Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47f45bb6b4f07f7d432390b14be121ef3fde57d9170f5a9f4b4c37cff8852554
+oid sha256:434e9148a55d7de38db07465532dbaab0cdcfec5676d112c61532c1b6dbdca8d
 size 4725640

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7d8969f31b5a0f091cc220fc791b3de73ca8cb027c812d52dcbb2597614b59c
+oid sha256:b0acaa33677f5b343e216066837b318cd2dc361ba008f7a6195aeade17a72da0
 size 2423738

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef17d5f9b420f5d86fa9fe589f3c843a6c4095df024510341423c1a1b417d1a8
+oid sha256:b250d2763d35faebbdd3f9ef34837fd6af467c994efa1d3cf9d8c38a46fa8c98
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1b46a53d749681ad7163f82e3c76fde0da752adc35db447dc604f9a8c960ad4
+oid sha256:02758e7835c7a932b7dc5b6b1f15336e44a2ac260859979939ab13fea0a3b332
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.226020094479855e-05,
+  "epoch": 7.782525118099818e-05,
   "eval_steps": 500,
-  "global_step": 80,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -35,6 +35,13 @@
       "learning_rate": 1.3166666666666665e-05,
       "loss": 3.5865,
       "step": 80
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 1.9482054710388184,
+      "learning_rate": 1.65e-05,
+      "loss": 3.3337,
+      "step": 100
     }
   ],
   "logging_steps": 20,
@@ -42,7 +49,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 457519177248768.0,
+  "total_flos": 543796744273920.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null