Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6051d0599f14aaacc3b7a5b4a8cd9aad7c0ed892279482b9eda5c93c642df4df
+oid sha256:250984e1bfad00366cf9fd3fb737b7fdf7f164b3d32e62ba305197e3a32f1bba
 size 247944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c316a9384811dd5223f4baa07931f9c8571114fc8598b02189dc3ad1a4e787a
+oid sha256:93ff39f8297fafec9263ec264ebe63f41b58c53d3aabced597b468904eb3d9e7
 size 263088

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:399f12128758c20f45f058a67599e1b9a2d9cd495e1ccd71687a907821c8d121
+oid sha256:49593839f9d1f47c098855c411ae242b6ae0da44eb823919bbad1cbb6de79de6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0004890274466654441,
+  "epoch": 0.0007335411699981661,
   "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": 35.386,
       "eval_steps_per_second": 35.386,
       "step": 6
+    },
+    {
+      "epoch": 0.0005705320211096848,
+      "grad_norm": 2.844712495803833,
+      "learning_rate": 0.00014,
+      "loss": 44.4716,
+      "step": 7
+    },
+    {
+      "epoch": 0.0006520365955539254,
+      "grad_norm": 2.5091469287872314,
+      "learning_rate": 0.00016,
+      "loss": 44.2388,
+      "step": 8
+    },
+    {
+      "epoch": 0.0007335411699981661,
+      "grad_norm": 1.7652978897094727,
+      "learning_rate": 0.00018,
+      "loss": 44.4253,
+      "step": 9
+    },
+    {
+      "epoch": 0.0007335411699981661,
+      "eval_loss": 11.101712226867676,
+      "eval_runtime": 73.0556,
+      "eval_samples_per_second": 35.357,
+      "eval_steps_per_second": 35.357,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 249594642432.0,
+  "total_flos": 374391963648.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null