Training in progress, step 1960, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e4888f9f08518c6d58c830b271bb36cd465eedb56a20771aba351e68172f6cc
+oid sha256:736ce521e7280bd2c0975bc603cc94348d6eccc9990efd864828bf986063810d
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f5fea76bac96f4fa5b326844005d6d3b5178ec7b954adc7a2817b3325dbd873
+oid sha256:d5d973aa7ba038a74b7db64dcfe60c4781913554719fcda63eaae556dc3e290b
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6675257a869fc0efa3dc4f0df7900ffd4f952e0843913706c20ca08cfdb2c54f
+oid sha256:f02d6e86658ff6b5c2087c9efdb8f98bc5474610047eb47a7fd80ecf387cb826
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f77432e61737c0e6ca92ad6d407da985441feb6cfec781ba12cb31c4ebbe3608
+oid sha256:07fafb27edca5562e76184af344027e6c5895e3f1fc53905ab247cd738263f94
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6940966010733453,
+  "epoch": 0.7012522361359571,
   "eval_steps": 500,
-  "global_step": 1940,
+  "global_step": 1960,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1559,14 +1559,30 @@
       "loss": 0.3968,
       "num_input_tokens_seen": 1312434,
       "step": 1940
+    },
+    {
+      "epoch": 0.6976744186046512,
+      "grad_norm": 0.27954959869384766,
+      "learning_rate": 6.0465116279069765e-05,
+      "loss": 0.4071,
+      "num_input_tokens_seen": 1320352,
+      "step": 1950
+    },
+    {
+      "epoch": 0.7012522361359571,
+      "grad_norm": 0.36177489161491394,
+      "learning_rate": 5.974955277280859e-05,
+      "loss": 0.3683,
+      "num_input_tokens_seen": 1326200,
+      "step": 1960
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1312434,
+  "num_input_tokens_seen": 1326200,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 2.951200594107187e+16,
+  "total_flos": 2.98215546679296e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null