Training in progress, step 80, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c13c1fb05d548b619e4ea3b6565286621267c5c8ce62890c4968c123b771070
+oid sha256:e72960fe1f5461766c235a01313cd773da95227563f32936ac3a015ff0459139
 size 12803224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68903178a78f75a3d0256b3cd6634ad0163adbc4d74cda491a06a4482ccf1d07
+oid sha256:9382d52e6821be11c14df84b7893ef587ba8bd5a15f4fe4d93d554e30030c8d6
 size 6472698

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd37aad04b91620e0c3483fdbb04450826c4bfc1adad9bf38a9c80870ce97622
+oid sha256:80ebca932a50bd9cfabfd23733c5f77d34c6627e8990d72f32cbb244a43bf7bf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b207be31c66d2c120e6fb6b0a2aa4e289fca3c6de3dc048cad8998306d1d4ca
+oid sha256:a0533425b70142c89e8cb8876e2451acb905d0925372b0f8e777ed24de781cce
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.669515070859891e-05,
+  "epoch": 6.226020094479855e-05,
   "eval_steps": 500,
-  "global_step": 60,
+  "global_step": 80,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -28,6 +28,13 @@
       "learning_rate": 8.666666666666668e-06,
       "loss": 3.5164,
       "step": 60
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 109.34711456298828,
+      "learning_rate": 1.2e-05,
+      "loss": 4.0846,
+      "step": 80
     }
   ],
   "logging_steps": 20,
@@ -35,7 +42,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 253168758374400.0,
+  "total_flos": 337115655782400.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null