Training in progress, step 260, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc8fd63357e965db07708c36a2a6ae6a6c03fc9d02bf6c61fc572c8f7b789e81
+oid sha256:2136a266464d0b9812183c2c7ec272f51ec8b4b2a73d98b99839dce69364c4ad
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:feaefc33b89d5098807e8eae0d0a7015b62dd9813ee04ec553624e04230f3ead
+oid sha256:7b78d6de461909c4794f6a8ea0bace8d45003ec511a44c6c02656a3209c5b403
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ef207b513398f9a5cd5415aae0d38d9a46813960e1af4ca47c167d0338fb7a0
+oid sha256:93d073fb3e4a146a793ea03f10d54796a90197d4dfbe3f76b45137b6f4230b74
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:343e65a0194c6a62b1ee6752dea639ee422801e05f7e64962871b691822c4617
+oid sha256:12e5cd7fc3da76dcdde9887af968b8b3aba1c1bb4ddd30a416d2f9a0e9367d84
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08586762075134168,
+  "epoch": 0.09302325581395349,
   "eval_steps": 500,
-  "global_step": 240,
+  "global_step": 260,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -199,14 +199,30 @@
       "loss": 0.446,
       "num_input_tokens_seen": 162267,
       "step": 240
+    },
+    {
+      "epoch": 0.08944543828264759,
+      "grad_norm": 0.360166996717453,
+      "learning_rate": 0.0001821109123434705,
+      "loss": 0.4549,
+      "num_input_tokens_seen": 168817,
+      "step": 250
+    },
+    {
+      "epoch": 0.09302325581395349,
+      "grad_norm": 0.342385470867157,
+      "learning_rate": 0.0001813953488372093,
+      "loss": 0.4297,
+      "num_input_tokens_seen": 174828,
+      "step": 260
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 162267,
+  "num_input_tokens_seen": 174828,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 3648811801614336.0,
+  "total_flos": 3931264333799424.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null