Training in progress, step 99, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:788c3cfa8c1ae6b7c7ec6fa95104c7a1e06e713c86d04f38d66e74c8f3cec915
+oid sha256:25b70ee8b75e53df56323eae615074ee1deb3d806205795e6e5e66fb5e9e086e
 size 90207248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31191c6100e74bfadd9e2865b4bf9f1e5e16a1c788de30d987acb063ad81dfff
+oid sha256:c6a94e2ae73d560b1a10d0cb238f88b143b183bd897b90d490f45c2367eca6db
 size 180543866

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bcfcc4ad1af034c86638428856e3dd9d70ffbaa6d196158eb1307cb616c0b6c
+oid sha256:ac622e2083c93ed0eba2b56ac80f2109ba1dcc99439ddb2eafbfe40970cfa64a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6b7babead6c4be4368caff2650e543461856d401ff242b042a60fc57cd3bcca
+oid sha256:7041fa0be7432c15ac468c1425bc3b5d595e4b5b769cfa7728743ab80ef12291
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.14118339134271288,
+  "epoch": 0.15530173047698417,
   "eval_steps": 9,
-  "global_step": 90,
+  "global_step": 99,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -305,6 +305,35 @@
       "eval_samples_per_second": 14.482,
       "eval_steps_per_second": 7.241,
       "step": 90
+    },
+    {
+      "epoch": 0.14588950438746998,
+      "grad_norm": 0.37905701994895935,
+      "learning_rate": 3.7544763546352834e-06,
+      "loss": 1.5333,
+      "step": 93
+    },
+    {
+      "epoch": 0.15059561743222707,
+      "grad_norm": 0.37757179141044617,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 1.4955,
+      "step": 96
+    },
+    {
+      "epoch": 0.15530173047698417,
+      "grad_norm": 0.3686583936214447,
+      "learning_rate": 7.709637592770991e-08,
+      "loss": 1.4875,
+      "step": 99
+    },
+    {
+      "epoch": 0.15530173047698417,
+      "eval_loss": 1.4919251203536987,
+      "eval_runtime": 145.2178,
+      "eval_samples_per_second": 14.792,
+      "eval_steps_per_second": 7.396,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.650176684097536e+16,
+  "total_flos": 9.494394776322048e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null