Training in progress, step 700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47a786cb7e329ab254056667d426149e3d8fdebab584d397cb89abcf19af80a5
+oid sha256:492e9bfe4ebba8f76c952f180f47c9cd45d836d79bcc296f61bd7c6937f1f837
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56515d5bf8b580a1af4072d013fcbb554ac9e14c88047bc94ba821081fe267fc
+oid sha256:9e5e587c0a8509f9abdc181c0e4c8cfa9c47ce2d6e2d2651942fc12828249a48
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:921d9fb33186cf89374abb76830ea684f9fce9b882a59843abd028a94eb6a3ca
+oid sha256:1d4c85b40db0299b4138faa4f07831cc38c4a75cd15d55868fc1a79092f4af3b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2df9b5bd996870bb5715debb3fbbd7b3fa2c91fccb5940591d8533888c8fdda4
+oid sha256:7fb4dcda05611092a70b2a0de5cf4d1bbece588e1c89258bd7ebf150f37ad548
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.24329159212880144,
+  "epoch": 0.2504472271914132,
   "eval_steps": 500,
-  "global_step": 680,
+  "global_step": 700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -551,14 +551,30 @@
       "loss": 0.3951,
       "num_input_tokens_seen": 455612,
       "step": 680
+    },
+    {
+      "epoch": 0.24686940966010734,
+      "grad_norm": 0.3687816560268402,
+      "learning_rate": 0.00015062611806797855,
+      "loss": 0.4176,
+      "num_input_tokens_seen": 461846,
+      "step": 690
+    },
+    {
+      "epoch": 0.2504472271914132,
+      "grad_norm": 0.32070156931877136,
+      "learning_rate": 0.00014991055456171735,
+      "loss": 0.4111,
+      "num_input_tokens_seen": 468333,
+      "step": 700
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 455612,
+  "num_input_tokens_seen": 468333,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 1.0245104935428096e+16,
+  "total_flos": 1.0531155302590464e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null