Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1149ac7d2e20a3329470bc1ff37dc81499b3a2cb0df815434dcf8dae04d7c3e3
+oid sha256:ec4ab9a57a93c3513ea05caae28c984ac3710ebaf13f368939d8bad1fd992ae0
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdd9e444faaff4d97315caba29dfc8c642a3e55aa3d110711caa1e01bf50f4b7
+oid sha256:97d9a87ee6b6052046f0b14d04eaaf0357892b7a7f4727b789c67069b7547c6a
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffef31896db6975b47a1bdf431486b1a47c0e23e76fe29d6042f106a12e8af6b
+oid sha256:87fe9fb3b31ca0189979c0daa73883f6e8cf029b274919616b419e017ad599ca
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84691b1971218726e113e2882d1da3f46cde022409a500bc85e18521371a8edd
+oid sha256:511871b8163e6c2442a4d43033ca6a9432c171a817a07d44c57891428e700525
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.17173524150268335,
+  "epoch": 0.17889087656529518,
   "eval_steps": 500,
-  "global_step": 480,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -391,14 +391,30 @@
       "loss": 0.4089,
       "num_input_tokens_seen": 319432,
       "step": 480
+    },
+    {
+      "epoch": 0.17531305903398928,
+      "grad_norm": 0.31139102578163147,
+      "learning_rate": 0.00016493738819320215,
+      "loss": 0.4244,
+      "num_input_tokens_seen": 325211,
+      "step": 490
+    },
+    {
+      "epoch": 0.17889087656529518,
+      "grad_norm": 0.34276363253593445,
+      "learning_rate": 0.00016422182468694098,
+      "loss": 0.4133,
+      "num_input_tokens_seen": 332100,
+      "step": 500
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 319432,
+  "num_input_tokens_seen": 332100,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 7182897640390656.0,
+  "total_flos": 7467756224716800.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null