Training in progress, step 720, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50e6594b364a0fbb854abb5d965c726e8f15fa01c9001b41d915e779549b2215
+oid sha256:fea491b3b1391cebeed659bd3578d064da132e8ae050b25368833ae5a10ca588
 size 1316913776

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9629f232980735b2c724e023cd63526e09d46d3ef9ec65dbafa2e8570647df4b
+oid sha256:04ed2b24885e7eebc909afa04e3fc3dcc986e27c10b7a80cc077f1a38645d3a8
 size 8908124

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.15242593387720052,
+  "epoch": 0.15457277801631603,
   "eval_steps": 500,
-  "global_step": 710,
+  "global_step": 720,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -504,6 +504,13 @@
       "learning_rate": 0.00042378703306139977,
       "loss": 0.8205,
       "step": 710
+    },
+    {
+      "epoch": 0.15457277801631603,
+      "grad_norm": 1.7332643270492554,
+      "learning_rate": 0.00042271361099184204,
+      "loss": 0.845,
+      "step": 720
     }
   ],
   "logging_steps": 10,
@@ -511,7 +518,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 10,
-  "total_flos": 5.317746260637773e+16,
+  "total_flos": 5.413961972677248e+16,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null