Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4983167ce78cbacb24eb88ea300fe3e231b5bc8f93ae59a3e72854453bf17959
+oid sha256:10be61646e88bc5e7441dbc7a09476535c193be193f1d56e8c403fd41180efa0
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09f31447ba534fefaaf4738db6d69a6616b3ee9f3d62dab496622fe57a28b757
+oid sha256:9a62570fc8ba8253f8e594b01511db77e34cbc4c8a82f537556f0212794c8d4c
 size 42608388

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89b0adb77585b2b0b7543e8c4e6edef9521ed6c9f57d2c0e5ecf0dd71a6b95a6
+oid sha256:109b8c22932ad62bd6928b9697c542e220711bf5ad21c38302c083898a0bc155
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9fbbdb6036d2372f81987526c35ebf7be4064ed59a37e6c1ea765cbfb6cc373
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.040613432046536224,
+  "epoch": 0.05076679005817028,
   "eval_steps": 8,
-  "global_step": 24,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -207,6 +207,48 @@
       "eval_samples_per_second": 13.919,
       "eval_steps_per_second": 6.96,
       "step": 24
+    },
+    {
+      "epoch": 0.04230565838180857,
+      "grad_norm": 0.36267876625061035,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.9153,
+      "step": 25
+    },
+    {
+      "epoch": 0.04399788471708091,
+      "grad_norm": 0.40100884437561035,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.2008,
+      "step": 26
+    },
+    {
+      "epoch": 0.04569011105235325,
+      "grad_norm": 0.3713359534740448,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 2.0199,
+      "step": 27
+    },
+    {
+      "epoch": 0.047382337387625595,
+      "grad_norm": 0.38803306221961975,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 2.1263,
+      "step": 28
+    },
+    {
+      "epoch": 0.04907456372289794,
+      "grad_norm": 0.38876503705978394,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 1.9215,
+      "step": 29
+    },
+    {
+      "epoch": 0.05076679005817028,
+      "grad_norm": 0.39528387784957886,
+      "learning_rate": 0.0,
+      "loss": 2.0199,
+      "step": 30
     }
   ],
   "logging_steps": 1,
@@ -221,12 +263,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.890504384328499e+16,
+  "total_flos": 4.865643726136934e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null