Training in progress, step 720, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdd2b033c37ea585607e13b612382752fbbf5831ea87bfde1779052c9548263d
+oid sha256:1c45456e15b715e832578812b0fb91f6d12ecbc982f37418d06778355c669ff0
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc024aef51b8b4a76784a1b906c3a074ffe3132bca5c716f8008e5db1bda9248
+oid sha256:7c738e308e224171798b402d3a6ac45b253baab98b34c3df38c3ff42425b504b
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d06388efd867746ee7b2b43995b42ab18afa26615084fe04f539f5258e161c0
+oid sha256:eeda755d8af1c86d4b713bb10ccad9341acf16a71464d9a966bcdbb17ea7bbc4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34730a30badf61b0bc873f35cf479882a6238fa6b272daf2b616d260608eda89
+oid sha256:b25c4cabb03cb09a4b2b9dff8deb04b1e269253acadef5d021452c833fa5d68c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.056,
+  "epoch": 0.0576,
   "eval_steps": 500,
-  "global_step": 700,
+  "global_step": 720,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -252,6 +252,13 @@
       "learning_rate": 2.9998033254984483e-05,
       "loss": 3.7841,
       "step": 700
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 24.310373306274414,
+      "learning_rate": 2.999716791440959e-05,
+      "loss": 3.679,
+      "step": 720
     }
   ],
   "logging_steps": 20,
@@ -259,7 +266,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1669066414129152.0,
+  "total_flos": 1713780872970240.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null