Training in progress, step 4, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a6a698efcf1fa1983cc7a5357e73aea4701b441fb05b96634f37348bd9afa02
+oid sha256:c457c7be754ba218b6d852ffd82c371d2ed3d647ee1766dd2ccdeea35c03f7c9
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:915a8c572b83ba3cfe45e20023f9b5dc47eec6cef297a6594bcfe590eadcc9f2
+oid sha256:53ee9d2c93687767baf0fbb1cece292545d8c8b316929bea25117885b3b185b6
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ff1a5a76862bbee56a9275ee6a5621dff6f0928cd044fcf7d46b0f5941256ac
+oid sha256:b8d6b9a0e9e9502751def1097143074ef257eab24506a0f12d159e188fa21987
 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": 0.005709188224799286,
+  "epoch": 0.011418376449598573,
   "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": 544.88,
       "eval_steps_per_second": 272.44,
       "step": 2
+    },
+    {
+      "epoch": 0.00856378233719893,
+      "grad_norm": 0.01757071539759636,
+      "learning_rate": 3e-05,
+      "loss": 10.3764,
+      "step": 3
+    },
+    {
+      "epoch": 0.011418376449598573,
+      "grad_norm": 0.020210521295666695,
+      "learning_rate": 4e-05,
+      "loss": 10.3757,
+      "step": 4
+    },
+    {
+      "epoch": 0.011418376449598573,
+      "eval_loss": 10.376739501953125,
+      "eval_runtime": 1.1665,
+      "eval_samples_per_second": 505.773,
+      "eval_steps_per_second": 252.886,
+      "step": 4
     }
   ],
   "logging_steps": 1,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 174567260160.0,
+  "total_flos": 342669066240.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null