Training in progress, step 1240, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e8e5d6c8e35a31822eb871dc12fd823552b7a9eb9ab33cebd109faea9d529ed
+oid sha256:4989f417f8af82aa5afd207ae1fd0befd4ae0dcdae5fdc748922cf8c530c7b97
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fd6895bed1fe4adfa252f7f5652144d6386071fff8967514a353129d7f88c54
+oid sha256:d90bdbd8e9dba7260bfc44bfde0f43461ac775cf18170c0d1133ac88052f92e9
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9866c1c14b91e373c14a64f4ded163a467e354a089a0218d545dc01da1c17aaa
+oid sha256:9c48f3975b279f6efbdc2f7b3c963816b9fdd9626320f2bf9378c327c8e958c2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57764528c21ae418357b945c42fcac06191f00649d4e1a2cbc30bb9cceaa547a
+oid sha256:33e5e3b3844635e28b48697b64695f6ae48a5abd3795536da24be2a1a747340e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4364937388193202,
+  "epoch": 0.44364937388193204,
   "eval_steps": 500,
-  "global_step": 1220,
+  "global_step": 1240,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -983,14 +983,30 @@
       "loss": 0.3817,
       "num_input_tokens_seen": 821166,
       "step": 1220
+    },
+    {
+      "epoch": 0.4400715563506261,
+      "grad_norm": 0.36095812916755676,
+      "learning_rate": 0.00011198568872987479,
+      "loss": 0.4097,
+      "num_input_tokens_seen": 829461,
+      "step": 1230
+    },
+    {
+      "epoch": 0.44364937388193204,
+      "grad_norm": 0.34367650747299194,
+      "learning_rate": 0.0001112701252236136,
+      "loss": 0.4028,
+      "num_input_tokens_seen": 835022,
+      "step": 1240
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 821166,
+  "num_input_tokens_seen": 835022,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 1.846512348095693e+16,
+  "total_flos": 1.8776695989989376e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null