Training in progress, step 4200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb01ed2a8ec6b8d9ca441331f478bc184548ba2cd587732637da94911f94caa3
+oid sha256:bafc3f6442e5ba84431ff078caa6e69b3a936652a78ec4e062738afe5c219732
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48b28c6356ac383f9524b669dda20f0fa6982eb51ae20cccd0122514477c4f52
+oid sha256:e921e944e51dba181ad318d41576f8ac3157dc39c4bff064cdc6b4b895ad6d05
 size 84581014

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3712761bc2feaa4dd59bbca7eb1e2751ef5fe3d141fa66ff9fb4561780df39c8
+oid sha256:de92704bc3b6ffc2d27e74d056f93cc6b41e535e9e0201f0fa7c3b78e6075e90
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17c0443aeeda2543522ca2ca694a10a6e2b344c5716e020a89e9019e3511777c
+oid sha256:8ae6e4af65e99b8816fc6ca644da9b1cf355b8cdc1d577590a1d02007539bd66
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.002974652244561034,
+  "epoch": 0.003123384856789086,
   "eval_steps": 2000,
-  "global_step": 4000,
+  "global_step": 4200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -147,6 +147,13 @@
       "learning_rate": 1.999998261213993e-05,
       "loss": 1.6025,
       "step": 4000
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 2.5482230186462402,
+      "learning_rate": 1.9999980825767474e-05,
+      "loss": 1.5963,
+      "step": 4200
     }
   ],
   "logging_steps": 200,
@@ -154,7 +161,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 5.2577140632576e+16,
+  "total_flos": 5.526240672691814e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null