Training in progress, step 780, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a21005b0c25f84187a6d837e3d90bc53f433f50e714145c05d0b17b4d6481985
+oid sha256:58046564a6a589cf046b1d0ed096919f55ce08a5adccffe843ca27704d205f04
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f8e8c28b45c3d4944833b51532fd8aea3a328fbd53d387d4481409ba0bd1c56
+oid sha256:78b486af472acc17cc180f369840ef98398fc54f8652e4989457cd2fb7dee143
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:744f87a373b7e8aca2b7ead73d8f8e4c8c1a6ad775f7cdeecb51f2b91e13de93
+oid sha256:3e9460a84ba57fb2b123198c54834de44fe0225b3afabca45a0f72ec4b268c32
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4433212656c2840008788d3ef4721ac521814715c0310491af53892cc2f91958
+oid sha256:4858d4115c512f42db83d85957355d46797903bfa9e8ae0671a225f442708fed
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.27191413237924866,
+  "epoch": 0.27906976744186046,
   "eval_steps": 500,
-  "global_step": 760,
+  "global_step": 780,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -615,14 +615,30 @@
       "loss": 0.4113,
       "num_input_tokens_seen": 508236,
       "step": 760
+    },
+    {
+      "epoch": 0.27549194991055453,
+      "grad_norm": 0.4110952317714691,
+      "learning_rate": 0.00014490161001788908,
+      "loss": 0.4232,
+      "num_input_tokens_seen": 514982,
+      "step": 770
+    },
+    {
+      "epoch": 0.27906976744186046,
+      "grad_norm": 0.3558269441127777,
+      "learning_rate": 0.00014418604651162791,
+      "loss": 0.4076,
+      "num_input_tokens_seen": 521248,
+      "step": 780
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 508236,
+  "num_input_tokens_seen": 521248,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 1.1428432859455488e+16,
+  "total_flos": 1.1721026788982784e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null