Training in progress, step 960, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54feb64c3399e2d177b3320958c14f58182a063070ccf185b38c3c93faf06ba6
+oid sha256:b4d41e09cf715f5c480ebcecf2f4c4b59c1d7cbb96dd62a4fd9c60c489a12f83
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:286c8444a82510a393c4334b2b71f0c3fefdea093f054e1ac5163e84ffed12a5
+oid sha256:eb1e93632969717d6834dc55b3a7d547324cf934ac0de101cf1f8be5edafa9d0
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c758c6fee7768e4e82a953db4ab52fd9cdd7279c05a83ae3720484a80b13b34
+oid sha256:8dc6ef0cad902c7ed89d7d51fae3e56f0c1df9768a842dd46649a938c724d41a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9a899a01093b9339f9c8c19476d5e45ea0568d456cd5b623e8894115dc39246
+oid sha256:dda93804f1297e9fd3b6077f94fd7515a08ffe7dad678fb1eb78468822988185
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3363148479427549,
+  "epoch": 0.3434704830053667,
   "eval_steps": 500,
-  "global_step": 940,
+  "global_step": 960,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -759,14 +759,30 @@
       "loss": 0.3929,
       "num_input_tokens_seen": 625029,
       "step": 940
+    },
+    {
+      "epoch": 0.33989266547406083,
+      "grad_norm": 0.3364561200141907,
+      "learning_rate": 0.00013202146690518784,
+      "loss": 0.4217,
+      "num_input_tokens_seen": 630571,
+      "step": 950
+    },
+    {
+      "epoch": 0.3434704830053667,
+      "grad_norm": 0.3077852129936218,
+      "learning_rate": 0.00013130590339892665,
+      "loss": 0.4223,
+      "num_input_tokens_seen": 636343,
+      "step": 960
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 625029,
+  "num_input_tokens_seen": 636343,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 1.4054694987589632e+16,
+  "total_flos": 1.4309106893420544e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null