Training in progress, step 9360, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:751f9f960dca5d1bc5b5f0841d1b2cd22831c5a9dd0e4a5ca9f8a71c9bacbd5a
+oid sha256:ce3133fc8023dc9fec5e655ff4095b17d357c0b7879a0cb32cee9112f5995b98
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:568119d120e0792ab2007ac43295445f846bf7d46a353f3c9997e7874c17c32e
+oid sha256:a8cc9cb8b2654a9d8d631a10c10e390e4fcaec9c1afb800e42a2d87bc9203baf
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9a0d75844d6619f1d43c17c2161774384d43f6fff4ebf0f3423379b5d726d2c
+oid sha256:326613a61f7ba42eb9028eedd563cedc07a0da8a535fbe448e54c2eb7d1c1b65
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c57b84b3c01996ecacc9d6df616fa036107288915c2593ed0d7afa9b69854186
+oid sha256:719ba58f8d34bc5a5298f55e15bc61b57310339d8425df02e38a130cb9f3b6fa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7472,
+  "epoch": 0.7488,
   "eval_steps": 500,
-  "global_step": 9340,
+  "global_step": 9360,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3276,6 +3276,13 @@
       "learning_rate": 1.73225223029007e-05,
       "loss": 3.5017,
       "step": 9340
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 33.9267578125,
+      "learning_rate": 1.7274514748802418e-05,
+      "loss": 3.4322,
+      "step": 9360
     }
   ],
   "logging_steps": 20,
@@ -3283,7 +3290,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 2.208257832045773e+16,
+  "total_flos": 2.212768645024973e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null