Training in progress, step 3680, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbcfaec3e348c7d2277c6b26e72513d8f233c50f6153d77f79fb16607816e019
+oid sha256:aef5ea8b79738fa0b1afc11d4b2107af60cdd8cb8f1d9e425e3dbf9f968e4c88
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e9a7c0408bb21c6add531c8ecf332ee65e8da095897c11526a8a71159a612bd
+oid sha256:cde1575d56a414a2045e8dbdaca0d2f623d7e43dfc4fc696b88d5f3e863f7170
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbdcee77be9827de8d12c3593b0e445ae8e58c98fda9d45171de520fb50310c0
+oid sha256:a5ad82d08ebc1302cfaf16005dda10850453ff7fda97e1c6c54c3d6aaca32ef8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75387a128862b4898057b986470075974f53b66436a53a12635d2da9900d5d04
+oid sha256:a07985d480aea598ad66efeed57f22e38607f1040692f61ddafbb1ee20e27674
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2928,
+  "epoch": 0.2944,
   "eval_steps": 500,
-  "global_step": 3660,
+  "global_step": 3680,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1288,6 +1288,13 @@
       "learning_rate": 2.8195755409920584e-05,
       "loss": 3.4387,
       "step": 3660
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 43.26001739501953,
+      "learning_rate": 2.8172585936822056e-05,
+      "loss": 3.5127,
+      "step": 3680
     }
   ],
   "logging_steps": 20,
@@ -1295,7 +1302,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 8653740454772736.0,
+  "total_flos": 8695239934181376.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null