Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d63daef62dc77f1ba6f764f83f7b02999fff144c3b161ea32cef10d37c7ed4a
+oid sha256:2c0461a9617d9f9dd277ef637f7fb067a4e4ab45293d071942bcd84da9c1c0e6
 size 228140600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a75c69a5c2f8f95f9a8dd4e08c386857b1b16ba220d6c66832a60471fd5234df
+oid sha256:bc2ecdc163215d8d22ff0d3dfa949bc3648659239933c57e85f69e44d114a943
 size 116472340

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:744a5a6bba1f0aff99d5e21c41ab079ee18b65574a5f3f9abbf77c2cfb749393
+oid sha256:03ad0c4652463f1096182a18d963eb133233e4b3378834bfb14790c18a607c56
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92b4cf85d7ba7a497f88ff799bf4dec5af7dd95be6e00f78bf46ba5deb56bbf8
+oid sha256:1eca0ddb3ec890c90e8e6e7325bec40cdb8b59e4bebf5c0da8473b02809de875
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.026023312550826783,
+  "epoch": 0.03903496882624018,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 4.745,
       "eval_steps_per_second": 2.378,
       "step": 6
+    },
+    {
+      "epoch": 0.030360531309297913,
+      "grad_norm": 146.9974365234375,
+      "learning_rate": 7e-05,
+      "loss": 94.7878,
+      "step": 7
+    },
+    {
+      "epoch": 0.03469775006776904,
+      "grad_norm": 144.07135009765625,
+      "learning_rate": 8e-05,
+      "loss": 81.1473,
+      "step": 8
+    },
+    {
+      "epoch": 0.03903496882624018,
+      "grad_norm": 177.5219268798828,
+      "learning_rate": 9e-05,
+      "loss": 70.3032,
+      "step": 9
+    },
+    {
+      "epoch": 0.03903496882624018,
+      "eval_loss": NaN,
+      "eval_runtime": 82.0919,
+      "eval_samples_per_second": 4.739,
+      "eval_steps_per_second": 2.375,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.489473131380736e+16,
+  "total_flos": 8.234209697071104e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null