Training in progress, step 940, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c80d0cc296c9aca69746bef2484e11ff18da0d10137405a84bdb5b47da0b2fda
+oid sha256:54feb64c3399e2d177b3320958c14f58182a063070ccf185b38c3c93faf06ba6
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6bb63f7e63d0bb877282c464d113433128c3280a6e53182bfc42899506e4622
+oid sha256:286c8444a82510a393c4334b2b71f0c3fefdea093f054e1ac5163e84ffed12a5
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b5c274f729f78aaa763e0731ccb54809267c56bffe03386fccc50594bf6ee56
+oid sha256:5c758c6fee7768e4e82a953db4ab52fd9cdd7279c05a83ae3720484a80b13b34
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6048c9d241563f2d3e6c4169ee79753731cd3df1e3a9e7b7b302429a0457fa3f
+oid sha256:e9a899a01093b9339f9c8c19476d5e45ea0568d456cd5b623e8894115dc39246
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3291592128801431,
+  "epoch": 0.3363148479427549,
   "eval_steps": 500,
-  "global_step": 920,
+  "global_step": 940,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -743,14 +743,30 @@
       "loss": 0.4329,
       "num_input_tokens_seen": 612959,
       "step": 920
+    },
+    {
+      "epoch": 0.33273703041144903,
+      "grad_norm": 0.39697644114494324,
+      "learning_rate": 0.0001334525939177102,
+      "loss": 0.4062,
+      "num_input_tokens_seen": 620181,
+      "step": 930
+    },
+    {
+      "epoch": 0.3363148479427549,
+      "grad_norm": 0.4615568220615387,
+      "learning_rate": 0.00013273703041144903,
+      "loss": 0.3929,
+      "num_input_tokens_seen": 625029,
+      "step": 940
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 612959,
+  "num_input_tokens_seen": 625029,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 1.3783283311491072e+16,
+  "total_flos": 1.4054694987589632e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null