Training in progress, step 6660, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e70f472f3208fce22e711727d3f51a955b9502ee4635cf3b354a7a5849495f64
+oid sha256:765933f0e535032650bafcefa1a947ab8a32b8bace5e91a869c8d023f473bbcc
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ce48b5f0a4182d0f3ca44b8f6292a94f1e4dd3c84342481403240c0341f492c
+oid sha256:63d11185a3e70b21eb44c951a672b731aa6be859ffabc9e46db234a2d5ba4ad8
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f483dbbbbb5dc1b41e41475eede183d58a38381ca60f4870fc45bb7a64baedfd
+oid sha256:aa10b0a2acb8a95d8431784ea3421efb241e65fea072752db25baf816c8a24aa
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:127254ff30131eb4f46f0ab26f5bfb221842284bc63a371736d3849e9dc192b7
+oid sha256:7ae054faf87e180e83b9ebfb98f4e8927964f8f999fd61086772e7360b72432e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5312,
+  "epoch": 0.5328,
   "eval_steps": 500,
-  "global_step": 6640,
+  "global_step": 6660,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2331,6 +2331,13 @@
       "learning_rate": 2.3378941214219545e-05,
       "loss": 3.5401,
       "step": 6640
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 29.300914764404297,
+      "learning_rate": 2.3338602049646372e-05,
+      "loss": 3.4601,
+      "step": 6660
     }
   ],
   "logging_steps": 20,
@@ -2338,7 +2345,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1.5672073361719296e+16,
+  "total_flos": 1.5720560500506624e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null