Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fdc12111ad3d7618d3e81c756565e6f38c02dc3127382405ac051b71f190a9f
+oid sha256:eddf933738373c83e94bbb76cd09b08e9d34b3e3289253695074f88f4f61085e
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88507e3a53490111544515490437226df14a3413cccc0f1816896e77eaeea383
+oid sha256:6fb0673f5d388bdd4b785df200f0fdeacabf5f3288378c7a5d1c0c1b70383371
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41810fe096e6b4d052f8f28df59f954f31c494aaf06ad1a1e4ef360b424e255b
+oid sha256:58c2ed27daacb297ae7b25c41878ce9000cae4eb9a5dfa070adaf49263e60f46
 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": 0.008204193254329991,
+  "epoch": 0.016408386508659983,
   "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": 4.523,
       "eval_steps_per_second": 0.565,
       "step": 9
+    },
+    {
+      "epoch": 0.010938924339106655,
+      "grad_norm": 4.259462833404541,
+      "learning_rate": 9.987820251299122e-05,
+      "loss": 9.506,
+      "step": 12
+    },
+    {
+      "epoch": 0.013673655423883319,
+      "grad_norm": 4.685791492462158,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 9.2787,
+      "step": 15
+    },
+    {
+      "epoch": 0.016408386508659983,
+      "grad_norm": 6.113475799560547,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 8.9251,
+      "step": 18
+    },
+    {
+      "epoch": 0.016408386508659983,
+      "eval_loss": 2.118788003921509,
+      "eval_runtime": 408.4849,
+      "eval_samples_per_second": 4.524,
+      "eval_steps_per_second": 0.566,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.250014395780301e+16,
+  "total_flos": 4.605498216362803e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null