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:bce7e75781ecacb66e0165646e8b468ed9d8d43b4d76b40feb1f0525f730910b
+oid sha256:80f351aaa7df23993dfe05e65876b3a00b5bf80165d70ff35b9ae1e4c8b6a93d
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92fcb324a85dfb026d35da06dd06c2e681c7702d4fe5e3e125f729cab555afce
+oid sha256:42d2f45429f9d37940063eb667d819fcd4d1beb0b6a8ac7882199e9654688838
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd574b2b6cae2e6cda789f12f30f8aef85111dba8a85323388551cfa4755dbff
+oid sha256:f7228ab32cb35189945fdb9fb849db02b93b2ac24f0f5b14bd52a4d3d1e38a7d
 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": 0.008146812347512465,
+  "epoch": 0.01018351543439058,
   "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": 6.862,
       "eval_steps_per_second": 3.431,
       "step": 24
+    },
+    {
+      "epoch": 0.008486262861992151,
+      "grad_norm": 0.3728681802749634,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0167,
+      "step": 25
+    },
+    {
+      "epoch": 0.008825713376471837,
+      "grad_norm": 0.0,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.009165163890951521,
+      "grad_norm": 0.16944009065628052,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.0052,
+      "step": 27
+    },
+    {
+      "epoch": 0.009504614405431207,
+      "grad_norm": 0.0,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.009844064919910894,
+      "grad_norm": 0.10501183569431305,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 0.0033,
+      "step": 29
+    },
+    {
+      "epoch": 0.01018351543439058,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "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": 1.4244235844360602e+17,
+  "total_flos": 1.7805294805450752e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null