Training in progress, step 1220, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a978d2ea4c2ef178cab56e079e834d41ad51771ce490d4892a323b4ec39be6be
+oid sha256:6e8e5d6c8e35a31822eb871dc12fd823552b7a9eb9ab33cebd109faea9d529ed
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:469403812ebd6b0168f1cfd10dc9051127cd1573ac3bdf23aca7e0e5a8a0418b
+oid sha256:1fd6895bed1fe4adfa252f7f5652144d6386071fff8967514a353129d7f88c54
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c4a6bdcee541f4bc227f467016d9bc346f4f8483027f6990cb0f3a9b7a1f71e
+oid sha256:9866c1c14b91e373c14a64f4ded163a467e354a089a0218d545dc01da1c17aaa
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d836f79887d280f068e10ec79168f2ea91f57c6fbb35eab33b10757b0316f93b
+oid sha256:57764528c21ae418357b945c42fcac06191f00649d4e1a2cbc30bb9cceaa547a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4293381037567084,
+  "epoch": 0.4364937388193202,
   "eval_steps": 500,
-  "global_step": 1200,
+  "global_step": 1220,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -967,14 +967,30 @@
       "loss": 0.4032,
       "num_input_tokens_seen": 807607,
       "step": 1200
+    },
+    {
+      "epoch": 0.4329159212880143,
+      "grad_norm": 0.25886887311935425,
+      "learning_rate": 0.00011341681574239715,
+      "loss": 0.416,
+      "num_input_tokens_seen": 813956,
+      "step": 1210
+    },
+    {
+      "epoch": 0.4364937388193202,
+      "grad_norm": 0.336000919342041,
+      "learning_rate": 0.00011270125223613597,
+      "loss": 0.3817,
+      "num_input_tokens_seen": 821166,
+      "step": 1220
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 807607,
+  "num_input_tokens_seen": 821166,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 1.8160229453101056e+16,
+  "total_flos": 1.846512348095693e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null