Training in progress, step 5800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:283dd7cd18659a3c9d3097777e6a3109d1270cd6b8e6372800d079fa0c6abec5
+oid sha256:d4f6bee707bd16994812f4ab6abe0b76396f1fcd5a795587aa16fd0375503283
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6b30e324e0c0ca3d4e69841f3e1c91025824da6588bf53e3d9fec35c7904fe9
+oid sha256:4a78778227fc0abc34ed31ed4cde0a6bd77af35f8cb0ff481a8a83ef11c522ed
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1680fcc8fd6c2f3a95198a6b5dcd06c9a4a57f3225e8f95006ad95075adefeb1
+oid sha256:05d955c232a1730a709d883a685c93094aec6c22aa6fdd94806aef697f010076
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:447f6f7a97384eaf154d22cf9cf079d353a317926c5cc0034d003c8c0323b94e
+oid sha256:27226a26f79ee380c55eb9253588111984d20dcd9f4210cd93f6516c9d906461
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4624,
+  "epoch": 0.464,
   "eval_steps": 500,
-  "global_step": 5780,
+  "global_step": 5800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2030,6 +2030,13 @@
       "learning_rate": 2.5024918927404005e-05,
       "loss": 3.5194,
       "step": 5780
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 59.62504959106445,
+      "learning_rate": 2.4988728375175216e-05,
+      "loss": 3.5436,
+      "step": 5800
     }
   ],
   "logging_steps": 20,
@@ -2037,7 +2044,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1.3688234216423424e+16,
+  "total_flos": 1.3734753000456192e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null