Training in progress, step 1160, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ccf5782593e66412849cf0331f694759fa6cadfe866582a92dc1f5db7cfb19c
+oid sha256:1b0dd6d9eecd111fc6fbe2ea756eb3599bab074e1522852ef4565a8d0ad6a8c8
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33ace10175162fbb0251f3a59624654383e563ccfa7daaa8f8a330925f01cfae
+oid sha256:311a37a787f8e244031ec691411ba1c79ba76c28a8310c7bb68b2848e9a6c30e
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db963a2a49fb5002a715398d59757b5b39bdbc3ac8e778ee4bf9108f72ec61a1
+oid sha256:347b707ba8c2977c0e73867f80277a74052c00e5d1c0dbac8e14d68e38fd054c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76c7c7c62106d50e468f60a02081ed9ee14be8c90f56cb0a1ed1c7569018541d
+oid sha256:4e645a96d4cb253e4a9c4e19eba1a73b1611a46e51a63b85e8070050f71348c7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.407871198568873,
+  "epoch": 0.4150268336314848,
   "eval_steps": 500,
-  "global_step": 1140,
+  "global_step": 1160,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -919,14 +919,30 @@
       "loss": 0.4247,
       "num_input_tokens_seen": 766054,
       "step": 1140
+    },
+    {
+      "epoch": 0.41144901610017887,
+      "grad_norm": 0.322694331407547,
+      "learning_rate": 0.00011771019677996423,
+      "loss": 0.416,
+      "num_input_tokens_seen": 772192,
+      "step": 1150
+    },
+    {
+      "epoch": 0.4150268336314848,
+      "grad_norm": 0.4780764877796173,
+      "learning_rate": 0.00011699463327370303,
+      "loss": 0.3937,
+      "num_input_tokens_seen": 778619,
+      "step": 1160
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 766054,
+  "num_input_tokens_seen": 778619,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 1.7225849223032832e+16,
+  "total_flos": 1.7508391701092352e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null