Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:499021d5974a1d58fa0fba533b68748ea7a31152e36d089c0b3a969ef19b1306
+oid sha256:4c385a6b977858414e8fa5e7312988b0c9d861e60935b4e0ac6a4cb1e36d6b28
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:176416be9b73270ec6fc12b7d5c18a945e6dac43b2b18c09713600fb32776cbe
+oid sha256:2d73a6bf6ce1c19943dd784e79ebbaf22b62419fb5eae06ec44005a9f3d65420
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b0e1e671455c353fa99a1d12b6e48bbd12137e1c5f529ac1c3f24d8e1df3f99
+oid sha256:20fcd20993d40639a43d37688307179c27149f3c2c0e22843985ee1afc726a1b
 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": 0.0003007104283870644,
+  "epoch": 0.00045106564258059665,
   "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": 20.616,
       "eval_steps_per_second": 10.308,
       "step": 6
+    },
+    {
+      "epoch": 0.00035082883311824184,
+      "grad_norm": 0.506304919719696,
+      "learning_rate": 0.00014,
+      "loss": 0.9069,
+      "step": 7
+    },
+    {
+      "epoch": 0.0004009472378494193,
+      "grad_norm": 0.7822049260139465,
+      "learning_rate": 0.00016,
+      "loss": 1.3244,
+      "step": 8
+    },
+    {
+      "epoch": 0.00045106564258059665,
+      "grad_norm": 0.65694260597229,
+      "learning_rate": 0.00018,
+      "loss": 1.1036,
+      "step": 9
+    },
+    {
+      "epoch": 0.00045106564258059665,
+      "eval_loss": 1.054183006286621,
+      "eval_runtime": 407.7644,
+      "eval_samples_per_second": 20.605,
+      "eval_steps_per_second": 10.303,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1849564248145920.0,
+  "total_flos": 2681868159811584.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null