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:e72960fe1f5461766c235a01313cd773da95227563f32936ac3a015ff0459139
+oid sha256:04d2ee0f7546c8480db5f6b7431a5ecf9eddea3854bdd7845dc94b84bfe03f1e
 size 12803224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9382d52e6821be11c14df84b7893ef587ba8bd5a15f4fe4d93d554e30030c8d6
+oid sha256:59b49f44bfe27f33fffa35d6a1b635c18d402e2a88fc86d9dbed22e0915f99bf
 size 6472698

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80ebca932a50bd9cfabfd23733c5f77d34c6627e8990d72f32cbb244a43bf7bf
+oid sha256:feb6a083f723a87350cb3b90d9283b4cc20674e7bae0ce04043b935951292bbf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0533425b70142c89e8cb8876e2451acb905d0925372b0f8e777ed24de781cce
+oid sha256:4a47285efa6c5fa8c4bc001ed2983530f9e5cd23c9aaa5e045805156a46a25d3
 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": 1.2e-05,
       "loss": 4.0846,
       "step": 80
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 75.66071319580078,
+      "learning_rate": 1.5333333333333334e-05,
+      "loss": 3.594,
+      "step": 100
     }
   ],
   "logging_steps": 20,
@@ -42,7 +49,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 337115655782400.0,
+  "total_flos": 426432203366400.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null