Training in progress, step 280, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2136a266464d0b9812183c2c7ec272f51ec8b4b2a73d98b99839dce69364c4ad
+oid sha256:8e4cede093a047dae1d9b39f98f01ebd38cf9627aaf8ecf1e2945971471563b4
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b78d6de461909c4794f6a8ea0bace8d45003ec511a44c6c02656a3209c5b403
+oid sha256:7f858b048df2c4990c74df403bfc1d645b453dacbbe71b54093671cdea7cfc9f
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93d073fb3e4a146a793ea03f10d54796a90197d4dfbe3f76b45137b6f4230b74
+oid sha256:155906040ca3a73448d35f864001cf3a30094785911dc4949af7556c64d5da61
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12e5cd7fc3da76dcdde9887af968b8b3aba1c1bb4ddd30a416d2f9a0e9367d84
+oid sha256:aba7537afe16c3362d871f59e72c1a9387d8f379b5c058726a66f4dd3222a4f6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.09302325581395349,
+  "epoch": 0.1001788908765653,
   "eval_steps": 500,
-  "global_step": 260,
+  "global_step": 280,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -215,14 +215,30 @@
       "loss": 0.4297,
       "num_input_tokens_seen": 174828,
       "step": 260
+    },
+    {
+      "epoch": 0.09660107334525939,
+      "grad_norm": 0.37481924891471863,
+      "learning_rate": 0.00018067978533094814,
+      "loss": 0.4314,
+      "num_input_tokens_seen": 181578,
+      "step": 270
+    },
+    {
+      "epoch": 0.1001788908765653,
+      "grad_norm": 0.28545519709587097,
+      "learning_rate": 0.00017996422182468694,
+      "loss": 0.4332,
+      "num_input_tokens_seen": 187842,
+      "step": 280
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 174828,
+  "num_input_tokens_seen": 187842,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 3931264333799424.0,
+  "total_flos": 4223903236263936.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null