Training in progress, step 4000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dad49df5b2df7646aa362b89959fb3a68f02e445d91649201aa7875d14451182
+oid sha256:eb01ed2a8ec6b8d9ca441331f478bc184548ba2cd587732637da94911f94caa3
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:267a2036f4138e7cda6f843ad4f4096f8ff700ae0fe86cbe32da71d427faaf00
+oid sha256:48b28c6356ac383f9524b669dda20f0fa6982eb51ae20cccd0122514477c4f52
 size 84581014

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:872e352590e3a4a2cb815be063d894442037481619a588e6b703cf8f8edc317a
+oid sha256:3712761bc2feaa4dd59bbca7eb1e2751ef5fe3d141fa66ff9fb4561780df39c8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a02c00cee72ba53cc6916bd67dc0363d3b2574076a95ff3d48c5db212f6a902
+oid sha256:17c0443aeeda2543522ca2ca694a10a6e2b344c5716e020a89e9019e3511777c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0028259196323329825,
+  "epoch": 0.002974652244561034,
   "eval_steps": 2000,
-  "global_step": 3800,
+  "global_step": 4000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -140,6 +140,13 @@
       "learning_rate": 1.9999984311180655e-05,
       "loss": 1.5804,
       "step": 3800
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 5.269617557525635,
+      "learning_rate": 1.999998261213993e-05,
+      "loss": 1.6025,
+      "step": 4000
     }
   ],
   "logging_steps": 200,
@@ -147,7 +154,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 4.986484165808947e+16,
+  "total_flos": 5.2577140632576e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null