Training in progress, step 3880, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcf9e22c88e0fb0603b9cd82abbc6b98b49f7ad3ed9dc4c142244b973e2719d2
+oid sha256:cde6f153e1e8b9a9e7c00323ae4d7db7386328f2d24b06facfc13a8ee245b3fe
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4e0a82f4d4487e9ab1022d1b2edd903560854e8fb2a0c9abf71fe128a2a2b94
+oid sha256:124b7ab2647d2a34f2d76c3fe8f556de61ab2239e56a049ecc9fdd7887cdf35e
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:877a724df59c57e1a2f0f22ee80507c6df287299fe61cc0042cb8694e46f52f4
+oid sha256:9cbc3f7eb6570c006a685ab90bed6095506dc3296d40e802ec891bd2b2edc3fe
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:861a7b99be1280c1ac6dbca0c55884807e0dfa7f21363b76c38ae1c977205711
+oid sha256:073260aeda648df98a231950123c1b6238009c89906d5834aa58374e8953701f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3088,
+  "epoch": 0.3104,
   "eval_steps": 500,
-  "global_step": 3860,
+  "global_step": 3880,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1358,6 +1358,13 @@
       "learning_rate": 2.7957872481757377e-05,
       "loss": 3.5455,
       "step": 3860
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 23.779598236083984,
+      "learning_rate": 2.793333244167681e-05,
+      "loss": 3.5345,
+      "step": 3880
     }
   ],
   "logging_steps": 20,
@@ -1365,7 +1372,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 9104592111304704.0,
+  "total_flos": 9159181149831168.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null