Training in progress, step 4, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3a25fada972cd23bc7fecab10c3b6e9e225c133101d8ea851067319e92d3f37
+oid sha256:55f6fec4dabcbfc0cfa0f4a79622ecc31315d0e652e2837b087e6e8aa275fabe
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d96e42ecb56c134a1f08f63e021d6b353709e471878a00071eec17716c8e1f0b
+oid sha256:8f69fda602f49d1a0a050670acc6aabee9a30b4e7042b5e90ffaaf97b83bfcff
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:759f00bd42f633a116695ed96e50762ec29f3ad83a6ed253b7dbe3f4ae57c86e
+oid sha256:93c053e16d7f83703cebaad6496a567cd5cda468439832ce178034d1a20a52d0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60f8f27a9d76e31d3721bb37f2f4c76e866b8dedf8d4315f175dac906a4a966d
+oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.009184845005740528,
+  "epoch": 0.018369690011481057,
   "eval_steps": 2,
-  "global_step": 2,
+  "global_step": 4,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,28 @@
       "eval_samples_per_second": 2.317,
       "eval_steps_per_second": 1.162,
       "step": 2
+    },
+    {
+      "epoch": 0.013777267508610792,
+      "grad_norm": 23.370132446289062,
+      "learning_rate": 3e-05,
+      "loss": 106.701,
+      "step": 3
+    },
+    {
+      "epoch": 0.018369690011481057,
+      "grad_norm": 25.078439712524414,
+      "learning_rate": 4e-05,
+      "loss": 106.0416,
+      "step": 4
+    },
+    {
+      "epoch": 0.018369690011481057,
+      "eval_loss": NaN,
+      "eval_runtime": 161.5216,
+      "eval_samples_per_second": 2.272,
+      "eval_steps_per_second": 1.139,
+      "step": 4
     }
   ],
   "logging_steps": 1,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2532979444285440.0,
+  "total_flos": 5065958888570880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null