Training in progress, step 10600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2bbb20e2e294c1c21192f562a8c629ebccc06ad6cd551b6f30c8e039ab4706c
+oid sha256:3b157da58de763723afba58a487dce4affd5aa4ea8842fbd4da7c7f50fe12697
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ec42b92ca3eacb4edf3bf7f17472e3af6a7858800cee747ed46bbcad71a1cbe
+oid sha256:64b66793c07b1b0a84c67dfb67dabbc667be148932241d1875f1cf4cef5d93cb
 size 84581014

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e76cdf884e11761c200ac34b58dbb495717e6bde399a5bd34f22ad9223e288af
+oid sha256:96a19a56fa0d8bb9b191b59d03bf40b790346150a7f3d469cfde615d3a433c9a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:267883072a6671c244f08bafb8d77a7436e4752bd5182174b7eeacf1d55aa425
+oid sha256:6a2e63dae0ad86e6af927f787db5624af1572bceb0832f3c088d78644536e527
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007734095835858689,
+  "epoch": 0.007882828448086741,
   "eval_steps": 2000,
-  "global_step": 10400,
+  "global_step": 10600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -371,6 +371,13 @@
       "learning_rate": 1.999988217717089e-05,
       "loss": 1.5754,
       "step": 10400
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 1.9017295837402344,
+      "learning_rate": 1.9999877597068942e-05,
+      "loss": 1.572,
+      "step": 10600
     }
   ],
   "logging_steps": 200,
@@ -378,7 +385,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 1.3591987236736205e+17,
+  "total_flos": 1.3848555079593984e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null