Training in progress, step 9260, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7fe8097e3bf3e1d6200427c42cdec0c2208ac0a54599f9e26cee7d2c0f344fc
+oid sha256:938525068b6affe51d56c10c21cd3683b8cd87b2c9b36021f0fc9f229aa10e06
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3eaf1fbcdbde0059ee1f06c827026e1b557db2f3b07d9f7936261fe98f775bdb
+oid sha256:fef582d6fb7f736aed00910a585ea555f629e0cab2920275497f4ecfb33fa9c0
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e15b7ccc90968bcd87b2edf84a9cd99b1e92aa9a9e59ab6ccd2cb1a860be1afb
+oid sha256:2c27546fd78d101ec781385e794415edc478f7ce4f562ffe7088df05bb23fa05
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63037139d6ccc8c3ea7fa5702f09392e604fb2ed06455649be80ce23f1ff1ce0
+oid sha256:aa213266e45979e004936b8984e2a9dc7a7156f7190dd7acdf777fd4628091f0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7392,
+  "epoch": 0.7408,
   "eval_steps": 500,
-  "global_step": 9240,
+  "global_step": 9260,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3241,6 +3241,13 @@
       "learning_rate": 1.7562184578517207e-05,
       "loss": 3.4478,
       "step": 9240
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 22.82186508178711,
+      "learning_rate": 1.751430386579385e-05,
+      "loss": 3.4226,
+      "step": 9260
     }
   ],
   "logging_steps": 20,
@@ -3248,7 +3255,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 2.184768798641357e+16,
+  "total_flos": 2.190296594910413e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null