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:ceccfeaef2f603dd826b62bbd17d0a16138b62c172cbb19761a03ff9e63118e9
+oid sha256:be60dc0fdd3b7d4769eabc848a3e2be3b7f92e989eecfbfd5f547f4e606379af
 size 119597408

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:643ad014d564d43fba118bb47e2349fec5d1bd980a4dd3ca2110f90241e83ca0
+oid sha256:ed9905e3fa9cb8d2884d0e47c48438bfa64b718fde2b74a755705ba1093fec7e
 size 61226900

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f41b3739ec867670425c2ee79777d8a4b6394928778c4946abbbcffa2d3b6275
+oid sha256:8a64eb481f5f641f99d01d21113d1d464f1dd44b92498ba3deb6f433c0c84bf9
 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": 0.10526315789473684,
+  "epoch": 0.21052631578947367,
   "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": 10.414,
       "eval_steps_per_second": 1.302,
       "step": 9
+    },
+    {
+      "epoch": 0.14035087719298245,
+      "grad_norm": 0.5038430094718933,
+      "learning_rate": 9.987820251299122e-05,
+      "loss": 5.6881,
+      "step": 12
+    },
+    {
+      "epoch": 0.17543859649122806,
+      "grad_norm": 0.6504800319671631,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 5.8583,
+      "step": 15
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 0.47255322337150574,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 5.4709,
+      "step": 18
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "eval_loss": 1.407480001449585,
+      "eval_runtime": 13.8137,
+      "eval_samples_per_second": 10.424,
+      "eval_steps_per_second": 1.303,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.327975769309184e+16,
+  "total_flos": 2.655951538618368e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null