Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:addb0c1b7a800e63794e93854322c9bf523594ff24779c2f2aa6618a16d40309
+oid sha256:99d0c9bd199202667ea6ddbff77fe3ae44382dbee87987c33da7a5166a176c83
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e46ec7da17f5ce24c7f97b1ef89920acea78c3f36706608629ded472832f4667
+oid sha256:b1e71b573c3bf82448bdee7bdd69394a5e893e8bf4a6afc29744347d8da35762
 size 37965300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81eef1339e8f499efe37cf6787a5508274bd53f0e74fe093964cfc634b1c8e4b
+oid sha256:ba011c9e555bcbe3ac2f8124b37661b41ac93648fa02f025e3ad48558449cb1d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:922634a168fad3088c2a461ec82359f2941891b1472f492b835996e27c3cba9d
+oid sha256:d899e046e5eb8fee9b81979db8db7b88d6dc92f30a13d049b906f3a3be1dfc0f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.002124950459984316,
+  "epoch": 0.0024285148114106467,
   "eval_steps": 9,
-  "global_step": 63,
+  "global_step": 72,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -218,6 +218,35 @@
       "eval_samples_per_second": 30.134,
       "eval_steps_per_second": 3.767,
       "step": 63
+    },
+    {
+      "epoch": 0.002226138577126426,
+      "grad_norm": 0.28922489285469055,
+      "learning_rate": 1.56348351646022e-05,
+      "loss": 0.7805,
+      "step": 66
+    },
+    {
+      "epoch": 0.0023273266942685365,
+      "grad_norm": 0.30259978771209717,
+      "learning_rate": 1.3263210930352737e-05,
+      "loss": 0.8183,
+      "step": 69
+    },
+    {
+      "epoch": 0.0024285148114106467,
+      "grad_norm": 0.2592143714427948,
+      "learning_rate": 1.1020177413231334e-05,
+      "loss": 0.8365,
+      "step": 72
+    },
+    {
+      "epoch": 0.0024285148114106467,
+      "eval_loss": 0.8151922225952148,
+      "eval_runtime": 1656.7975,
+      "eval_samples_per_second": 30.138,
+      "eval_steps_per_second": 3.768,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.9724659436027904e+16,
+  "total_flos": 2.2337197109673984e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null