee79774d94fdd36893b0bfe0699b1fc33
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6898f7cfc8c513f569f819ae2f0d2d8879521f0304cfc0f28a4a019543aabbec
+oid sha256:8e699daa34b94905d677ee7d2001f460693531758e3745e205c3ed4e29615cc1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ed723721bc2dad2381ab5522e40123ba4aa738fa3e449c48809fa9c2697eb95
+oid sha256:bd4a07944f7914b974e23583756a2e0907223f4627a9b1ba247bd8f732140689
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0675422138836773,
+  "epoch": 0.10131332082551595,
   "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": 13.719,
       "eval_steps_per_second": 3.475,
       "step": 18
+    },
+    {
+      "epoch": 0.07879924953095685,
+      "grad_norm": 7.399054050445557,
+      "learning_rate": 9.635919272833938e-05,
+      "loss": 0.2436,
+      "step": 21
+    },
+    {
+      "epoch": 0.0900562851782364,
+      "grad_norm": 3.5452539920806885,
+      "learning_rate": 9.414737964294636e-05,
+      "loss": 0.246,
+      "step": 24
+    },
+    {
+      "epoch": 0.10131332082551595,
+      "grad_norm": 3.253471851348877,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 0.1533,
+      "step": 27
+    },
+    {
+      "epoch": 0.10131332082551595,
+      "eval_loss": 0.11802710592746735,
+      "eval_runtime": 16.4414,
+      "eval_samples_per_second": 13.685,
+      "eval_steps_per_second": 3.467,
+      "step": 27
     }
   ],
   "logging_steps": 3,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.279699816808448e+16,
+  "total_flos": 1.919549725212672e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null