Training in progress, step 3660, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d54e67b174db8aa6d78fd7e5ad7cc14e255ae9e2ac4b07617e63a3c6e1f44fd1
+oid sha256:fbcfaec3e348c7d2277c6b26e72513d8f233c50f6153d77f79fb16607816e019
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a538e98a56080dc8b839b137de6d2baa98652765c46f5d7d5638ebbff1fc24e
+oid sha256:8e9a7c0408bb21c6add531c8ecf332ee65e8da095897c11526a8a71159a612bd
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77ef44b95127212e765792a1cf83babb6419dbbbc5242f9919c1607c1deb549f
+oid sha256:fbdcee77be9827de8d12c3593b0e445ae8e58c98fda9d45171de520fb50310c0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6436b03258a74e4e347dfaffcfa88289f9f39a08c2a52b4713027be6b232347
+oid sha256:75387a128862b4898057b986470075974f53b66436a53a12635d2da9900d5d04
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2912,
+  "epoch": 0.2928,
   "eval_steps": 500,
-  "global_step": 3640,
+  "global_step": 3660,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1281,6 +1281,13 @@
       "learning_rate": 2.8218786465788984e-05,
       "loss": 3.6001,
       "step": 3640
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 27.951440811157227,
+      "learning_rate": 2.8195755409920584e-05,
+      "loss": 3.4387,
+      "step": 3660
     }
   ],
   "logging_steps": 20,
@@ -1288,7 +1295,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 8607877788991488.0,
+  "total_flos": 8653740454772736.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null