Training in progress, step 1000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46722a6c1e8fcc1af409969eb6dda679f6ae4f5765bfa779279b1bbf7a6a1b81
+oid sha256:4cc0e03b9e41c36bebd5290c036c6ab8219fc845aed5c0fa6e9fcd25304615e4
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:051ec58c662275272caf7cf3e35e2605b9f5cd07bfadcb5837f612847dc33adf
+oid sha256:6b25ff21c077ced998e166c13b16ca46c3928f2a8dec143c1e29895bcf0ed63e
 size 84581014

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c47dc8cc8d9492142296c3e4e14a06d78de1dc5b37a7008b6df2888e1109d0f8
+oid sha256:437c777924390da1dedc2bce8c9e0b6f4eb89d30ea814cea3a93ff7b5d5fae05
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8f132012c5b818670e4adff6f24c665930d4cab15cd962aaaeccbdabdd884fe
+oid sha256:89ee446e7e0c91089e5e6b7b626fa10c97dc177ed58fc09c887e3e9c3cd58b38
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0005949304489122069,
+  "epoch": 0.0007436630611402585,
   "eval_steps": 2000,
-  "global_step": 800,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -35,6 +35,13 @@
       "learning_rate": 1.999999931524823e-05,
       "loss": 1.5416,
       "step": 800
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 2.783194065093994,
+      "learning_rate": 1.999999892574807e-05,
+      "loss": 1.5775,
+      "step": 1000
     }
   ],
   "logging_steps": 200,
@@ -42,7 +49,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 9978438301335552.0,
+  "total_flos": 1.2689424120840192e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null