Training in progress, step 2660, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0000bbde3dcfa655946e65ba64b87f6dfeccdafdb1ea253bdb538beadca3e2c8
+oid sha256:4ac4c2e27c7954ba8f32458e86bce305764577f448e1ef7b05942fdf1638b8d3
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b083f483839d99e8ac45ae2be560977e810fb410bb8320e1ced4f7ba0955e463
+oid sha256:281f3e1e3de94056c7322594abe70311fe1bd96ae510bce52c2cda2200510403
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e793c6900656f10a2db884b32b210a11518f8eaa9b09fba8fb850e868ac57958
+oid sha256:61c76e152102faadd3e0723a7b1e98668fc77dc3b57498a40931f275e4f17e53
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb9e8f81be6bfdad3c91514c14230cbe82f9f3e206c903e15baf685a171dafda
+oid sha256:ae0efadb0abbc637034bafcf665143567ca2a6d58001c0ddda8fd674ac11d7db
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9445438282647585,
+  "epoch": 0.9516994633273703,
   "eval_steps": 500,
-  "global_step": 2640,
+  "global_step": 2660,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2119,14 +2119,30 @@
       "loss": 0.3877,
       "num_input_tokens_seen": 1790778,
       "step": 2640
+    },
+    {
+      "epoch": 0.9481216457960644,
+      "grad_norm": 0.3405713140964508,
+      "learning_rate": 1.037567084078712e-05,
+      "loss": 0.3674,
+      "num_input_tokens_seen": 1797992,
+      "step": 2650
+    },
+    {
+      "epoch": 0.9516994633273703,
+      "grad_norm": 0.4525390565395355,
+      "learning_rate": 9.660107334525939e-06,
+      "loss": 0.376,
+      "num_input_tokens_seen": 1804337,
+      "step": 2660
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1790778,
+  "num_input_tokens_seen": 1804337,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 4.026827328089702e+16,
+  "total_flos": 4.05731673087529e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null