Training in progress, step 800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbc59f60f0b03fc7d848bb49dd337a2c313e7da3137d63d5330c2fd0bf931778
+oid sha256:46722a6c1e8fcc1af409969eb6dda679f6ae4f5765bfa779279b1bbf7a6a1b81
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:674fd7d1b2da8e8b572dcd8c5c60764fe92b223569cb37500fc42668fb9f866e
+oid sha256:051ec58c662275272caf7cf3e35e2605b9f5cd07bfadcb5837f612847dc33adf
 size 84581014

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b38798aed442913f3edb40ed2e6dd248c47415757a186238aa4d86325b07c484
+oid sha256:c47dc8cc8d9492142296c3e4e14a06d78de1dc5b37a7008b6df2888e1109d0f8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f02eb1d87c6e64756c982d23c5194d17c9b128eb05ac315db5c766e38219aacd
+oid sha256:e8f132012c5b818670e4adff6f24c665930d4cab15cd962aaaeccbdabdd884fe
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00044619783668415513,
+  "epoch": 0.0005949304489122069,
   "eval_steps": 2000,
-  "global_step": 600,
+  "global_step": 800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -28,6 +28,13 @@
       "learning_rate": 1.9999999617416517e-05,
       "loss": 1.6314,
       "step": 600
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 10.143038749694824,
+      "learning_rate": 1.999999931524823e-05,
+      "loss": 1.5416,
+      "step": 800
     }
   ],
   "logging_steps": 200,
@@ -35,7 +42,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 7590307482550272.0,
+  "total_flos": 9978438301335552.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null