Training in progress, step 1800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e031d128a56e1f2c0d13eb1bdf24b11e3161a5c84ee640ffe8148c5cde2e7779
+oid sha256:0d87d7b00b2cd87fc029fa649fcad601b3ab7944457ec983484f19f24a594882
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68b7b1fbf5329eb8a91ba2dd7567fcfc9167143f8b5b1e8a308611118d62b893
+oid sha256:665a4d9783c05d43fa2505e60c3df4f8fdb4f033e3075cab2b640d9f0f0ef616
 size 84581014

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d51ba13d8ecce76d2ed0ab5874b7250d2ee372ca336a46f1c56ac6d02ec40073
+oid sha256:3d6334547612743196cb899c468f052098297738886954360e857941f54e2a3c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c9e9f1ae41fa1e5ee80b76c39d1d8aae5af530178bf78fd25d0ba3cffdc224c
+oid sha256:3a72ce24312e683508adae33679f3e646acad48e43aa6427ea385038cc671f18
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0011898608978244138,
+  "epoch": 0.0013385935100524654,
   "eval_steps": 2000,
-  "global_step": 1600,
+  "global_step": 1800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -63,6 +63,13 @@
       "learning_rate": 1.9999997233256404e-05,
       "loss": 1.6001,
       "step": 1600
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 3.046320676803589,
+      "learning_rate": 1.9999996494428805e-05,
+      "loss": 1.5682,
+      "step": 1800
     }
   ],
   "logging_steps": 200,
@@ -70,7 +77,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 2.07320002916352e+16,
+  "total_flos": 2.3336484713988096e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null