Training in progress, step 140, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c38bdb0979c928e502c97dd82b769114b80aa32487f2fa00dc25b698969b75a2
+oid sha256:50c0bb52227566fdedffa529ef2d112337892b1e2363fcc0565a80cbf56fd4e9
 size 8077608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ebcaa011427412ab8e2fea63b8c8e971f5197b41f6e48c45c3d73093532d3f8
+oid sha256:f474e44cad3c1f610a848788a9e23480fd594303c6b8a18f59815051a95de18a
 size 4052500

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e768a159af022ca8d40d66c6ad973ca9bd9af8b77073a0bd9deb9b53bc1bafcb
+oid sha256:c36ebb57abad726f999a1058e5d2aef9e13a8edeb533955d4fe52a63ff0447b3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0024,
+  "epoch": 0.0028,
   "eval_steps": 500,
-  "global_step": 120,
+  "global_step": 140,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -49,6 +49,13 @@
       "learning_rate": 6e-06,
       "loss": 4.4426,
       "step": 120
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 43.68627166748047,
+      "learning_rate": 7e-06,
+      "loss": 5.0142,
+      "step": 140
     }
   ],
   "logging_steps": 20,
@@ -56,7 +63,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 42048279232512.0,
+  "total_flos": 47457760075776.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null