Training in progress, step 980, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4d41e09cf715f5c480ebcecf2f4c4b59c1d7cbb96dd62a4fd9c60c489a12f83
+oid sha256:54ac97e83b1ff548309589aabfdab6d2e1d4687dfe98f37c20e887408a1980e3
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb1e93632969717d6834dc55b3a7d547324cf934ac0de101cf1f8be5edafa9d0
+oid sha256:5ff578aab41031ebce89be46228ea8e5cc738b9955991c2357aa125882c47fbc
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dc6ef0cad902c7ed89d7d51fae3e56f0c1df9768a842dd46649a938c724d41a
+oid sha256:a9fa9b80e86e6f00faed171296591e6c820ce1205bc98d1e1dac11ed9c33eb11
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dda93804f1297e9fd3b6077f94fd7515a08ffe7dad678fb1eb78468822988185
+oid sha256:439d59a79ea6f98b7e31cb3d3d054d5d78bf9c23ea4b4c438d0a10fd0910fe22
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3434704830053667,
+  "epoch": 0.35062611806797855,
   "eval_steps": 500,
-  "global_step": 960,
+  "global_step": 980,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -775,14 +775,30 @@
       "loss": 0.4223,
       "num_input_tokens_seen": 636343,
       "step": 960
+    },
+    {
+      "epoch": 0.3470483005366726,
+      "grad_norm": 0.4563674032688141,
+      "learning_rate": 0.00013059033989266548,
+      "loss": 0.4093,
+      "num_input_tokens_seen": 644448,
+      "step": 970
+    },
+    {
+      "epoch": 0.35062611806797855,
+      "grad_norm": 0.3391217291355133,
+      "learning_rate": 0.00012987477638640431,
+      "loss": 0.4146,
+      "num_input_tokens_seen": 651211,
+      "step": 980
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 636343,
+  "num_input_tokens_seen": 651211,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 1.4309106893420544e+16,
+  "total_flos": 1.4643435708684288e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null