Training in progress, step 24, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e01e0738e55ded32665062b5eacd851f951e10f4c953ef6fbeec7723a8e650ef
+oid sha256:054c70d8035d82e945522193b539e683c600bb0e9f798f7c82730ddb7fef4f7e
 size 59933632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19769188e794ad86ebb7534153f42269fefe85fd1f6bfdfa3be597cb2fa02010
+oid sha256:e3cd5109d2eb1369e0b205545d200ad136e50b37a7c8dad3f011fae2b1196400
 size 31822948

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c85569d1686f8ba93d75e7b353f9695d92b235909b55766986026f293fb4e532
+oid sha256:9c9cfe7a3bba15e469438e2ee49b8e6f00a56bbac96deddb2e649369b950ad3c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8232409f9118bd6e2dc49d05ffecc9b647656351afdcd110ebfa4e9f56796acf
+oid sha256:fe253fd3c50869b3b413fa44d3f808dd4b8eee9f82cff1555f3e301210ae2483
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.003757436593257489,
+  "epoch": 0.005009915457676652,
   "eval_steps": 6,
-  "global_step": 18,
+  "global_step": 24,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -165,6 +165,56 @@
       "eval_samples_per_second": 6.361,
       "eval_steps_per_second": 3.18,
       "step": 18
+    },
+    {
+      "epoch": 0.003966183070660683,
+      "grad_norm": 0.7557439804077148,
+      "learning_rate": 5.6611626088244194e-05,
+      "loss": 1.79,
+      "step": 19
+    },
+    {
+      "epoch": 0.004174929548063876,
+      "grad_norm": 1.1588376760482788,
+      "learning_rate": 3.7651019814126654e-05,
+      "loss": 1.626,
+      "step": 20
+    },
+    {
+      "epoch": 0.00438367602546707,
+      "grad_norm": 0.9426946640014648,
+      "learning_rate": 2.181685175319702e-05,
+      "loss": 1.8441,
+      "step": 21
+    },
+    {
+      "epoch": 0.004592422502870264,
+      "grad_norm": 0.914899468421936,
+      "learning_rate": 9.903113209758096e-06,
+      "loss": 1.718,
+      "step": 22
+    },
+    {
+      "epoch": 0.004801168980273458,
+      "grad_norm": 0.9161064028739929,
+      "learning_rate": 2.5072087818176382e-06,
+      "loss": 1.6262,
+      "step": 23
+    },
+    {
+      "epoch": 0.005009915457676652,
+      "grad_norm": 1.4570006132125854,
+      "learning_rate": 0.0,
+      "loss": 1.9771,
+      "step": 24
+    },
+    {
+      "epoch": 0.005009915457676652,
+      "eval_loss": 1.7649872303009033,
+      "eval_runtime": 317.1607,
+      "eval_samples_per_second": 6.363,
+      "eval_steps_per_second": 3.181,
+      "step": 24
     }
   ],
   "logging_steps": 1,
@@ -179,12 +229,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2468183889936384.0,
+  "total_flos": 3290911853248512.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null