Training in progress, step 9220, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1191e15f1f075f04e1758ba87cec35bdffa2da050944d1bbd85df57885868d03
+oid sha256:32794401cb308b267d0bd79030d66e61135ddaadf4fd04203a94ef1dc084f749
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a010ce7c172b0d1642d9d0d0c2e4c836b9098269d1f3df199282ff380452442
+oid sha256:806be36c7d4247910d10d0a3d4e85abf9ecb886dba015205196e017aa6a69b3d
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:267bfcd733ebdb94275f330516fcaee122db5c84d3b8dd0fa12ab600e130ce3a
+oid sha256:7d0e1721e39570a369ee3212183976850af3d42923a35fa475e14d07fb127160
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd1f9483d4afb3a72629e531d61449865b645ed3eea3223a993e49f084490f43
+oid sha256:99eb28a147ff3b3e70b87395088aa61d9ebc6ba66456bca527ae02b29c9a018a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.736,
+  "epoch": 0.7376,
   "eval_steps": 500,
-  "global_step": 9200,
+  "global_step": 9220,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3227,6 +3227,13 @@
       "learning_rate": 1.7657864873688343e-05,
       "loss": 3.4515,
       "step": 9200
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 41.386260986328125,
+      "learning_rate": 1.761003841513674e-05,
+      "loss": 3.4684,
+      "step": 9220
     }
   ],
   "logging_steps": 20,
@@ -3234,7 +3241,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 2.1755437760249856e+16,
+  "total_flos": 2.1795953062281216e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null