Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3489772ef92d34c5b2bf8f9cb3670eee09f66614c4f24c389ecff5b52364788d
+oid sha256:924927f284f209925f9dbccc6f77053d4403693b16774130947e03cb8a85d192
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd3fed0e4ceb02fc2b0c584e2f16f085b060583b166301ff6e4145e01d9b853e
+oid sha256:9b1d43b5b694f1adc323c8fd98b95a665df3cb082203896b9fd09b5f2e3e32e7
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7824cda9b09088755df9c1fad3a0258c249f3861ebeb526074259caef60b1595
+oid sha256:ffe0152387846c1162de177cdc53167a9183696b149d3eb20d4cf5fbd6b53e78
 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": 0.08847926267281106,
+  "epoch": 0.1327188940092166,
   "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": 24.855,
       "eval_steps_per_second": 12.536,
       "step": 6
+    },
+    {
+      "epoch": 0.1032258064516129,
+      "grad_norm": 2.1391870975494385,
+      "learning_rate": 7e-05,
+      "loss": 3.2799,
+      "step": 7
+    },
+    {
+      "epoch": 0.11797235023041475,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 3.136,
+      "step": 8
+    },
+    {
+      "epoch": 0.1327188940092166,
+      "grad_norm": 2.1525681018829346,
+      "learning_rate": 9e-05,
+      "loss": 3.2295,
+      "step": 9
+    },
+    {
+      "epoch": 0.1327188940092166,
+      "eval_loss": NaN,
+      "eval_runtime": 4.6219,
+      "eval_samples_per_second": 24.882,
+      "eval_steps_per_second": 12.549,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8364653021233152.0,
+  "total_flos": 1.2546979531849728e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null