Training in progress, step 9400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bec6bca3c48b3e9f7ec1a052500985b06b331ed7b76a2c7795a8ebc958fc6fb
+oid sha256:b528e15f2baa32d13f72d5933c2caee1fa810d425b6d906195b78816a26f46ed
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ca5553eb1deb65392427bfb5f3e004d9236ac9eeebf32208464d046a530ffce
+oid sha256:6646ed4f92934c93346d35442db142ff8da438dedae14ca63dc2b43a723658c1
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f652f4e3db4d7a26e9dba2e7386e5cf6c51fb000752a737298ff24d1508a8460
+oid sha256:86f07a568a4d1f63a6cca332674bee5175abc2cc7d297e5628f2c0e96ec86411
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca42f36f25082c2beb3fc00186e8ed8c12110e85da52d110e31ee1b1dc6e0295
+oid sha256:b753d0c4d4469dd7c3eaf7aa0c54015d01c2f776466e9c9fb599fbba12d176ec
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7504,
+  "epoch": 0.752,
   "eval_steps": 500,
-  "global_step": 9380,
+  "global_step": 9400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3290,6 +3290,13 @@
       "learning_rate": 1.7226483336120707e-05,
       "loss": 3.443,
       "step": 9380
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 19.676841735839844,
+      "learning_rate": 1.7178428568682357e-05,
+      "loss": 3.443,
+      "step": 9400
     }
   ],
   "logging_steps": 20,
@@ -3297,7 +3304,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 2.217039974842368e+16,
+  "total_flos": 2.2213834776674304e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null